时间线

2276 条归档信号，按捕获日倒序

2026-11-07 · 12 条

paperInformation Games: Strategic Crowding and Firm Repositioning in Language-Model Space🔥3 paperOpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery🔥6 paperHard Sample-Conditioned Decorrelated Attention for Robust Face Recognition🔥2 paperStepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models🔥4 paperSigned but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation🔥4 paperTools Need Not Speak in Text: Latent Context Compression for Agents🔥5 paperOn the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer🔥15 paperReducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens🔥6 paperTowards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation🔥5 paperTerminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling🔥11 paperMuir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout🔥11 paperSwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization🔥9

2026-11-06 · 47 条

paperIdentically Trained Language Models Break on Different Jailbreaks🔥3 paperMonitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors🔥4 paperSynthFaces: Balanced Large Scale Human Dataset🔥1 paperRandom Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand🔥51 paperTAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens🔥16 paperDecoupled Predictive Decision Making: A Shared Conditional Predictor for Agents🔥115 paperHeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation🔥8 paperThe SIMPLE Law for Energy Cost of LLM Inference🔥11 paperTaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation🔥3 paperAsk, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization🔥3 paperEvoMemState: Evolving Memory State for Personal Agents🔥32 paperMulti-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention🔥4 paperWhy Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost🔥14 paperHarness-S: Learning from Sibling Harnesses for Generalizable Agent Training🔥64 paperHalley: A Predictive Control Plane for Optical AI Data Center Networks🔥39 paperFuture Representation Distillation for Imagination-free World Action Models🔥9 paperVisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents🔥22 paperHERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias🔥2 paperDRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI🔥0 paperGaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats🔥3 paperNitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers🔥8 paperLiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds🔥5 paperUniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling🔥2 paperD3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding🔥19 paperTailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing🔥40 paperOpen-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models🔥31 paperT$^2$-Splat: Adaptive Topology Mesh Splatting with Texture ResidualsSI 65 paperDecode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models🔥9 paperStochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEsSI 65 paperA Deep-Learning Framework for the Generalized Emulation of Atmospheric Radiative Transfer at Microwave FrequenciesSI 79 paperMatriarchy Classics: A Computational Approach to Swap Only Gendered Words in Classic NovelsSI 67 paperA Machine Learning Approach to Coupling Photoionization & Multi-Frequency Radiation HydrodynamicsSI 54 paperWeLM-Image: A Unified Image Generation Model towards Visual IntelligenceSI 64🔥43 paperPSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic ReasoningSI 58 paperArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint DerivationSI 68 paperOperationalizing NCII and CSAM Law in the Age of AI: Open ProblemsSI 67 paperTowards Foundation Decision Models: Drex🔥22 paperEDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure🔥14 paperConstructive Probability, Foundations and Numerical Analysis for mathematical finance and machine learningSI 70 paperPerception Over Geometry: Rethinking Gaussian Allocation in Mesh-based SplattingSI 59 paperSAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization🔥9 paperRegret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price MechanismSI 56 paperQuantum Fourier integration of decay rates at next-to-leading orderSI 61 paperProQuant: Progressive Quantization-aware Training for Edge MLLMsSI 65 paperNPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma🔥3 paperSLA: Scaling Spatial-Language-Action Model via Continual Pre-training🔥151 paperVFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding🔥102

2026-11-05 · 50 条

paperWhen Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing🔥0 paperGameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling🔥33 paperVideoMemBench: How Well Do MLLMs Remember in Video Conversations?🔥19 paperHow I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates🔥6 paperEvery Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation🔥11 paperMUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation🔥20 paperHybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents🔥17 paperCross-Prompt Reuse of Entity-Replacement Responses🔥1 paperStreamDuo: A Live Commentator and a Research Agent for Unseen Games🔥18 paperQFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board🔥0 paperFinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting🔥1 paperSpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding🔥8 paperSolv3R: 3D Looped Transformer as a Multi-view Solver🔥13 paperAnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds🔥9 paperVidDub: Replacement-Aware Distillation for Two-Step Video Dubbing🔥8 paperBEND 2.0: Benchmarking the Capabilities Needed to Design DNA🔥2 paperDory1.0-4B: A Looped Normalized-GPT🔥6 paperSay the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs🔥1 paperLength Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval🔥0 paperHuman-to-Robot Transfer via Bridging Representation and Action Space in VLAs🔥12 paperSphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere🔥1 paperVeriSpoof: Beyond Real or Fake with One Audio LLM🔥4 paperKoopman Generative Operators for Efficient Probabilistic Time-Series Forecasting🔥3 paperKierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks🔥1 paperLoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers🔥9 paperPyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data🔥20 paperAdversarial Speculative Reasoning Improves Long Horizon Agents🔥6 paperAI-Driven SaaS Platform Integration: AI Express for Unified Generative AI Services with Pay-As-You-Go Credit Systems and Scalable Microservice ArchitectureSI 64 paperBrewing another binary in the Teapot: Nandou=Phi SagittariiSI 63 paperClassical training of conditional instantaneous quantum polynomial-time Born machinesSI 66 paperOn the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation🔥19 paperTurbocharging PiPNN for Proximity and $k$-NN Graph BuildingSI 55 paperFrequent Optical Flares in an M-type Detached Eclipsing Binary TIC 349005337SI 57 paperHardware Demonstration of Neural-Surrogated Quantum-Enhanced MCMC for Large-Scale Constrained Boltzmann SamplingSI 62 paperAgentic Wireless Optimization: Workflow Automation, Algorithm Design, and Multi-Timescale Network OperationsSI 60 paperSleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?🔥6 paperNextGAN: Towards Simple and Scalable GAN Training for Image and Video GenerationSI 70 paperWhat Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?🔥35 paperEmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL🔥23 paperRAGAM-AI: A Hybrid Reinforcement Learning based Agentic approach powered by Generative AI for Edge Resource ManagementSI 62 paperThe formation and evolution of Wolf-Rayet stars with temperature-dependent windsSI 69 paperAgent-Driven Generative Priors for Pathology Image Synthesis and SegmentationSI 55 paperEnergy-Guided Transport for Projection-Free Physics-Informed Flow MatchingSI 71 paperTurns Matter: Advancing Streaming Video RL via Turn-Level Credit🔥126 paperPyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World🔥12 paperVA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation🔥12 paperAlignment Myopia in Generative AISI 61 paperProcedural Adversarial LearningSI 62 paperFrontierPhysics: Evaluating Agents for End-to-End Physics Research🔥50 paperFrom Pixels to Actions - Towards Native Vision-Language-Action Policies🔥50

2026-11-04 · 64 条

paperAre Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena🔥3 paperAdvancing SVD-based LLM Compression via Layer-Wise Error Model Search🔥4 paperMulti-Agent Relay Thinking🔥8 paperDo We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG🔥2 paperMuon Makes the First Mixture-of-Experts Layer Harder to Balance🔥2 paperA Tutorial on Generative Models for Music Audio🔥3 paperCross-Primitive Consistency in Jev🔥9 paperWhere to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents🔥2 paperMoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery🔥9 paperEvoTeam: Multi-Agent Collaboration via Evolving Teams🔥25 paperMage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses🔥8 paper"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents🔥11 paperWhat We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning🔥2 paperDAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention🔥5 paperWords Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy🔥47 paperIs Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks🔥3 paperSwitch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?🔥6 paperParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost🔥16 paperOrder-Only On-Policy Distillation🔥30 paperCan AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories🔥8 paperGigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data🔥1 paperRoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild🔥34 paperSpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding🔥15 paperSeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling🔥2 paperMoviEdit: Long-form Multi-Shot Video Editing Made Easy🔥43 paperHistory Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models🔥15 paperDR Pixel: Page-Native Deep Research with Vision-Language Models🔥5 paper3D Gaussian Splatting within Self-Learned Neural View-Dependent Color FieldsSI 55 paperKlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RLSI 57 paperFineCraft: Enhancing VLA Models for Fine-Grained ManipulationSI 56 paperAuto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction🔥1 paperAxion 1.0: Open Agent Foundation Models, SimplifiedSI 57🔥33 paperEvery Pixel Is an Option: A System One Model for Medical Ultrasound Biometry🔥2 paperIdeaTaste: Do LLMs Share the Research Taste of Human Researchers?🔥38 paperWebHarbor: Docking Real Websites for Evolving GUI Agent Environments🔥14 paperLOLPlay: Benchmarking Real-Time Visual Agents in League of Legends🔥6 paperte-comp: A Complete MLIR Compiler Generating Self-Contained C Inference Engines for MCUsSI 58 paperEnhancing Stock Market Information Retrieval with Retrieval-Augmented Generation🔥1 paperThe Hot Neptune Initiative (HONEI): IV. TOI-4129 b, an Adolescent Neptune in the RidgeSI 71 paperA Wolf-Rayet nebula in its disruption phase: high-resolution radio observations of PCG 11SI 63 paperRecursa: Toward Recursively Self-Improving Foundation Model Systems🔥9 paperRGDM: Robust Graph Diffusion ModelSI 64 paperPoint interpolation and distributional universality in flow-based generative modelsSI 62 paperFlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing🔥10 paperVidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks🔥25 paperNear-Zero Token Embeddings Silently Stall Training in Gated Sequence Models🔥7 paperIs Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models🔥2 paperSheaf-MPNN: A Library for Sheaf Neural Networks as Message PassingSI 76 paperVISAGE: Vertex-based Intrinsic Surface Appearance GEneration via Dual-Stream Diffusion for Arbitrary 3D HeadsSI 75 paperThink Less, Locally: Local Preference Learning for Reasoning Compression🔥53 paperPrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations🔥9 paperBehind Video Generation: Observations and Insights on Multimodal Understanding from Kling🔥46 paperRGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge ReportSI 67 paperToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents🔥31 paperRoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On🔥6 paperFactorized MLLM Embeddings for Composed Image Retrieval🔥45 paperPhysics-informed traditional and generative Mori-Zwanzig-reduced models for multiscale systemsSI 62 paperGoing Deeper With Memories🔥1 paperRoute Anything: A Study of Model and Policy Routing for General-Purpose AI Systems🔥82 paperYANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction🔥26 paperWonder 4: A Mixture-of-Experts Recipe for Image Quality EnhancementSI 66 paperYou don't need long context🔥9 paperFrom Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human IntelligenceSI 56🔥87 paperDreamX: Video Diffusion Model is a Universal Latent Action Learner🔥54

2026-11-03 · 57 条

paperProVe: Proposer-Verifier Decoding🔥2 paperLost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay🔥22 paperSupervising the Visible State: Separating Representation from View Selection in Streaming Video🔥5 paperOSWAM: An Effective World Action Model with One-Step Action Generation🔥5 paperSOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding🔥5 paperLearning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling🔥7 paperFollow the Gradient: Tracing Safety Degradation Back to Training Data🔥29 paperGEPA-Curator: Curated Learning for Self Improving Agents🔥5 paperDeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers🔥8 paperThink Twice: The Metis-1.6 Technical Report🔥4 paperOn-Policy Self-Distillation with Teacher Evolution🔥2 paperWorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining🔥6 paperDiagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning🔥14 paperVideo Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement🔥58 paperWhen Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications🔥9 paperMAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads🔥4 paperrTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment🔥2 paperTSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research🔥1 paperTinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents🔥3 paperAuditFL: A Contract-Backed Clearing Layer for Open Federated Learning🔥1 paperSelf-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer🔥3 paperBYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion🔥5 paperTurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish🔥2 paperDecisionRank: On-Policy Distillation for Decision-Model Rerankers🔥9 paperSFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image GenerationSI 60 paperTropical Cyclone Wind Field Diagnosis with Image-to-Image ModelsSI 74 paperFaces or Models? Where the Age Gap in Facial Expression Recognition Comes FromSI 63 paperSIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time🔥1 paperWhen Morphs Look Better: Face Image Quality as a Training-Free Signal for Morphing Attack Detection🔥1 paperFrom Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings🔥20 paperBeyond Semantic IDs: Atomic Creator Tokens for Large-Scale Generative RecommendationSI 59 paperAgent Stack for ML Training Lifecycle: Generation, Validation, and OptimizationSI 64 paperWave Forcing: Towards Speed-of-Light Streaming Video Generation🔥80 paper4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge ReportSI 78 paperFermat curves and explicit class field theory for real quadratic number fieldsSI 80 paperAn Introduction to Financial Derivatives: Open Lecture NotesSI 51 paperA Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI DevelopmentSI 53 paperThe Marvelous Meixner Polynomials: Second Kind, First ClassSI 57 paperCan Large Language Model Agents Learn by Watching Tutorial Videos?🔥1 paperCrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents🔥19 paperDemocratizing Robot-Use Agents: A Unified Harness with Open Models🔥33 paperSpecial and General Computational AestheticsSI 54 paperAdvances in Agentic Computer GraphicsSI 58 paperLarge Geometry Models Are Priors For Fast Physics PretrainingSI 54 paperNorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale🔥24 paperQFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face VerificationSI 57 paperLatent Diffusion-GAN: Adversarial Learning in the Autoencoded Latent SpaceSI 54 paperMeasuring AI Agents as Teammates with Collaborative Intelligence🔥3 paperPhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments🔥3 paperLab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments🔥1 paperAvatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents🔥14 paperCUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements🔥37 paperCoworkOS:Scaling Agent Coworkers for Real-world Automation🔥56 paperCan Coding Agents Sustain Continual Evolution without Forgetting?🔥0 paperFLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell🔥6 paperLibrary of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime🔥2 paperReviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning🔥23

2026-11-02 · 39 条

paperRex: A Family of Reversible Exponential (Stochastic) Runge-Kutta SolversSI 88 paperTowards Provably Secure Generative AI: Reliable Consensus SamplingSI 67 paperWeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search🔥5 paperR^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop🔥41 paperTernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation🔥1 paperGLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching🔥10 paperCEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems🔥17 paperFrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation🔥24 paperVenus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage🔥22 paperSciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World🔥4 paperHALO: Human-Grounded Granular Evaluation of Proactive Agents🔥6 paperMemSteer: Turning User Histories into Supervision for Agent Memory Optimization🔥6 paperDoes Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?🔥54 paperWizard: Manipulate Any World in Real Time via Agentic Control🔥23 paperHiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model🔥22 paperProbing Spatial State Representations in Visual Foundation Models🔥10 paperVoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step🔥5 paperApriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use🔥15 paperWorldBridge: Bridging Video and Action for Task Generalization in World Action Models🔥11 paperDyCraft: An Agentic System for Long-Horizon 4D Scene GenerationSI 46 paperThe assembly of dusty galaxies at $z \geq 4$: grain growth and the evolutionary origin of the dust-to-stellar-mass scatterSI 49 paperCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents🔥16 paperCircumventing the Computational Hardness of Computational ArbitrageSI 57 paperNo Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates🔥18 paperOn the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning🔥5 paperPP-Mark: Provable and Publicly Verifiable Watermarking for Generative AISI 47 paperSketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement🔥1 paperPyQLAS: A Quantum-Classical Hybrid Solver Library for Linear SystemsSI 51 paperPolarFlow: Spectral Geometric Flow Matching for Directed Graph Generation via Polar DecompositionSI 52 paperA Hybrid Message-Passing and Electric-Field Representation for Electrostatic QM/MM Embedding with Machine Learning Interatomic PotentialsSI 52 paperEngineered Learning Problems on Noisy Quantum ProcessorsSI 63 paperA Robust High-order Approximation of the Gray Thermal Radiative Transfer EquationsSI 71 paperAn end-to-end CNN search for ultra-short-period planets in TESS: from the blend ceiling to the independent validation of TOI-6662 bSI 66 paperREA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control🔥17 paperCausalWAM: Learning the Causes of Actions in World Action Models🔥2 paperQuantum 3xplorer: AI-Native Engine for Next-Generation Quantum Materials ModelingSI 47 paperReLift: Dense 3D Tracking as Lifted Trajectory Repair🔥10 paperRoboArchitect: Automating the Design of Robotic Agents with Persistent Memory🔥5 paperLatent Reasoning in Continuous Space for Unified Multimodal Models🔥30

2026-10-31 · 11 条

paperBroken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them🔥6 paperABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics🔥4 paperHolo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion🔥6 paperMatched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents🔥6 paperScaling Lean Theorem Proving for Real-World Code Verification🔥7 paperEPSBench: Benchmarking LLM Agents for Earnings Forecasting🔥3 paperWeaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models🔥3 paperUnlocking Any-Order Generation in Pretrained Autoregressive Image Models🔥3 paperProving and Improving the Platonic Representation Hypothesis with JEPAs🔥67 paperFDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss🔥2 paperTraining Foundation Models with a Single Algorithm🔥12

2026-10-30 · 50 条

paperAmortizing Sequential Experimental Design in Reasoning LLMs🔥9 paperCoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models🔥13 paperRealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents🔥18 paperPersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas🔥17 paperYour Benchmark Is an Empirical Measure Over Difficulty🔥143 paperLongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data🔥8 paperTauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents🔥11 paperA Broader Look into MLLM's Retrieval Heads🔥28 paperVibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team🔥22 paperPreView: Enhancing GUI Grounding with Preprocessed Views and Cues🔥4 paperCo-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models🔥21 paperEvaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks🔥8 paperInstruction Capacity: Behavior and Degradation of Language Models under Controlled Load🔥4 paperLook Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs🔥110 paperWorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training🔥36 paperAfter One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System🔥2 paperWebAnything: From the Wild Web to Scalable Agent Environments🔥12 paperGOFish: Full Field-of-View Gaussian Splatting and Mesh ExtractionSI 64 paperA Witnessing Duality for ReLU Network DepthSI 61 paperNSF-DOE Vera C. Rubin Observatory's First View of the Neptune Trojan L5 (Trailing) Cloud: Two New Long-Term Stable TrojansSI 64 paperMulti-Token Prediction Done Right🔥20 paperInvestor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?🔥13 paperWeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video🔥18 paperStructure-retained low-rank adapters for weather synthesisSI 63 paperIntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation🔥14 paperRecurrent Bipartite Graph Neural Networks for QC-MDPC Error Decoding in McEliece CryptosystemsSI 59 paperA-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement🔥158 paperAskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding🔥10 paperMCCL: Training Pytorch models across a fleet of Macs at Skywalker SoundSI 59 paperPhysicsNeMo-Mesh: GPU-Native Meshes and Simulation Cases for Physics AISI 58 paperOnline Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps🔥10 paperOpenFlyV2: An onboard vision-language-action model for aerial perception and navigation🔥7 paperYoutu-Parsing-Omni: One Encoder, One Schema, All Modalities🔥128 paperROAD: Modern Adversarial Training for Simple One-Step Distillation at ScaleSI 63 paperOperator-Aware Posterior Sampling for Multivariate Weather DownscalingSI 78 paperIntrinsic Distribution Matching🔥239 paperAB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers🔥7 paperEditAgent: Rethinking Agentic Image Editing🔥10 paperAI at a Turning Point: From ChatGPT through Neural Networks to Neuromorphic AISI 71 paperPhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive AssetsSI 93 paperAdversarial Pilot Injection Against AI-Based CSI Feedback in FDD Massive MIMO SystemsSI 59 paperYour LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training🔥17 paperTEMPEST - A modular Python-based thermophysical model for rough, irregularly-shaped airless bodiesSI 66 paperPhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions🔥14 paperGlance: The Generator Is Its Own Reranker🔥12 paperA Parameterized Stochastic Hamiltonian Process on Graphs with Two-Point Boundary ConditionsSI 66 paperEarly career researcher responses to AI in mathSI 81 paperHairDeck: Animation-Ready Stylized Hair Cards from a Single Image🔥22 paperL3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory🔥44 paperRead, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers🔥36

2026-10-29 · 23 条

paperQuaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection🔥2 paperOmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning🔥2 paperThe Lexical Imprint of Pre-training Data🔥9 paperFoundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural NetworksSI 42 paperAlphaBet: Reinforcement Learning for LLM Event Forecasting Agents🔥3 paperT-DIG: Text-Conditioned Diversity for Image Generation🔥2 paperCausGround: Causal Interaction Grounding for Adaptive Embodied Planning🔥4 paperSelf-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models🔥3 paperSensorimotor Alignment: A Platonic Proxy for Embodied Policy Success🔥33 paperSub-monolayer tracking of molecular states at buried interfaces🔥3 paperEfficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes🔥152 paperAdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science🔥2 paperHuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience🔥2 paperWhat Outcome RL Buys: Finishing, Reliability, Rarely Reach🔥4 paperMultiscale Policy Optimization for Long-Horizon LLM Agents🔥377 paperDTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models🔥256 paperOmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images🔥50 paperh1: A Taste of the Bitter Lesson in Automated Theorem Proving🔥16 paperHow Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning🔥4 paperLipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It🔥1 paperBeyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models🔥11 paperTAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving🔥18 paperEmbeddingGemma 2: Unified and Efficient Multimodal Representations🔥21

2026-10-28 · 65 条

paperGluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations🔥4 paperHow Far Can Coding Agents Go in Visual Generation?🔥12 paperRepresentation Redistribution in Sparse Autoencoders🔥36 paperOn the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction🔥19 paperHABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory🔥80 paperTruncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation🔥28 paperMoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching🔥3 paperCellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models🔥2 paperCRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments🔥9 paperCan Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?🔥119 paperΨ-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model🔥5 paperOpenESM: Energy-Steered Models Are Scalable Foundation Learners🔥3 paperOvisOCR3 Technical Report🔥29 paperRSI Arena: Towards Recursive Self-Improvement with Human Feedback🔥16 paperEnvLunch: The Environment as a Free Lunch for Learning to Interact🔥5 paperReGE: Stronger Agents through Experience Synthesis🔥13 paperMemory Tax: Dissecting the Net Value of Agent Memory🔥147 paperChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence🔥131 paperParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?🔥9 paperWhat Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents🔥11 paperRethinking Verification in Agent Harnesses🔥8 paperBenchmarking Obstacle-Conditioned Safety in Household Robot Navigation🔥8 paperSearchHorizonBench: A Benchmark for Search Value in AI Agents🔥7 paperHarness-Model Collaboration for Long-Horizon Continual Learning🔥2 paperPhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds🔥2 paperDid the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models🔥5 paperOmni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams🔥14 paperMatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting🔥18 paperVibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation🔥174 paperQuantile Regression Postprocessing with Negative Electricity Price ForecastsSI 52 paperCondition-Enhanced Generative Adversarial Network for Aerodynamic Configuration Design of Commercial AircraftSI 52 paperQuadratic Reciprocity via Vandermonde MatrixSI 52 paperEvaluation of a Double Integral with Exponentials and Two Generalized Laguerre Polynomials and Its Associated MomentsSI 50 paperPractice Makes Perfect: Tacit Knowledge, Generative AI, and Returns to Schooling and ExperienceSI 51 paperLearning and Reasoning with Geometry: How Generation Helps Spatial Understanding🔥5 paperRollback: Experience Backtracking in World Models for Policy Improvement🔥48 paperThe Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents🔥540 paperProximal Point Newton Methods for Nonconvex OptimizationSI 53 paperCross-modal Steering Vectors Exist Across Both Image and Text Generation🔥7 paperFASST: A Compact Stateless Atmosphere Model for Long-Term Ocean CouplingSI 67 paperSO-101 Bench: Accessible Spatial Manipulation🔥8 paperLociArt: A Unified Paradigm for Free-Style Local Video Stylization🔥28 paperNemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation🔥3 paperHy-Nomas: Towards Free-form Interactive World Generation🔥108 paperRynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions🔥9 paperVisual Autoregressive Generation with Next Token ImaginationSI 59 paperA lightweight C Code Generator for Heterogeneous TinyML SystemsSI 51 paperZooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception🔥26 paperMapping Artistic Engagement with Quantum TechnologiesSI 72 paperPhysics-Guided Flow Matching: A Generative AI Framework for Global Total Electron Content ForecastingSI 55 paperMLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model🔥4 paperVision-Language-Action or World-Action? Just Action Models🔥5 paperYour Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces🔥7 paperMathematical Reality Capture: from the age of discoveries to mathematical topography and surveysSI 53 paperCodeCap-Bench: Can Code Serve as a Good Video Caption?🔥49 paperPDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations🔥144 paperChannel Selection for Mixture-of-Experts Decoding Needs No Calibration Data🔥21 paperPara-Gaussian Approximations of Random Deep Neural NetworksSI 50 paperEvidence for a nova super-remnant surrounding the recurrent nova V745 Scorpii using eROSITASI 51 paperTimestral🔥7 paperRare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions🔥5 paperKnow, then Draw: A New Learning Paradigm for Visual GenerationSI 62🔥2 paperCan LLMs Uncover Hidden Physical Laws through Free Exploration?🔥7 paperCan Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?🔥90 paperThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning🔥51

2026-10-27 · 62 条

paperProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning🔥9 paperJockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making🔥4 paperFunction-Space Temporal Self-Distillation for Policy Optimization🔥36 paperKANLab: TensorFlow Playground for Kolmogorov-Arnold Networks🔥3 paperKolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows🔥6 paperminiTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning🔥2 paperHow Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication🔥2 paperPredictive Closure: A Set-Level Characterization of JEPA's Feature Selection🔥2 paperJudging the Justification: Decision Certificate Supervision for Generative Reward Models🔥2 paperWORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot🔥2 paperRoboJudge: Multimodal Language Models as Judges for Embodied Video Generation🔥4 paperWhat Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories🔥2 paperSteering Black-Box Large Language Model Agents with Pitfall Anticipation World Model🔥2 paperLLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification🔥3 paperExtreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization🔥5 paperFocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models🔥2 paperOn the Token Collapse Phenomenon in Textual Graph Soft Prompting🔥1 paperHiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction🔥5 paperDoes LeWorldModel Preserve Local Action Geometry?🔥3 paperFLORA: An Open Model Suite for Scaling Robotics Data Engines🔥1 paperPaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean🔥6 paperSpeculative Diffusion is a Tale of Two Tradeoffs🔥4 paperDiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning🔥17 paperPrincipia: Test-Time Hypotheses to Principle Construction for Scientific Discovery🔥16 paperTrial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution🔥119 paperRethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access🔥6 paperWorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control🔥41 paperWorld-in-Context: Interactive Video World Modeling with In-Context Conditioning🔥17 paperProxima Centauri's Angular Diameter RevisitedSI 60 paperQwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement🔥16 paperNovel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination🔥5 paperEat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL🔥22 paperTrajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents🔥153 paperMycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities🔥2 paperBeyond Affine Reconstruction: Multi-Resolution Transformer DeepONets for the Radiative Transfer EquationSI 68 paperBuild, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players🔥8 paperSecuring Edge & Physical AI: Post-Quantum IoT Blockchain for Mission-Critical Cyber-Physical AgentsSI 71 paperContinual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents🔥11 paperInteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants🔥78 paperAGENS: Agentic Link Construction for Environment and Intent Aware 6G CommunicationSI 79 paperHumans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?🔥1 paperLoopGR: Parameter-Efficient Scaling for Generative Recommendation via Recurrent DepthSI 59 paperΔτ-Bench: Pushing Agents Toward a Moving Capability🔥15 paperRynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions🔥9 paperSpatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion🔥31 paperDynaFlow: Learning Free-Form Multi-Agent Orchestration🔥72 paperAgentProofBench: Benchmarking Reusable Verifiers for Web Agents🔥4 paperStreamVibe: Proactive Video Agents for Evolving User Intent🔥142 paperSceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation EnvironmentsSI 83 paperTransporting Quantiles to Codebook: Scalable Vector Quantization without Codebook CollapseSI 69 paperAIPC: Evidence-Guided Agent Workflows for PyTorch Project DeploymentSI 83 paperFrontGI: Architecture-Aware Parallel GNN Inference on Chiplet-Based Multicore SystemsSI 55 paperGenerative AI in Turbulence: Foundations, Applications, Validations and BenchmarksSI 87 paperTrustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges🔥11 paperBeyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in ArtworksSI 60 paperMesoscale Modelling of Titan's Shangri-La region: the impact of surface properties on windsSI 55 paperEmbodiedLab: Benchmarking Embodied Agents That Act to Know🔥1 paperSkill^{infty}: Recursive Self-Improvement for Agent Skill Optimization🔥2 paperS3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning🔥10 paperActive Learning of Conditional Generative Models via the Transport Neural Tangent KernelSI 58 paper$\kappa$-Parametrized Boltzmann Distribution Sampling on Quantum Approximate Optimization AlgorithmSI 77 paperWork Agents: Systems, Capabilities, and Optimization🔥25

2026-10-26 · 41 条

paperA path-following framework on fiber bundle for variational inequalities🔥2 paperThe fixed-point bundle method over product-of-simplex domains arising from game equilibria🔥2 paperMMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning🔥3 paperSliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing🔥1 paperCo-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval🔥1 paperFLOMSS: Generative Music Source Separation by Flow Matching🔥4 paperMultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation🔥5 paperDuoLM: Fast and Effective Personalized Recommendation with Language Models🔥2 paperOmni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs🔥21 paperTenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics🔥1 paperGeneralized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding🔥3 paperBuilding Auditable AI Text Detectors with Sparse Autoencoders🔥3 paperUserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents🔥36 paperDual Exam: Controlled Evaluation of Multimodal Agents and World Models🔥13 paperHiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games🔥29 paperDISC: Domain-Integrated Similarity Cost for Time-Series Dataset🔥1 paperEcho: Coupled Action and Task Status Signal Denoising for Vision Language Action Models🔥3 paperDirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model🔥3 paperNested Sparsity for Scalable Pretraining and Continual LearningSI 52🔥1 paperEvery Weight Is a Path of Shared Discrete Decisions🔥7 paperDraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation🔥7 paperRADIANT: Object-Centric Feed-Forward Global IlluminationSI 69 paperImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image GenerationSI 64 paperMPQ: A Message-Passing View of Post-Training QuantizationSI 61 paperImplicit Neural Representations for Variational Problems on GraphonsSI 59 paperForging Emotions: a deep learning experiment on emotions and artSI 62 paperWeak adversarial tensor neural network for high-dimensional Fokker-Planck equationsSI 78 paperEasy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction🔥3 paperRSIHub: A Composable Framework for Agent-Evolution Methods🔥24 paperCoPiT: A conditional Position-induced Transformer for aerodynamic field prediction on unstructured meshesSI 68 paperMeasuring the Energy Cost of Completing Tasks with Quantized Language-Model AgentsSI 57 paperClassical Pre-Training of Large Shallow Parametrized Quantum Circuits through Pauli Propagation and deployment on Quantum HardwareSI 52 paperSemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric CorrespondencesSI 63 paperOn-Policy Self-Training: Data-Free Self-Improvement in Large Language Models🔥4 paperPhysics Informed Neural Network for Multi-dimensional Turbulent Self-gravitating FlowsSI 60 paperLoCA: Enabling Multi-Modality in Geospatial Location Encoders🔥3 paperHoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training🔥2 paperRecommender regret for improving regularised RL estimation with bandits and MCTSSI 56 paperA Tutorial on Physics Constrained Machine Learning for Hybrid Modeling, Optimization, and ControlSI 63 paperOne-Million-Year-Old Nascent Eclipsing Binaries in the LMCSI 79 paperRynnUnify: Towards Unified Embodied Brain🔥27

2026-10-24 · 17 条

paperEvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?🔥22 paperRealism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective🔥7 paperRTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation🔥19 paperThe LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems🔥10 paperMambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models🔥9 paperIF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems🔥9 paperBridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization🔥8 paperDiffusion Language Models Change Speed Across Tasks and Languages🔥10 paperWho Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans🔥10 paperHyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second🔥10 paperTARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments🔥8 paperAgent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems🔥23 paperSplatLab: Autonomous Scientific Discovery for 3DGS Research🔥8 paperFilmFlow: Agentic System for 3D Virtual Film Cinematography🔥32 paperDifferent Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models🔥23 paperRIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention🔥16 paperBrickWright: Agentic Creation of Physically Feasible Brick Builds🔥13

2026-10-23 · 50 条

paperRouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing🔥25 paperMolLean: A Process-Verifiable Language for Chemical Reasoning🔥15 paperExploring The Empirical Privacy Landscape of Synthetic Data🔥4 paperLanguage Models Learn to Improve Language Models🔥6 paperWhat Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models🔥40 paperEditing Images into Reusable Layers via Compositional Edit-Prior Distillation🔥182 paperDesign Anything, Design at Scale🔥5 paperDeep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models🔥48 paperTILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models🔥9 paperHeartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents🔥22 paperSEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS🔥7 paperBridged Self-Distillation for On-Policy Learning🔥2 paperSame Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy🔥2 paperMMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows🔥4 paperMeta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE🔥30 paperRLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting🔥25 paperLaLa-World: Scaling Latent World Models with Natural Language Actions🔥36 paperRoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation🔥3 paperCode2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V🔥33 paperStratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity🔥3 paperVerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents🔥9 paperPolicy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks🔥50 paperHidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication🔥9 paperDiffResearch: Accelerating Deep Research with Diffusion Language Models🔥8 paperStyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion🔥10 paperToward Recursive Self-Improvement in Physical AI🔥57 paperRetrieval Augmented Generation Compositionality🔥30 paperFrontierCS 2: A Benchmark for Computer Science R&D🔥3 paperToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination🔥8 paperLooped Uniform Diffusion Language Models🔥5 paperQuant-Arena: Benchmarking LLM Agents for Quantitative Trading Research🔥22 paperDeep Search in Real-World Web Environments🔥160 paperSelf-Distilling Future Video Representations for World Action Models🔥37 paperFoundation4D: Towards a unified perception and reconstruction model for autonomous vehicles🔥10 paperIs Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought🔥21 paperVerus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos🔥18 paperInherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models🔥13 paperMaking MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation🔥172 paperIQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems🔥100 paperSCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs🔥12 paperBeyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports🔥23 paperCola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation🔥20 paperWeVisOne-VL: Unified Visual Perception from Objects to Pixels🔥244 paperAnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark🔥17 paperSkeleton-Grounded Latent Action Model for Robot World Models🔥7 paperAgentVQA: A Unified Benchmark for Agentic Visual Understanding🔥17 paperRethinking Sequence Compression with Test-time Regression🔥18 paperWhat Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models🔥12 paperF2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation🔥12 paperReading, Writing, Sharing, and Interacting with the World through Video🔥275

2026-10-22 · 64 条

paperNot All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models🔥1 paperToward Part-Aware Choral Transcription with singing voice assignment🔥1 paperRight Screen, Wrong Transition: World Models as Verifiers for GUI Agents🔥1 paperCompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction🔥1 paperEAU: Environment-Agent-User Co-evolution for Training User-Centric Agents🔥11 paperSocratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills🔥29 paperDeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents🔥8 paperPrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis🔥44 paperSpectral-Spatial Interpretation🔥33 paperEntertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally🔥2 paperWhat Makes a Good Symbol for Hybrid Discrete-Continuous Planning?🔥2 paperOn the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMs🔥5 paperAxiomatic World Modeling for Physics Reasoning🔥2 paperBiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks🔥2 paperATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference🔥3 paperSpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?🔥20 paperACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models🔥4 paperWhich Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams🔥7 paperAsk to Distill: Learning to Synthesize Data for On-Policy Distillation🔥10 paperReal In, Real Out: What If We Only Use Real Data for Scene Text Editing?🔥9 paperWorld Models with Configurable Perception🔥2 paperTraining the Whole Agent, Not Just the Model🔥11 paperSelf-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling🔥6 paperStreamEval: Evaluating Interactive Streaming Video Generation Models🔥28 paperAnswering in the User's Variety: Calibrated Accommodation Pairs for Post-Training🔥2 paperCache Engineering for Agents🔥65 paperAgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics🔥17 paperScaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds🔥17 paperQwen-Audio-3.1-ASR Technical Report🔥3 paperAutomating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?🔥9 paperExtreme Low-State Quantized Transformer for Electricity-Load ForecastingSI 54 paperBuilding AI Research Teams for Autonomous Discovery of Linear Attention Architectures🔥12 paperTransformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention ClusteringSI 57 paperHumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form VideoSI 51 paperLocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level ConsistencySI 60 paperA Unified Evaluation Framework of Physical Adversarial Robustness in the Edge VLM EraSI 51 paperSpatialBrain: Spatial Intelligence Growing from Experience🔥6 paperWorkflow-Aware Communication and Computation Scheduling for Mobile Edge AI AgentsSI 81 paperMemory-Centric Continual Learning for AI Agents🔥17 paperRubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding🔥2 paperSparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers🔥13 paperHarness Scaling for Generalizable Agentic Reinforcement Learning🔥6 paperPACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States🔥7 paperFrom VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation🔥4 paperEntangled Futures: Quantum Computing's Potential and Challenges in Computer ScienceSI 51 paperProbabilistic Machine Learning for Short-Term Atmospheric Seeing ForecastingSI 53 paperLorentz-Equivariant Geometric Algebra Transformers for Top-Quark Event ReconstructionSI 56 paperTraceForge: Distilling with Your Own Thinking🔥15 paperEfficient Generative Image Compression with Quantized Latents RefinementSI 56 paperWill AI kill us all---or just make mathematicians obsolete?SI 70 paperEvolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting🔥3 paperNeutron Star-Main-Sequence Star Collision: Formation and Long-Term Evolution of Thorne-\.Zytkow ObjectsSI 82 paperAutomated Discovery of Physically Interpretable Subgrid Length Scales for Detached Eddy Simulation via Agentic AISI 57 paperTractable Inference with Kolmogorov-Arnold NetworksSI 61 paperCulturalRiddles: A Multicultural Benchmark of Riddles🔥3 paperLooking Ahead: Modeling Future Evolution in Autoregressive Video Generation🔥58 paperDONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations🔥17 paperRealMe: Immersive Volumetric Video from Minimal Captures🔥5 paperOn OpenAI's proof of the Nagata conjectureSI 86 paperVX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift🔥2 paperMultimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use🔥13 paperALPS: Visual State Encoders for World Models🔥11 paperThink Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation🔥5 paperAgentic World Action Models🔥4

2026-10-21 · 63 条

paperSpecter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading🔥14 paperBeyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization🔥2 paperOmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning🔥3 paperCorrection Training for Diffusion Models🔥23 paperλ_0: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation🔥3 paperWinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding🔥2 paperEvent-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning🔥3 paperHarness-Delta Attribution: Dissecting Gains From Harness Evolution🔥3 paperPredicting Privileged Information Effectiveness for On-Policy Self-Distillation🔥5 paperFirst Passage Attention🔥0 paperCompetence-Based Evaluation of Logical Reasoning in Large Language Models🔥0 paperHumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time🔥2 paperEdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends🔥8 paperGood Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success🔥5 paperHybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents🔥4 paperEpi: Towards a Persistent, Self-Improving Agent for Autonomous Research🔥7 paperVLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse🔥33 paperCoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?🔥33 paperLegal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations🔥1 paperVision as Proprioception: Estimating Humanoid Robot Pose from Video🔥1 paperPainting Change Map as guidance for generating painting processes🔥12 paperTRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Prediction🔥2 paperSWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation🔥23 paperPhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning🔥16 paperFocused Omni-Modal GUI Agents🔥101 paperHarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL🔥6 paperBreaking Diffusion: Parallel Reasoning with Draft Refinement🔥13 paperFrom Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping🔥11 paperTokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning🔥1 paperSpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration🔥1 paperRopedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience🔥63 paperPhysical AI: Concepts, Techniques, and ChallengesSI 75 paperLOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book ModelsSI 62🔥4 paperLeviathan: a very massive, extended sub-millimetre galaxy spectroscopically confirmed at $\rm z = 4.05$SI 59 paperSionna Bench: Towards Benchmarks in Wireless CommunicationsSI 69 paperEMBER: Predicting TCR--pMHC Binding Without a Docked Complex🔥3 paperOn the Limits of Scale: Inverse Scaling in Vision-Language Models🔥0 paperPerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error CompensationSI 80 paperMore Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents🔥5 paperTokenFlow: Latent Token Rectified Flow Matching for 3D Point Cloud GenerationSI 56 paperHarness Self-Evolution for Long-Horizon Terminal Agents🔥4 paperPAR: Progress-Aligned Recurrence for Length Generalization in State Tracking🔥78 paperMMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records🔥19 paperMatrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds🔥56 paperWeak-$L^\alpha$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy TailsSI 50 paperAttractive Faces Skew Text-to-Image Reward Models and LeaderboardsSI 70 paperAgentic Communication Networks: When Agents Become Network EntitiesSI 57 paperObservation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station ObservationsSI 53 paperS-Agent 2.0: Spatial Reasoning with a General Coding Agent🔥57 paperA note on the cube inequalitySI 69 paperMultimodal Reranking Is a System One Decision🔥3 paperEvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning🔥2 paperMARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and AutonomySI 54 paperDiscrete Exterior Calculus-based Whittle-Mat\'ern Fields on MeshesSI 75 paperDecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems🔥7 paperLarge Flow Language Models🔥5 paperConvergence of stochastic gradient descent for learning linear neural networksSI 71 paperSage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition🔥56 paperLearning the 4D World through Point Trajectory Forecasting🔥37 paperEvolving Agent Interfaces🔥10 paperEfficient Edge-aware Attention Network for Graph GenerationSI 76 paperSolarRenderer: Few-Step Generative Reference Rendering🔥37 paperJoints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs🔥5

2026-10-20 · 65 条

paperAffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation🔥14 paperSelf-Evaluating Recursive Agents🔥6 paperMemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents🔥19 paperSparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models🔥0 paperLIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints🔥0 paperEvidence-First Agentic Verification🔥11 paperEmpowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution🔥2 paperRobust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning🔥1 paperInterlock: From Local Correctness to Task Completion in Long-Horizon Agents🔥5 paperCo-Evolving Acting and Forecasting for Language Agents🔥2 paperRSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent🔥3 paperTokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents🔥0 paperSelf-Evolving Coding Agents via Harness-Policy Optimization🔥32 paperQD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity🔥0 paperLearning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable🔥4 paperAI-Experiment: an augmented reality art project co-created with artificial intelligenceSI 88 paperFactorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding🔥3 paperFast Construction of Inner Sphere Trees Using Machine LearningSI 58 paperBlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References🔥8 paperOR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners🔥26 paperNewly Identified Planetary Nebula Candidates in M31 using Deep-Learning Search of Hubble Space Telescope ImagesSI 61 paperHSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference🔥2 paperUDL-RT: A unified differentiable all-sky microwave radiative transfer model with learnable parameterizationsSI 60 paperMuse Glimmer 30B: An On-Device Agentic ModelSI 68🔥0 paperECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction🔥1 paperUniAVC: Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling🔥1 paperFirst-Order LoRA Training with Phone NPUsSI 64 paperCoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents🔥28 paperFineSplat: Fine Patches, Local Groups, Detailed Splats🔥3 paperThink Visually Across Space and Time: Grounded Reasoning for Video Segmentation🔥10 paperPolynomial Learning of Positive ReLU Networks under Gaussian InputsSI 61 paperSPARC: Spoken Profile Authorship Recognition Corpus🔥0 paperWorld Model Interpretability: From Decoding Representations to Understanding Latent Worlds🔥3 paperMT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion🔥30 paperFrom Formulation to Articulation: Considerations for AI-Assisted Research in Information TheorySI 70 paperA Method for Linearization of Systems of Quadratic EquationsSI 61 paperBeyond the record: evaluating probabilistic AI weather forecasts deep in the tailSI 68 paperFrechet Forcing: Training Long-Horizon Streaming World Models from Short Clips🔥9 paperPlate-YOLO: An End-to-End Object Detection Framework for Robust Astrometric Registration of Historical PlatesSI 68 paperScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation🔥43 paperLearning from Fleet Experience: A Collective Learning Paradigm for Robots🔥87 paperVision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation🔥1 paperAdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments🔥13 paperA 36.34-day Sub-Neptune Candidate Transiting the Nearby K Dwarf TIC 402710280SI 71 paperDeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal🔥10 paperRoAR-VAE: Improving Latent Diffusability through Robust Prediction🔥23 paperMobile Embodied Agent Network (MEAN): Integrated Framework, Enabling Technologies, and Task-Driven DeploymentSI 86 paperRemembering Has a Price: Learning Memory Worth under Resource Constraints🔥1 paperHoli-World: Building Holistic World Intelligence from Human-Ego Experience🔥27 paperEgoXperience: Learning World-Grounded Egocentric Representations from Human Experience🔥27 paperHandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation🔥3 paperHarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs🔥12 paperTwo hidden layer suffice: the caterpillar netSI 59 paperScaling Parameter-Efficient Fine-Tuning for Brain Encoding🔥18 paperState World Models: Execute the Rules, Generate the Pixels🔥9 paperSpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum🔥20 paperAgent World Model in the Wild: Computer-Use Agent Environment SynthesisSI 60🔥57 paperCompeting Learning in Hybrid Architectures🔥1 paperKronecker Delta Rule for Long Context Linear Attention🔥16 paperAnyGoal: On World Model Generalization Beyond Expert Rollouts🔥22 paperWhere is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy🔥7 paperManga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning🔥15 paperInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation🔥20 paperOpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory🔥60 paperText-to-Image Generative Modeling Without Language Pretraining🔥0

2026-10-19 · 60 条

paperBelief-Trajectory Energy: Measuring the Path to a Prediction🔥8 paperFC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents🔥3 paperConsistent Distribution Matching for Data-Free Diffusion Distillation🔥2 paperOPMD: On-Policy Mechanism Distillation Beyond Output Supervision🔥4 paperBridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries🔥29 paperDream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems🔥6 paperDuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck🔥7 paperFailure Recovery via Belief Updates and World Modeling for Long-Horizon Agents🔥3 paperPack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents🔥92 paperGame2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?🔥4 paperInto the Unknown: Benchmarking AI agents on open scientific research problems🔥71 paperDAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections🔥3 paperSparse Autoencoders Are a Shared Coordinate System for Symbolic Matching🔥2 paperMorphAct: Robot Policies Morphing with the Worlds They Act In🔥6 paperBizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business🔥75 paperReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models🔥7 paperSpeculative Sampling in Interactive Video Generation🔥22 paperPRISM: PRIvileged Sibling-guided Multi-Agent Topology Design🔥2 paperLEV: Thinking Fast and Deep with Looped Decision Models🔥3 paperPremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews🔥4 paperSkip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files🔥3 paperSciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents🔥10 paperResisting Harmful Instructions through Training-Free Weight Editing🔥3 paperDusting the Phantom: Gaussian Allocation for Fading Dynamic Content🔥3 paperCan Visual Generation Expand What Unified Multimodal Models Know?🔥9 paperDuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription🔥2 paperFrom Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research🔥25 paperLearning to Think and Explore in 3D World🔥72 paperSelection Is Not Learning: Choosing Model Futures🔥3 paperLexical Reference Frames: Interpreting LM Residual Streams in Native Semantics🔥17 paperAVC-Reward: Event-Centric Audio-Video Consistency Evaluation🔥8 paperGeoState: Learning View-Decoupled Geometry States for 3D World Modeling🔥1 paperAligning Information Theory and Formal Verification: A Lean Formalization of Rate-Distortion TheorySI 57 paperEnd-to-End Learned Image Coding: From Rate-Distortion Optimization to Practical DeploymentSI 63 paperEmbeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models🔥4 paperHas GPT-6-Astra Achieved Embodied Intelligence?🔥111 paperGenerative AI Produces and Transmits Beauty BiasSI 67 paperAtmospheric Chemistry-Climate Modeling with an AI Foundation ModelSI 61 paperStuck on Shuffle: On Attribute-Object Binding in Vision-Language Models🔥10 paperQuantum-Classical Neural Networks for Solving Lindblad Master EquationsSI 54 paperTowards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design🔥4 paperTriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene GenerationSI 49 paperInfluence of Droplet Morphology on Fluid Dynamics and Impact Erosion of Wind Turbine BladesSI 57 paperTree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning🔥23 paperOfficeTown: Generative Organizations for Evolving Agent Intelligence🔥14 paperEnergy-Aware Earth System Science: A Community RoadmapSI 55 paperRAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars🔥17 paperAgentic Image Generation in the WildSI 60 paperLearning angles for quantum approximate optimizationSI 57 paperExplicit Oblique Inverses of the Approximate Discrete Radon TransformSI 65 paperMOSS-Image Technical ReportSI 59🔥9 paperHexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents🔥82 paperExecution Before Memory: Diagnosing Memory Failures in Video World Models🔥15 paperA Language-Informed Loss for Visual GenerationSI 60🔥2 paperTool Recommendation for Multi-Step Agents: Finding Every Tool a Task NeedsSI 61 paperDLite: History-free Speculative Decoding for Agentic AI🔥18 paperPersistent Planar Memory for Video World Models🔥3 paperDiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses🔥13 paperStopWatch: Goal Grounding for Object-goal Navigation🔥2 paperBrennan's Conjecture and the Universal Integral Means SpectrumSI 66

2026-10-17 · 25 条

paperPAIR: Bridging Perception and Action in Vision-Language-Action Models🔥1 paperForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion🔥2 paperSpeech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription🔥3 paperScalable Weak-to-Strong Verifier Hardening for Agent Environments🔥4 paperBeyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR🔥8 paperLeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification🔥5 paperFlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention🔥8 paperVirtual Head Attention🔥10 paperCopy-Paste Language Models🔥5 paperEqual CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR🔥2 paperDiminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility🔥1 paperOne Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation🔥2 paperLearning to Read Out: Unembedding Dynamics in Language Model Pretraining🔥3 paperCan World and Action Modeling Benefit Each Other under Unified Causal Training?🔥40 paperMine, Sample, Render: Test-Time Diversity Alignment Of Generative Models🔥7 paperBehavioral Compositionality of Sparse Autoencoder Representations🔥107 paperWhen the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill🔥2 paperData World: Scaling Data Environments from Scratch🔥28 paperExplaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization🔥3 paperLEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents🔥7 paperFDE-Gym: The Last Mile of AI Delivery🔥285 paperSUPRA-TEX: 3D Generation with Super-Aligned Texture🔥8 paperOmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling🔥32 paperPathFM: Fast Generative Forecasting of Multivariate Trajectories🔥3 paperGen4P: Video Generators are 4D Perceivers🔥5

2026-10-16 · 60 条

paperSimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models🔥2 paperCLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling🔥1 paperDo Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?🔥14 paperSimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models🔥15 paperLearning Where to Split: Dynamic Band Splitting for Audio Source Separation🔥56 paperANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs🔥0 paperPINT: A Unified Model with Shared Predictive Intent for Robot Manipulation🔥2 paperRecursive Environment Scaling for General Long-Horizon Agents🔥4 paperInfoVis: Unified Slide Image Generation and Editing🔥22 paperEdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation🔥20 paperRoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment🔥201 paperCowork-Gym: Synthesizing Interactive Work Environments at Scale🔥7 paperH-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression🔥3 paperSelf-Evolving Agent Harness🔥199 paperAI-Driven, Timing-Aware Power Optimization🔥1 paperWorldMemBench: A Comprehensive Benchmark for Memory of Video World Models🔥8 paperSERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning🔥5 paperTimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models🔥1 paperDeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding🔥32 paperRepForcing: Representation-Space Initialization for Autoregressive Video Distillation🔥2 paperInfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views🔥39 paperVascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution🔥2 paperCommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation🔥18 paper86 unknowns for Hilbert's tenth problem over the rationalsSI 49 paperOrbia: Do Generated Videos Form a Consistent 3D World?🔥28 paperWorldCast: Exploring Intelligent Visual Generation in World State Prediction🔥30 paperSymplectic groupoid multiplication and Poisson integratorsSI 59 paperMAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer EnvironmentsSI 52🔥153 paperAthanor: An Agent-Native System for Autonomous Post-Training ResearchSI 54🔥8 paperA One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL TensorizationSI 48 paperPhysical AI: A Survey of Models, Learning, Systems, and Open ChallengesSI 60 paperWhen Rotation Bounds Nothing: Streaming Image Classifiers to Field Nodes Under Physical CaptureSI 54 paperVLA-Δ: Learning Physical State Transition for Vision-Language-Action Models🔥54 paperEach Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL🔥56 paperCarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance🔥10 paperTrajectory-Level Speculation with Semantic Verification for Tool-Using AgentsSI 55🔥21 paperKolmogorov-Arnold Networks: Curse of Dimensionality and Structural BiasSI 53 paperWaypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation🔥666 paperHurricane Laura-induced loads on wind turbines -- Part I: High-fidelity modeling and sensitivity to turbulent inflow conditionsSI 75 paperCoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness🔥2 paperJianmu-Q: Bridging Quantum Field Theory and Quantum Hardware with AI AgentsSI 49 paperMemory as Weights: Internalizing Long-Term History for Streaming Videos🔥6 paperCan AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical CyclonesSI 55 paperIntern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling🔥17 paperMosaic: Multi-Session Agentic Reinforcement Learning🔥54 paperEVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment🔥1 paperTerminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine🔥18 paperOpenGCUA: Toward a Fully Open Stack for Generalist Computer Use🔥315 paperSkill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models🔥1 paperOS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using AgentsSI 51🔥9 paperMMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents🔥5 paperSCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation🔥50 paperMJev-Spatial: System One Spatial Intelligence via Native Attention Matching🔥352 paperRouting Policy Optimization for Online Diffusion Reinforcement Learning🔥18 paperVelox: Spatial Memory Makes World Models Efficient🔥13 paperA team of Gemini 4 Argon agents beats MinecraftSI 51🔥1 paperLearning Self-Orchestration in Decentralized Agent Swarms🔥11 paper3DCodeVerse: Exploring 3D Worlds as Code🔥50 paperMLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning EngineeringSI 58🔥25 paperCoDA: Co-Evolution of Data Engines and Action Policies🔥9

2026-10-15 · 65 条

paperG^3VLA: Geometric Inductive Bias for Vision-Language-Action Models🔥5 paperHumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution🔥11 paperSuper-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate🔥13 paperVela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization🔥0 paperMimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking🔥1 paperNavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime🔥2 paperJag: Direct Box Prediction for Efficient Visual Grounding🔥1 paperBeyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation🔥24 paperSWEeper-Bench: Can Agents Discover Bugs in Interactive Software?🔥2 paperBigCell: Generating Gigapixel Whole-Slide Images🔥3 paperKV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization🔥25 paperProgAgent: Learning Tool Orchestration through Programmatic Training🔥5 paperExploring the Limits of Combinatorial Generalization in Embodied Manipulation🔥2 paperApertus 1.5: From Open Text Models to Open Multimodal Reasoners🔥24 paperSkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification🔥8 paperSyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation🔥0 paperProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty🔥1 paperActing Through Registers🔥2 paperMany Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders🔥1 paperDiff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing🔥1 paperAre We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models🔥3 paperEfficient Scene-Text Refinement via Pixel-Space Grouped Image Generation🔥6 paperScaling Online Optimal Transport Minibatches for Flow Matching🔥1 paperHybrid Reasoning Agents🔥19 paperWong--Zakai Convergence and FNO Learning for Stochastic Volterra EquationsSI 52 paperNon-Abelian quantum Hall states at strong Landau level mixing: finding anyons with first-principles AISI 50 paperFirst L-type substellar object discovered in the vicinity of the embedded cluster NGC 2023SI 57 paperJoint Subspace Sparse Attention for Efficient Long-Context Decoding🔥0 paperNeural networks applied to forecasting the astroclimatic and meteorological parameters in an operational contextSI 77 paperDecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision🔥2 paperMA-Bench: Measuring Operational Planning in Language Models🔥0 paperThe grounded spirituality of mathematicsSI 64 paperDeep Learning for Atmospheric Turbulence Mitigation: A Comparison Between GANs and TransformersSI 77 paperSeeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory🔥31 paperixi-sLM: On-Device sLM for AI Call Agent ServiceSI 67 paperDiagnosing and Correcting Reward Hacking in Verifiable Instruction Following🔥6 paperTextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering🔥3 paperτ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions🔥9 paperShare the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models🔥1 paperRuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios🔥43 paperGenerative World Simulation with DAO and JING🔥2 paperIdentifying Planetary Nebulae Candidates from IPHAS and VPHAS+ Surveys via YOLO Deep Learning ModelsSI 79 paperQ-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset TokenizationSI 50 paperMore Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning🔥11 paperActionOPD: Distilling Decisions, Not Tokens🔥44 paperEuler: Towards Human-Centered Multi-Agent Mathematical DiscoverySI 53 paperLatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation🔥49 paperTrainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training NetworksSI 57 paperWhat Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds🔥2 paperLong-Horizon RL Needs Muon🔥4 paperAre We Overthinking One-Step Generation?SI 70 paperDoc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents🔥39 paperDo AI Agents Gossip? Evaluative Talk in Human and AI-Agent Online CommunitiesSI 59 paperCortex: Consolidating Context into Parametric Memory🔥46 paperTowards Agentic Robots: Model, Data, Environment, and Harness🔥18 paperThe COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation🔥1 paperProbabilistic AI models outperform numerical weather prediction models on record breaking heat extremesSI 59 paperPhysical Time as a Missing Dimension of Robot Policy Memory Dynamics🔥2 paperAny Time, Any Space: A World-State-Centric Framework for Agentic Video Generation🔥164 paperRecovering Reliable Supervision via Critique-Guided On-Policy Distillation🔥47 paperLatent Compaction with Test-Time Training🔥1 paperPlayer-1: Learning to Play from Synthetic Experience🔥117 paperVITAL: From Visual Motion to Precise Action🔥3 paperRepresentation Conditioning for GenerationSI 63 paperSafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving🔥2

2026-10-14 · 64 条

paperScoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics🔥33 paperDiffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength🔥3 paperSALD: Self-Referenced Advantage Learning for Diffusion Models🔥30 paperVEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval🔥17 paperWeb$hell: A Unified Interface for Agentic Web Access🔥0 paperPsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems🔥1 paperA Gauge-Inspired Coupled Fokker--Planck System for Multistate Stochastic Dynamics: Formalism and 1-D Numerical ImplementationSI 68 paperThe Future of AI-assisted Physics: Discovering, Verifying and Organizing Results via FormalizationSI 66 paperMeshRepair: Autoregressive Topology Repair for Generated Artisan MeshesSI 86 paperClawLoop: Self-Improving Agents via Harness-Native Training Loop🔥13 paperOpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native ToolsSI 70🔥29 paperAutoEnvScaling: Automating the Data Flywheel with Terminal Agents🔥5 paperLatent World Action Model for GUI Agents🔥2 paperGeoFix: Geometry Fixing for 4D Consistent Generation🔥10 paperAI Meets Turbulence Modeling: Complex Systems PerspectiveSI 74 paperEviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment🔥12 paperLightVAE: Towards Compact and Efficient Video Autoencoders🔥9 paperPro-t-VAE: Closed-Form Student's t Mixtures for Robust Prototype DiscoverySI 75 paperProbable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents🔥1 paperExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling🔥21 paperHGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation ModelsSI 84 paperCIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks🔥2 paperCyclic steepest descent is $R$-superlinearly convergent for almost every initialization on two-spectrum quadraticsSI 66 paperA Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution🔥14 paperData-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping🔥4 paperVIEWCRAFT: Evolving What Multimodal Agents See and How They Read It🔥3 paperElephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding🔥4 paperSelf-Distillation with Verbal Regularization🔥7 paperHexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision🔥2 paperSpectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards🔥5 paperCineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction🔥14 paperQueue-Aware Token Communications: Bridging AI Representation and Wireless ServiceSI 71 paperTPPO: Tracking-Value PPO For Language Model Reasoning🔥40 paperX-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning🔥27 paperWhat the Machine Invented: Mining New Mathematical Instruments from OpenAI's October 2026 Release of AI-Generated MathematicsSI 77 paperMultics: Generative Multi-Player World Model with Hierarchical Communication🔥32 paperAReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers🔥8 paperTacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency🔥0 paper4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling🔥0 paperOpen-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence🔥14 paperDeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter🔥15 paperOn quasi-lisse affine vertex algebras $L_{-1-h/6}(\mathfrak{g})$ from rank-one Argyres-Douglas theoriesSI 68 paperLearning How to Remember: Memory Modality Selection for GUI Agents🔥27 paperAgent-Reflex: Teaching Language Agents to Act Reflectively🔥17 paperFish Audio Drama 3 Technical Report🔥5 paperSHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces🔥1 paperWorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution🔥8 paperSWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents🔥3 paperJevGPT: Thinking Fast and Slow in Autonomous Research🔥3 paperPING: physics informed graph neural network for advection-diffusion processes with applications to solar power forecastingSI 81 paperUnsupervised and Supervised Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 2)SI 74 paperUrbex: Agentic Spatial Grounding for City-Scale 3D Scenes🔥58 paperReTerm: Recovery Training for Self-Improving Terminal Agents🔥11 paperWAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction🔥7 paperVideoJev: System One Model for Video Understanding and Interaction🔥38 paperRubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges🔥5 paperJeva: System One Models from First Principles🔥41 paperRelative-Entropy Geometry and Convergence in Nonconvex Wiretap OptimizationSI 67 paperWorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D WorldSI 64🔥7 paperAesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards🔥22 paperDoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning🔥1 paperTev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards🔥10 paperCepheid: Decoupling Scale from Structure for Cross-Family Motion Completion🔥12 paperEgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ🔥14

2026-10-13 · 32 条

paperRelevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents🔥29 paperSystematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method🔥9 paperCrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation🔥16 paperQuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching🔥6 paperGroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed🔥17 paperGroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives🔥114 paperSAGE: Salient Factor Discovery and Generation with Visual Foundation Representations🔥2 paperThe Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation🔥3 paperMetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code🔥17 paperWhen to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models🔥2 paperDistributionally Robust Mixture-of-Experts Training🔥5 paperHumanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models🔥19 paperSPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code🔥1 paperVIS-Ground: Video Interactive Storytelling with Contextual Grounding🔥15 paperARCS: Towards Precise Text-to-SQL via Structured Disambiguation🔥4 paperCoding-Agent Benchmarks Should Match Their Users' Task Flows🔥11 paperVideo-Conditioned Generative Joint 2D-3D Hand Motion Recovery🔥1 paperLess from More: Reinforcing Sparse Video Reasoning from Dense References🔥4 paperClinician use of language models diverges from how the models are evaluated🔥3 paperThinking Inertia: LLMs Keep Thinking When Told Not To🔥43 paperFew-Step Generation via Data-Space Iteration🔥3 paperUniversal Textual Teaching for LLMs🔥10 paperBudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion🔥3 paperMAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances🔥1 paperMental-Models for Multi-Agent Systems🔥4 paperOne Model to Loop Them All: Elastic Latent Recurrence for Language Models🔥6 paperSelf-Preservation in Language Models🔥3 paperLearning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training🔥5 paperScaling Agentic Data for Long-Horizon Terminal Intelligence🔥86 paperAgentSWE: Can Coding Agents Build the Agent You Actually Want?🔥76 paperMulti-Stream Attention Residuals🔥32 paperSpatialASM: Internalizing Active Mentalization for Spatial Reasoning🔥15

2026-10-12 · 41 条

paperInducing Process Supervision from Outcome-Only Reinforcement Learning🔥19 paperEncore: Few-Shot Agentic Discovery of Manipulation Strategies🔥1 paperPolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence🔥27 paperVideo-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution🔥11 paperHere the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation🔥48 paperFrom Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning🔥11 paperWhen Do Biological Reasoning Models Use Their Biological Inputs?🔥10 paperGraphDecisionBench: Benchmarking System One Models on Graph Tasks🔥10 paperSoloQ: Calibration-Free Quantization for Diffusion Language Models🔥30 paperStateless Language Agents: Scaling Long-Horizon Automated Research🔥9 paperVisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs🔥48 paperWhich Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning🔥1 paperJudging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression🔥14 paperTouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning🔥11 paperWhen Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better🔥17 paperSepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model🔥34 paperDataVista: Diagnosing Multimodal LLMs on Data Video Understanding🔥13 paperCan AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition🔥43 paperDex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration🔥1 paperSWE-Duel: Towards a Self-Scaling Arena for Coding Agents🔥15 paperContextual Correction of Parallel Draftsfor Speculative Decoding🔥26 paperDiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models🔥130 paperSoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments🔥86 paperRecurrent Harness for Agentic Continual Learning🔥11 paperReflex: Visually Grounded Reactive Humanoid Control🔥100 paperSurfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding🔥13 paperLearning Representations to Guide Pixel Diffusion Transformers🔥21 paperWork2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction🔥42 paperEmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents🔥56 paperContinually Post-training Small Models via Synthetic Self-distillation🔥32 paperThe value of information and the emergence of communication in evolved e-puck robots🔥9 paperPreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling🔥11 paperMixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement🔥10 paperRethinking Relative Policy Differences Transfer of On-Policy Distillation🔥10 paperThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning🔥4 paperProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents🔥41 paperS-Space: Exploring Spatial Workspace in Multimodal Language Models🔥267 paperAMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis🔥9 paperRSI-Anything: Unlocking Recursive Self-Improvement with World Models🔥24 paperInstantFusion: A Shared Latent Interface for Heterogeneous Image Generators🔥16 paperTowards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark🔥16

2026-10-10 · 20 条

paperA GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning🔥13 paperOpera: A Verbal Critic Framework for Long-horizon Coding Agents🔥14 paperMara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution🔥9 paperBehavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics🔥4 paperInvestigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation🔥5 paperSpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models🔥7 paperYou Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue🔥6 paperIncidental information contaminates patient notes and disrupts clinical reasoning in large language models🔥6 paperCan AI Agents Make Open-Ended Scientific Discovery? Evidence from Station🔥8 paperFrozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI🔥6 paperEvaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation🔥4 paperMIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent🔥8 paperSynthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction🔥7 paperSkill Constellations: Tracing the Supply Chain of Agent Skills on GitHub🔥5 paperIncremental Open-Ended Deep Research with Structured Harness🔥7 paperMemento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks🔥35 paperPredicting Cable Dynamics with Physical Attention Bias🔥5 paperA Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization🔥8 paperPumpire: Unified Benchmark for Metric Distance Estimation🔥18 paperOne Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts🔥7

2026-10-09 · 63 条

paperFoundations of Large Language Models🔥42 paperMARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination🔥5 paperSatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery🔥5 paperLearning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors🔥5 paperReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning🔥12 paperIn-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks🔥38 paperSparseEngine: Sparse-First Inference Engine🔥17 paperTerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows🔥5 paperPost-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards🔥29 paperRetrieval-Centric Deep Learning in Growing Nonparametric Neural Networks🔥4 paperDo LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation🔥14 paperFrom Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation🔥163 paperWhat Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents🔥12 paperMC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers🔥37 paperSanSi: A Looped Typed Decision Model for System 1.5 Thinking🔥6 paperLearn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?🔥103 paperCARE: Certifying Acceleration for Vision-Language-Action Inference🔥6 paperSPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation🔥5 paperEDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks🔥6 paperU-Space: Uncovering When and Why Uncertainty Arises in Language Models🔥38 paperOn-Policy Distillation Teaches New Skills but Not New Knowledge🔥6 paperA faster matrix multiplication algorithm through structured optimizationSI 55 paperHigh-Fidelity Baseline Design and Station Keeping Analyses for Earth-Moon Vertical OrbitsSI 51 paperBarron Optimal Transport I: Generative ModelingSI 54 paperGATOR: Generative and Agentic 3D Object Reconstruction From Casual ImagesSI 54🔥1 paperThe Lattice of Transition LawsSI 63🔥5 paperREMORY: Learning Residual Memory for Context Compaction🔥40 paperUSDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation🔥12 paperSpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces🔥6 paperA Physics-Constrained Implicit Profile Network for Continuous Reconstruction of Tropical Cyclone Near-Surface Wind ProfilesSI 60 paperWhy machines will still not rule the worldSI 51 paperSAIL: Scientific Agentic Intelligence via a Science-Aware LoopSI 55 paperScaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals🔥2 paperHI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High ResolutionSI 70 paperProbing Massive Star Formation with Intrinsic Multiplicity Constraints from TESS Eclipsing BinariesSI 59 paperChaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers🔥4 paperAutomated Disinformation and Malicious AI Swarms: Risks for Democracy and Development in AfricaSI 60 paperMiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement🔥72 paperSuperNav: An Agentic Navigation System for Any Task in Any Scene🔥59 paperExtending convolutional neural networks to finite-volume meshes for fine-scale reconstruction of wall-bounded turbulenceSI 50 paperVibeEdit: Image Editing with Canvas Instructions🔥12 paperFrom Prompting to Composing: A Spatial Canvas Interface for Poster Generation🔥6 paperTokenRouter: Efficient Serving System for Token-Level LLM Routing🔥84 paperToward Lunar Legged Robots: Field Deployment Lessons at LUNASI 52 paperTestPrism: Rethinking Test Evaluation Beyond a Single Reference🔥34 paperMulti-Agent Egocentric World Model with Fine-Grained Embodied Interaction🔥52 paperSparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference🔥21 paperReasoning-Informed Visual Editing🔥12 paperDistilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models🔥8 paperAccurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict🔥8 paperEmbodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement🔥19 paperAgentGarten: Code Worlds for Evolving AgentsSI 59🔥102 paperSpaceFlow: Locally Controllable 3D Generation🔥8 paperSpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models🔥6 paperViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills🔥9 paperOneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video🔥24 paperBeyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching🔥38 paperLEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation🔥16 paperBrickBench: Evaluating Agentic Brick Design🔥7 paperOmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning🔥15 paperWorldGuide: Goal-Directed Video World Model for Procedural Task Execution🔥8 paperOuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs🔥42 paperDreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training🔥32

2026-10-08 · 63 条

paperLearning Multimodal Embeddings with Evidence-Aligned Readout🔥7 paperSWE-Game: Can Coding Agents Build the Games We Want?🔥22 paperSalt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation🔥1 paperSTEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization🔥84 paperReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation🔥29 paperSemifactual Credit-Augmented Policy Optimization🔥33 paperVIEScore2: Unified Image Evaluation with Spatially Grounded Explanations🔥20 paperUniWAM: Unified World-Action Model🔥41 paperRethinking World-Action Model for Compositional and In-Context Robotic Manipulation🔥3 paperFastOPD: On-Policy Distillation for Lightweight VLA Deployment🔥1 paperWebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites🔥15 paperGains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective🔥23 paperStepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search🔥0 paperQuestioning the Questions: Sustaining Self-Evolution in Reasoning Models🔥56 paperAgentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads🔥17 paperSheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision🔥1 paperVepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction🔥51 paperImproving Proactive AI Assistance with Hierarchical Procedural Understanding🔥7 paperMinimal Witness Reinforcement Learning🔥15 paperInternalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation🔥7 paperRecurrent Looped Transformer🔥19 paperDLoop: Looped Speculative Decoding🔥8 paperOn-Policy Distillation with Negative-Policy Rollouts🔥13 paperDecepEval: A Benchmark for Evaluating Deception in LLM Agents🔥55 paperRecursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness🔥62 papernanoMuse: An Open-Source Personal Agent for Every Device You Own🔥67 paperWorldSonus: Bringing Sound to Worlds🔥31 paperJoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint RepresentationSI 74 paperTask-Sufficient Contraction: Source Selection for Machine Information Interfaces🔥0 paperRe-calibrated analytic stellar evolution formulae for the main sequence: Extension to massive stars and variations in $[\alpha/\mathrm{Fe}]$SI 67 paperOn KL-Regularized Policy Optimization🔥18 paperPhysEvo: Astra Can Act, Let It🔥8 paperTowards AI-Generated Music Plagiarism Detection as a Version Identification ProblemSI 67 paperDepth-to-RGB: Repurposing a Frozen Depth Estimator for Geometry-Guided CompositingSI 52 paperCADFather: Autonomous CAD Reconstruction through Coordinated Tool Use🔥0 paperQ-PACE: Dynamic Precision Allocation for Quantization-Aware TrainingSI 51 paperCo-Evolving Robot Orchestrators and Policies through Deployment🔥1 paperDerived Picard reconstruction for graded surfaces with stopsSI 49 paperRLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning🔥17 paperFrom Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery🔥13 paperEC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matchingSI 47 paperMeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent SpacesSI 80 paperArtificial intelligence pathways from weather to climateSI 60 paperOn-Demand Robotic Assembly via Differentiable Geometric Part RepairSI 51 paperEfficient 3D Gaussian Head Avatars for Edge DevicesSI 62 paperUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation🔥18 paperSkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles🔥2 paperInverting Multi-Vector Visual Document Indices🔥15 paperDo Generative Priors Align with Human Naturalness Perception?SI 55 paperPerspective: Content-addressable memories as a computing primitive for today's AI and beyondSI 60 paperAdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation🔥16 paperMechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position🔥24 paperUniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy🔥3 paperRoboQuest: Generalist Physical Agents that Search, Inspect and Test🔥3 paperRobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments🔥23 paperSGF+: Decoupling Gradient Flows for Autoregressive Video Generation🔥46 paperConditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate FieldsSI 56 paperRunningTab: Direct Workspace Interaction with Environment-Side Tabs🔥32 paperQuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation🔥10 paperGRACE: Generation-aware latent compression for efficient video generation🔥55 paperLong-WAM: Scaling the Context of World-Action Models🔥77 paperEngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory🔥1 paperTetris3D: 3D Scene Generation With Objects That Fit Together🔥29

2026-10-07 · 64 条

paperAccent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning🔥4 paperAdaptive Latent Capacity for World Models🔥7 paperSlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving🔥7 paperTaming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing🔥20 paperMaking LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment🔥10 paperSource Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution🔥0 paperGUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution🔥8 paperAGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation🔥11 paperSelection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents🔥12 paperThe AI Theorist reveals excitonic structure in α-RuCl_3🔥3 paperHarness-Aware Distillation for Small Language Model Agents🔥4 paperDuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation🔥55 paperWorld Action Learning via Interaction-Centric Spectral Latent Guidance🔥23 paperSEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting🔥16 paperUnAct: Gradient-Free Unlearning via Targeted Activation Intervention🔥4 paperConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution🔥0 paperLearning Discriminative Geometry for Drifting Models🔥2 paperDiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling🔥7 paperEVISKILL: Grounding Skill Evolution in Replayable Evidence🔥32 paperAutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents🔥23 paperHLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing🔥1 paperMiniCorp: The Last Mile of the AI Agent Firm🔥9 paperMEND: RL For Flow Models via Proximal Velocity Matching🔥1 paperHuatuoGPT-3: RL-Only Domain Adaptation from Base Models🔥18 paperJLD: Perceptual Distance Through A Jacobian Lens🔥1 paperJudged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions🔥2 paperCapability-Driven Self-Evolution of Agent Memory🔥12 paperLoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches🔥11 paperLearning to Read the Contextual Tokens in Diffusion Transformers🔥1 paperDistScene: Object-to-Scene Distillation for 3D Scene Generation🔥4 paperEvaluating Inference Compute for Generative AI: A Framework for Enterprise WorkloadsSI 82 paperMuon Is Theoretically Wrong For Convolutions, But Empirically EffectiveSI 71 paperMoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image PairsSI 57 paperArmillary: A Label-Free Coordinate System for Stellar SpectraSI 62 paperIs this machine playing?SI 53 paperNetAgent: Multi-Task Agentic Network Traffic Analysis Made PracticalSI 60 paperAlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationSI 56 paperUnderstanding and Enhancing Backdoor Persistency in LLM Agent Post-Training🔥5 paperPersonal-Agent Mediated Recommendation with Cross-Platform User History🔥3 paperHiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution🔥5 paperHiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models🔥3 paperFrom Evidence to Action: How Tool-Using Agents Fail🔥28 paperAdversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian MixturesSI 57 paperTRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models🔥39 paperAttacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents🔥2 paperHarness Engineering for Software Engineering via Modular Executable Dev-Primitives🔥3 paperEmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation🔥10 paperDAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks🔥4 paperAlign, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language ModelsSI 69 paperStarspots on weak-lined T Tauri stars in the sigma Orionis clusterSI 55 paperAlgebraic Eisenstein classes for $\mathrm{GL}_n$ with applications to the Bianchi caseSI 56 paperInfrastructure-Native Computing with Electric Power GridsSI 64 paperNeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale🔥7 paperRethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability🔥109 paperUNREAL: Unifying Retrieval and Long-Context with a Single Model🔥15 paperSingular Value Decomposition: A Geometric Rediscovery, Where Proofs Become AlgorithmsSI 56 paperSOPHIE and TESS characterization of fourteen TESS Objects of Interest: nine planetary systems and five low-mass stellar companionsSI 58 paperTowards In-Parameter Memory Augmentation for Large Language Models🔥2 paperVeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning🔥1 paperAdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model🔥3 paperCtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching🔥0 paperALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing🔥3 paperBuilding Rome from a Single ImageSI 54🔥2 paperWorld Models' Last Exam in Physics🔥1

2026-10-06 · 65 条

paperTextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization🔥2 paperOSWorld-Pro: Process-based Evaluation for Computer Use Agents🔥9 paperLearning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment🔥1 paperPluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins🔥2 paperThe Extender: A Log-Structured Transformer🔥6 paperWM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning🔥10 paperData Unlearning via Inverse Distillation🔥0 paperFoundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym🔥7 paperTail-Influence Sampling for CVaR Policy Evaluation🔥21 paperQuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code🔥5 paperJEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts🔥2 paperCANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG🔥11 paperFrom Knowledge Access to Source Learning: Developing Source-Specific Competence🔥2 paperThe Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models🔥2 paperOpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies🔥1 paperSelf-Supervised Scaling of Terminal Environments for Scientific Domains🔥7 paperImproving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing🔥7 paperPointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation🔥29 paperOmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination🔥0 paperIn-Distribution Forcing for Long Video Generation at Test Time🔥4 paperEyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras🔥9 paper4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes🔥20 paperGeneralizable Neural Downscaling of Earth System Model Wind Fields via Continuous Dynamics ModelingSI 76 paperTraining Numerical Intelligence via Auto-Diagnosis and Skill Discovery🔥3 paperProbabilistic Algorithms for Ising Machines from Optimization to Generative AISI 82 paperPeriscope: Extending Frozen Language Models Beyond Their Context Window🔥1 paperWhy Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image ClassificationSI 66 paperAEGIS: Differentiable Mars Climate Model with Neural ClosuresSI 66 paperCUAWright: A Minimal Unified Interface for Digital Agents🔥4 paperDynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction🔥3 paperALoDLM: Adaptively Looped Diffusion Language Models🔥37 paperQuantized Transformers for Massive MIMO Precoding with Automatic Resolution TuningSI 61 paperCurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model🔥0 paperPaLoRA: Paced Low-Rank Adaptation for Continual Learning🔥3 paperRethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency🔥8 paperSpecific Algorithmic Interpretability of Neural Networks: A Case Study on TexturesSI 63 paperPerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training🔥3 paperHybrid Ray-Tracing and Physics-Embedded Neural Modeling for High-Fidelity Channel Reconstruction in Wireless Digital TwinsSI 66 paperRobotUse: Allocating Computation, Context, and Decisions🔥6 paperCode2Games: Enabling Coding Agents for Gaming World Generation🔥3 paperSelf-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation🔥1 paperSearchJev: A Fast and Calibrated System-1 Model for Search Agents🔥8 paperMemadapter: Counterfactual Adaptation Against Memory-induced Sycophancy🔥7 paperArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single ImageSI 76 paperMobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian SplattingSI 60🔥16 paperASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience🔥11 paperDemonstration of a Structured Agentic Workflow for Applied Quantum Computing ResearchSI 65 paperPrism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training🔥4 paperAI Agents as a Research Team: A Human-Supervised Case Study in Stellar SpectroscopySI 59 paperPoisson-GENERIC Neural Operators: Exact Metriplectic Structure in Function Space via Casimir EntropiesSI 62 paperKandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation🔥88 paperNexus: An Execution Fabric for AI Agents Across Cloud, Edge, and DevicesSI 60 paperWhen to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models🔥7 paperCertification of Real Images through Calibrated Content Authentication🔥7 paperLearning to Learn a Language🔥1 paperNoise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering🔥8 paperArm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models🔥1 paperGolod--Shafarevich for arithmetic surfacesSI 63 paperOptimizing the Optimizer: Language Models Discover Faster Molecular Relaxation🔥4 paperQuantum codes are quantized codes: Stabilizer codes from quantization over finite fieldsSI 63 paperRealtimeWAM: One-Step Asynchronous World Action Models🔥7 paperRepresentation-Space MMD for Diffusion Language Models🔥3 paperTowards Looped Models Done Right, Part II: Rethinking at Fixed Points🔥8 paperInterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation🔥0 paperBase Models Can Reason By Taking a Cue From Training Data🔥6

2026-10-05 · 50 条

paperGTR: Gated Token Recurrence for Efficient Dense Prediction🔥3 paperDEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS🔥9 paperPDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs🔥18 paperLVMT: Video Mask Transformer for Long-term Video Segmentation🔥0 paperTriadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling🔥3 paperOn-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training🔥2 paperMotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation🔥63 paperHelixWorld: A Real-time Interactive Audio-Visual World Model🔥2 paperFrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation🔥37 paperDoes Learning Protein Folding Generalize to Broader Reasoning?🔥91 paperCovert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems🔥3 paperLexReward: A Taxonomy-Driven Reward Framework for Legal Language Models🔥13 paperDiptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production🔥7 paperDream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling🔥0 paperScience or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers🔥11 paperVeriHarness: Scaling Agentic Verification for Long-Horizon Tasks🔥4 paperLooping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts🔥4 paperScience Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems🔥7 paperLocal Support Learning🔥2 paperEditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling🔥6 paperSimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation🔥9 paperSCION: Scene Composition with Instanced Neural PrimitivesSI 64 paperOctrees as an Explicit 3D Language🔥2 paperSideKernel: A Usable microVM Sandbox for AI Coding Agents on macOSSI 66 paperFrom Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders🔥1 paperWorld Action Modeling with Progressive Visual Planning🔥2 paperPost-Training Quantization of Autoregressive Weather ModelsSI 80 paperSpatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory🔥3 paperA Token Service Interface for AI-Native RANsSI 76 paperMathematical Illustration: Proof, Intuition and AISI 81 paperSkill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation🔥2 paperMetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning🔥5 paperScaling Trajectories for Complex Tasks through Recursive Self-Rewrite🔥27 paperA new upper bound for the irrationality exponent of $\zeta(2)$SI 50 paperLight Entropic Optimal Transport on Riemannian ManifoldsSI 54 paperSource Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It🔥15 paperEvolving Hybrid Quantum-Classical Architectures for Image ClassificationSI 68 paperT3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from ImagesSI 90🔥7 paperEnergetic Variational Deep Learning for Solving High-Dimensional Stationary Fokker-Planck EquationsSI 55 paperNative Action-Prior Learning from Videos for World Action Models🔥9 paperEdgeAgent: Orchestrating On-Device LLM inference for End-User Multi-Agent Systems on CPU-GPU Unified Memory ArchitecturesSI 52 paper16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit CostsSI 61 paperThe origin of dispersion in the wind mass-loss rate--luminosity relation of massive O starsSI 63 paperI2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision GeometrySI 49 paperEfficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability🔥5 paperHyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents🔥13 paperWorld Embedding Benchmark🔥16 paperProAR: Learning Prospective Reasoning with Autoregressive Video Models🔥6 paperPivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models🔥18 paperPlanning to LearnSI 56

2026-10-03 · 25 条

paperArchitect-Ant: Editable Automatic Furnishing of Architectural Floor Plans🔥27 paperReplacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration🔥5 paperOpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories🔥14 paperX-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization🔥65 paperRLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers🔥12 paperOn-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics🔥179 paperWhen Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs🔥6 paperPersona Dosing: Calibrated Activation Steering for Graded Trait Control🔥48 paperMemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization🔥7 paperTransformers Stop Thinking Too Early, and a Tiny LoRA Fixes It🔥72 paperOTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport🔥7 paperHoneycomb: Constant-Size Scene Memory Representation for Video World Models🔥5 paperLOCI: Spatial Linear Memory for Streaming World Models🔥10 paperRemoving the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation🔥11 paperJevSpawn: Adaptive Agentic Inference through Compositional Action Spaces🔥7 paperPhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop🔥17 paperSemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation🔥11 paperVideo Generation Models: A Survey of Post-Training and Alignment🔥56 paperEgo2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation🔥25 paperGeneralization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs🔥9 paperLatent-Foresight: End-to-End Learning Predictable Representations for Latent World Models🔥5 paperWhere-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes🔥17 paperKeyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models🔥5 paperDecoding Looped Transformers Better for (Almost) Free🔥25 paperScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research🔥11

2026-10-02 · 64 条

paperDecentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding🔥41 paperPrefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs🔥7 paperWhen Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents🔥7 paperDo Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents🔥5 paperDataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration🔥10 paperJoint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy🔥1 paperDoes Native 3D Texture Generation Necessarily Require 3D Assets for Training?🔥8 paperLearning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models🔥0 paperAgent Priors-guided Policy Learning🔥44 paperCorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning🔥24 paperControlled Decoding Attacks on Black-Box LLMs🔥2 paperPretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing🔥3 paperE-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models🔥57 paperDevils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models🔥9 paperExplore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling🔥7 paperFlexRouter: Learning Complementary Model Sets for Flexible LLM Routing🔥1 paperPrompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions🔥1 paperBenchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation🔥11 paperSmaller Models, Better Rejects: Preference Distillation Scaling🔥15 paperA Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review🔥32 paperBeyond the Current Scene: Event-Referential Grasping with Active View Selection🔥18 paperEgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos🔥45 paperBetter Supervision Is Nearby: Neighborhood On-Policy Self-Distillation🔥15 paperMultimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces🔥23 paperFACET at WMT 2026 Automated Translation Quality Evaluation TaskSI 53 paperPredictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts🔥1 paperDexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation🔥0 paperPixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion🔥7 paperMemorizon: Training World Models Beyond Their Context Window🔥10 paperEvaluating Hybrid Quantum-Classical Models for Reduced-Order Brain Deformation DynamicsSI 60 paperMake Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL🔥50 paperBenchmarking Generative Models for Weather Data Assimilation on Real Station ObservationsSI 59 paperPersonalized Image Generation with Reasoning and Reflection🔥1 paperAlign Then Reason: A Multimodal Lip-Sync Judge for Dubbing🔥3 paperActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization🔥32 paperPlatonic Task ArithmeticSI 53 paperRPTune: Learned Context Curation for LLM Catalog Search🔥9 paperPay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization🔥0 paperAgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines🔥11 paperOptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent PivotsSI 78 paperDiscrete Wasserstein Flows for One-Step Generative ModelingSI 73 paperBeyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States🔥56 paperAgentic Wireless Digital Twin Construction and Calibration Using Real-World MeasurementsSI 72 paperVTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation🔥10 paperSharpening Tax in Post-Training🔥31 paperAdversarial Robustness in Fake Quantum SimulatorsSI 78 paperBefore It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs🔥5 paperOneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction🔥161 paperQPI-DeepONet-MAC: A Scalable and Stable Hybrid Classical-Quantum Architecture for Physics-Informed Deep Operator NetworksSI 61 paperLiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene ReconstructionSI 68 paperZTA-Q: an Open-source RISC-V Platform for Accurate Quantized CNN InferenceSI 77 paperLACHESIS: Robust stellar parameters through Bayesian model averaging of isochrone gridsSI 57 paperFewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens🔥34 paperMingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real TasksSI 67 paperArgo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows🔥21 paperOmni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation🔥19 paper4Director: Controlling Video World Models with Rigid 3D Geometry🔥12 paperWorld Observer: Joint Actor-Observer Generation for Persistent World Modeling🔥37 paperOmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning🔥3 paperInterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation🔥43 paperSILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation🔥27 paperROWBench: Do Video Models Render What the Program Specifies?🔥29 paperKaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards🔥8 paperSphere Encoder 2SI 55

2026-10-01 · 65 条

paperUnderstanding Multimodality in Generative Behavioral Cloning🔥0 paperNot Every Token Is Worth Distilling: Selective Supervision for Direct-OPD🔥1 paperLANTERN: Illuminating Hidden Mathematical Knowledge in Language Models🔥10 paperUnmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models🔥14 paperDuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation🔥4 paperSlideDP: Scaling Host-Resident LLM Fine-Tuning Across Multiple GPUs🔥1 paperThe Low-Rank Structure of VLA Reinforcement Learning🔥1 paperCheatBench: Measuring Reward Gaming in AI Agents🔥0 paperATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning🔥1 paperThe Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation🔥179 paperDating the Model: Hidden Dates in System Prompts Affect LLM Evaluation🔥1 paperThe Geometry of Inference in Transformer Residual Streams🔥1 paperRetrieval Capacity of Self-Attention Under Competition🔥0 paperOvercoming Scaling Limits in On-Policy Self-Distillation for LLM Reasoning🔥0 paperWUSH-KV: KV Cache Quantization with Data-Adaptive Transforms🔥12 paperAdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation🔥0 paperLearning Meta-Skills for Agent Harness Design in Test-Time AI4AI🔥41 paperAREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks🔥64 paperAn Infant Sub-Saturn in Scorpius-CentaurusSI 75 paperLearning Gaia: A Generative Model Trained on the Gaia Data Release 3 Source CatalogSI 52 paperEVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making🔥37 paperLoopVL: Recurrent Visual Intelligence🔥2 paperAIM: Agentic Idea Management for Automated Research🔥10 paperAutoregressive Frontier Expansion: Growing Trees with Graph Machine LearningSI 62 paperSystematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies🔥12 paperExploring Forum Post Retrieval with Generative ModelingSI 59 paperAgBench: Agentic AI Benchmarks for Personal AI DevicesSI 57 paperBreaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation🔥12 paperHigh-accuracy simulation of Picard HMC, part I: Gaussian cloud correctionSI 67 paperUniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement🔥125 paperPatchHolmes: Agentic Patch Retrieval via Listwise Selection🔥0 paperSkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale🔥1 paperMore Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models🔥29 paperScale-Split Neural Operator for Memory- and Data-Efficient 3D Turbulence PredictionSI 55 paperMeshOctave generates meshes via cascading resolution transitionsSI 66 paperProvable Classical and Quantum Local Algorithms for Max-$k$-Cut and Quantum Advantage at Moderate GirthSI 65 paperRSIGame: Autonomous Agentic Game Development with Recursive Self-improvement🔥13 paperFalse Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents🔥68 paperDC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence🔥10 paperWorking Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost🔥1 paperThe AI crisis for teaching: "Train your own neural network!"SI 65 paperA2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?🔥4 paperThinking Outside the Box: Can Language Models Rely on External Guidance Selectively?🔥3 paperIntroduction to Computer VisionSI 79 paperBAM! Bayesian Anything Model: a foundation model for generative computational imagingSI 57 paperThe Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends🔥4 paperRoboCoach: World Models as Active Coaches for Compositional Robot Skills🔥7 paperBTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D GenerationSI 71 paperSafety of Latent Communication in Multi-Agent Systems🔥1 paperProbabilistic Adversarial TrainingSI 84 paperSynthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior🔥4 paperKUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative RecommendationSI 73 paperDyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes🔥5 paperOSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software🔥4 paperMid-Harness: Scaling Actions Between Model and Harness for Terminal Agents🔥58 paperCoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding🔥1 paperAgent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training🔥19 paperGame-Guided Skill Discovery through Self-Play for Playable Agent Control🔥3 paperEviRover: Reinforcing Agentic Perception Beyond a Glance🔥1 paperDecision-Oriented Recommendation Reranking: An Empirical Study of Jev🔥1 paperPivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents🔥4 paperScaling Laws for Looped Mixture of Experts🔥5 paperI Have a Stream: Making Self-Supervised Learning Work on Continuous Video🔥6 paperEvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery🔥60 paperPhysis-Lang: Self-Evolving Language as a Physical Representation for Video World Model🔥5

2026-09-30 · 65 条

paperOmni-Decision: Evidence-Ledger Planning for Omni-Modal Agents🔥6 paperOmni-IO Skills: Harnessing Your Agent Omni-Native🔥58 paperCaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs🔥0 paperPrismQuant: Optimal Null-Space Rotations for Grouped Quantizers🔥2 paperBeyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations🔥29 paperVoxMem: Benchmarking Multimodal Memory in Large Audio Language Models🔥52 paperANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces🔥7 paperPretraining Transformers with Quantized Softmax in Attention🔥2 paperStoryEngine: A State-Grounded Agentic Framework for Video Storytelling🔥7 paperAnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models🔥1 paperPlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?🔥1 paperMarathoner: Ultra-Long-Horizon Autonomous Intelligence🔥12 paperSEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents🔥1 paperPreference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement🔥1 paperPanoVLN: Towards Effective Panoramic Vision-and-Language Navigation🔥90 paperAutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?🔥2 paperUnderstanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders🔥1 paperBeyond Selection: Token Parameterization for Extreme Visual Token Compression🔥3 paperJev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration🔥0 paperOne Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices🔥1 paperHyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling🔥0 paperSame Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection🔥1 paperROSS: Relearning from Self-Generated Rollouts through Selective Supervision🔥15 paperToddlers in Resonance I: low masses and eccentricities of the 17 Myr giant planets HIP 67522 bc from transit timing variationsSI 54 paperIn-Context Learning for Robots: Methods and Applications🔥45 paperPersistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion🔥2 paperMixture-of-Kittens: MoE Megakernel for NVL72sSI 52 paperLongCat-DeepResearch Technical Report🔥26 paperAn Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration ArchitecturesSI 55 paperXiaomi-OCR-0 Technical ReportSI 48 paperLanguage Models Are "Insecure" Reporters🔥3 paperCool, Cloudy Nights on an Ultrahot Neptune: A Panchromatic NIRISS/NIRSpec Transmission Spectrum of LTT 9779 bSI 78 paperStructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks🔥1 paperLEGO-Anything: Coding Agents for 3D Scene Reconstruction🔥17 paperSu\^etes: An end-to-end differentiable non-hydrostatic limited-area dynamical coreSI 55 paperSecond-Moment Stochastic Approximation MethodsSI 66 paperAI as a Compiler: Compiling Triton kernels without the Triton compilerSI 69 paperEasyPPO: Stabilizing the Critic Is Key🔥12 paperSINO: Scale-Invariant Neural OperatorSI 48 paperChinese-Jev: Bringing System One Model to Chinese-Language Tasks🔥4 paperSelecting The Most Informative Tokens in Natural Language Autoencoders🔥6 paperWindowed and Quantized Group-Based ADMM for Distributed Optimization in Heterogeneous Edge NetworksSI 52 paperReal2Gym: Building Gyms from Videos, Bringing Skills to Robots🔥3 paperFollow the Entities: A Corpus Map for Agentic Search🔥22 paperInteracting particle guidance for sampling reward-tilted generative priorsSI 56 paperAsking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents🔥1 paperCollision-Aware and Observation-Aligned Object-Centric Scene Reconstruction from Point CloudSI 78 paperEngineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited ComputeSI 51 paperA Short Proof of a Theorem of Pan and ZhangSI 52 paperGraphVQ: Structure-Aware Autoregressive Decoding over Context-Quantized Graph TokensSI 55 paperEngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?🔥26 paperContext Language Models🔥7 paperEpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory🔥3 paperTabFM: A Zero-Shot Foundation Model for Tabular Data🔥4 paperSoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video🔥12 paperTabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models🔥3 paperHybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents🔥13 paperEVO-WAM: Evolving World Action Models through Video-Action Verification🔥13 paperWorldLine: Action-Driven Visual Simulation for Robotic Manipulation🔥11 paperCrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments🔥11 paperVideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents🔥5 paperBreaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE🔥1 paperLongLive-Plug: Once-for-All Distillation for Video Generation🔥13 paperEmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation🔥4 paperAdversarial Training for Pixel Diffusion🔥5

2026-09-29 · 65 条

paperHow Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline🔥1 paperNot All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization🔥1 paperSafe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation🔥1 paperPost-Training Leaves Behavioral Shadows on Unrelated Decisions🔥52 paperHow Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure🔥0 paperNanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization🔥1 paperThe Wang Transform InequalitySI 64 paperDuplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue🔥30 paperExact Trade-Level Attribution of FRTB-IMA CapitalSI 66 paperArithmetic Simplicity in Stochastic Gradient MethodsSI 83 paperResidual Transferability in Neural Image Watermarking🔥7 paperSkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback🔥1 paperDepthBench: Measuring How Residual Connections Enable More Computational Depth🔥20 paperIn-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion🔥6 paperChange the Product, Keep the Parameters: Associative Algebra Layers for Transformers🔥3 paperPrecision As You Need: Stochastic Computing Is a Dense Adaptive QuantizerSI 65 paperKernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation🔥1 paperOn Device Agentic Operation Caches -- Classifier-Centric NL-to-Action GenerationSI 61 paperDroneWAM: Efficient World Action Model for Drone Visual Navigation🔥2 paperStructured Residual Connectivity Matters for Diffusion Transformers🔥12 paperWhen Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions🔥0 paperIs AI Widening the Wage Gap? A Hybrid Agentic Simulation for Labor EquitySI 75 paperRecursive Harness Distillation across Agents for Robot Manipulation🔥3 paperWideSWE: Can Coding Agents Coordinate Changes Across Repositories?🔥15 paperSciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation🔥8 paperTT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining🔥7 paperSMAT: Simple and Efficient Merge-Aware Training🔥1 paperA Visual Classification Dataset and Model Evaluation for Historical Manuscript IllustrationsSI 69 paperWhat masking geometry works best for EEG foundation models?🔥0 paperAn elementary treatment of Ramanujan's elementary continued fractionsSI 85 paperAI's solution of Conjecture 9.1SI 63 paperQwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents🔥16 paperRethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry🔥5 paperPReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction🔥2 paperKVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems🔥2 paperTraining and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive Reduction🔥0 paperAdaGuard: An Adaptive Guard Model with User-defined Policies🔥0 paperKnowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge🔥25 paperPrecise Editing and Flexible Referencing for Interactable Worlds🔥9 paperDraft-KV: Learning Useful Latent Communication Between Language Models🔥4 paperNotes on Magnetostatic Interactions in $\mathbb R^3$SI 63 paperWhen Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety🔥2 paperColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport🔥2 paperGraph-Based Learning for Multi-Horizon Martian Atmospheric ForecastingSI 68 paperRenderRank: Learning to Rerank Text with Compressed Visual Tokens🔥5 paperEdgeCraft: Automated Model Crafting for Edge IoTSI 69 paperImprint Reader: From Weight-Update Readout to Behavioral Intervention🔥8 paperMeasuring Collapse and Correction in Homogeneous-Panel LLM Debate🔥4 paperLeiden Declaration on Artificial Intelligence and MathematicsSI 64 paperBeyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation🔥65 paperHow Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining🔥38 paperWhy Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning🔥1 paperSolveEdit: Benchmarking Visual Problem Solving in Generative Models🔥10 paperAn RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning🔥4 paperBaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation🔥6 paperWorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon🔥22 paperOn-Policy Self-Distillation for Multi-Turn Image Editing🔥1 paperEvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold🔥1 paperFlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching🔥2 paperAI Agent Swarms as Researchers: Progress, Challenges, and Open QuestionsSI 73 paperGeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space🔥5 paperMINT: Modeling GenAI Impact on Network TrafficSI 76 paperInfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video🔥7 paperTokenCast: Forecasting Token Consumption During LLM Agent Execution🔥3 paperLearning Native Reflection in Unified Models with Interleaved Reinforcement Learning🔥26

2026-09-28 · 31 条

paperCARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation🔥4 paperDo Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs🔥3 paperRayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation🔥37 paperTactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors🔥2 paperFoMo: Forking Moment in Generative Trajectory as a Perceptual Distance🔥7 paperMorphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy🔥1 paperSLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL🔥6 paperJev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem🔥5 paperTrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations🔥6 paperQuantum Laurent positivity in rank threeSI 49 paperFOTO: Figure-Level Semantic Search for AstronomySI 61 paperEncryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural NetworksSI 47 paperWeather and Climate Without Fluid MechanicsSI 66 paperTRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding🔥2 paperInsurance Reserve Intelligence PlatformSI 44 paperDeep-Learning Solvers and Surrogates for Infinity and p-Laplace ProblemsSI 41 paperAligning One-Step Generative Models with Reward-Weighted Transport DistillationSI 41 paperFrom Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native DeeplinksSI 54 paperZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker🔥3 paperModeling quantum neural network gradient with reinforcement learningSI 70 paperBlock Sparse Attention with Log-Linear Complexity🔥14 paperThe NEMESIS general YSO catalogue - I. Supervised classification with deep learning methodsSI 82 paperEnhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning🔥6 paperFormalizing Carleson's Theorem in LeanSI 43 paperInternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data🔥17 paperGame Arena: Strategic LLM Evaluation in Competitive Environments🔥4 paperPhysics-induced impact on the properties of Kepler/K2 solar analogs in the light of PLATO's requirementsSI 73 paperBandwidth, Latency, and 400 Million Kilometers: The Case for Mars-Local ComputeSI 50 paperAgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs🔥4 paperStatistical attribute alignment for black-box generative AI via output post-processingSI 70 paperFuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders🔥93

2026-09-26 · 7 条

paperLearning to Discover Interesting Mathematics🔥12 paperRGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation🔥8 paperParts-of-Speech as Emergent Categories in SAE Latent Space🔥11 paperJust Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures🔥9 paperAV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation🔥5 paperYour Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs🔥77 paperCoding Agents for Generalized Task and Motion Planning Problems🔥11

2026-09-25 · 39 条

paperSelf-Organizing Agent Teams Learn to Reason Together🔥6 paperNeural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone🔥8 paperOmniEcho: Spatial Audio Understanding for Embodied Agents🔥24 paperUranus: Building the Next-Generation Simulation Infrastructure for Embodied AI🔥4 paperX-Planner: Event-Structured Task Planning for Embodied Intelligence🔥2 paperGeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression🔥13 paperCalibration as a First-Class Criterion in LLM Evaluation🔥2 paperKnowledge Pull Requests for Continual Document Authoring🔥2 paperCapable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models🔥15 paperThe Linear Representation Hypothesis Needs a Group Action🔥3 paperFLEET: From Logits Entropy to Enhanced Trajectories in Text Generation🔥5 paperSix Layers Less: Encoder Pruning for Whisper with Label-Free Recovery🔥4 paperAgent-Editing World Model: Rethinking World Modeling for LLM Agents🔥20 paperGenerative AI May Reinforce Social Biases in Software Engineering EducationSI 48 paperHybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency AssessmentSI 63 paperQuantization and Mirror Reduction Do Not Commute in Hamiltonian Embeddings of Nonreciprocal DynamicsSI 47 paperAstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical ResearchSI 63 paperHClimRep-Ocean: A Global Ocean Emulator on an Unstructured MeshSI 51 paperAll Quiet on the AI Front: The Future of Undergraduate Math Research, Viewed from DuluthSI 68 paperTraining Object Permanence in World Models🔥208 paperM-plicits: Neural Implicit Surfaces via Nested Multiscale ResidualsSI 69 paperDeltaWAM: Delta World Action Models for Bimanual Manipulation🔥4 paperCentral stars of newly discovered infrared nebulae: eruptive Be stars PY Gem and HD253659SI 62 paperViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation🔥3 paperMulti-Agent Orchestration of 3GPP Channel EstimatorsSI 65 paperThe Marcus-Minc Transform InequalitySI 54 paperRufus-Air: An Open LLM Post-Training Recipe🔥19 paperIterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis🔥9 paperAgentKernel: The Trust-Native Agentic Operating SystemSI 48🔥7 paperVQ-LIC: Shared Vector-Quantized Learned Image Compression on a Resource-Constrained FPGASI 64 paperPUBG Ally: A Conversational Embodied Agent as an AI Teammate🔥11 paperQwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents🔥14 paperARIS: Low-Resource Glass-Box Neural Source-Filter Synthesis for Phonetic Stimulus ManipulationSI 56 paperTheta operators at $t=1$, Macdonald cumulants, and LLT positivitySI 56 paperWorld Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal🔥7 paperKernelOPT: Dispatch-Aware Agentic Search for GPU Kernel OptimizationSI 52 paperRate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates🔥2 paperExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds🔥19 paperWanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation🔥36

2026-09-24 · 43 条

paperTri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts🔥5 paperEmbedding Physics Priors in Robot Learning: A Survey🔥2 paperRewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling🔥24 paperSpatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World🔥48 paperPackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing🔥11 paperHappyWorld-Bench🔥42 paperLatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay🔥4 paperImIR: Image-Instruction Tuning for All-in-One Image Restoration🔥3 paperRoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents🔥4 paperMemoryAthena: Adaptive Routing over Latent and Generated Memories🔥6 paperBlaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament🔥4 paperPACT: From Credit Assignment to Critic Alignment🔥16 paperJEV-as-a-Judge: Accept When Confident, Escalate When Unsure🔥26 paperSpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue🔥83 paperAgensh: Scaling Organizational Intelligence to 1,024 Agents🔥14 paperHARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis🔥0 paperRaytracing Black Holes with AI AcceleratorsSI 49 paperA High Resolution View of Three Massive Young Stellar Objects in the Magellanic CloudsSI 52 paperSequential Star-Formation and the Near-Infrared Stellar Populations within N159SI 55 paperFrom PyTorch to the NPU: LLM-Agent-Driven Model Conversion Across Heterogeneous Inference RuntimesSI 92 paperHunyuan-A13B Technical Report🔥10 paperKITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM ScalingSI 62 paperEmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics🔥3 paperVerifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms🔥12 paperJust-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents🔥35 paperWhatWorkedBench: Benchmarking Experimental Understanding in AI Agents🔥9 paperDistributed Stochastic Approximation Algorithms and Heavy-Tailed Age of InformationSI 62 paperInternW0: A Foundational Physical World Model for Efficient Real-World Interactions🔥6 paperRefuting the QAOA fixed-angle conjectureSI 52 paperSchrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?🔥15 paperAll modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation🔥8 paperBinary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output DimensionsSI 61 paperPISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early WarningSI 49 paperExact Quantile Balancing and Load-Error Injection for Mixture-of-ExpertsSI 50 paperHigh-Resolution Modelling of Coronae and Winds in Solar-type Stars with Varying Rotation Rates II. Stellar WindsSI 56 paperTraining Mathematicians in the Age of AI: Intellectual Agency, Cognitive Offloading, and the PhD ThesisSI 59 paperFinite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge CoordinationSI 53 paperMemBodied: Recurrent Associative Memory for Vision-Language-Action Models🔥11 paperMicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and InferenceSI 75 paperImage Compression Using Quantum Wavelet Transform and Quantum Convolutional NetworksSI 65 paperThe Past Frames the Future: Memory for Autoregressive Video Generation🔥39 paperStudentBench: AI and human tutoring yield equivalent GRE learning gains🔥3 paperOn the Diffusibility of High-Dimensional Latents🔥6

2026-09-23 · 43 条

paperSkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness🔥6 paperThe information geometry of large language models is shared, learned, and controllable🔥4 paperShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models🔥4 paperBellman Policy Optimization🔥25 paperThe Functionalizer: Lossless Functional Decomposition for Subword Tokenization🔥11 paperPrediction-Powered Smoothing and Validation for Disaggregated AI Evaluation🔥3 paperTAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision🔥1 paperA Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal🔥4 paperALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning🔥3 paperTowards Full Pipeline FP8 Reinforcement Learning for LLMs🔥8 paperUltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing🔥3 paperACLArena: Agent Continue Learning in Multi-stage Post-training🔥9 paperAll-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts🔥37 paperEDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation🔥2 paperCircuit Hypernetworks for Quantum-Augmented Diffusion Language Models🔥24 paperStreaming Video Editing with Easy Adaptation🔥8 paperComplex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention🔥5 paperEmergent Collusion in Long-Horizon LLM Agent Interaction🔥6 paperGAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation🔥40 paperFrontierMath Erd\H{o}sSI 49 paperCategorical representations of algebraic groups in positive characteristicSI 62 paperOvis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings🔥33 paperFrom Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health🔥16 paperLean Pool: An AI-Maintained Archive of Formalized Mathematics🔥12 paperGeometric and Semantic Coupling for Interaction Understanding in 3D Scenes🔥4 paperRULER: Instance-aware Rubric Rewards for SVG Generation🔥62 paperUsing Machine Learning to Model Stellar Collisions in our Galactic CenterSI 45 paperNarrowband Voice Communication Using Streaming Neural CompressionSI 56 paperMean Velocity Matching: Rethinking Generative Dynamics in Diffusion ModelsSI 51 paperMassive stars in the SDSS-V survey: New O2 stars in the Large Magellanic CloudSI 53 paperContinuous Optimization for p-adic ModelsSI 49 paperWhen Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum SystemsSI 69 paperThe Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks🔥115 paperAT3D-AD: Anomaly Type-Aware 3D Anomaly Detection via Hierarchical Point-Language AlignmentSI 65 paperAre there really some eccentric eclipsing binaries having orbital periods below 1 d?SI 46 paperEMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based DiffusionSI 69 paperOn the OpenAI whole-cube boundSI 61 paperTopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE InferenceSI 45 paperNGTS clusters survey - VII. An Enigmatic Short-Period Circumsecondary Disk Candidate in OrionSI 54 paperRecursive self-improvement of AI research agents🔥7 paperStableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training🔥22 paper\phi-RIE: From Photorealistic Reconstruction to Interactive EnvironmentsSI 45 paperFlash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs🔥14

2026-09-22 · 48 条

paperHuRo: Robotizing Human Videos for Scalable VLA Pretraining🔥19 paperSteerDuplex: Steerable Duplex Speech Dialogue Models🔥2 paperCADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design🔥5 paperSiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops🔥3 paperGAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning🔥3 paperRefinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network🔥2 paperBI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence🔥14 paperRetention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy🔥3 paperGeometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models🔥3 paperIntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts🔥92 paperOmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue🔥31 paperFrom Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention🔥5 paperGricea: An Open Science Platform for Conversational AI Research🔥8 paperAPort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport🔥2 paperDesigner-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design🔥24 paperMeasuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles🔥3 paperDeep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations🔥13 paperMoonworks Lunara: Modeling Artistic IntelligenceSI 86 paperFrom IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause AnalysisSI 59 paperScout: Open-World Species Recognition on the EdgeSI 77 paperExactness as an Explanatory and Computational Target: A Reduction Architecture for First-Order ODEs, with a Higher-Order OutlookSI 55 paperExact Realization of Deep ReLU Computation in a Microscopic Statistical-Mechanical SystemSI 73 paperTransferring the Intelligence of VLMs to Robotic Control🔥101 paperA Quantum-Inspired Two-Dimensional Lattice Polarized Radiative Transfer SimulatorSI 77 paperAdversary-as-Agents: A Co-Evolutionary Agent-Based Threat-Modelling Framework for Wireless and Mobile NetworksSI 58 paperOmniEdu: Open Foundation Models for Learning and Teaching🔥139 paperOne to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents🔥29 paperStyleAT: Defending Face Recognition Against Semantic AttacksSI 75 paperWhy Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms🔥11 paperMira-Scene: Pixel-Aligned Layouts for Generative 3D SceneSI 62🔥4 paperReal-time Generalizable Heart Valve Mechanics for Clinical Disease Assessment via a Physics-Conditioned Neural OperatorSI 56 paperGrounded Action Model: 3D Grounding as a Foundation for Robotics🔥74 paperJev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents🔥14 paperThe Auslander--Reiten conjecture for quantum complete intersectionsSI 54 paperCARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies🔥11 paperDocument Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion🔥51 paper1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation🔥12 paperPositive formulas for q-Zeta numerators of Ferrers-cell posetsSI 61 paperThink Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies🔥5 paperFourth-Order Energy-Consistent Average Vector Field Discrete Gradient Methods for Dissipative Hamiltonian SystemsSI 62 paperTiga: Compiling Graph Message Passing at ScaleSI 71 paperTwo-loop amplitude for the associated production of a top-anti-top pair and a $W$ boson at hadron collidersSI 57 paperRRSI: Regularized Recursive Self-Improvement of Agent Harnesses🔥167 paperHarness-Zero: Harness Distillation via Agent-as-Harness🔥13 paperonPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction🔥29 paperWorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory🔥122 paperVideoGen-Agent: Reinforcing Video Generation Agents🔥39 paperGameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay🔥113

2026-09-21 · 31 条

paperGrounded Skill Synthesis from Code at Scale for Agentic Intelligence🔥91 paperMLLMs Hallucinate when Information Distribution Drifts in Synergy Heads🔥5 paperMoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup🔥7 paperEvoOntology: A Self-Evolving Ontology Layer for Data Agents🔥126 paperTeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection🔥4 paperFRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection🔥4 paperTraining-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation🔥3 paperLearning Foresight without Explicit Trajectories for 3D Diffusion Policies🔥1 paperPaint-Anything: Unified Any-Color Control for Image Generation and Editing🔥30 paperDoes the Universe Have Bugs? Adversarial Physics and the Configuration FrontierSI 55 paperMassive type 0A string theory and M-theorySI 49 paperWhen AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation🔥5 paperCharacter theory for 2-representationsSI 55 paperPlantShade: Predicting Plant Shadows for Lighting-Aware Robotic Agricultural OperationSI 48 paperMarsFM: Shading-Regularized Flow Matching for Martian Relief EstimationSI 49 paperHMB-GAN: Hybrid Multi-B\'ezier GAN for Vector Shape SynthesisSI 80 paperAI-Driven Scientific Computing Workflows: A Systems Review of Orchestration, Execution, Reproducibility and ProvenanceSI 47 paperOpenRoIS: A Community-Driven Open-Source Middleware Implementing the Robotic Interaction Service (RoIS) Framework for Physical Robots and Virtual AgentsSI 48 paperLearning-to-Optimize as the Missing Architectural Layer of AI-Native NetworksSI 67 paperCalibrating Teacher--Student Discrepancy for On-Policy Distillation🔥7 paperLenNet: Direct Detection and Localization of Strong Gravitational Lenses in Wide-Field Sky Survey ImagesSI 60 paperFaithful Neural Embeddings for 3D Exoplanet Climate ModelingSI 55 paperSome challenges for the long-term survival of Naiad, Neptune's innermost moonSI 60 paperGraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills🔥9 paperWhen AI Enters the Workplace, Who Faces Greater Risks? A Gendered AnalysisSI 49 paperBeyond Shadow Weights: Quantization-Aware Training as Quantized-Endpoint DescentSI 66 paperThe Weight Is Over - Interactive Diffusion on Consumer GPUsSI 63 paperRecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents🔥63 paperCodeMidas: Scaling Agentic Coding RL Environments from Code Itself🔥103 paperOmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation🔥20 paperMintAct: A Unified Visual Agent for Digital Environments🔥13

2026-09-19 · 7 条

paperSrijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts🔥26 paperVerifiable Social Reasoning for LLM Assistants🔥49 paperCan MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model🔥114 paperSample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling🔥29 paperSelf-Evolving Search Index🔥46 paperVākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering🔥23 paperDon't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL🔥28

2026-09-18 · 39 条

paperUFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation🔥30 paperAssessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026🔥2 paperRiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation🔥42 paperFingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand🔥1 paperLimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence🔥418 paperFathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches🔥3 paperReflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents🔥38 paperThe Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction🔥14 paperPACT: Can Enterprise AI Assistants Be Trusted Under Pressure?🔥26 paperCERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents🔥8 paperIn-Context Robot Learning with VLM Agents🔥18 paperPerceptual Refinement of an End-to-End Video Streaming Pipeline via Generative AI LayersSI 48 paperRadio-Frequency Convolutional Neural NetworksSI 64 paperTransformers as Intrinsic Optimizers for Quantum Approximate Optimization AlgorithmSI 57 paperAgentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless NetworksSI 50 paperVABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control🔥33 paperScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AISI 45 paperWhen2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models🔥33 paperRegion-Level Policy Optimization for Fine-grained MLLM Perception🔥27 paperContagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading SystemsSI 57 paperPoint, Revise, Review: Grounded Agentic Analysis in Reactive Notebooks with marimo-lensSI 52 paperThe Life of a Token: from Words to Bits on the WireSI 45 paperDynamics of Stochastic Hamiltonian systems I - Wong-Zakai Variational integratorsSI 53 paperDeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression🔥140 paperQuantum Graph Convolutional Networks: Implementation and Trainability AnalysisSI 69 paperThe 2025.6 X-ray Minimum of Eta CarinaeSI 48 paperAI-Driven Real-Time Relay Optimisation in Smart Urban NR-V2X Networks via Learning-to-Optimise Graph Neural NetworksSI 47 paperGenerating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial ModelSI 46 paperWeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing🔥35 paperWhen EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation🔥95 paperSoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness🔥95 paperRecursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature ForecastingSI 56 paperCoupled Orbital and Interior Evolution of Sub-NeptunesSI 56 paperWhat Does Privileged Information Add to On-Policy Self-Distillation?🔥30 paperVideo DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation🔥34 paperRetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning🔥40 paperJEPA-Anything: Learning Predictive Models across Different Worlds🔥58 paperAn Empirical Study of Harness Design for Coding Agents🔥72 paperFAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations🔥29

2026-09-17 · 40 条

paperRelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs🔥4 paperGeneralized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement🔥60 paperConvergent Emergence of In-Context Learning Across Modalities🔥3 paperFlattening Every Memory Peak in Long-Context Mixture-of-Experts Training🔥12 paperSpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization🔥24 paperAnother Blueprint In The Wall: How to Ask Frontier AI Like a Kid?🔥7 paperModularRSI: Modular and Generalizable Recursive Harness Self-Improvement🔥11 paperHarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness🔥17 paperVC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention🔥37 paperHypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses🔥27 paperOmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning🔥2 paperRegister Tokens for Bounded-State Reasoning in Diffusion Language Models🔥5 paperFLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation🔥15 paperImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals🔥3 paperEventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset🔥22 paperEvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents🔥33 paperLecture notes on Physics Informed Neural Networks, Neural Operators, and their applicationsSI 82 paperConfidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents🔥56 paperGeometry-Driven Shadow Harmonisation for Composited Faces: A Multiplicative, Albedo-Preserving Relighting PipelineSI 69 paperPointGrade: Geometric Priors for Grading MoonBoard ProblemsSI 63 paperQiT: Quantum-Inspired Transformer for Visual Recognition TaskSI 91 paperProto-Planetary Nebulae Are Not the Precursors of Planetary Nebulae With Close Binary Central StarsSI 56 paperZing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control🔥31 paperTuiML: Machine Learning for AI AgentsSI 53 paperNewer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model GenerationsSI 75 paperGaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX🔥23 paperAgora: Git as Shared Memory for Collective AutoResearch🔥45 paperA Comprehensive Review of Generative Physical Artificial IntelligenceSI 63 paperQuanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge GraphsSI 59 paperWhere Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud ContinuumSI 69 paperThe spectral edge of sparse directed Erd\"os-R\'enyi graphsSI 64 paperActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models🔥41 paperDeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot ManipulationSI 63🔥3 paperRethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening🔥65 paperProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks🔥49 paperHigh-order discrete differential and integral calculus and Galerkin variational integratorsSI 71 paperQuantum Computing in Next-Gen Smart Grid Operations: A Comprehensive ReviewSI 60 paperScienceIDE: Turning World's Scientific Codebase into Agent Learnable EnvironmentsSI 68🔥77 paperPANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection🔥11 paperA Zeroth-Order Paradigm for LLM Preference Alignment🔥23

2026-09-16 · 24 条

paperLearning Sparse Decision Trees via Transformer Variational Auto-Encoders🔥2 paperContinual Learning Mechanisms Compose for Long-Horizon Memorization🔥290 paperThe Last AI Built by Humans: Toward Genuine Recursive Self-Improvement🔥88 paperDynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model🔥6 paperLearning to Solve Hard Problems in RL for LLMs by Never Giving Up🔥9 paperRoot-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures🔥3 paperDrift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models🔥2 paperTraining Specialist Models without Reasoning Trajectories for Domain Expert Distillation🔥2 paperThought without systematicity? Evaluating reasoning models on rule induction tasks🔥2 paperStepAudio 3 Realtime Technical Report🔥100 paperE2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning🔥2 paperLightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition🔥2 paperHow Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus🔥29 paperModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs🔥1 paperMind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States🔥5 paperDisentangling Representation Evolution in Transformers through Directional Decomposition🔥4 paperThe Router Within: Eliciting Native Skill Routing from a Frozen LLM🔥3 paperStepAudio 3 Music Technical Report🔥76 paperDecoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration🔥2 paperAI for Games in the Foundation Model Era🔥113 paperEmergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems🔥2 paperPhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control🔥3 paperScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents🔥20 paperModality-Autoregressive World-Action Models🔥7

2026-09-15 · 55 条

paperBuilding and Evaluating Fixed-Voice Thai TTS from Synthetic Speech🔥1 paperHow Far Can Synthetic Data Take Thai OCR?🔥2 paperDataFlex-RL: An Evaluation Platform for RLVR Data Policies🔥108 paperMobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control🔥1 paperAmbient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision🔥3 paperAmbient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model🔥3 paperActionSplice: In-Flight Action Editing for Interactive World Models🔥3 paperReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation🔥1 paperTRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents🔥2 paperTowards a Deterministic Math Solver for Clinical Language Models🔥1 paperStudying Without a Syllabus: Task-Agnostic Environment Preprocessing🔥4 paperReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs🔥33 paperVidu S2: Real-Time Interactive, Editable, and Spatial Video Generation🔥633 paperThe Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile DevicesSI 73 paperEfficient AI Model Deployment Using Quantization Analysis ToolSI 78 paperOccamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work🔥26 paperPelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence🔥17 paperFeature Recovery for Object Understanding After Irreversible Fire Damage🔥1 paperCompetence-Gated Pooling of Language Models and Priors for Event Forecasting🔥2 paperOn Identifying Adversarial Intent Injection in AI-Native 6G NetworksSI 48 paperBlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI AgentsSI 51 paperMInTRL: Off-policy Intervention can boost On-policy RL🔥6 paperAn End-to-End Automated Pipeline for Controllable Crack Data SynthesisSI 48 paperMagnetic Fields and Asymmetric Accretion in the Class 0 Protostellar System L1527 IRSSI 60 paperAMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel OptimizationSI 73 paperWhen Does AI Augment Work? A Workflow-Level Framework for Human-Agent CollaborationSI 57 paperExtended Wigner's Friend Scenarios with Agent-like Observers on Quantum ComputersSI 43 paperAgent as Policy for Robotic Manipulation🔥12 paperQuality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts InstancesSI 53 paperConvergence of Stochastic Gradient Methods under Heavy-Tailed Noise and Hölder SmoothnessSI 52 paperMGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance ModelingSI 59 paperPhysics-enriched neural solvers for transient ice-flow simulationSI 43 paperGenerative Retrieval for Unsupervised Text-Based Person SearchSI 53 paperExpert-Space Exploration in MoE Reinforcement Learning🔥5 paperGrouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction🔥61 paperLLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents🔥13 paperAttention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning🔥5 paperZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search🔥298 paperBuilding a Production Greek-English Speech Recognizer🔥3 paperRealtime-Venus: A full-duplex interaction system with asynchronous delegation🔥207 paperAlayaVista: Streaming World Modeling from Panoramic States to Perspective Video🔥21 paperDream-RSI: Recursive Self-Improvement through Evolving Worlds🔥266 paperPhysBrain 1.5: From Vision-Language Models to Physical Foundation Models🔥170 paperPick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks🔥7 paperNot All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training🔥9 paperEnabling Creative Exploration for Vibe Design Agents🔥4 paperOmni-Streaming Thinking🔥19 paperHazardAuditor: From Executable Threats to Safer Computer-Use Agents🔥14 paperWhen Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis🔥12 paperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments🔥67 paperBVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender🔥23 paperKaininja: Extending Native 3D Generators to the Part Level🔥16 paperAtria Dawn: The Dawn of Agentic Superintelligence🔥416 paperLynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows🔥46 paperDiscovery Foundation Models: Toward Open-Ended Discovery Intelligence🔥24

2026-09-14 · 10 条

paperPLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization🔥26 paperOnline Learning with LLM Experts from Limited Feedback🔥5 paperBeyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents🔥5 paperFeyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models🔥129 paperBenchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation🔥152 paperCOBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization🔥32 paperBreaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models🔥66 paperStepAudio 3 Gen Technical Report🔥31 paperSAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking🔥43 paperSNAP3D: Physically Grounded 3D Parts for Assembly from a Single ImageSI 52🔥3

2026-09-12 · 12 条

paperAdaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2🔥23 paperActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation🔥23 paperStudying Image Tokenizers as Visual Languages in Unified Multimodal Models🔥28 paperBuilding Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning🔥27 paperIdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications🔥23 paperThink Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking🔥22 paperBeyond Solver Verdicts: Generative Reward Models for Autoformalization🔥28 paperDRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat🔥22 paperMi-Ripple: Restoring Images Degraded by Iterative AI Editing🔥49 paperFreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation🔥34 paperMemory as Plans: World-Action Modeling with Memory-Grounded Planning🔥37 paperNegative Self-Distillation: Learning to Reason by Avoiding Flaws🔥31

2026-09-11 · 46 条

paperThe Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements🔥3 paperScaling Automatic Research Agents via World Models🔥449 paperHyQuant: Hybrid-Precision Quantization for LLM Attention🔥31 paperTempCloze: Can Video-LLMs Identify the Missing Middle?🔥29 paperFrom Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution🔥3 paperA Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware🔥11 paperEvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents🔥59 paperOracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution🔥13 paperPARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents🔥23 paperTrain Smarter, Not Harder: Switching Signal-Guided Training in Active Learning🔥10 paperCARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation🔥24 paperSpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem🔥134 paperDF26: We Cannot Tell Fake From Real Anymore🔥4 paperSchemeArena: Factorized Stress Testing of Scheming in LLM Agents🔥10 paperSWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents🔥23 paperAgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems🔥93 paperPlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving🔥7 paperSyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators🔥14 paperStochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean🔥9 paperMetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes🔥32 paperReference-Based Bias Detection in LLMs via Relative Representations of Hidden States🔥5 paperThe Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding🔥5 paperWhy Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs🔥13 paperOptimizing AI Inference Across the Deployment StackSI 53 paperSome Early Results by Tutte Regarding the Cycle Double Cover Conjecture in 1948SI 48 paperEnergy deposition in planetary and exoplanetary atmospheres induced by cosmic raysSI 54 paperAn Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics🔥37 paperNCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction🔥303 paperAlternative AI Philosophy: Daoism as Method for AI in EducationSI 52 paperLearned Continuous Synthesis of Quadratic Difference Tone SpectraSI 49 paperT1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks🔥56 paperReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and ModulationSI 50 paperLAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone PhotosSI 58 paperUniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration🔥24 paperDiversity of EML-type operatorsSI 58 paperX-RACE: XAI-assisted Recurrent neural network Attribution for Channel EstimationSI 48 paperVirtual quantum neural networksSI 74 paperX-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation🔥43 paperGaussian Light TransportSI 56 paperPH2T-splines, Part I: A Reasonable Mesh AssumptionSI 63 paperRecursive Code World Models: Building Complex Worlds through Recursive Scene Programs🔥28 paperMean Square Error Analysis of Stochastic Runge--Kutta IntegratorsSI 50 paperWorld in World: Explore the World with World Models🔥28 paperMultimodal Taxonomic Conditioning for Generative Plankton ImagerySI 49 paperGenerative Late-Interaction Embeddings For Visual Document RetrievalSI 53🔥26 paperSenseNova-U1.5: Towards Native Unified Visual Intelligence🔥247

2026-09-10 · 65 条

paperSQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions🔥15 paperRecognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions🔥15 paperPuppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation🔥16 paperStudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?🔥15 paperGraph Machine: Towards Better Pretraining via Edges🔥3 paperMasterControl Seventeen Every Time🔥1 paperEVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?🔥5 paperLearning 3D Editing without Paired Supervision via Generative Prior Distillation🔥0 paperBeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference🔥32 paperRoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?🔥21 paperWearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data🔥37 paperGE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation🔥49 paperWhat Did I Just Say? Self-Listening for Full-Duplex Speech Models🔥16 paperRenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives🔥2 paperDiffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models🔥8 paperCadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model🔥16 paperCounter-Swarm Doctrine: Containing Coordinated Agent Intrusions🔥3 paperVDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification🔥22 paperSteering Geometry: Validating Human Value Geometry in LLM Steering Space🔥27 paperTransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation🔥18 paperDianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents🔥12 paperReason Through the Latent! Making Latent Visual Reasoning Necessary🔥30 paperRevisiting Complete Reasoning Traces for Post-Training🔥10 paperEncoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise🔥15 paperOpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining🔥55 paperRelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting🔥8 paperMeasuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy🔥18 paperCosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements🔥25 paperHarnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection🔥15 paperA*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM🔥11 paperReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding🔥15 paperMarigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation🔥46 paperSynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation🔥15 paperCoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs🔥20 paperDifficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR🔥2 paperEliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation🔥84 paperAuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing🔥183 paperOmni Interaction Agent Technical Report🔥122 paperSAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?🔥19 paperMask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout🔥43 paperCo-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails🔥7 paperNOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting🔥3 paperProcedural Graphs: Self-Evolving Execution Structures for LLM Agents🔥23 paperTANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model🔥19 paperTowards a Quantum Erlangen ProgramSI 59 paperAgenticGen: Reward-Guided Agentic Video Generation for Advertising🔥7 paperScores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents🔥17 paperWhere Does the Human End? Creative Agency with Generative AI across Five Years of Chinese Digital PaintingSI 74 paperAcademia x Industry: The Role of Fundamentals for Silicon in an AI Native EraSI 46 paperExact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-LeaderSI 48 paperPlanetary Nebula Central Stars as Tracers of Planetary Nebula-Star Cluster Associations in the GalaxySI 83 paperRESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems🔥3 paperChance, Persistent Advantage, and the Generative-AI Era in Open-Source Package CareersSI 60 paperViolet: Enabling Full Virtualization for M-mode RTOS on RISC-VSI 51 paperThe magnetic field in M16: new results from the JCMT BISTRO surveySI 78 paperA Multi-Model Non-Intrusive Reduced-Order Framework for Parametric Erosion Prediction via Kinematic Cross-Moment CompressionSI 62 paperAXON: A ROS 2 RMW with Shared-Memory/QUIC Transport and QKD/ML-KEM Key EstablishmentSI 65 paperField-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogateSI 45 paperPhysics-Informed Multi-Task Surrogate Model for the Martian Nightside ThermosphereSI 70 paperΦ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?🔥9 paperAn $O(1/T^3)$ algorithm for minimizing convex quadratic functions over the $L_1$ ballSI 50 paperStencil Computation at the Intersection of AI and HPCSI 83 paperGradient-Enhanced Proximal Algorithms for Mean Field Planning on SurfacesSI 74 paperShow-Harness: Just a VLM Agent Can Play Robots🔥132 paperProgrammable World Model🔥83