时间线
65 条归档信号，按捕获日倒序
2026-09-10 · 65 条
paperSQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions🔥15paperRecognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions🔥15paperPuppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation🔥1paperStudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?🔥12paperGraph Machine: Towards Better Pretraining via Edges🔥2paperMasterControl Seventeen Every Time🔥1paperEVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?🔥4paperLearning 3D Editing without Paired Supervision via Generative Prior Distillation🔥0paperBeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference🔥32paperRoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?🔥21paperWearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data🔥16paperGE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation🔥49paperWhat Did I Just Say? Self-Listening for Full-Duplex Speech Models🔥16paperRenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives🔥2paperDiffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models🔥1paperCadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model🔥16paperCounter-Swarm Doctrine: Containing Coordinated Agent Intrusions🔥3paperVDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification🔥22paperSteering Geometry: Validating Human Value Geometry in LLM Steering Space🔥27paperTransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation🔥18paperDianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents🔥4paperReason Through the Latent! Making Latent Visual Reasoning Necessary🔥30paperRevisiting Complete Reasoning Traces for Post-Training🔥5paperEncoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise🔥15paperOpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining🔥55paperRelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting🔥8paperMeasuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy🔥18paperCosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements🔥25paperHarnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection🔥15paperA*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM🔥11paperReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding🔥15paperMarigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation🔥46paperSynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation🔥15paperCoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs🔥20paperDifficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR🔥0paperEliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation🔥84paperAuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing🔥183paperOmni Interaction Agent Technical Report🔥122paperSAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?🔥8paperMask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout🔥43paperCo-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails🔥1paperNOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting🔥3paperProcedural Graphs: Self-Evolving Execution Structures for LLM Agents🔥23paperTANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model🔥19paperTowards a Quantum Erlangen ProgramSI 59paperAgenticGen: Reward-Guided Agentic Video Generation for Advertising🔥2paperScores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents🔥11paperWhere Does the Human End? Creative Agency with Generative AI across Five Years of Chinese Digital PaintingSI 74paperAcademia x Industry: The Role of Fundamentals for Silicon in an AI Native EraSI 46paperExact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-LeaderSI 48paperPlanetary Nebula Central Stars as Tracers of Planetary Nebula-Star Cluster Associations in the GalaxySI 83paperRESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems🔥0paperChance, Persistent Advantage, and the Generative-AI Era in Open-Source Package CareersSI 60paperViolet: Enabling Full Virtualization for M-mode RTOS on RISC-VSI 51paperThe magnetic field in M16: new results from the JCMT BISTRO surveySI 78paperA Multi-Model Non-Intrusive Reduced-Order Framework for Parametric Erosion Prediction via Kinematic Cross-Moment CompressionSI 62paperAXON: A ROS 2 RMW with Shared-Memory/QUIC Transport and QKD/ML-KEM Key EstablishmentSI 65paperField-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogateSI 45paperPhysics-Informed Multi-Task Surrogate Model for the Martian Nightside ThermosphereSI 70paperΦ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?🔥3paperAn $O(1/T^3)$ algorithm for minimizing convex quadratic functions over the $L_1$ ballSI 50paperStencil Computation at the Intersection of AI and HPCSI 83paperGradient-Enhanced Proximal Algorithms for Mean Field Planning on SurfacesSI 74paperShow-Harness: Just a VLM Agent Can Play Robots🔥32paperProgrammable World Model🔥22