- 1 FeatCal: Feature Calibration for Post-Merging Models ↗
- 2 MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning ↗
- 3 Context Training with Active Information Seeking ↗
- 4 RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data ↗
- 5 Revisiting DAgger in the Era of LLM-Agents ↗
- 6 Asymmetric Flow Models ↗
- 7 Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation ↗
- 8 Many-Shot CoT-ICL: Making In-Context Learning Truly Learn ↗
- 9 FrameSkip: Learning from Fewer but More Informative Frames in VLA Training ↗
- 10 Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling ↗
- 11 Qwen-Image-VAE-2.0 Technical Report ↗
- 12 Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context ↗
- 13 RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation ↗
- 14 AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation ↗
- 15 MinT: Managed Infrastructure for Training and Serving Millions of LLMs ↗
- 16 Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation ↗
- 17 AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation ↗
- 18 F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking ↗
- 19 Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition ↗
- 20 PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents ↗
- 21 IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages ↗
- 22 Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization ↗
- 23 ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes ↗
- 24 Position: LLM Inference Should Be Evaluated as Energy-to-Token Production ↗
- 25 Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? ↗
- 26 Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion ↗
- 27 PresentAgent-2: Towards Generalist Multimodal Presentation Agents ↗
- 28 Learning Agentic Policy from Action Guidance ↗
- 29 The DAWN of World-Action Interactive Models ↗
- 30 TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking ↗
- 31 WriteSAE: Sparse Autoencoders for Recurrent State ↗
- 32 Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling ↗
- 33 M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement ↗
- 34 MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading ↗
- 35 HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution ↗
- 36 MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image ↗
- 37 From Pixels to Concepts: Do Segmentation Models Understand What They Segment? ↗
- 38 Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs ↗
- 39 The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs ↗
- 40 FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation ↗
- 41 Retrieval from Within: An Intrinsic Capability of Attention-Based Models ↗
- 42 Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge ↗
- 43 SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety ↗