Paper abstract and links
The authors’ abstract, vote count and code link of any paper on the current daily list.
On the current list
- ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
- Hy-Nomas: Towards Free-form Interactive World Generation
- PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
- Rollback: Experience Backtracking in World Models for Policy Improvement
- The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
- ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
- CodeCap-Bench: Can Code Serve as a Good Video Caption?
- Memory Tax: Dissecting the Net Value of Agent Memory
- HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory
- LociArt: A Unified Paradigm for Free-Style Local Video Stylization
- Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
- MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
- RSI Arena: Towards Recursive Self-Improvement with Human Feedback
- Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams
- Cross-modal Steering Vectors Exist Across Both Image and Text Generation
- RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions
- Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces
- Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
- What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
- VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
- Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation
- OvisOCR3 Technical Report
- Can LLMs Uncover Hidden Physical Laws through Free Exploration?
- Vision-Language-Action or World-Action? Just Action Models
- Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation
- Timestral
- SearchHorizonBench: A Benchmark for Search Value in AI Agents
- Harness-Model Collaboration for Long-Horizon Continual Learning
- On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
- Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions