Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Paper • 2605.30280 • Published 8 days ago • 137
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models Paper • 2605.30263 • Published 8 days ago • 56
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models Paper • 2605.30219 • Published 8 days ago • 24
Self-Improving Language Models with Bidirectional Evolutionary Search Paper • 2605.28814 • Published 9 days ago • 58
GPIC: A Giant Permissive Image Corpus for Visual Generation Paper • 2605.30341 • Published 8 days ago • 2
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 9 days ago • 419
Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing Paper • 2604.28142 • Published Apr 30 • 1
DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking Paper • 2605.26087 • Published 11 days ago • 1
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 10 days ago • 137
DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion Paper • 2506.14202 • Published Jun 17, 2025 • 4
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published 14 days ago • 221
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks Paper • 2605.24218 • Published 14 days ago • 42
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems Paper • 2605.22794 • Published 15 days ago • 1
Forecasting Scientific Progress with Artificial Intelligence Paper • 2605.22681 • Published 15 days ago • 43
Why Fine-Tuning Encourages Hallucinations and How to Fix It Paper • 2604.15574 • Published Apr 16 • 25