Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 3 days ago • 515
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation Paper • 2608.28460 • Published 8 days ago • 28
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 167
BadWAM: When World-Action Models Dream Right but Act Wrong Paper • 2607.15207 • Published Jul 16 • 54
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos Paper • 2607.11523 • Published Jul 13 • 13
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation Paper • 2607.00052 • Published Jun 30 • 7
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published Jun 11 • 85
Agent Skills Should Go Beyond Text: The Case for Visual Skills Paper • 2606.01414 • Published May 31 • 11
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 434