TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 7 days ago • 165
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published 10 days ago • 139
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published 6 days ago • 196
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM Paper • 2607.11683 • Published 13 days ago • 143
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World Paper • 2607.17250 • Published 7 days ago • 89
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 8 days ago • 135
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models Paper • 2607.01774 • Published 6 days ago • 38
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 5 days ago • 292