ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 6 days ago • 299
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 10 days ago • 136
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 9 days ago • 165
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published Jun 16 • 77
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 252