PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback Paper • 2608.30241 • Published 30 days ago • 12
Trimming the Long-Tail of Visual World Modeling Evaluation Paper • 2606.24256 • Published Jun 23 • 41
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 65
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published Apr 9 • 49
LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training Paper • 2510.14969 • Published Oct 16, 2025 • 8