Trimming the Long-Tail of Visual World Modeling Evaluation Paper • 2606.24256 • Published 21 days ago • 42
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published Apr 9 • 51
LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training Paper • 2510.14969 • Published Oct 16, 2025 • 8
OpenCLIP LAION-2B Collection OpenCLIP models trained on LAION-2B • 19 items • Updated Oct 20, 2025 • 26