Trimming the Long-Tail of Visual World Modeling Evaluation Paper • 2606.24256 • Published 11 days ago • 40
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
asymmetric-VLM Collection Datasets for https://asymmetric-vlm-post-training.github.io/ • 3 items • Updated 25 days ago
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published Apr 9 • 51