Winson Han
3 papers · Latest:
Robotics
MolmoAct2: Action Reasoning Models for Real-world Deployment
MolmoAct2 is an open-source action reasoning model for robots, featuring a specialized VLM, new datasets, and efficient architecture for real-world deployment.
2605.02881
Computer VisionPosterior Augmented Flow Matching
PAFM enhances flow matching by using posterior-augmented supervision to reduce training variance, preventing flow collapse and improving generative models.
2605.00825
Computer VisionMolmoWeb: Open Visual Web Agent and Open Data for the Open Web
MolmoWeb introduces open visual web agents and a large, diverse dataset (MolmoWebMix) that achieve state-of-the-art performance on web-use benchmarks.
2604.08516
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.