Principal Researcher, Massachusetts Institute of Technology
3 papers at NeurIPS 2025
We generalize CLIP training to worldwide web-scale, with +0.8% better than English only counterpart on zero-shot ImageNet classification (no compromise), SoTA on zero-shot multilingual: 57.4% on CVQA and 50.2% on Babel-ImageNet.
We introduce ROVER, a recursive framework that improves the video reasoning accuracy and efficiency of vision-language models in embodied settings.
