Research

I am broadly interested in machine learning, computer vision and multimodal models. My research interests are right at the intersection of visual recognition and language models. More specifically, I am interested in designing better evaluation techniques for visual language models/multimodal generative models, studying their robustness and improving their understanding on visual language tasks.

Check my Google Scholar for updated information!

Publications

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

  • [NeurIPS 2024] Baiqi Li*, Zhiqiu Lin*, Wenxuan Peng*, Jean de Dieu Nyandwi*, Daniel Jiang, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan

Research Articles

  • The Transformer Blueprint: A Holistic Guide to the Transformer Neural Network Architecture | Blog | Views: 31K | July 2023