today local_bar

Vikash Sehwag

Researcher, Google

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges

#4310 Spotlight · Kevin David Hayes, Micah Goldblum, Vikash Sehwag, Gowthami Somepalli, Ashwinee Panda, Tom Goldstein

We jointly evaluate VLMs and diffusion models by seeing whether VLMs can evaluate diffusion model failure modes.