Pei-Hua Mai

See, Think, Use: Diagnosing Perception and Reasoning Failures in VLMs

We present See, Think, Use, a protocol that traces each answer of a vision-language model to perception, reasoning or the use of perception. The diagnosis shows a developer which stage to improve and directs test-time compute to the stage that fails. Benchmarks score the final answer, and an answer that rests on the im...