Cohere For AI - Patrick (Tsung-Han) Wu, PhD Candidate, UC Berkeley

Visual Haystacks: Answering Harder Questions About Sets of Images

Will explore new methods in Multi-Image Visual Question Answering, focusing on retrieval and reasoning across diverse image collections using the Visual Haystacks benchmark

Patrick (Tsung-Han) Wu (he/him) is a second-year CS PhD student at UC Berkeley, advised by Prof. Trevor Darrell and Prof. Joseph E. Gonzalez. His recent work focuses on exploring the zero-shot applications and addressing the limitations of Large (Vision) Language Models. For more information, visit his personal website: https://tsunghan-wu.github.io/.