Hongyang Du

MS student, Brown University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

#4715 · Zongxia Li, Xiyang Wu, Guangyao Shi, Yubin Qin, Hongyang Du, Tianyi Zhou, Dinesh Manocha, Jordan Lee Boyd-Graber

We present VideoHallu, a benchmark of over 3,000 synthetic videos with expert-crafted counterintuitive QA pairs, evaluating MLLMs' ability to detect perceptually obvious abnormalities often missed due to language priors.