today local_bar

Zenghui Yuan

Associate Professor, Hangzhou Dianzi University

2 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models

#3915 · Hai Yan, Haijian Ma, Xiaowen Cai, Daizong Liu, Zenghui Yuan, Xiaoye Qu, Jianfeng Dong, Runwei Guan, Xiang Fang, Hongyang He, Yulai Xie, Pan Zhou

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

#5100 · Guiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu, Tianhe Gu, Ruihang Zhang, Sizhe Zhang, Junran Wu, Xiaoyue Tu, Ming Jin, Qingsong Wen, Lixing Chen, Pan Zhou, Lichao Sun

This paper introduces CorrectBench, the first comprehensive benchmark for systematically evaluating self-correction mechanisms in LLMs.