Jian Liang

PhD student, Wuhan University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

#1406 · Xuankun Rong, Wenke Huang, Jian Liang, Jinhe Bi, Xun Xiao, Yiming Li, Bo Du, Mang Ye

We detect and remove backdoor samples in MLLM fine-tuning by identifying abnormal attention entropy patterns without requiring clean data or model modifications.