today local_bar

Jun Luo

Full Professor, Nanyang Technological University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

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

Exhibit Hall C,D,E

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

#4914 Spotlight · Jingjing Jiang, Chongjie Si, Jun Luo, Hanwang Zhang, Chao Ma

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs

#1410 · Zhixin Xie, Xurui Song, Jun Luo

Exploiting the overfitting of LLMs, we use only ten benign QA pairs to fine-tune and jailbreak them.