today local_bar

Di Wang

Assistant Professor, KAUST

5 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

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

Exhibit Hall C,D,E

Private Training Large-scale Models with Efficient DP-SGD

#1915 · Liangyu Wang, Junxiao Wang, Jie Ren, Zihang Xiang, David E. Keyes, Di Wang

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

#1101 · Lin Zhang, Wenshuo Dong, Zhuoran Zhang, Shu Yang, Lijie Hu, Ninghao Liu, Pan Zhou, Di Wang

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents

#2410 · Xiaochuan Gou, Ziyue Li, Tian Lan, Junpeng Lin, zhishuai Li, Bingyu Zhao, Chen Zhang, Di Wang, Xiangliang Zhang

Poster Session 6

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

Exhibit Hall C,D,E

Second-Order Convergence in Private Stochastic Non-Convex Optimization

#808 · Youming Tao, Zuyuan Zhang, Dongxiao Yu, Xiuzhen Cheng, Falko Dressler, Di Wang

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence

#4904 · Shaopeng Fu, Liang Ding, Jingfeng Zhang, Di Wang

We find that it is effective to defend "long-length" jailbreak attacks via efficient "short-length" LLM adversarial training, supporting by both theoretical and empirical evidence.