logo
today local_bar

Xingjun Ma

Associate Professor, Fudan University

5 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

3 papers
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
OmniSVG: A Unified Scalable Vector Graphics Generation Model
#5512 · Yiying Yang, Wei Cheng, Sijin Chen, Xianfang Zeng, Fukun Yin, Jiaxu Zhang, Liao Wang, Gang YU, Xingjun Ma, Yu-Gang Jiang
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
#4814 · Ye Sun, Hao Zhang, Henghui Ding, Tiehua Zhang, Xingjun Ma, Yu-Gang Jiang
SafeVid: Toward Safety Aligned Video Large Multimodal Models
#1203 · Yixu Wang, Jiaxin Song, Yifeng Gao, Xin Wang, Yang Yao, Yan Teng, Xingjun Ma, Yingchun Wang, Yu-Gang Jiang

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
#1405 · Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

In this work, we introduce \textit{BackdoorLLM}, the first comprehensive benchmark for studying backdoor attacks and defenses on LLMs.

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
#5207 · Jiaxin Song, Yixu Wang, Jie Li, Xuan Tong, rui yu, Yan Teng, Xingjun Ma, Yingchun Wang