About me

• I am currently a researcher in Beijing, China. Before that, I earned my PhD from Chinese Academy of Sciences, where I was mentored by Prof. Xian Sun.

• Research interests: Design, Optimization, and Application of Large Language Models and Multimodal Large Models.

News

• 2025.7: Congrats! Our paper has been accepted by ACM MM 2025!
• 2025.5: Congrats! Our two papers have been accepted by ACL 2025!

Publications

* for corresponding author, ^# for corresponding author.

• ACM MM 2025 From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models, Yuying Shang, Xinyi Zeng, Yutao Zhu, Xiao Yang, Zhengwei Fang, Jingyuan Zhang, Jiawei Chen, Zinan Liu, Yu Tian*.
• ACL 2025 Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level, Xinyi Zeng, Yuying Shang, Jiawei Chen, Jingyuan Zhang, Yu Tian*.
• ACL 2025 TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos, Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, Victoria W., Fuzheng Zhang.
• AAAI 2025 Workshop PDLM Feature-Aware Malicious Output Detection and Mitigation, Weilong Dong, Peiguang Li, Yu Tian*, Xinyi Zeng, Fengdi Li, Sirui Wang.
• TGRS Sopermodel: Leveraging social perception for multi-agent trajectory prediction, Heming Yang, Yu Tian, Changyuan Tian, Hongfeng Yu, Wanxuan Lu, Chubo Deng, Xian Sun.
• EMNLP 2024 Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal, Zhicong Lu, Li Jin, Peiguang Li, Yu Tian*, Linhao Zhang, Sirui Wang, Guangluan Xu, Changyuan Tian, Xunliang Cai.
• NAACL 2025 toFindings Autobreach: Universal and adaptive jailbreaking with efficient wordplay-guided optimization, Jiawei Chen, Xiao Yang, Zhengwei Fang, Yu Tian, Yinpeng Dong, Zhaoxia Yin, Hang Su.
• Neurocomputing Graph-enhanced context aware framework for session-based recommendation, Xinyi Zeng, Zequn Zhang, Shuchao Li, Zhi Guo, Yu Tian, Li Jin, Xian Sun.
• Arxiv Bspa: Exploring black-box stealthy prompt attacks against image generators, Yu Tian, Xiao Yang, Yinpeng Dong, Heming Yang, Hang Su, Jun Zhu.
• Arxiv Evil Geniuses: Delving into the Safety of LLM-based Agents, Yu Tian, Xiao Yang, Jingyuan Zhang, Yinpeng Dong, Hang Su.
• NeurIPS 2023 R0-FoMo How Robust is Google’s Bard to Adversarial Image Attacks?, Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, Jun Zhu.
• Science China Information Sciences From single-to multi-modal remote sensing imagery interpretation: A survey and taxonomy, Xian Sun, Yu Tian, Wanxuan Lu, Peijin Wang, Ruigang Niu, Hongfeng Yu, Kun Fu
• ISPRS Fully-weighted HGNN: Learning efficient non-local relations with hypergraph in aerial imagery, Yu Tian, Xian Sun, Ruigang Niu, Hongfeng Yu, Zicong Zhu, Peijin Wang, Kun Fu
• COLING 2022 Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding, Zhaoye Fei^#, Yu Tian^#, Yongkang Wu^#, Xinyu Zhang^#, Yutao Zhu, Zheng Liu, Jiawen Wu, Dejiang Kong, Ruofei Lai, Zhao Cao, Zhicheng Dou, Xipeng Qiu

Awards

• Excellent Doctoral Dissertation Award of the Chinese Academy of Sciences (approximately 100 selected annually from UCAS and USTC)
• CAS President Scholarship
• ICRA 2024 The RoboDrive Challenge Track 2: Robust Map Segmentation 1st Place
• The 8th National Conference on Social Media Processing The Evaluation of Chinese Judicial Reading Comprehension Technology 1st Place

Academic Services

• PC Member: ACL Rolling Review, ICLR, AAAI
• Journal Reviewer: TKDD, Pattern Recognition