|
Ming Yin I am a first-year PhD student at Duke University, supervised by Prof. Yiran Chen and Prof. Hai Li.
I received my Bachelor's degree from School of the Gifted Young, USTC in 2024 at 20 years old.
I am currently interested in LLM Agents, LLM Reasoning, and Trustworthy AI. π― From May to August 2025, Iβm serving as a GenAI Research Intern at Zoom in Seattle. Please feel free to reach out if youβd like to chat, connect or collaborate! Email / Google Scholar / LinkedIn / CV / |
|
π Publications(* indicates Equal Contribution) |
|
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Shaokun Zhang*, Ming Yin*, Jieyu Zhang, Jiale Liu, Zhiguang Han, Jingyang Zhang, Beibin Li, Chi Wang, Huazheng Wang, Yiran Chen, Qingyun Wu ICML 2025 (π Spotlight, 313/12107 = 2.58%) Media Coverage: [ζΊε¨δΉεΏ] |
|
Poisoning Federated Recommender Systems with Fake Users
Ming Yin*, Yichang Xu*, Minghong Fang, Neil Gong WWW 2024 |
|
LoBAM: LoRA-Based Backdoor Attack on Model Merging
Ming Yin, Jingyang Zhang, Jingwei Sun, Minghong Fang, Hai Li, Yiran Chen ICLR 2025 Workshop, also under review as a conference paper |
|
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
Yudong Liu, Jingwei Sun, Yueqian Lin, Jingyang Zhang, Ming Yin, Qinsi Wang, Jianyi Zhang, Hai Li, Yiran Chen preprint |
|
Robust Federated Learning Mitigates Client-side Training Data
Distribution Inference Attacks
Yichang Xu*, Ming Yin*, Minghong Fang, Neil Gong WWW 2024
|
β Industrial Experience |
|
Zoom, GenAI Research Intern
Seattle, WA May 2025 - Aug 2025 |
π Reviewer ServiceICLR 2025, ICCV 2025, NeurIPS 2025, TDSC |
Thanks Jon Barron for the template.