Ming Yin

Publications

* equal contribution    † corresponding author

Training and Evaluation

MARS: Multi-resolution Adaptive Routing for Sequential Recommendation

Ming Yin, Sixun Dong, Yudong Liu, Wen-Yun Yang, Yunjiang Jiang, Yiran Chen

NeurIPS 2026 Paper

When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation

Ming Yin, Yuhan Yang, Chen Chen, Xinyu Lin, Wentao Shi, Fangcong Yin, Chaofei Yang, Chao Yang, Jiyan Yang, Hui Zhang, Ning Jiang, Yiran Chen, Qifan Wang

Preprint 2026 Work done at Meta Paper

Agents’ Last Exam

Yiyou Sun, Xinyang Han, Weichen Zhang, …, Ming Yin, …, Dawn Song

NeurIPS 2026 Paper

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 Spotlight Paper Code and data Synced

LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

Ming Yin, Dinghan Shen, Silei Xu, Sixun Dong, Mian Zhang, Yebowen Hu, Shujian Liu, Jianbing Han, Simin Ma, Song Wang, Sathish Reddy Indurthi, Xun Wang, Yiran Chen†, Kaiqiang Song†

Preprint 2026 Paper Synced AK

LogicIF: Towards Complex Logic Instruction Following

Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Steven Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song

COLM 2026 Paper

Efficient multimodal LLMs

MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

Sixun Dong, Juhua Hu, Mian Zhang, Ming Yin, Yanjie Fu, Qi Qian

ICLR 2026 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

ICCV 2025 Paper

Trustworthy machine learning

Poisoning Federated Recommender Systems with Fake Users

Ming Yin, Yichang Xu, Minghong Fang, Neil Gong

WWW 2024 Paper

Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks

Yichang Xu*, Ming Yin*, Minghong Fang, Neil Gong

WWW 2024 Paper

LoBAM: LoRA-Based Backdoor Attack on Model Merging

Ming Yin, Jingyang Zhang, Jingwei Sun, Minghong Fang, Hai Li, Yiran Chen

ICLR 2025 Workshop Paper

A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use

Yutong Ke*, Ming Yin*, Chongwen Zhao, Kaizhu Huang

Preprint 2026 Paper

Survey

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Minghao Guo, Qingyue Jiao, Xiujin Liu, …, Ming Yin, …, Mengdi Wang, Jiawei Han, Philip S. Yu, Ziyi Ye

Preprint 2026

Experience

Meta

May 2026 – Dec 2026

Research Scientist Intern, Menlo Park, CA

LLM post-training for recommendation and long-horizon LLM agents. First author of When History Misleads.

Zoom

May 2025 – Aug 2025

Research Intern, Seattle, WA

Agent tool calling and the Model Context Protocol (MCP). Led LiveMCP-101, a benchmark of 101 real-world queries that need multi-step use of MCP tools across 41 servers and 260 tools.

Education

Duke University

Aug 2024 – present

Ph.D. in Electrical and Computer Engineering

Advisor: Prof. Yiran Chen

University of Science and Technology of China

Sep 2020 – Jun 2024

B.E. in Computer Science, School of the Gifted Young

Advisor: Prof. Weiming Zhang

Honors and awards

• Duke PhD Fellowship2024
• Qiangwei Progress Scholarship, USTC (top 1%)2023
• Excellent Student Scholarship, Gold, USTC (top 3%)2021, 2023
• ICPC Asia Regional Contest (top 5%)2022
• First Prize, Chinese Physics Olympiad, Jiangsu Province (top 0.04%)2019