Hi, I am Suyu (Michael) Ye, a Junior at Johns Hopkins University advised by Professor Tianmin Shu. I am double majoring in Computer Science and Applied Mathematics and Statistics, supported by a National Merit Scholarship. I am interested in building safe, trustworthy, and intuitive AI systems that collaborate with people in complex, multimodal environments. My interests spans human–robot interaction, multimodal learning, and multi-agent reasoning. I aim to enable robots and embodied agents to infer human intent, ground their reasoning in perception and action, and adaptively coordinate with people in everyday settings.

News

• [Nov 2025] - RealWebAssist accepted to AAAI 2026 (17.6% acceptance rate)
• [Nov 2025] - RealWebAssist selected as a spotlight paper at the NeurIPS 2025 LAW Workshop
• [Jan 2025] – MuMA-ToM accepted to AAAI 2025 as an Oral Presentation
• [Sept 2024] – Assessing the limitations of relief based algorithms in detecting higher order interactions published on BioData Mining
• [Oct 2024] – MuMA-ToM accepted to NeurIPS 2024 Video Language Workshop.
• [Oct 2024] – MuMA-ToM accepted to NeurIPS 2024 Behavioral ML workshop.

Publications

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

Haojun Shi*, Suyu Ye*, Xinyu Fang, Chuanyang Jin, Leyla Isik, Yen-Ling Kuo, Tianmin Shu (*equal contribution)
AAAI 2025 (Oral)
Paper | Website | Code

Assessing the limitations of relief-based algorithms in detecting higher-order interactions

Philip J. Freda, Suyu Ye, Robert Zhang, Jason H. Moore, Ryan J. Urbanowicz
BioData Mining
Paper

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users

Suyu Ye*, Haojun Shi*, Darren Shih, Hyokun Yun, Tanya Roosta, Tianmin Shu
(*equal contribution)
Accepted to AAAI 2026
Paper | Website | Code