Ke Li

I’m a Ph.D. student at Stony Brook University, advised by Dr. Ruwen Qin. Previously, I earned my M.S. in Civil Engineering from UIUC (2023) and my B.S. from Southeast University (2021).

My research focuses on Generative AI, diffusion models for autonomous driving, with an emphasis on perception, recognition, and safety-critical driving scenarios.

Research Interests: Generative AI, Diffusion Models, Video Prediction, Autonomous Driving.

portrait

News

July 09, 2026
Excited to share that our paper CCFM has been accepted to the ECCV 2026.
Jan 16, 2026
Excited to share that our paper has been accepted to the IEEE Intelligent Vehicles Symposium (IV) 2026.
Jan 10, 2026
Honored to attend TRB 2026 and present a poster in a conference session.
Sep 17, 2025
Our work on the KAA-CAL model is now available on arXiv.

Projects

thumbnail
CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation
Ke Li,Kaidi Liang, Yuxin Ding, Debojyoti Biswas, Xianbiao Hu, and Ruwen Qin
ECCV2026
PAGE CODE PDF
thumbnail
CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis
Kaidi Liang, Ke Li, Xianbiao Hu, and Ruwen Qin
ArXiv2026
PAGE CODE PDF
thumbnail
HMPDM: A Diffusion Model for Driving Video Prediction with Historical Motion Priors
Ke Li, Tianjia Yang, Kaidi Liang, Xianbiao Hu, Ruwen Qin
IEEE IVS2026
PAGE CODE PDF
thumbnail
Multi-label Scene Classification for Autonomous Vehicles: Acquiring and Accumulating Knowledge from Diverse Datasets
Ke Li, Chenyu Zhang, Yuxin Ding, Xianbiao Hu, Ruwen Qin
ArXiv2025
PAGE CODE PDF