Zewei Zhang

I am Zewei Zhang, an AI researcher and founder with a PhD in Electrical & Computer Engineering from McMaster University, where I was supervised by Prof. Jun Chen. I was a Visiting Researcher at the University of British Columbia with Prof. Renjie Liao, previously worked closely with Prof. Xiangyu Xu, and completed an Applied Scientist internship at Amazon in Toronto.

My research spans generative modeling, video and trajectory prediction, controllable editing, and learning-guided search. Across these areas, I study how models represent motion, structure, and time, and how generation, evaluation, and search can improve prediction, control, and decision-making.

My current focus is AI systems that learn from real-project experience. Real projects unfold through questions, hypotheses, experiments, failures, revisions, and delayed outcomes; this history contains important information that final artifacts alone do not preserve. I am building a research-first AI company around this direction, with the goal of developing learning systems that help models improve across projects.

• Sep 2026 Completed my PhD defense in Electrical & Computer Engineering at McMaster University.
• Aug 2026 Completed my Applied Scientist internship at Amazon in Toronto.
• May 2026 Joined Amazon in Toronto as an Applied Scientist Intern, focusing on human-guided video-to-video motion editing.
• Mar 2026 Released TrajLoom, a dense future trajectory generation framework for long-horizon video modeling.
• Jan 2026 Boolean Satisfiability via Imitation Learning was accepted to ICLR 2026.
• Jun 2025 Began a Visiting Researcher position at UBC with Prof. Renjie Liao, working on trajectory-based video generation and evaluation.
• Mar 2025 GoodDrag was accepted to ICLR 2025.