About
Yuhan Wang
Founder & CTO @ Engram · MIT Researcher · Imperial College
I am the Founder & CTO of Engram, where we are building a local-first cognitive alignment layer for AI systems. I hold a Master's in Joint Mathematics and Computer Science from Imperial College and am a graduate researcher at MIT Media Lab.
My work spans deep learning, robotics, computer vision, and agent engineering. My research interests include 3D/4D foundation models, world model, VLA, robotics, agent infra, and cognitive AI.
Previously, I conducted research at MIT Media Lab on 4D perception (PAGE-4D, ICLR 2026), and I will join Millennium's Equity Technology Team as an AI Engineer Intern in Summer 2026.
For academic collaboration, reach me at yuhanwangwork14@gmail.com. For business and Engram inquiries, yuhan@engramai.co.
News
- 2026.03 🚀 PAGE-4D training + evaluation code fully open-sourced! Check it out on GitHub.
- 2026.02 🏗️ Founded Engram — building a local-first cognitive alignment layer for AI systems.
- 2026.01 🎓 PAGE-4D paper accepted by ICLR 2026!
- 2025.11 💼 Accepted an offer from Millennium's Equity Technology Team as an AI Engineer Intern!
- 2025.06 🎓 Joined MIT Media Lab as a Visiting Graduate Researcher!
Publications
- ICLR 2026
PAGE-4D: Disentangled Pose and Geometry Estimation for 4D PerceptionKaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang.