Dori Litvak

I'm a Computer Science PhD student at UT Austin working with Prof. Leqi Liu.
My research focuses on how can we build personal AI systems that truly understand us.
This question is far from trivial.
Specifically, I'm interested in building multimodal agentic systems that understand people over time, reason across modalities, and adapt to support human thinking.
My work draws inspiration from Theory of Mind, Cognitive Psychology, Computer Vision, Bayesian Nonparametric Models, Reinforcement Learning, and Dynamical Systems.

Before that, I was a visiting student at the Stanford Vision Lab supervised by Prof. Jiajun Wu. I obtained my master's degree from Ben-Gurion University of the Negev, working at the Vision, Inference, and Learning (VIL) Lab supervised by Prof. Oren Freifeld.

Publications

🐎 Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos.

Sun*, Litvak*, Zhang, Li, Wu†, Wu†, ECCV, 2024.

[Project Page] [Paper] [Video]

🐏🐕🐁🦌🐘🦒🦓🐆🦘🐄🐖🐈🐅🦝🐎🦬🦙 Learning the 3D Fauna of the Web.

Li*, Litvak*, Li, Zhang, Jakab, Rupprecht, Wu†, Vedaldi†, Wu†, CVPR, 2024.

[Project Page] [Paper] [Demo]

🐘 Unsupervised Online Multiple Animal Tracking.

Litvak, Dinari, Freifeld, CV4Animals Workshop, CVPR 2022.

[Poster]

🎾 JA-POLS: a Moving-camera Background Model via Joint Alignment and Partially-overlapping Local Subspaces.

Chelly, Winter, Litvak, Rosen, Freifeld, CVPR 2020.
[Paper] [Code]

Teaching

Contact