Catherine (Cathy) Ji

I'm a Physics PhD candidate at Princeton University advised by Benjamin Eysenbach and Gautam Reddy. I'm interested in unsupervised reinforcement learning, applying reinforcement learning to understand the physics of decision-making systems, and estimating and maximizing human agency. I am supported by the NSF GRFP and the Centennial Fellowship. Previously, I did my undergrad at MIT, where I received a B.S. in Physics and Math.

cj7280 [at] princeton [dot] edu / Scholar / GitHub

Papers

* denotes equal contribution.

	Scaling Empowered Agents Catherine Ji, Vivek Myers, Joshua Lin, Alexandra Wingate, Sergey Levine, Benjamin Eysenbach Preprint, 2026 interactive project page / arXiv
	The Geometry of Empowerment Catherine Ji, Vivek Myers, Sergey Levine, Benjamin Eysenbach Preprint, 2026 project page / arXiv / code
	Review: Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning Emmy Blumenthal, Nikolas Claussen, Benjamin Eysenbach, Catherine Ji, Gautam Reddy, Colin Scheibner, Benjamin Sorkin (alphabetical order) Preprint, 2026 arXiv
	Identifying Nonequilibrium Degrees of Freedom in High-Dimensional Stochastic Systems Catherine Ji, Ravin Raj, Benjamin Eysenbach, Gautam Reddy Physical Review Research, 2026 journal / arXiv / code
	Discovering Diverse Behaviors via Temporal Contrastive Learning Faisal Mohamed, Catherine Ji, Benjamin Eysenbach, Glen Berseth ICLR, 2026 arXiv
	Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration Chirayu Nimonkar, Shlok Shah, Catherine Ji, Benjamin Eysenbach NeurIPS, 2026 project page / arXiv
	Low-N Protein Activity Optimization with FolDE Jacob B. Roberts, Catherine R. Ji, Isaac Donnell, Thomas D. Young, Allison N. Pearson, Graham A. Hudson, Leah S. Keiser, Mia Wesselkamper, Peter H. Winegar, Janik Ludwig, Sarah H. Klass, Isha V. Sheth, Ezechinyere C. Ukabiala, Maria C. T. Astolfi, Benjamin Eysenbach, Jay D. Keasling Preprint, 2025 arXiv / code
	BuilderBench: The Building Blocks of Intelligent Agents Raj Ghugare, Roger Creus Castanyer, Catherine Ji, Kathryn Wantlin, Jin Schofield, Karthik Narasimhan, Benjamin Eysenbach RLBrew Workshop, 2025 blog post / arXiv / code
	Horizon Generalization in Reinforcement Learning Vivek Myers, Catherine Ji, Benjamin Eysenbach ICLR, 2025 project page / arXiv

Talks

The Geometry of Empowerment
Invited talk (with Benjamin Eysenbach), RLxF: RL from World Feedback workshop, ICML 2026

Horizon Generalization in Reinforcement Learning
Invited talk, Cohere reinforcement learning reading group, 2025

Website template from Jon Barron.