I'm a Research Scientist at The Institute for Human and Machine Cognition. Previously, I was a postdoctoral fellow in the Department of Psychology at Harvard University, advised by Sam Gershman, a PhD student at University of Rochester advised by Robbie Jacobs, and before that a research assistant with Josh Tenenbaum and Peter Battaglia at MIT. I have an undergraduate degree in mechanical engineering from Purdue University.

Research

My current interests are in AI. One line of work is on building agents that can learn and adapt to new domains (such as games) as readily as humans. Another line of work is on building AI applications that understand human moral preferences and help us make better policy decisions and improve cooperation in society.

My previous work has focused on the question of what we remember (and forget) about images, in the short term as well as the long term. A central challenge for this line of work is that human visual representations are highly complex and sophisticated in ways that are hard to recreate in scientific models. My work develops a methodology for tackling this problem, which I hope can be built on by the larger research community. For example, I have found success extracting human-like visual representations from deep neural networks and building noisy decision models on top of these.

In my earlier work on "intuitive physics", we asked to what extent people can predict the behavior of fluids under various scenarios. Based on our experimental task, I made a browser game which simulates liquid using the same method powering our cognitive models (courtesy of liquidFun).

Talks

University of Pennsylvania (March 6, 2020) [video link]

Selected Publications

Bates, C. J., Bose, R., Keeney, R. G., Kazakova, V. A. (2023). Contractual AI: Toward More Aligned, Transparent, and Robust Dialogue Agents. In 2023 AAAI Fall Symposium: Assured and Trustworthy Human‑centered AI.

Bates, C. J., Alvarez, G., & Gershman, S. J. (2023). Scaling models of visual working memory to natural images. bioRxiv, 2023-03. [Paper][Code]

Bates, C., & Gershman, S. (2022). Coding Strategies in Memory for 3D Objects: The Influence of Task Uncertainty. In Proceedings of the Annual Meeting of the Cognitive Science Society (Vol. 44, No. 44). [Paper]

Bates, C. J., & Jacobs, R. A. (2020, April 23). Efficient Data Compression in Perception and Perceptual Memory. Psychological Review. Advance online publication. http://dx.doi.org/10.1037/rev0000197 [Paper]

Bates, C. J., Lerch, R. A., Sims, C. R., & Jacobs, R. A. (2019). Adaptive allocation of human visual working memory capacity during statistical and categorical learning. Journal of Vision, 19(2), 11-11. [Paper]

Bates, C. J., Yildirim, I., Tenenbaum, J. B., & Battaglia, P. (2019). Modeling human intuitions about liquid flow with particle-based simulation. PLOS Computational Biology, 15(7), e1007210. [Paper]

Jacobs, R. A., & Bates, C. J. (2018). Comparing the Visual Representations and Performance of Humans and Deep Neural Networks. Current Directions in Psychological Science, 0963721418801342. [Paper]