Publications
* indicates equal contribution
Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
arXiv
The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences
arXiv
Animate Agent World Modeling Benchmark
Proceedings of the Annual Meeting of the Cognitive Science Society
From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning
NeurIPS Agent Learning in Open-Endness Workshop
How well do unsupervised learning algorithms model human real-time and life-long learning?
NeurIPS Datasets and Benchmarks Track
Defending against microphone-based attacks with personalized noise
Proceedings on Privacy Enhancing Technologies
Learning the generative principles of a symbol system from limited examples
Cognition