Dedieu, Antoine

Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps

George, D., Rikhye, R. V., Gothoskar, N., Guntupalli, J. S., Dedieu, A., & Lázaro-Gredilla, M. (2021) · Nature Communications

Memory and Neural MechanismsSpatial Cognition and Navigation

Cited by 109

Schema-learning and rebinding as mechanisms of in-context learning and emergence

Swaminathan, S., Dedieu, A., Raju, R. V., Shanahan, M., Lazaro-Gredilla, M., & George, D. (2023) · arXiv

Neural Networks and ApplicationsCognitive Science and Education Research

Cited by 8

Learning higher-order sequential structure with cloned HMMs

Dedieu, A., Gothoskar, N., Swingle, S., Lehrach, W., Lázaro-Gredilla, M., & George, D. (2019) · arXiv

Speech Recognition and SynthesisTopic Modeling

Cited by 7

Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments

Dedieu, A., Lehrach, W., Zhou, G., George, D., & Lázaro-Gredilla, M. (2024) · arXiv

Reinforcement Learning in RoboticsAI-based Problem Solving and Planning

Cited by 2

AutoHarness: improving LLM agents by automatically synthesizing a code harness

Lou, X., Lázaro-Gredilla, M., Dedieu, A., Wendelken, C., Lehrach, W., & Murphy, K. P. (2026) · arXiv

Artificial Intelligence in GamesArtificial Intelligence Applications

Cited by 0