Michael Curtis Mozer

19 papers A* 10Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Exploring exploration with foundation agents in interactive environments.
Trans. Mach. Learn. Res.
Daniel P. Sawyer, Nan Rosemary Ke, Hubert Soyer, Martin Engelcke, John Reid, David P. Reichert, Drew A. Hudson, Alexander Lerchner, Danilo Jimenez Rezende, Timothy P. Lillicrap, Michael Curtis Mozer, Jane X. Wang
2025 J jnl
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization.
CoRR
Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou
2025 J jnl
Low Compute Unlearning via Sparse Representations.
Trans. Mach. Learn. Res.
Vedant Shah, Frederik Träuble, Ashish Malik, Hugo Larochelle, Michael Curtis Mozer, Sanjeev Arora, Yoshua Bengio, Anirudh Goyal
2025 A* conf
On the Transfer of Object-Centric Representation Learning.
ICLR
Aniket Rajiv Didolkar, Andrii Zadaianchuk, Anirudh Goyal, Michael Curtis Mozer, Yoshua Bengio, Georg Martius, Maximilian Seitzer
2025 — conf
Racing Thoughts: Explaining Contextualization Errors in Large Language Models.
NAACL (Long Papers)
Michael A. Lepori, Michael Curtis Mozer, Asma Ghandeharioun
2025 J jnl
Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data.
CoRR
Stefan Schoepf, Michael Curtis Mozer, Nicole Mitchell, Alexandra Brintrup, Georgios Kaissis, Peter Kairouz, Eleni Triantafillou
2024 J jnl
Improving Discrete Optimisation Via Decoupled Straight-Through Gumbel-Softmax.
CoRR
Rushi Shah, Mingyuan Yan, Michael Curtis Mozer, Dianbo Liu
2024 A* conf
On the Foundations of Shortcut Learning.
ICLR
Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer
2024 J jnl
Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery.
CoRR
Anand Gopalakrishnan, Aleksandar Stanic, Jürgen Schmidhuber, Michael Curtis Mozer
2023 A* conf
Can Neural Network Memorization Be Localized?
ICML
Pratyush Maini, Michael Curtis Mozer, Hanie Sedghi, Zachary Chase Lipton, J. Zico Kolter, Chiyuan Zhang
2023 A* conf
Discrete Key-Value Bottleneck.
ICML
Frederik Träuble, Anirudh Goyal, Nasim Rahaman, Michael Curtis Mozer, Kenji Kawaguchi, Yoshua Bengio, Bernhard Schölkopf
2023 A* conf
Learning in temporally structured environments.
ICLR
Matt Jones, Tyler R. Scott, Mengye Ren, Gamaleldin Fathy Elsayed, Katherine L. Hermann, David Mayo, Michael Curtis Mozer
2023 A* conf
Learning to Induce Causal Structure.
ICLR
Nan Rosemary Ke, Silvia Chiappa, Jane X. Wang, Jörg Bornschein, Anirudh Goyal, Mélanie Rey, Theophane Weber, Matthew M. Botvinick, Michael Curtis Mozer, Danilo Jimenez Rezende
2023 J jnl
Neural Causal Structure Discovery from Interventions.
Trans. Mach. Learn. Res.
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Bernhard Schölkopf, Michael Curtis Mozer, Christopher Pal, Yoshua Bengio
2023 A* conf
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning.
ICLR
Dianbo Liu, Vedant Shah, Oussama Boussif, Cristian Meo, Anirudh Goyal, Tianmin Shu, Michael Curtis Mozer, Nicolas Heess, Yoshua Bengio
2022 A* conf
Coordination Among Neural Modules Through a Shared Global Workspace.
ICLR
Anirudh Goyal, Aniket Rajiv Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Curtis Mozer, Yoshua Bengio
2021 J jnl
Discrete-Valued Neural Communication.
CoRR
Dianbo Liu, Alex Lamb, Kenji Kawaguchi, Anirudh Goyal, Chen Sun, Michael Curtis Mozer, Yoshua Bengio
2021 A* conf
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments.
ICLR
Anirudh Goyal, Alex Lamb, Phanideep Gampa, Philippe Beaudoin, Charles Blundell, Sergey Levine, Yoshua Bengio, Michael Curtis Mozer
2021 A* conf
Wandering within a world: Online contextualized few-shot learning.
ICLR
Mengye Ren, Michael Louis Iuzzolino, Michael Curtis Mozer, Richard S. Zemel