← Authors

Murray Shanahan

13 papers · 2018–2025 · 4 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (22) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (6) 🧬 Topic Evolution πŸ’Ž Century Club (13) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (6)

Conferences

ICML (6) ICLR (4) NIPS (2) IJCAI (1)

Top co-authors

Antonia Creswell (3) Christos Kaplanis (3) Irina Higgins (2) Matthew Botvinick (2) Claudia Clopath (2) Marta Garnelo (2) Alexander Lerchner (1) S. M. Ali Eslami (1) Vikram Voleti (1) Francesco Belardinelli (1)

Keywords

continual learning (2) deep reinforcement learning (2) reinforcement learning (2) catastrophic forgetting (2) multimodal learning (1) few-shot learning (1) representation learning (1) template learning (1) attention mechanism (1) in-context learning (1) sequence prediction (1) visual reasoning (1) relational reasoning (1) gaussian process (1) schema learning (1) continuous control (1) function approximation (1) associative memory (1) scene understanding (1) unsupervised learning (1)

Papers

Learning dynamics in linear recurrent neural networks ICML 2025
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning ICLR 2023
Schema-learning and rebinding as mechanisms of in-context learning and emergence NIPS 2023
Abstraction for Deep Reinforcement Learning IJCAI 2022
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications ICLR 2022
Unsupervised Object-Based Transition Models For 3D Partially Observable Environments NIPS 2021
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules ICML 2020
An Explicitly Relational Neural Network Architecture ICML 2020
Policy Consolidation for Continual Reinforcement Learning ICML 2019
Deep reinforcement learning with relational inductive biases ICLR 2019
Conditional Neural Processes ICML 2018
SCAN: Learning Hierarchical Compositional Visual Concepts ICLR 2018
Continual Reinforcement Learning with Complex Synapses ICML 2018