| 2025 | ICLR | From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks. | Clmentine Carla Juliette Domin, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M. Saxe |
| 2025 | ICLR | Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks. | Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe |
| 2025 | ICLR | A Theory of Initialisation's Impact on Specialisation. | Devon Jarvis, Sebastian Lee, Clmentine Carla Juliette Domin, Andrew M. Saxe, Stefano Sarao Mannelli |
| 2025 | ICML | Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks. | Lukas Braun, Erin Grant, Andrew M. Saxe |
| 2025 | ICML | Algorithm Development in Neural Networks: Insights from the Streaming Parity Task. | Loek van Rossem, Andrew M. Saxe |
| 2025 | ICML | Strategy Coopetition Explains the Emergence and Transience of In-Context Learning. | Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe |
| 2025 | ICML | Training Dynamics of In-Context Learning in Linear Attention. | Yedi Zhang, Aaditya K. Singh, Peter E. Latham, Andrew M. Saxe |
| 2024 | ICML | Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning. | Jin Hwa Lee, Stefano Sarao Mannelli, Andrew M. Saxe |
| 2024 | ICML | Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks. | Stefano Sarao Mannelli, Yaraslau Ivashinka, Andrew M. Saxe, Luca Saglietti |
| 2024 | ICML | When Representations Align: Universality in Representation Learning Dynamics. | Loek van Rossem, Andrew M. Saxe |
| 2024 | ICML | What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation. | Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe |
| 2024 | ICML | Understanding Unimodal Bias in Multimodal Deep Linear Networks. | Yedi Zhang, Peter E. Latham, Andrew M. Saxe |
| 2023 | EACL | Know your audience: specializing grounded language models with listener subtraction. | Aaditya K. Singh, David Ding, Andrew M. Saxe, Felix Hill, Andrew K. Lampinen |
| 2023 | ICLR | On The Specialization of Neural Modules. | Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe |
| 2022 | ICML | Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation. | Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe |
| 2022 | ICML | The Neural Race Reduction: Dynamics of Abstraction in Gated Networks. | Andrew M. Saxe, Shagun Sodhani, Sam Jay Lewallen |
| 2021 | CogSci | Inferring Actions, Intentions, and Causal Relations in a Deep Neural Network. | Keno Juechems, Andrew M. Saxe |
| 2021 | ICML | Continual Learning in the Teacher-Student Setup: Impact of Task Similarity. | Sebastian Lee, Sebastian Goldt, Andrew M. Saxe |
| 2018 | ICLR | Hierarchical Subtask Discovery with Non-Negative Matrix Factorization. | Adam Christopher Earle, Andrew M. Saxe, Benjamin Rosman |
| 2018 | ICLR | On the Information Bottleneck Theory of Deep Learning. | Andrew M. Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D. Tracey, David D. Cox |
| 2017 | ICML | Hierarchy Through Composition with Multitask LMDPs. | Andrew M. Saxe, Adam Christopher Earle, Benjamin Rosman |
| 2016 | CogSci | Tutorial Workshop on Contemporary Deep Neural Network Models. | James L. McClelland, Steven Stenberg Hansen, Andrew M. Saxe |
| 2014 | CogSci | Modeling Perceptual Learning with Deep Networks. | Rachel Lee, Andrew M. Saxe |
| 2014 | CogSci | Deep Learning and the Brain. | Andrew M. Saxe |
| 2014 | CogSci | Multitask model-free reinforcement learning. | Andrew M. Saxe |
| 2013 | CogSci | Learning hierarchical categories in deep neural networks. | Andrew M. Saxe, James L. McClelland, Surya Ganguli |
| 2011 | ICML | On Random Weights and Unsupervised Feature Learning. | Andrew M. Saxe, Pang Wei Koh, Zhenghao Chen, Maneesh Bhand, Bipin Suresh, Andrew Y. Ng |