This page provides a (laggy) list of selected publications. For an up-to-date, comprehensive list, see my Google Scholar or Semantic Scholar.

2023

Friedman, D.; Lampinen, A.; Dixon, L.; Chen, D.; Ghandeharioun, A. (2023), "Interpretability illusions in the generalization of simplified models", arXiv, [Preprint]

Sucholutsky, I.; Muttenthaler, L.; Weller, A.; Peng, A.; Bobu, A.; Kim, B.; Love, B. C.; Grant, E.; Achterberg, J.; Tenenbaum, J. B.; Collins, K. M.; Hermann, K. L.; Oktar, K.; Greff, K.; Hebart, M. N.; Jacoby, N.; Marjieh, R.; Geirhos, R.; Chen, S.; Kornblith, S.; Rane, S.; Konkle, T.; Thomas P O'Connell, Unterthiner, T.; Lampinen, A. K.*; Müller, K.-R.*; Toneva, M.*; Griffiths, T. L.* (2023), "Getting aligned on representational alignment", arXiv, (*equal advising/senior authors), [Preprint]

Lampinen, A. K.; Chan, S. C. Y.; Dasgupta, I; Nam, A. J.; Wang, J. X. (2023), "Passive learning of active causal strategies in agents and language models", Advances in Neural Information Processing Systems, [Preprint]

Muttenthaler, L.; Linhardt, L.; Dippel, J.; Vandermeulen, R.; Hermann, K; Lampinen, A. K.; Kornblith, S. (2023), "Improving neural network representations using human similarity judgements", Advances in Neural Information Processing Systems, [Preprint]

Carvalho, C.; Saraiva, A; Filos, A.; Lampinen, A. K.; Matthey, L.; Lewis, R. L.; Lee, H; Singh, S.; Rezende, D. J.; Zoran, D (2023), "Combining behaviors with the successor features keyboard", Advances in Neural Information Processing Systems, [Preprint]

Hudson, D. A; Zoran, D; Malinowski, M; Lampinen, A. K.; Jaegle, A; McClelland, J. L.; Matthey, L; Hill, F; Lerchner, A. (2023), "SODA: Bottleneck Diffusion Models for Representation Learning", arXiv, [Preprint]

Wei, J.; Hou, L; Lampinen, A. K.; Chen, X.; Huang, D; Tay, Y; Chen, X; Lu, Y; Zhou, D.; Ma, T; Le, Q. V. (2023), "Symbol tuning improves in-context learning in language models", arXiv preprint, [Preprint]

Singh, A. K.; Ding, D.; Saxe, A.; Hill, F. & Lampinen, A. K. (2023), "Know your audience: specializing grounded language models with the game of Dixit", EACL, [Preprint]

2022

Lampinen, A. K. (2022), "Can language models handle recursively nested grammatical structures? A case study on comparing models and humans" arXiv preprint, [Preprint]

Dasgupta, I.*; Lampinen, A. K.*; Chan, S. C. Y.; Creswell, A.; Kumaran, D.; McClelland, J. L. & Hill, F. (2022), "Language models show human-like content effects on reasoning" arXiv preprint, (*equal contribution), [Preprint]

Lampinen, A. K.; Dasgupta, I.; Chan, S. C. Y.; Matthewson, K.; Creswell, A.; McClelland, J. L.; Rabinowitz, N. C..; Wang, J. X. & Hill, F. (2022), "Can language models learn from explanations in context?" Findings of EMNLP, [Preprint]

Tam, A. C.; Rabinowitz, N. C..; Lampinen, A. K.; Roy, N. A.; Chan, S. C. Y.; Strouse, DJ; Wang, J. X.; Banino, A. & Hill, F. (2022), "Semantic Exploration from Language Abstractions and Pretrained Representations" Advances in Neural Information Processing Systems, [Preprint]

Chan, S. C. Y.; Santoro, A.; Lampinen, A. K.; Wang, J. X.; Singh, A. K.; Richemonde, P. H.; McClelland, J. L. & Hill, F. (2022), "Data Distributional Properties Drive Emergent In-Context Learning In Transformers" Advances in Neural Information Processing Systems, [Preprint]

Chan, S. C. Y.; Dasgupta, I.; Kim, J.; Kumaran, D; Lampinen, A. K.& Hill, F. (2022), "Transformers generalize differently from information stored in context vs in weights" Memory in Artificial and Real Intelligence Workshop, NeurIPS 2022, [Preprint]

Lampinen, A. K.; Roy, N. A.; Dasgupta, I.; Chan, S. C. Y.; Tam, A. C.; McClelland, J. L.; Yan, C.; Santoro, A.; Rabinowitz, N. C..; Wang, J. X. & Hill, F. (2022), "Tell me why! Explanations support learning relational and causal structure" International Conference on Machine Learning, [Preprint] [Poster]

Chan, S. C. Y.*; Lampinen, A. K.*; Richemond, Pierre H.* & Hill, F.* (2022), "Zipfian Environments for Reinforcement Learning" Conference on Lifelong Learning Agents, (*equal contribution), [Preprint]

2021

Lampinen, A. K.; Chan, S. C. Y.; Banino, Andrea & Hill, F. (2021), "Towards mental time travel: A hierarchical memory for reinforcement learning agents," Advances in Neural Information Processing Systems, [Preprint], [Poster]

Lampinen, A. K.; Chan, S. C. Y.; Santoro, A. & Hill, F. (2021), "Publishing fast and slow: A path toward generalizability in psychology and AI," Commentary in Behavioral and Brain Sciences, [Preprint]

Santoro, A.*; Lampinen, A. K.*; Matthewson, K.; Lillicrap, Timothy; Raposo, David (2021), "Symbolic Behaviour in Artificial Intelligence," arXiv preprint, (*equal Contribution), [Preprint]

2020

Lampinen, A. K. & McClelland, J. L. (2020), "Transforming task representations to allow deep learning models to perform novel tasks," Proceedings of the National Academy of Sciences, [Article], [Preprint]

Hermann, K. L.* & Lampinen, A. K.* (2020), "What shapes feature representations? Exploring datasets, architectures, and tasks," Advances in Neural Information Processing Systems, (*equal contribution), [PDF]

Lampinen, A. K. (2020), "A computational framework for learning and transforming task representations," Ph.D. Dissertation, [PDF], [Short Talk]

McClelland, J. L., McNaughton, B. L., & Lampinen, A. K. (2020), "Integration of new information in memory: new insights from a complementary learning systems perspective," Proceedings of the Royal Society B, [Preprint]

Racanière, S.*, Lampinen, A. K.*, Santoro, A., Reichert, D. P., Firoiu, V., & Lillicrap, T. P. (2020), "Automated curricula through setter-solver interactions," International Conference on Learning Representations (ICLR), (*equal contribution), [PDF]

Hill, F., Lampinen, A. K., Schneider, R., Clark, S., Botvinick, M., McClelland, J. L. & Santoro, A. (2020), "Emergent systematic generalization in a situated agent," International Conference on Learning Representations (ICLR), [PDF]

2019

Lampinen, A. K. & McClelland, J. L. (2019), "Zero-shot task adaptation by homoiconic meta-mapping," Learning Transferable Skills Workshop, NeurIPS, [PDF], [Poster]

Lampinen, A. K. & Ganguli, S. (2019), "An analytic theory of generalization dynamics and transfer learning in deep linear networks," International Conference on Learning Representations (ICLR), [PDF]

2018

Hawkins, R. X. D., Smith, E. N., Au, C., Arias, J. M., Catapano, R., Hermann, E., Keil, M., Lampinen, A., Raposo, S., Reynolds J., Salehi, S., Salloum, J., Tan, J., & Frank, M. C. (2018), "Improving the Replicability of Psychological Science Through Pedagogy," Advances in Methods and Practices in Psychological Science, [PsyArXiv Preprint]

Lampinen, A. K. & McClelland, J. L., (2018), "Different presentations of a mathematical concept can support learning in complementary ways," Journal of Educational Psychology, [Preprint PDF]

2017:

Hansen, S. S., Lampinen, A. K., Suri, G., & McClelland, J. L., (2017), "Building on prior knowledge without building it in," Behavioral & Brain Sciences, [Preprint PDF]

Lampinen, A. K. & McClelland, J. L. (2017), "One-shot and few-shot learning of word embeddings," arXiv preprint, [PDF]

Lampinen, A. K., So, D., Eck, D., & Bertsch, F. (2017), "Improving image generative models with human interactions," arXiv preprint, [PDF]

Lampinen, A. K., Hsu, S., & McClelland, J. L., (2017), "Analogies Emerge from Learning Dynamics in Neural Networks," Proceedings of the 39th Annual Meeting of the Cognitive Science Society, [PDF]