Hannah Sheahan

I am a Research Engineer at Google DeepMind. I work on human-AI interaction in large language models.

Before switching to AI research, I researched human learning. I did my PhD at The University of Cambridge in the Computational & Biological Learning Lab, supervised by Daniel Wolpert, and a postdoc at The University of Oxford with Chris Summerfield.

My PhD and postdoc were in cognitive science. I was interested in motor learning, generalisation and the effects of context and task structure on learning in humans (and later, neural networks). I also hold a BEng (hons) in engineering from the University of Auckland in NZ.

Publications

Muhle-Karbe, P.*, Sheahan, H.*, Pezzulo, G., Spiers, H., Chien, S., Schuck, NW.*, Summerfield C.* (2023), Goal-seeking compresses neural codes for space in the human hippocampus and orbitofrontal cortex. Neuron

Bakker, M.*, Chadwick, M.*, Sheahan, H.*, Tessler, MH., Campbell-Gillingham L., Balaguer, J., McAleese, N., Glaese, A., Aslanides J., Botvinick M., Summerfield. C. (2022), Fine-tuning language models to find agreement among humans with diverse preferences. NeurIPS.

Bondi, L., Koster, R., Sheahan, H., Chadwick, M., Bachrach, Y., Cemgil, T., Paquet U., Dvijotham, K. (2022), Role of human-ai interaction in selective prediction. AAAI. 36(5)

Hawthorne, C., Jaegle, A., Cangea, C., Borgeaud, S., Nash, C., Malinowski, M., Dieleman, S., Vinyals, O., Botvinick, M., Simon, I., Sheahan, H., Zeghidour, N., Alayrac, JB., Carreira, J., & Engel. J. (2022), General-purpose, long-context autoregressive modeling with perceiver ar. ICML.

Sheahan, H.*, Luyckx, F.*, Nelli, S., Teupe, C., & Summerfield C. (2021), Neural state space alignment for magnitude generalization in humans and recurrent networks. Neuron. 109 (7), 1214-1226

Albert, S., Jang, J., Sheahan, HR., Teunissen, L., Vandevoorde, K., & Shadmehr, R. (2021), An implicit memory of errors limits human sensorimotor adaptation. Nature Human Behaviour.

Summerfield, C., Luyckx, F., & Sheahan, H. (2020), Structure learning and the posterior parietal cortex. Progress in Neurobiology. 184

Sadeghi, M., Sheahan, HR., Ingram, JN., & Wolpert, DM. (2019), The visual geometry of a tool modulates generalization during adaptation. Scientific Reports. 9, (2731)

Sheahan, HR., Ingram, JN., Zalalyte, GM. & Wolpert, DM. (2018), Imagery of movements immediately following performance allows learning of motor skills that interfere. Scientific Reports. 8 (14330)

Sheahan, HR., Franklin, DW. & Wolpert, DM. (2016), Motor Planning, Not Execution, Separates Motor Memories. Neuron. 92 (4), 773-779

For a more recent update, you can find my papers on my Google Scholar profile.

Contact

London, UK
Github
Twitter
Google Scholar
hsheahan@deepmind.com