publications
Google Scholar
2025
- PreprintBetween Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic BiasesPreprint, 2025
- How to visualize training dynamics in neural networksIn The Fourth Blogpost Track at ICLR, 2025
2024
- PreprintBigger is not always better: The importance of human-scale language modeling for psycholinguisticsPreprint, 2024
- CogSciComparing Abstraction in Humans and Large Language Models Using Multimodal Serial ReproductionProceedings of the Annual Meeting of the Cognitive Science Society, 2024
2023
- TMLR
2022
- ACL WorkshopUsing Natural Language to Guide Meta-Learning Agents towards Human-like Inductive BiasesIn ACL Workshop on Learning with Natural Language Supervision, 2022