Research

Publications and presentations.

2024

  1. corners.png
    Don’t Cut Corners: Exact Conditions for Modularity in Biologically Inspired Representations
    Will Dorrell, Kyle Hsu, Luke Hollingsworth, and 6 more authors
    arXiv preprint arXiv:2410.06232, 2024
  2. geo.png
    Geometric Signatures of Compositionality Across a Language Model’s Lifetime
    Jin Hwa Lee, Thomas Jiralerspong, Lei Yu, and 2 more authors
    arXiv preprint arXiv:2410.01444, 2024
  3. shaping.png
    Why do animals need shaping? a theory of task composition and curriculum learning
    Jin Hwa Lee, Stefano Sarao Mannelli, and Andrew Saxe
    arXiv preprint arXiv:2402.18361, 2024

2023

  1. encodingSpace.png
    Learnable latent embeddings for joint behavioural and neural analysis
    Steffen Schneider*, Jin Hwa Lee*, and Mackenzie Weygandt Mathis
    Nature, 2023
    HTML

2022

  1. lstm.png
    Deep reinforcement learning for optimization at early design stages
    Lorenzo Servadei, Jin Hwa Lee, José A Arjona Medina, and 4 more authors
    IEEE Design & Test, 2022
    HTML

2021

  1. morph.png
    Out-of-distribution generalization of internal models is correlated with reward
    Khushdeep Singh Mann, Steffen Schneider, Alberto Chiappa, and 4 more authors
    In Self-Supervision for Reinforcement Learning Workshop-ICLR, 2021
    PDF