8 papers
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung
Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success across many domains, further s…
Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
Chi-Ning Chou, Oscar Uzdelewicz, Neng-Chun Chiu +2
Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in gr…
Emergent Manifold Separability during Reasoning in Large Language Models
Chanwoo Chun, Alexandre Polo, SueYeon Chung
Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representation geometry remain poorly unders…
Linear Readout of Neural Manifolds with Continuous Variables
Will Slatton, Chi-Ning Chou, SueYeon Chung
Brains and artificial neural networks compute with continuous variables such as object position or stimulus orientation. However, the complex variability in neural responses makes…
Diagnosing Generalization Failures from Representational Geometry Markers
Chi-Ning Chou, Artem Kirsanov, Yao-Yuan Yang +1
Generalization, the ability to perform well beyond the training context, is a hallmark of biological and artificial intelligence, yet anticipating unseen failures remains a central…
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
Chi-Ning Chou, Hang Le, Yichen Wang +1
Integrating task-relevant information into neural representations is a fundamental ability of both biological and artificial intelligence systems. Recent theories have categorized…