collaborators

8 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

q-bio.NC2026

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…

cs.LG2026

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…

cs.LG2025

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…