4 papers
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…
Estimating Dimensionality of Neural Representations from Finite Samples
Chanwoo Chun, Abdulkadir Canatar, SueYeon Chung +1
The global dimensionality of a neural representation manifold provides rich insight into the computational process underlying both artificial and biological neural networks. Howeve…
Estimating Neural Representation Alignment from Sparsely Sampled Inputs and Features
Chanwoo Chun, Abdulkadir Canatar, SueYeon Chung +1
In both artificial and biological systems, the centered kernel alignment (CKA) has become a widely used tool for quantifying neural representation similarity. While current CKA est…
Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices
Chanwoo Chun, SueYeon Chung, Daniel D. Lee
Analyzing the structure of sampled features from an input data distribution is challenging when constrained by limited measurements in both the number of inputs and features. Tradi…