Seok Hyeong Lee — accepted AI-conference papers

2026

Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement

Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee, Chris Mingard, Niclas Alexander Göring, Ouns El Harzli +3

ICLR 2026poster

Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limiting analysis of their relationship. We propose a computationally efficient, performance-independent metric of richness…

Cited by 0 Source ↗Scholar ↗

2025

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)

Yoonsoo Nam, Seok Hyeong Lee, Clémentine Carla Juliette Dominé, Yeachan Park, Charles London, Wonyl Choi +2

ICML 2025poster

In physics, complex systems are often simplified into minimal, solvable models that retain only the core principles. In machine learning, layerwise linear models (e.g., linear neural networks) act as simplified representations of neural network dynamics. These models follow the dynamical feedback pr…

Cited by 11 Source ↗PDF ↗Scholar ↗

2024

An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem

Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee, Chris Mingard, Ard A. Louis

NeurIPS 2024poster

Deep learning models can exhibit what appears to be a sudden ability to solve a new problem as training time, training data, or model size increases, a phenomenon known as emergence. In this paper, we present a framework where each new ability (a skill) is represented as a basis function. We solve…

Cited by 0 Source ↗PDF ↗Scholar ↗