activity
20242026
collaborators

5 papers

cs.LG2026

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning

Junsoo Oh, Wei Huang, Taiji Suzuki

Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous th…

cs.LG2025

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning

Junsoo Oh, Jerry Song, Chulhee Yun

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to exp…

cs.CL2025

Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons

Seonil Son, Ju-Min Oh, Heegon Jin +3

As Large Language Models (LLMs) expand across domains, LLM judges have become essential for systems evaluation. Current benchmarks typically compare system outputs against baseline…

cs.LG2024

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

Baekrok Shin, Junsoo Oh, Hanseul Cho +1

Warm-starting neural network training by initializing networks with previously learned weights is appealing, as practical neural networks are often deployed under a continuous infl…

cs.LG2024

Provable Benefit of Cutout and CutMix for Feature Learning

Junsoo Oh, Chulhee Yun

Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive the…