Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization

Jihun Yun*, Sungjoon Yoon*, Beomhan Baek, Minhak Song, Jongha Jon Ryu, Kwang-Sung Jun

Theroetical Langauge ModelReinforcement Learning NeurIPS 2026

Beyond Clipping: Signed Logarithmic Smoothing for Policy Optimization

AMUSE: Anytime Muon with Stable Gradient Evaluation

Jueun Kim*, Baekrok Shin*, Jihun Yun, Beomhan Baek, Minhak Song, Chulhee Yun

TheoreticalLanguage Model NeurIPS 2026 Spotlight

AMUSE: Anytime Muon with Stable Gradient Evaluation

Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA

Changmin Kang*, Jihun Yun*, Baekrok Shin, Yeseul Cho, Chulhee Yun

Theoretical NeurIPS 2026

Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

Chungpa Lee, Jy-yong Sohn, Kangwook Lee

Theoretical ICML 2026

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA

Changmin Kang*, Jihun Yun*, Baekrok Shin, Yeseul Cho, Chulhee Yun

Theoretical ICML 2026 Workshop

Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA

AMUSE: Anytime Muon with Stable Gradient Evaluation

Jueun Kim*, Baekrok Shin*, Jihun Yun, Beomhan Baek, Minhak Song, Chulhee Yun

Theoretical ICML 2026 Workshop

AMUSE: Anytime Muon with Stable Gradient Evaluation

Convex Distance Operator Transport: Convex and Geometry-Preserving Formulation

Junhyoung Chung, Euijong Song, Won Hwa Kim, Gunwoong Park

Theoretical ICML 2026

Convex Distance Operator Transport: Convex and Geometry-Preserving Formulation

Zeroth-Order Optimization at the Edge of Stability

Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh

Language Model ICML 2026

Zeroth-Order Optimization at the Edge of Stability

Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch

Hyuck Lee, Taemin Park, Heeyoung Kim

Theoretical ICCV 2025

Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch

SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization

Geonwoo Ko, Sungyeob Yoo, Seri Ham, Seeyeon Kim, Minkyu Kim, Joo-Young Kim

Theoretical TMLR 2025

SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization