works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

AMUSE: Anytime Muon with Stable Gradient Evaluation

Jueun Kim, Baekrok Shin, Jihun Yun +3

The paper introduces AMUSE, an optimization method that combines Muon's orthogonal momentum updates with Schedule-Free iterate averaging to achieve fast, stable training without le…

cs.CL2026

Pruning and Distilling Mixture-of-Experts into Dense Language Models

Junhyuck Kim, Jihun Yun, Haechan Kim +3

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for…

cs.LG2026

Beyond RLHF: A Unified Theoretical Framework of Alignment

Jihun Yun, Juno Kim, Jongho Park +4

Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However,…

cs.AI2026

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

Seanie Lee, Sangwoo Park, Yumin Choi +6

Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However…

cs.CL2026

Raon-Speech Technical Report

Beomsoo Kim, Changho Choi, Dohyun Kim +23

We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and generation, and Raon-SpeechChat,…

cs.LG2026

Uniform Spectral Growth and Convergence of Muon in LoRA-Style Matrix Factorization

Changmin Kang, Jihun Yun, Baekrok Shin +2

Spectral gradient descent (SpecGD) orthogonalizes the matrix parameter updates and has inspired practical optimizers such as Muon. They often perform well in large language model (…