7 papers
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…
AMUSE: Anytime Muon with Stable Gradient Evaluation
Jueun Kim, Baekrok Shin, Jihun Yun +3
Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimization removes explicit sched…
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,…
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 (…
Coverage Improvement and Fast Convergence of On-policy Preference Learning
Juno Kim, Jihun Yun, Jason D. Lee +1
Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts…
ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
Seanie Lee, Sangwoo Park, Yumin Choi +6
Large reasoning models achieve strong performance through reinforcement learning but can suffer safety degradation. External teacher distillation can restore safety yet may comprom…
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,…