collaborators

5 papers

cs.AI2026

Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation

Liming Liu, Mingze Wang, Tuo Zhao

As large language models serve ever more requests, cumulative inference cost is growing relative to the one-time cost of training. In typical serving, prompt prefill runs in parall…

cs.LG2026

BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models

Liming Liu, Binxuan Huang, Zixuan Zhang +3

Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation…

cs.LG2025

COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs

Liming Liu, Zhenghao Xu, Zixuan Zhang +5

Large Language Models (LLMs) have demonstrated remarkable success across various domains, yet their optimization remains a significant challenge due to the complex and high-dimensi…

cs.LG2025

NorMuon: Making Muon more efficient and scalable

Zichong Li, Liming Liu, Chen Liang +2

The choice of optimizer significantly impacts the training efficiency and computational costs of large language models (LLMs). Recently, the Muon optimizer has demonstrated promisi…

cs.LG2025

A Minimalist Example of Edge-of-Stability and Progressive Sharpening

Liming Liu, Zixuan Zhang, Simon Du +1

Recent advances in deep learning optimization have unveiled two intriguing phenomena under large learning rates: Edge of Stability (EoS) and Progressive Sharpening (PS), challengin…