collaborators

6 papers

cs.LG2026

Grouter: Decoupling Routing from Representation for Accelerated MoE Training

Yuqi Xu, Rizhen Hu, Zihan Liu +2

Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneously train expert weights while searchi…

cs.LG2026

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs

Wuyue Zhang, Chongdong Huang, Chunbo You +3

Training large-scale Mixture-of-Experts (MoE) models is bottlenecked by activation memory and expert-parallel communication, yet FP4 training remains impractical on Hopper-class GP…

cs.LG2026

Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement

Shuchen Zhu, Rizhen Hu, Mingze Wang +4

Pre-training Large Language Models requires immense computational resources, making optimizer efficiency essential. The optimization landscape is highly anisotropic, with loss redu…

cs.LG2026

Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization

Rizhen Hu, Yuan Cao, Boao Kong +2

Sparse Mixture-of-Experts (MoE) models scale Transformers efficiently but suffer from expert overlap -- redundant representations across experts and routing ambiguity, resulting in…

cs.LG2025

FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error

Fengjuan Wang, Zhiyi Su, Xingzhu Hu +2

Training large Mixture-of-Experts (MoE) models remains computationally prohibitive due to their extreme compute and memory demands. Although low-precision training promises to acce…

cs.DC2025

MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization

Rizhen Hu, Yutong He, Ran Yan +3

As distributed optimization scales to meet the demands of Large Language Model (LLM) training, hardware failures become increasingly non-negligible. Existing fault-tolerant trainin…