collaborators

5 papers

cs.LG2026

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Zijian Zhang, Rizhen Hu, Athanasios Glentis +4

Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across tra…

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

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.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…