collaborators

11 papers

cs.LG2026

ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information

Zehua Liu, Yuxuan Yao, Xiaojin Fu +2

Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce di…

cs.LG2026

RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning

Zehua Liu, Shuqi Liu, Tao Zhong +1

While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samp…

cs.LG2026

Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations

Yuxuan Yao, Haonan Sheng, Qingsong Lv +11

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. Howev…

cs.CL2025

Activation-Guided Consensus Merging for Large Language Models

Yuxuan Yao, Shuqi Liu, Zehua Liu +6

Recent research has increasingly focused on reconciling the reasoning capabilities of System 2 with the efficiency of System 1. While existing training-based and prompt-based appro…

cs.LG2025

REG: A Regularization Optimizer for Robust Training Dynamics

Zehua Liu, Han Wu, Xiaojin Fu +4

Optimizers are crucial for the efficient training of Large Language Models (LLMs). While AdamW is the de facto standard, recent structure-aware optimizers like Muon have emerged, w…

cs.AI2025

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving

Teng Wang, Wing-Yin Yu, Zhenqi He +8

LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in ope…