collaborators

6 papers

cs.AI2026

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

Tianyuan Shi, Canbin Huang, Bei Li +4

Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather th…

cs.LG2026

When Model Merging Breaks Routing: Training-Free Calibration for MoE

Canbin Huang, Tianyuan Shi, Xiaojun Quan +3

Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing merging techniques, largely based o…

cs.CL2025

ProFuser: Progressive Fusion of Large Language Models

Tianyuan Shi, Fanqi Wan, Canbin Huang +6

While fusing the capacities and advantages of various large language models offers a pathway to construct more powerful and versatile models, a fundamental challenge is to properly…

cs.CL2025

Lookahead Routing for Large Language Models

Canbin Huang, Tianyuan Shi, Yuhua Zhu +2

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of het…

cs.LG2025

Mutual-Taught for Co-adapting Policy and Reward Models

Tianyuan Shi, Canbin Huang, Fanqi Wan +5

During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model…

cs.CL2025

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Ziyi Yang, Fanqi Wan, Longguang Zhong +3

We introduce FuseChat-3.0, a suite of large language models (LLMs) developed by integrating the strengths of heterogeneous source LLMs into more compact target LLMs. Our source mod…