activity
20242026
collaborators

6 papers

cs.CL2026

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Siyuan Huang, Pengyu Cheng, Haotian Liu +10

LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…

cs.LG2026

GDPO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

Haotian Liu, Yihao Liu, Jingwei Ni +11

As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorith…

cs.CL2026

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Fanmeng Wang, Haotian Liu, Guojiang Zhao +2

While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recen…

cs.LG2025

CGSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning

Haotian Liu, Shuo Wang, Hongteng Xu

Reinforcement Learning (RL) methods, exemplified by Group Relative Policy Optimization (GRPO) and its variants, play a central role in developing reasoning models. However, these m…

cs.CL2025

Learning an Effective Premise Retrieval Model for Efficient Mathematical Formalization

Yicheng Tao, Haotian Liu, Shanwen Wang +1

Formalized mathematics has recently garnered significant attention for its ability to assist mathematicians across various fields. Premise retrieval, as a common step in mathematic…

cs.LG2024

Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation

Shen Yuan, Haotian Liu, Hongteng Xu

While following different technical routes, both low-rank and orthogonal adaptation techniques can efficiently adapt large-scale pre-training models in specific tasks or domains ba…