collaborators

19 papers

cs.LG2026

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Zhepei Wei, Xinyu Zhu, Wei-Lin Chen +3

Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving reasoning in large language models (LLMs), yet the underlying geometry of the res…

cs.CL2026

Process Rewards with Learned Reliability

Jinyuan Li, Langlin Huang, Chengsong Huang +5

Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore…

cs.AI2026

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Langlin Huang, Chengsong Huang, Jinyuan Li +3

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Mode…

cs.CV2026

RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models

Jianwei Zhang, Chaoning Zhang, Sihan Cao +7

Large Vision-Language Models (LVLMs) suffer from prohibitive inference costs due to the massive number of visual tokens processed by the language decoder. Existing pruning methods…

cs.LG2026

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, e…

cs.CL2026

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Tong Zheng, Chengsong Huang, Runpeng Dai +9

Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-traj…