collaborators

11 papers

cs.CL2026

Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

Xuning He, Zinan Sheng, Yongding Tao +4

Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irre…

cs.LG2026

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning

Huanyu Liu, Jia Li, Yihong Dong +6

Reinforcement learning with verifiable reward (RLVR) has become a promising paradigm for post-training large language models (LLMs) to improve their reasoning capability. However,…

cs.AI2026

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

Yihong Dong, Xue Jiang, Yongding Tao +11

Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it struggles to break thro…

cs.SE2026

VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications

Hao Zhu, Jia Li, Cuiyun Gao +7

Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to…

cs.CL2026

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

Yongding Tao, Tian Wang, Yihong Dong +4

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in train…

cs.LG2026

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning

Huanyu Liu, Ge Li, Jia Li +3

How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g.,…