Research

研究概述

欢迎来到我的研究页面！在这里你可以了解我在多模态大语言模型、强化学习和智能体的最新工作和兴趣。

强化学习智能体视觉语言模型后训练

近期发表

强化学习

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe Wenjin Hou*, Shangpin Peng*, Weinong Wang, Zheng Ruan, et al. Arxiv 2026•paper•code

Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs Shangpin Peng, Weinong Wang, Zhuotao Tian, Senqiao Yang, et al., Min Zhang ICLR 2026•paper•code

视觉语言模型

HunyuanOCR Technical Report Hunyuan Vision Team, Pengyuan Lyu, Xingyu Wan, Gengluo Li, Shangpin Peng, et al., Chengquan Zhang Core Contributor of Technical Report•paper•code

Mitigating Object Hallucinations via Sentence-Level Early Intervention Shangpin Peng, Senqiao Yang, Li Jiang, Zhuotao Tian ICCV 2025•paper•code

Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters Gengluo Li, Shangpin Peng, Xingyu Wan, Chengquan Zhang, et al., Han Hu Arxiv 2026•paper•code

智能体

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Zhengyang Tang, et al., Shangpin Peng, et al., Chengquan Zhang, Han Hu Arxiv 2026•paper•code

相关链接

• Google 学术
• GitHub 主页
• 个人主页

欢迎浏览以上项目或联系我获取更多信息！