Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/9ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

Yilian Liu · Yang Liu · Guoshun Nan · Jiuyang Lyu · Zhican Chen · Tao Guan · Shuyuan Luo · Zhongyi Zhai · Yang Liu

安全社会与人本多模态OpenReview

作者位次 #3/3ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Offline Reinforcement Learning with Adaptive Feature Fusion

Tieru Wang · Kunbao Wu · Guoshun Nan

强化学习与后训练OpenReview

作者位次 #3/3ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Trajectory Generation with Conservative Value Guidance for Offline Reinforcement Learning

Tieru Wang · Kunbao Wu · Guoshun Nan

强化学习与后训练OpenReview

作者位次 #4/9ACL 2026Findings· Findings of ACL

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning

Haolang Lu · Minghui Pan · Ripeng LI · Guoshun Nan · Jialin Zhuang · Zijie Zhao · Zhongxiang Sun · Kun Wang · Yang Liu

摘要

Long chain-of-thought (CoT) reasoning improves the performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps. We suggest that hallucination in long CoT reasoning is better understood as an evolving latent state rather than a...

推理安全可解释性OpenReview 项目页

作者位次 #2/9KDD 2026Oral· Knowledge Discovery & Data Mining

SelPE: Progressive Selection for Private Structured Text Synthesis

Xuancheng Zhu · Guoshun Nan · Han Zhang · Ben Niu · Yang Yue · Zixu Wang · Yilian Liu · Min Lei · Xiaofeng Tao

检索与知识OpenReview

Guoshun Nan

获取完整研究档案

联系方式