Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/9ICLR 2026Oral

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

Deyu Zou · Yongqiang Chen · Jianxiang Wang · Garry YANG · Mufei Li · Qing Da · James Cheng · Pan Li · Yu Gong

推理智能体与工具强化学习与后训练OpenReview

作者位次 #2/6ICLR 2026Poster

On the Thinking-Language Modeling Gap in Large Language Models

Chenxi Liu · Yongqiang Chen · Tongliang Liu · James Cheng · Bo Han · Kun Zhang

OpenReview

作者位次 #4/7ICLR 2026Poster· Deep Learning / Robustness

TRACEDET: HALLUCINATION DETECTION FROM THE DECODING TRACE OF DIFFUSION LARGE LANGUAGE MODELS

Shenxu Chang · Junchi Yu · Weixing Wang · Yongqiang Chen · Jialin Yu · Philip Torr · Jindong Gu

安全代码OpenReview

作者位次 #2/3ACL 2026Poster· Natural Language Processing

C i PO : Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

Junyi Li · Yongqiang Chen · Ningning Ding

摘要

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data. However, the emergence of Large Reasoning Models (LRMs), whi...

推理安全检索与知识OpenReview 项目页

Yongqiang Chen

获取完整研究档案

联系方式

2026 顶会论文

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

On the Thinking-Language Modeling Gap in Large Language Models

TRACEDET: HALLUCINATION DETECTION FROM THE DECODING TRACE OF DIFFUSION LARGE LANGUAGE MODELS

C i PO : Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

常见合作者