Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/11ICML 2026Poster· Deep Learning / Large Language Models

Do LLMs “Feel”? Emotion Circuits Discovery and Control

Chenxi Wang · Yixuan Zhang · Ruiji Yu · Yufei Zheng · Lang Gao · Zirui Song · Zixiang Xu · Gus xia · Huishuai Zhang · Dongyan Zhao · Xiuying Chen

可解释性OpenReview

作者位次 #7/11ACL 2026Poster· Natural Language Processing

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Zirui Song · Qian Jiang · Mingxuan Cui · Mingzhe Li · Lang Gao · Zeyu Zhang · Zixiang Xu · Yanbo Wang · Guangxian Ouyang · Zhenhao Chen · Xiuying Chen

摘要

The rise of Large Audio-Language Models (LAMs) brings both potential and risks, as their audio outputs may contain harmful or unethical content. However, current research lacks a systematic, quantitative evaluation of LAM safety, especially against jailbreak attacks, which are challenging due to...

安全多模态评测与基准OpenReview 项目页

作者位次 #6/13AAAI 2026Poster· Artificial Intelligence

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models

Zirui Song · Guangxian Ouyang · Mingzhe Li · Yuheng Ji · Chenxi Wang · Zixiang Xu · Zeyu Zhang · Xiaoqing Zhang · Qian Jiang · Fengxian Ji · Zhenhao Chen · Zhongzhi Li · Xiuying Chen

推理多模态强化学习与后训练OpenReview

Zixiang Xu

获取完整研究档案

联系方式

2026 顶会论文

Do LLMs “Feel”? Emotion Circuits Discovery and Control

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models

常见合作者