Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/8ICLR 2026Poster

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation

Xingyu Zhu · Kesen Zhao · Liang Yi · Shuo Wang · Zhicai Wang · Beier Zhu · Hanwang Zhang · Xiangnan He

多模态安全强化学习与后训练OpenReview

作者位次 #5/7ACL 2026Poster· Natural Language Processing

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

Xingyu Zhu · Junfeng Fang · Shuo Wang · Beier Zhu · Zhicai Wang · Yonghui Yang · Xiangnan He

摘要

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine tuning on annotated data devoid of hallucinations offers the most direct solution, while its high computational cost motivates recent repres...

可解释性安全多模态OpenReview 项目页

作者位次 #2/6AAAI 2026Poster· Artificial Intelligence

Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input

Chenxu Li · Zhicai Wang · Yuan Sheng · Xingyu Zhu · Yanbin Hao · Xiang Wang

多模态评测与基准OpenReview

作者位次 #2/5AAAI 2026Poster· Artificial Intelligence

Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention

Zhe Xu · Zhicai Wang · Junkang Wu · Jinda Lu · Xiang Wang

安全OpenReview

Zhicai Wang

获取完整研究档案

联系方式

2026 顶会论文

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input

Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention

常见合作者