On the Faithfulness of Post-Hoc Concept Bottleneck Models
事后概念瓶颈模型的忠实性研究
Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler
机构
*
Institute of Data Science, German Aerospace Center(数据科学研究所,德国航空航天中心)
;
Computer Vision Group Jena, Friedrich Schiller University Jena(贾恩计算机视觉小组,弗里德里希·席勒大学贾恩)
;
GEOMAR Helmholtz Centre for Ocean Research Kiel(基尔海洋研究赫尔姆霍茨中心)
Comments6 pages, 2 figures, 4 tables. Accepted at the 2026 IEEE International Conference on Artificial Intelligence (CAI), 8-10 May 2026, Granada, Spain. Code: https://github.com/darianfgUgr/CoNa
Journal ref2026 IEEE International Conference on Artificial Intelligence (CAI), Granada, Spain, 2026, pp. 1405-1410
Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning
贝叶斯深度学习中的校准无采样不确定性估计
Tobias Jan Wieczorek, Leon de Andrade, Thomas Möllenhoff, Marcus Rohrbach
机构
*
TU Darmstadt & hessian.AI, Darmstadt, Germany(达姆施塔特工业大学 & hessian.AI,德国达姆施塔特)
;
RIKEN Center for Advanced Intelligence Project, Tokyo, Japan(日本理化学研究所革新智能研究中心,日本东京)
机构
*
School of Information Science and Engineering, Yunnan University(云南大学信息科学与工程学院)
;
School of Software, Yunnan University(云南大学软件学院)
;
National University of Singapore(新加坡国立大学)
;
School of Engineering, Yunnan University(云南大学工程学院)
专题命中
幻觉与鲁棒性
:multimodal large language model(abstract);分类 cs.AI、cs.LG
机构
*
U2IS, ENSTA, Institut Polytechnique de Paris(巴黎综合理工学院ENSTA学院U2IS实验室)
;
ISIR, Université Sorbonne, Pierre et Marie Curie(索邦大学皮埃尔和玛丽·居里分校ISIR实验室)
;
AMIAD, Pôle Recherche(AMIAD研究部)
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
通过代理特定偏差校正提高视觉-语言预训练模型上的对抗迁移性
Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu
机构
*
School of Cyber Science and Engineering, Southeast University(东南大学网络空间安全学院)
;
Purple Mountain Laboratories(紫金山实验室)
;
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院)
专题命中
幻觉与鲁棒性
:multimodal large language model(abstract);分类 cs.CV、cs.AI
机构
*
The Grainger College of Engineering, Nuclear, Plasma & Radiological Engineering, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校格雷格学院工程学院、核等工程学院)
;
Department of Nuclear Engineering, Hanyang University(汉阳大学核工程系)
;
University of Texas - El Paso(德克萨斯大学埃尔帕索分校)
;
National Center for Supercomputing Applications(国家超级计算应用中心)
;
Department of Applied Mechanics, Indian Institute of Technology Delhi(印度德里理工学院应用力学系)
;
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi(印度德里理工学院亚里人工智能学院)
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
什么使LVLMs更少产生幻觉?揭示影响幻觉鲁棒性的架构因素
Yusheng He, Jizhe Zhou, Xia Du, Zheng Lin, Jun Luo, Jiancheng Lv
机构
*
School of Computer Science, Engineering Research Center of Machine Learning and Industry Intelligence, Sichuan University(计算机科学学院,机器学习与产业智能工程研究中心,四川大学)
;
School of Computer and Information Engineering, Xiamen University of Technology(计算机与信息工程学院,厦门理工大学)
;
Department of Electrical and Computer Engineering, University of Hong Kong(电气与计算机工程系,香港大学)
;
College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
跨模态注意力校准用于LVLM幻觉缓解
Jiaming Li, Jiacheng Zhang, Zequn Jie, Lin Ma, Guanbin Li
机构
*
Sun Yat-sen University(中山大学)
;
The University of Hong Kong(香港大学)
;
Meituan(美团)
;
Inspur Database Technology(Inspur数据库技术)
;
Guilin University of Electronic Technology(桂林电子科技大学)
;
Shenzhen Loop Area Institute(深圳河套学院)
;
Guangdong Key Laboratory of Big Data Analysis and Processing(广东大数据分析与处理重点实验室)
机构
*
School of Intelligence Science and Technology(智能科学与技术学院)
;
State Key Laboratory for Novel Software Technology(新型软件技术国家重点实验室)
;
Nanjing University(南京大学)
专题命中
幻觉与鲁棒性
:multimodal large language model(abstract);分类 cs.AI、cs.LG
Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes
看见 vs. 相信:评估开源多模态大模型在反直觉场景中的语言偏见
Chen Ling, Tongwei Zhang, Hanqian Li, Nai Ding
机构
*
Zhejiang University(浙江大学)
;
Beijing University of Posts and Telecommunications(北京邮电大学)
;
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
专题命中
幻觉与鲁棒性
:multimodal large language model(abstract);分类 cs.CV、cs.AI
CommentsThis paper has been accepted by the International Journal of Computer Vision (IJCV), 2026. The first two authors contributed equally to this work. 28 pages
机构
*
Institute of Big Data Science and Industry(大数据科学与产业研究院)
;
Key Laboratory of Evolutionary Science Intelligence of Shanxi Province(山西省进化智能科学重点实验室)
;
School of Artificial Intelligence, Shanxi University(山西大学人工智能学院)
专题命中
幻觉与鲁棒性
:multimodal large language model(abstract);分类 cs.CV、cs.LG