AI 大模型

视觉大模型 / VLM

视觉语言模型、视觉推理、视觉问答、图文理解和视觉 grounding。

2025-09-22 至 2025-09-22 共收录 5 篇信号源：cs.CV, cs.AI, cs.LG

1. 幻觉与鲁棒性 5 篇

2509.16163 2025-09-22 cs.CV cs.AI cs.CL 84%

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks

Het Patel, Muzammil Allie, Qian Zhang, Jia Chen, Evangelos E. Papalexakis

机构 * University of California, Riverside（加州大学河滨分校）

专题命中幻觉与鲁棒性：vision-language model(title)；vision language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments To be presented as a poster at the Workshop on Safe and Trustworthy Multimodal AI Systems (SafeMM-AI), 2025

2509.15361 2025-09-22 cs.CL cs.AI cs.MM 79%

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院）； MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室）； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室）

专题命中幻觉与鲁棒性：multimodal large language model(title,abstract)；分类 cs.AI

Comments Accepted by EMNLP 2025 Findings

2509.16088 2025-09-22 cs.LG 74%

Randomized Smoothing Meets Vision-Language Models

Emmanouil Seferis, Changshun Wu, Stefanos Kollias, Saddek Bensalem, Chih-Hong Cheng

机构 * National Technical University of Athens（希腊雅典国家技术大学）； Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）； CSX-AI（CSX-AI公司）； Carl von Ossietzky University of Oldenburg（奥尔登堡卡尔·冯·奥西特齐大学）； Chalmers University of Technology（查尔姆斯理工大学）

专题命中幻觉与鲁棒性：vision-language model(title)；分类 cs.LG

Comments EMNLP'25 full version, including appendix (proofs, additional experiments)

2509.15803 2025-09-22 cs.CV cs.AI 73%

CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models

Fangjian Shen, Zifeng Liang, Chao Wang, Wushao Wen

机构 * School of Computer Science（计算机科学学院）； Engineering, Sun Yat-sen University, Guangzhou, China（工程学院，中山大学，广州，中国）

专题命中幻觉与鲁棒性：vision-language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments 5 pages, 7 figures, submitted to ICASSP2026

2507.07620 2025-09-22 cs.CV 57%

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez, Paul Couairon, Clément Rambour, Raphaël Fournier-Sniehotta, Ismail Ben Ayed, Jose Dolz, Nicolas Thome

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Journal ref International Conference on Computer Vision, ICCV 2025