arXiv AI July 7, 2026 By Junchi Liao, Jiawen Deng, Fuji Ren

VISTA: Auditing Semantic Divergence in Vision-Language Models

arXiv:2607. 02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideological symbols, some models produce unusually uniform responses that differ from what peer models say about the same input.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 1

Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?

arXiv:2606. 31407v1 Announce Type: cross Abstract: Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions.

By Ta Duc Huy, Trang Nguyen, Townim Chowdhury, Ankit Yadav, Minh-Son To, Zhibin Liao, Johan W. Verjans, Vu Minh Hieu Phan

llms rag multimodal benchmarks

Hugging Face Trending Papers

Jun 23

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards.

fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 14

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs

arXiv:2503. 08884v3 Announce Type: replace-cross Abstract: Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision.

By Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi

llms multimodal benchmarks safety

arXiv AI

Jun 2

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.

By Yiwei Chen, Yuguang Yao, Yihua Zhang, Bingquan Shen, Gaowen Liu, Sijia Liu

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

arXiv AI

Jul 7

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources

arXiv:2607. 03365v1 Announce Type: cross Abstract: Vision-language models (VLMs) increasingly read news and web content as images, where the publisher's identity is visually present.

By Chih-Ting Liao, Xin Cao

llms multimodal benchmarks safety

Related stories

Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources