arXiv AI August 6, 2026 By Shuo Liu, Huixiang Cai, Weiru Zhang, Xiaoyi Zeng

GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction

arXiv:2608. 04504v1 Announce Type: cross Abstract: Vision-language models excel in many multimodal tasks but remain prone to a subtle yet impactful failure mode: they tend to overestimate dominant visual-textual cues while underestimating sparse but decision-critical contextual variables.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 2

Visual Persuasion: What Influences Decisions of Vision-Language Models?

arXiv:2602. 15278v2 Announce Type: replace-cross Abstract: The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs).

By Manuel Cherep, Pranav M R, Pattie Maes, Nikhil Singh

llms agents diffusion multimodal safety

arXiv AI

Jun 19

The Hidden Evolution of Disguised Visual Context inside the VLM

arXiv:2606. 20077v1 Announce Type: cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals.

By Wish Suharitdamrong, Tony Alex, Muhammad Awais, Sara Atito

llms multimodal benchmarks

arXiv AI

Sep 7

When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs

The paper introduces MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images across 12 high-risk domains, each paired with a hidden user profile, to evaluate personalized safety in vision‑language models (VLMs). Eight leading VLMs were tested and found to almost always respond directly (86‑99%) without seeking missing context, scoring no higher than 2.6/5 on personalized safety. The authors identify a phenomenon called visual dominance, where visual information enters text representations early and suppresses textual risk signals, and propose PRISM, a lightweight input monitor that predicts when a query should be deferred, achieving 0.978 AUC and outperforming all tested models on the safety‑utility Pareto frontier.

By Edward Sun, Yuchen Wu, Zixian Ma, Eric Hanchen Jiang, Yijia Xiao, Xiaoyuan Yi, Ranjay Krishna, Wei Wang, Jindong Wang, Aylin Caliskan

llms multimodal benchmarks safety

arXiv AI

Sep 16

Same Answer, Different Representations: Hidden instability in VLMs

arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions r...

By Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena, Aryo Pradipta Gema, Wai-Chung Kwan, Fazl Barez, Maria Sofia Bucarelli, Fabrizio Silvestri, Pasquale Minervini

llms rag multimodal benchmarks safety

arXiv Computer Vision

2d ago

Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models

arXiv:2610.01625v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning enables distributed clients to adapt pretrained vision-language models without sharing raw data or updating t...

By Wentao Yue, Qingyu Mao, Tianyou Lai, Ahmed M. Abdelmoniem, Qilei Li

llms fine-tuning multimodal

arXiv Computation and Language

Aug 21

When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models

arXiv:2608. 19208v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are frequently exposed to auxiliary textual context, the impact of which on visually grounded tasks remains underexplored.

By Yinfeng Wang, Zhiyuan Yao, Zheren Fu, Lei Zhang, Zhendong Mao

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

Visual Persuasion: What Influences Decisions of Vision-Language Models?

The Hidden Evolution of Disguised Visual Context inside the VLM

When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs

Same Answer, Different Representations: Hidden instability in VLMs

Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models

When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models