The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung
The paper demonstrates that vision‑language models (VLMs) possess a small set of attention heads, called Visual Retrieval Heads (VRHs), that are causally responsible for linking text prompts to specific image regions. By adapting head‑scoring techniques from language models, the authors identify VRHs as the heads whose attention from output prediction tokens, summed over the ground‑truth referent region, most reliably indicates causal grounding. Experiments across eleven VLMs and five referring‑expression benchmarks show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect, and that VRHs generalize across diverse visual tasks and transfer across models sharing an LLM backbone.
The paper investigates how the modality gap— the separation between image and text representations in contrastive vision‑language models—affects different downstream tasks. By showing that a single dominant direction accounts for most of the image‑text mean separation, the authors explain why reducing or removing this gap can improve zero‑shot classification, degrade retrieval, or restore performance depending on the task. The study provides a geometric framework that clarifies when and why gap interventions should be applied in vision‑language systems.
By Aditya Sharma, Divya Saxena
arXiv:2609.15640v1 Announce Type: cross
Abstract: Long-text image--text congruence scoring is increasingly important for vision-language systems that must evaluate whether detailed textual descriptio...
By Alessandro Gambetti, Qiwei Han
arXiv:2605.26380v2 Announce Type: replace-cross
Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. How...
By Jingru Chen, Yiming Liu, Mingtao Chen, Sijie Chen, Richeng Xuan, Liang Yang, Zhichao Hu, Fanyang Lu
arXiv:2607. 18237v1 Announce Type: cross Abstract: Human visual similarity judgments are context-dependent.
By Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu, Eli Shechtman, Alexei A. Efros, Richard Zhang
Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce visually compelling outputs from simile prompts, yet even frontier models frequently misinterpret the metaphorical vehicle and confuse it with the object.
arXiv:2609.06245v1 Announce Type: cross
Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often str...
By Yixin Wan, Tianle Zheng, Kai-Wei Chang
arXiv:2606. 13870v1 Announce Type: cross Abstract: Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided.
By Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao, Raz Lapid, Amit LeVi, Allen G. Roush, Ravid Shwartz-Ziv, Hod Lipson
The paper investigates why multimodal large language models (MLLMs) struggle with vision‑centric tasks when visual evidence conflicts with pretrained language knowledge. Using image reconstruction and a new WhatIfVis benchmark, the authors show that MLLMs preserve coarse‑grained visual attributes but fail to consistently use them, and that supervised fine‑tuning and activation patching can improve controllability of visual context sensitivity. The study demonstrates that the main bottleneck lies in the models’ inability to reliably regulate their reliance on visual evidence rather than in visual perception itself.
By Jiaang Li, Chengzu Li, Zhaochong An, Yifei Yuan, Xi Liu, Serge Belongie, V\'esteinn Sn{\ae}bjarnarson
The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
By Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
arXiv:2609.00293v1 Announce Type: new
Abstract: We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in contex...
By Athulith Paraselli, Etha Tianze Hua, Ellie Pavlick