arXiv Computer Vision

Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models

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.

arXiv Computer Vision

3d ago

In-Context Learning Can Help Vision-Language Models Overcome Training Priors

The paper shows that controlled visual in‑context learning can help vision‑language models (VLMs) overcome errors caused by training priors. By providing demonstrations, the models focus more on visual evidence, yielding significant accuracy gains on counterfactual examples while leaving prior‑aligned performance largely unchanged. This effect is observed across five VLM families and five vision‑centric tasks, indicating that many VLMs possess latent visual grounding abilities that standard tests may miss.

By Kun Wang, Xindi Wu, Sanghyuk Chun, Olga Russakovsky, Esin Tureci

llms multimodal

arXiv AI

Oct 1

VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes

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

llms multimodal benchmarks

arXiv Machine Learning

Aug 6

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

arXiv:2608. 05000v1 Announce Type: cross Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining.

By Junlin Han, Shengbang Tong, David Fan, Minghao Chen, Philip Torr, Filippos Kokkinos, Mike Lewis

nlp multimodal safety

arXiv AI

Jun 19

ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models

arXiv:2606. 19965v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts.

By Yihao Wang, Zijian He, Jie Ren, Keze Wang

llms multimodal benchmarks

arXiv AI

Oct 2

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...

By Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc, Nicolas Thome, Spyros Gidaris

llms efficiency multimodal benchmarks

arXiv AI

Aug 6

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.

By Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott

llms multimodal safety

arXiv AI

Jun 2

Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models

arXiv:2606. 00275v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have demonstrated impressive performance on multimodal tasks through scaled architectures and extensive training.

By Zijie Zhou, Dandan Zhu, Hangxiangpan Wang, Heng Zhang, Huishen Jiao, Yi Zhao

llms 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

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

arXiv Computation and Language

Oct 5

The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems?

The paper introduces Percept-V, a dataset of 6,000 program-generated images across 30 domains designed to test simple visual perception skills from the TVPS-4 framework. Experiments show that state‑of‑the‑art multimodal large language models perform poorly compared to humans, especially as image complexity increases, and that fine‑tuning yields only limited generalization to related datasets. The study highlights specific perception skills that remain challenging for current models.

By Samrajnee Ghosh, Ashish Goswami, Naman Agarwal, Hemanshu Garg, Chinmay Mittal, Mausam, Parag Singla

llms fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 22

Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

The paper introduces a free, label‑free visual evidence signal that improves fine‑grained vision‑language reasoning. By selecting image crops that maximize the model’s answer distribution peak, the method locates answer‑bearing regions without training or annotations, boosting accuracy from 70 % to 85 %. The evidence gap also complements model confidence, enabling better correctness prediction and error flagging.

By Santi Ram Tiwari, Nihal Naik, Devbrat Pandey, Nishant Sinha

llms fine-tuning efficiency multimodal

arXiv AI

Sep 16

Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models

arXiv:2609.16795v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved...

By Zhenbin Wang, Lei Zhang, Lituan Wang, Wei Huang, Yan Wang, Zhenwei Zhang

llms multimodal benchmarks

Related stories