Large Vision-Language Models

Also known as LVLM

Large vision-language models combine a visual encoder with a language model, aligning them through feature projection, multimodal pretraining, and instruction tuning. Researchers improve their abilities with reinforcement learning, latent visual reasoning, and tools for grounding answers in image regions, especially in visual question answering, OCR, charts, and long-video understanding. To cut inference costs, methods prune visual tokens, select frames, or inspect high-resolution images selectively; other work targets hallucinations, bias, privacy, and adversarial vulnerabilities through data curation, attention interventions, and model editing. Performance is improving across many benchmarks, but reliable fine-grained spatial and temporal reasoning remains difficult, and fluent answers do not always reflect correct use of visual evidence.

Latest papers

404 papers44 papers in the last four weeks, up 63% on the four weeks before. 0.3% of all new papers.

Sep 29, 2025

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations: system prompting approaches could easily be overridden by user instructions, while applying activation-based steering vectors requires invasive runtime access to model internals, precluding deployment with API-based services and closed-source models. Finding steering methods that transfer across multiple VLMs is still an open area of research. To this end, we introduce universal visual input based steering for output redirection (VISOR++), to achieve behavioral control through optimized visual inputs alone. We demonstrate that a single VISOR++ image can be generated for an ensemble of VLMs to emulate each of their steering vectors. By crafting universal visual inputs that induce target activation patterns, VISOR++ eliminates the need for runtime model access while remaining deployment-agnostic. This means that when an underlying model supports multimodal capability, model behaviors can be steered by inserting an image input replacing runtime steering vector based interventions. We first demonstrate the effectiveness of the VISOR++ images on open-access models such as LLaVA-1.5-7B and IDEFICS2-8B along three alignment directions: refusal, sycophancy and survival instinct. Both the model-specific steering images and the jointly optimized images achieve performance parity closely following that of steering vectors for both positive and negative steering tasks. We also show the promise of VISOR++ images in achieving directional behavioral shifts for unseen models including both open-access and closed-access ones. Furthermore, VISOR++ images are able to preserve 99.9% performance on 14,000 unrelated MMLU evaluation tasks.

Ravikumar Balakrishnan, Mansi Phute

HiddenLayer, USA · Georgia Institute of Technology, USA

Language Model Steering Large Vision-Language Models

Ask PDF

Sep 29, 2025

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to generate a predefined target pattern, which is either inserted into or replaces the original content. We find that these fixed-pattern attacks are relatively easy to detect, because the attacked LVLM tends to memorize such frequent patterns in the training dataset, thereby exhibiting overconfidence on these targets given poisoned inputs. To address these limitations, we introduce TokenSwap, a more evasive and stealthy backdoor attack that focuses on the compositional understanding capabilities of LVLMs. Instead of enforcing a fixed targeted content, TokenSwap subtly disrupts the understanding of object relationships in text. Specifically, it causes the backdoored model to generate outputs that mention the correct objects in the image but misrepresent their relationships (i.e., bags-of-words behavior). During training, TokenSwap injects a visual trigger into selected samples and simultaneously swaps the grammatical roles of key tokens in the corresponding textual answers. However, the poisoned samples exhibit only subtle differences from the original ones, making it challenging for the model to learn the backdoor behavior. To address this, TokenSwap employs an adaptive token-weighted loss that explicitly emphasizes the learning of swapped tokens, such that the visual triggers and bags-of-words behavior are associated. Extensive experiments demonstrate that TokenSwap achieves high attack success rates while maintaining superior evasiveness and stealthiness across multiple benchmarks and various LVLM architectures.

Zhifang Zhang, Qiqi Tao, Jiaqi Lv +3

School of Computer Science and Engineering, Southeast University, China · School of Electrical Engineering and Computer Science, University of Queensland, Australia · Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore +2

VLM Robustness Adversarial Attacks on VLMs Vision-Language Models Large Vision-Language Models Backdoor Attacks on VLMs

Ask PDF

Aug 19, 2025

Mitigating Cross-Image Information Leakage in Multi-Image Understanding with Large Vision-Language Models

Large Vision-Language Models (LVLMs) exhibit strong performance on single-image tasks. However, their performance degrades significantly when handling multi-image inputs. While this degradation has been observed in prior work, its nature remains poorly understood. We empirically observe visual elements from different images become entangled in the model's representations and responses. We refer to this phenomenon as cross-image information leakage. To address this issue, we propose FOCUS, a training-free and architecture-agnostic method. FOCUS masks all but one image with random noise, guiding the model to focus on the single clean image. This process is applied across the target images to obtain logits under partially masked contexts. These logits are aggregated and then refined using a noise-only reference input, which suppresses the leakage and yields more accurate outputs. FOCUS consistently improves performance on diverse multi-image benchmarks. We further show that FOCUS generalizes to video understanding, extending its applicability beyond static multi-image inputs. This demonstrates that FOCUS offers a general solution for enhancing multi-image reasoning without additional training or architectural modifications.

Yeji Park, Minyoung Lee, Sanghyuk Chun +1

Sogang University · Princeton University · NAVER AI Lab

Large Vision-Language Models VLM Reasoning Multi-Image Reasoning VLM Inference

Ask PDF

Aug 5, 2025

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision

Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their real-world applicability. Although previous mitigation methods effectively reduce hallucinations in photographic images, they largely overlook the potential risks posed by stylized images, which play crucial roles in critical scenarios such as game scene understanding, art education, and medical analysis. In this work, we first construct a dataset comprising photographic images and their corresponding stylized versions with carefully annotated caption labels. We then conduct head-to-head comparisons on both discriminative and generative tasks by benchmarking 13 advanced LVLMs on the collected datasets. Our findings reveal that stylized images tend to induce significantly more hallucinations than their photographic counterparts. To address this issue, we propose Style-Aware Visual Early Revision SAVER, a novel mechanism that dynamically adjusts LVLMs' final outputs based on the token-level visual attention patterns, leveraging early-layer feedback to mitigate hallucinations caused by stylized images. Extensive experiments demonstrate that SAVER achieves state-of-the-art performance in hallucination mitigation across various models, datasets, and tasks.

Zhaoxu Li, Chenqi Kong, Yi Yu +6

ROSE Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · ROSE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · City University of Hong Kong, Hong Kong SAR +3

VLM Evaluation LLM Hallucination Mitigation Hallucination in Language Models VLM Hallucination Large Vision-Language Models VLM Hallucination Mitigation

Ask PDF

Jul 14, 2025

MLLM-Guided Autonomous Object Detection for Open-World Understanding

Object detection typically relies on predefined category vocabularies, while open-world and open-vocabulary approaches remain limited by generic unknown labels or externally specified detection concepts. We propose LAOD, an MLLM-Guided Autonomous Object Detection framework in which a Multimodal Large Language Model (MLLM) generates an image-specific detection vocabulary that is grounded by an open-vocabulary detector. This decomposition separates semantic concept discovery from spatial localization and removes the need to manually enumerate target categories at inference time. We evaluate LAOD using Class-Agnostic Average Precision (CAAP), Semantic Naming Average Precision (SNAP), and Semantic Localization Average Precision (SemLoc-AP), which measure localization, semantic naming, and their correct association, respectively. Experiments on COCO-Val, LVIS-minival, and COCO-OOD across multiple MLLMs and detectors demonstrate strong performance across common, long-tailed, and out-of-distribution objects, while showing that grounding quality remains a major determinant of end-to-end performance. LAOD also substantially outperforms both direct MLLM-based object detection and dedicated models trained specifically for open-ended detection. Overall, the results support a modular formulation of autonomous object detection in which MLLMs determine what to detect and specialized open-vocabulary detectors determine where those concepts occur.

Furkan Mumcu, Michael J. Jones, Anoop Cherian +1

University of South Florida · Mitsubishi Electric Research Laboratories (MERL)

Open-Vocabulary Object Detection Vision-Language Grounding Large Vision-Language Models

Ask PDF

Jun 18, 2025

GenRecal: Generation after Recalibration from Large to Small Vision-Language Models

Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V. However, deploying these models in real-world scenarios, particularly on resource-constrained devices, remains challenging due to their substantial computational demands. This has spurred interest in distilling knowledge from large VLMs into smaller, more efficient counterparts. A key challenge arises here from the diversity of VLM architectures, which are built on different LLMs and employ varying token types-differing in vocabulary size, token splits, and token index ordering. To address this challenge of limitation to a specific VLM type, we present Generation after Recalibration (GenRecal), a general-purpose distillation framework for VLMs. GenRecal incorporates a Recalibrator that aligns and adapts feature representations between heterogeneous VLMs, enabling effective knowledge transfer across different types of VLMs. Through extensive experiments on multiple challenging benchmarks, we demonstrate that GenRecal significantly improves baseline performances, eventually outperforming large-scale open- and closed-source VLMs.

Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro +2

NVIDIA · KAIST

Cross-Modal Knowledge Distillation VLM Distillation Large Vision-Language Models Knowledge Distillation

Ask PDF

May 27, 2025

Seeing Isn't Orienting: A Cognitively Informed Hierarchical Benchmark for Object Orientation in MLLMs

Humans develop object orientation understanding progressively, from recognizing which way an object faces to reasoning about orientations across multiple objects. Yet existing vision-language benchmarks largely conflate orientation with broader spatial reasoning. We introduce Discriminative Orientation Reasoning Intelligence (DORI), a cognition-informed hierarchical benchmark that establishes object orientation as the primary evaluation target. DORI decomposes orientation into four dimensions, each evaluated at coarse (categorical) and granular (metric) levels, yielding 33,656 multiple-choice questions over 13,652 real-world and synthetic images from 14 sources. Its design isolates orientation from confounding factors through object isolation, standardized reference frames, and structured prompts. Evaluating 26 state-of-the-art vision-language models reveals a consistent limitation: models strong on general spatial benchmarks remain near-random on object-centric orientation reasoning. The best model achieves only 64.2% on coarse and 42.9% on granular judgments, with the largest drops on compound rotations and inter-object reference frame shifts. Large coarse-to-granular performance gaps further indicate reliance on categorical heuristics rather than geometric reasoning. These results establish object orientation understanding as a fundamental open challenge for multimodal systems. Dataset: https://huggingface.co/datasets/appledora/DORI-Benchmark

Nazia Tasnim, Keanu Nichols, Yuting Yan +4

Boston University · Work done while at Boston University; currently at Johns Hopkins University

VLM Evaluation Visual Spatial Reasoning Large Vision-Language Models

Ask PDF

May 24, 2025

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance

Visual token pruning, which aims to compress and prune redundant visual tokens, plays a critical role in efficient inference with large vision-language models (LVLMs). However, existing methods fail to disentangle intra-modal visual redundancy from cross-modal redundancy between vision and language. We show that visual token diversity and task-specific token relevance are two crucial yet orthogonal factors that complement each other in conveying useful information and should therefore be treated separately for more effective visual token pruning. Building upon this insight, we design TODRE, a two-stage and training-free framework that incorporates Token Diversity and task RElevance for effective token compression and efficient LVLM inference. Instead of pruning redundant tokens, we introduce a greedy max-sum diversification algorithm that selects and retains a subset of diverse and representative visual tokens after the vision encoder. On top of that, ToDRE leverages an ``information migration'' mechanism to eliminate task-irrelevant visual tokens within certain decoder layers of the large language model (LLM), further improving token pruning and LVLM inference. Extensive experiments show that ToDRE prunes 90% of visual tokens after the vision encoder as well as all visual tokens in certain LLM decoder layers, leading to a 2.6x speed-up in total inference time while maintaining 95.0% model performance plus excellent model compatibility. The code is available at: this https URL.

Duo Li, Zuhao Yang, Xiaoqin Zhang +2

CCDS, NTU, Singapore · CCST, ZJUT, China · Terminus AI Lab, UCAS, China

Efficient VLM Inference Large Vision-Language Models Visual Token Pruning Visual Token Compression

Ask PDF

May 18, 2025

Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations, where generated content is inconsistent with the input image. Existing training-free hallucination mitigation methods often suffer from unstable performance and high sensitivity to hyperparameter settings, which limits their practicality and broader adoption. In this paper, we propose Decoding with Inter-layer Consistency via Layer Aggregation (DCLA), a training-free decoding mechanism that requires no retraining, fine-tuning, or access to external knowledge bases. Specifically, DCLA constructs a dynamic semantic reference by aggregating representations from previous layers and uses it to correct semantically deviated layers, thereby enforcing inter-layer consistency. Experiments across seven LVLMs and multiple benchmarks demonstrate the generality of DCLA: it surpasses standard decoding by 28.58 MME points on LLaVA1.5-7B and 42.6 MME points on Qwen2.5-VL, while improving POPE accuracy by 2.74 percentage points in the strongest setting.

Kai Tang, Jinhao You, Yichen Guo +8

Peking University · University of Pennsylvania · Nanyang Technological University +4

Vision-Language Models Hallucination in Language Models Large Vision-Language Models Object Hallucination in VLMs VLM Hallucination Mitigation VLM Inference

Ask PDF

Feb 6, 2025

PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?

Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current trend is to train MLLMs with pixel-level grounding supervision in terms of masks on large-scale labelled data and specialized decoders for the segmentation task. However, we show that such MLLMs when evaluated on recent challenging vision-centric benchmarks, exhibit a weak ability in visual question answering (VQA). Surprisingly, some of these methods even downgrade the grounding ability of MLLMs that were never trained with such pixel-level supervision. In this work, we propose two novel challenging benchmarks with paired evaluation for both VQA and grounding. We demonstrate that simple baselines that are not unified achieve performance that matches or surpasses some of the pixel-level MLLMs. Our paired benchmarks and evaluation enable additional analysis on whether the failure stems from VQA and/or grounding abilities. Furthermore, we propose a paired prompt sensitivity analysis on both the language and visual prompts tailored for the grounding task. Our benchmarking pushes pixel-level MLLMs to improve in both accuracy and robustness, without sacrificing language abilities. More importantly, we study the research question of ``When does grounding emerge in MLLMs with respect to the output tokens?'' We propose a post-hoc interpretability tool that can be plugged into any MLLM to study the aforementioned question. We show that grounding does not necessarily coincide with the exact referring expression in the output, but can coincide with the object parts, its location, appearance, context or state. Code and datasets are publicly available at https://msiam.github.io/PixFoundationSeries/.

Mennatullah Siam

Large Vision-Language Models Vision-Language Grounding VLM Evaluation VLM Interpretability Prompt Sensitivity

Ask PDF

Jan 28, 2025

Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?

The advances in Vision-Language models (VLMs) offer exciting opportunities for robotic applications involving image geo-localization - the problem of identifying the geo-coordinates of a place based on visual data only. In robotics, such capabilities are particularly relevant to the global re-localization stage of the kidnapped robot problem, where a robot must recover its pose without prior knowledge of its location. Recent work has focused on using a VLM as embedding extractor for geo-localization. However, the most sophisticated VLMs may only be available as black boxes that are accessible through an API, and come with a number of limitations: there is no access to training data, model features and gradients; retraining is not possible; and the number of predictions may be limited by the API. The potential of state-of-the-art VLMs as a stand-alone, zero-shot geo-localization systems at planet scale using a single text-based prompt is largely unexplored. To bridge this gap, this paper undertakes the first systematic study, to the best of our knowledge, to investigate state-of-the-art generative VLMs as stand-alone, zero-shot geo-localization systems in a black-box setting with realistic constraints. We consider three main scenarios for this thorough investigation: a) fixed text-based prompt; b) semantically-equivalent text-based prompts; and c) semantically-equivalent query images. Beyond standard accuracy, we introduce model consistency as a metric to account for the auto-regressive and probabilistic nature of generative VLMs. Our findings reveal that while VLMs demonstrate strong coarse-level localization and navigation priors, fine-grained localization degrades significantly under realistic variations, highlighting reliability challenges for deploying generative VLMs in robust, open-world robotic navigation systems.

Sania Waheed, Bruno Ferrarini, Michael Milford +2

School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ · MyWay srl, Via Osti, 6 - 29010 Vernasca (PC) · School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia +1

VLM Robustness Cross-View Geo-Localization Large Vision-Language Models Robot Localization VLMs for Robotics

Ask PDF

Dec 11, 2024

Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models

Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Existing attacks typically target the vision encoder's final output embeddings, implicitly treating the encoder as a uniform attack surface, while a systematic analysis of which internal components are most vulnerable has remained largely unexplored. We show such analysis is essential, as adversarial vulnerability in LVLM vision encoders is structurally concentrated rather than uniformly distributed. Building on this, we propose Vision Encoder Vulnerable-Component-Targeted Universal Adversarial Perturbation (VEV-UAP), a task-agnostic and cost-efficient attack framework. Through a component- and layer-wise analysis of attention mechanisms, we identify the value components in middle layers as critical vulnerabilities that strongly influence downstream language model behavior. VEV-UAP selectively targets these components to generate a single universal perturbation shared across images, without involving textual inputs or the language model during optimization. Experiments across multiple LVLMs and tasks show VEV-UAP achieves state-of-the-art attack success rates with reduced computational overhead. Moreover, a single VEV-UAP transfers across LVLMs sharing the same vision encoder, even when paired with different language models, making it a practical framework for scalable robustness evaluation.

Hee-Seon Kim, Minbeom Kim, Seokil Ham +1

School of Electrical Engineering, KAIST, Daejeon 34141, Republic of Korea

VLM Robustness Adversarial Attacks on VLMs Large Vision-Language Models Adversarial Perturbations Transfer-Based Adversarial Attacks

Ask PDF

May 27, 2024

Privacy-Aware Visual Language Models

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing even GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.

Laurens Samson, Nimrod Barazani, Sennay Ghebreab +1

Socially-Intelligent Artificial Systems Group, University of Amsterdam · University of Amsterdam · Fundamental AI Lab, University of Technology Nuremberg

VLM Evaluation VLM Adaptation Large Vision-Language Models Privacy Protection in VLMs

Ask PDF

Dec 4, 2023

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Large vision-language models (LVLMs) have demonstrated their incredible capability in visual question answering. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate a novel and practical targeted attack scenario that the adversary knows only the vision encoder of the victim LVLM, without the knowledge of its prompts and its underlying large language model. This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text. To this end, we propose an instruction-tuned targeted attack (dubbed InstructTA) to deliver the targeted adversarial attack on LVLMs with high transferability. Initially, we utilize a public text-to-image generative model to reverse the target response into a target image, and employ GPT-4 to infer a reasonable instruction

\boldsymbol{p}^\prime

from the target response. We then form a local surrogate model (sharing the same vision encoder with the victim LVLM) to extract instruction-aware features of an adversarial image example and the target image, and minimize the distance between these two features to optimize the adversarial example. To further improve the transferability with instruction tuning, we augment the instruction

\boldsymbol{p}^\prime

with instructions paraphrased from GPT-4. Extensive experiments on 6 victim LVLMs demonstrate the superiority of our proposed method in targeted attack performance and transferability. In particular, InstructTA achieves an attack success rate of 51.9% on BLIP-2, outperforming the strongest baseline by 10.5%, and consistently yields the highest attack success rates across all evaluated models. The code is available at https://github.com/xunguangwang/InstructTA.

Xunguang Wang, Pingchuan Ma, Zhenlan Ji +3

The Hong Kong University of Science and Technology, Hong Kong, China

Adversarial Attacks on VLMs Large Vision-Language Models Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks

Ask PDF