Modality Gap in VLMs

VLM: Vision-Language Model

Ask about this topic

Overview

The modality gap describes differences between how vision-language models represent or use images and text, even when the two convey the same information. Researchers study it through embedding geometry and paired-input evaluations, including image-text retrieval, visual reasoning, and tests that swap text for equivalent images. Approaches include contrastive and optimal-transport alignment, feature projection, modality-aware training, and diagnostics that measure whether outputs respond to relevant visual evidence. A central tension is that reducing representational separation can help some tasks but hurt others, while many models still favor language over images; reliable measures must connect the gap to task-specific performance.

Latest papers

CardsList

59 papers12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Apr 22, 2026

The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm

The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current VLMs faithfully synthesise multimodal data. We argue they often do not, and this gap reflects a trustworthiness problem in the dominant Vision Encoder-Projector-LLM paradigm. Rather than extracting grounded knowledge from visual inputs, state-of-the-art models frequently exhibit functional blindness, i.e., exploiting strong language priors to bypass severe visual representation bottlenecks. In this work, we challenge the conventional methodology of multimodal evaluation, which relies on data ablation or new dataset creation and therefore conflates dataset biases with architectural incapacity. We propose an information-theoretic departure: the Modality Translation Protocol, designed to quantify what we call the Expense of Seeing. By translating semantic payloads rather than ablating them, we formulate three novel metrics -- the Toll (ToS), Curse (CoS), and Fallacy (FoS) of Seeing -- culminating in the Semantic Sufficiency Criterion (SSC). Furthermore, we hypothesise a Divergence Law of Multimodal Scaling: as the underlying language engines scale to unprecedented reasoning capabilities, the penalty of the visual knowledge bottleneck may increase rather than diminish. We argue the community should move beyond "multimodal gain" as a primary evaluation target. By elevating the SSC from a passive diagnostic constraint to an active architectural blueprint, we provide a foundation for guiding the next generation of AI systems toward genuine multimodal reasoning.

Karan Goyal

IIIT Delhi, India

VLM EvaluationMultimodal ReasoningVision-Language GroundingModality Gap in VLMsMultimodal Model EvaluationMultimodal Understanding
AskPDF
Apr 17, 2026

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine vision-grounded reasoning or relies predominantly on the reasoning capabilities of their textual backbones. To systematically measure this, we introduce CrossMath, a novel multimodal reasoning benchmark designed for controlled cross-modal comparisons. Specifically, we construct each problem in text-only, image-only, and image+text formats guaranteeing identical task-relevant information, verified by human annotators. This rigorous alignment effectively isolates modality-specific reasoning differences while eliminating confounding factors such as information mismatch. Extensive evaluation of state-of-the-art VLMs reveals a consistent phenomenon: a substantial performance gap between textual and visual reasoning. Notably, VLMs excel with text-only inputs, whereas incorporating visual data (image+text) frequently degrades performance compared to the text-only baseline. These findings indicate that current VLMs conduct reasoning primarily in the textual space, with limited genuine reliance on visual evidence. To mitigate this limitation, we curate a CrossMath training set for VLM fine-tuning. Empirical evaluations demonstrate that fine-tuning on this training set significantly boosts reasoning performance across all individual and joint modalities, while yielding robust gains on two general visual reasoning tasks. Source code is available at https://github.com/xuyige/CrossMath.

Yige Xu, Yongjie Wang, Zizhuo Wu +3

College of Computing and Data Science, Nanyang Technological University, Singapore · Alibaba-NTU Global e-Sustainability CorpLab (ANGEL) · Tongyi Lab, Alibaba Group, China

Vision-Language ModelsVLM AdaptationVisual ReasoningVLM ReasoningModality Gap in VLMsMultimodal Model Evaluation
AskPDF
Apr 15, 2026

The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models

Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood. We propose centroid replacement, mapping tokens to their nearest K-means centroid and removing within-cluster residual structure, as a controlled probe for modal dependence. Across seven models spanning four architecture families, post-image text replacement costs 4x more accuracy than visual replacement on six BLINK tasks; VPBench and MedBLINK preserve this aggregate ordering. Since text replacement also disrupts the task and answer interface, the gap measures relative dependence. Text centroid contrastive decoding (TCCD) exploits this asymmetry without retraining, recovering up to +16.9% accuracy on an individual task at oracle best-per-task αinterpα_\text{interp}; every model gains on at least one task, although gains vary across tasks and models. Together, centroid replacement provides a retraining-free audit of modal dependence on labeled data, while TCCD offers a reusable inference-time intervention. Code and artifacts are available at: https://github.com/yahskapar/centroid-erasure

Akshay Paruchuri, Ishan Chatterjee, Henry Fuchs +2

Università della Svizzera italiana · Stanford University · University of Washington +1

Modality Reliance in Multimodal ModelsMultimodal Large Language ModelsModality Gap in VLMsMultimodal Model EvaluationContrastive Decoding
AskPDF
Apr 15, 2026

Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations

The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their adversarial robustness remains underexplored. We identify Visual Dominance Hallucination (VDH), where imperceptible visual cues can override textual price evidence in screenshot-based, price-constrained settings and lead agents to irrational decisions. We propose PriceBlind, a stealthy white-box adversarial attack framework for controlled screenshot-based evaluation. PriceBlind exploits the modality gap in CLIP-based encoders via a Semantic-Decoupling Loss that aligns the image embedding with low-cost, value-associated anchors while preserving pixel-level fidelity. On E-ShopBench, PriceBlind achieves around 80% ASR in white-box evaluation; under a simplified single-turn coordinate-selection protocol, Ensemble-DI-FGSM transfers with roughly 35-41% ASR across GPT-4o, Gemini-1.5-Pro, and Claude-3.5-Sonnet. We also show that robust encoders and Verify-then-Act defenses reduce ASR substantially, though with some clean-accuracy trade-off.

Jiachen Qian, Zhaolu Kang

City University of Hong Kong · Peking University

VLM RobustnessAdversarial Attacks on VLMsAdversarial Attacks on Unified Multimodal ModelsMultimodal HallucinationModality Gap in VLMs
AskPDF
Apr 15, 2026

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks

In-context learning (ICL) enables models to adapt to new tasks via inference-time demonstrations. Despite its success in large language models, the extension of ICL to multimodal settings remains poorly understood in terms of its internal mechanisms and how it differs from text-only ICL. In this work, we conduct a systematic analysis of ICL in multimodal large language models. Using identical task formulations across modalities, we show that multimodal ICL performs comparably to text-only ICL in zero-shot settings but degrades significantly under few-shot demonstrations. To understand this gap, we decompose multimodal ICL into task mapping construction and task mapping transfer, and analyze how models establish cross-modal task mappings, and transfer them to query samples across layers. Our analysis reveals that current models lack reasoning-level alignment between visual and textual representations, and fail to reliably transfer learned task mappings to queries. Guided by these findings, we further propose a simple inference-stage enhancement method that reinforces task mapping transfer. Our results provide new insights into the mechanisms and limitations of multimodal ICL and suggest directions for more effective multimodal adaptation. Our code is available here.

Yu Wang, Sharon Li

Department of Computer Sciences, University of Wisconsin-Madison

Multimodal ICLIn-Context LearningMultimodal Large Language ModelsModality Gap in VLMs
AskPDF
Apr 12, 2026

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning

Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference latency. By analyzing token-level gradient dynamics during latent training, we reveal two critical observations: (1) visual tokens exhibit significantly smaller gradient norms than their textual counterparts due to inherent language bias, resulting in systematic visual under-optimization; and (2) semantically simple tokens converge rapidly, whereas complex tokens exhibit persistent gradient instability constrained by fixed architectural depths. To address these limitations, we propose a visual replay module and routing depth scaling to collaboratively enhance visual perception and refine complicated latents for deeper contextual reasoning. The former module leverages causal self-attention to estimate token saliency, reinforcing fine-grained grounding through spatially-coherent constraints. Complementarily, the latter mechanism adaptively allocates additional reasoning steps to complex tokens, enabling deeper contextual refinement. Guided by a curriculum strategy that progressively internalizes explicit CoT into compact latent representations, our framework achieves state-of-the-art performance across diverse benchmarks while delivering substantial inference speedups over explicit CoT baselines.

Yudong Han, Yong Wang, Zaiquan Yang +3

Beijing Institute of Technology · AMAP, Alibaba Group · City University of Hong Kong +2

Latent Visual ReasoningContinuous Latent ReasoningAdaptive ComputationModality Gap in VLMsTest-Time Scaling for VLMs
AskPDF
Apr 6, 2026

DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs

When asked to describe a molecular diagram, a Vision-Language Model correctly identifies ``a benzene ring with an -OH group.'' When asked to reason about the same image, it answers incorrectly. The model can see but it cannot think about what it sees. We term this the perception-integration gap: a failure where visual information is successfully extracted but lost during downstream reasoning, invisible to single-configuration benchmarks that conflate perception with integration under one accuracy number. To systematically expose such failures, we introduce DISSECT, a 12,000-question diagnostic benchmark spanning Chemistry (7,000) and Biology (5,000). Every question is evaluated under five input modes -- Vision+Text, Text-Only, Vision-Only, Human Oracle, and a novel Model Oracle in which the VLM first verbalizes the image and then reasons from its own description -- yielding diagnostic gaps that decompose performance into language-prior exploitation, visual extraction, perception fidelity, and integration effectiveness. Evaluating 18~VLMs, we find that: (1) Chemistry exhibits substantially lower language-prior exploitability than Biology, confirming molecular visual content as a harder test of genuine visual reasoning; (2) Open-source models consistently score higher when reasoning from their own verbalized descriptions than from raw images, exposing a systematic integration bottleneck; and (3) Closed-source models show no such gap, indicating that bridging perception and integration is the frontier separating open-source from closed-source multimodal capability. The Model Oracle protocol is both model and benchmark agnostic, applicable post-hoc to any VLM evaluation to diagnose integration failures.

Dikshant Kukreja, Kshitij Sah, Karan Goyal +2

IIIT Delhi, India

Reasoning for VLMsVLM EvaluationVLM ReasoningModality Gap in VLMs
AskPDF
Apr 3, 2026

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave like its original language backbone under text-only prompting. This failure is not explained only by missing semantic information. Even when text descriptions preserve key content, confidence becomes unreliable, while adding a visual signal through generated images partially restores accuracy and calibration. We propose the Latent Imagination Module (LIM), a lightweight cross-attention module that predicts imagined latent embeddings from textual input and feeds them into a frozen VLM backbone without pixel-level image synthesis. Across text-only benchmarks, unseen tasks, and missing-image scenarios, LIM improves accuracy and reduces calibration error. These results suggest that latent modality completion is a practical approach for reliable VLM inference under missing-modality.

Mingyeong Kim, Jungwon Choi, Chaeyun Jang +1

Kim Jaechul Graduate School of AI, KAIST

Modality Gap in VLMsVLM InferenceMissing-Modality LearningVLM Calibration
AskPDF
Mar 31, 2026

The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal interchangeability, such as captioning and joint clustering. Existing post-processing approaches can partially improve cross-modal compatibility; however, we show through geometric analysis that they primarily reduce the global centroid offset while leaving the underlying distributional mismatch intact. We decompose the modality gap into a Centroid Gap and a Distribution Gap, and demonstrate that the Distribution Gap is the true predictor of cross-modal task quality (R2=0.986R^2 = 0.986), whereas the commonly used Raw Gap is misleading (R2=0.691R^2 = 0.691). Motivated by this observation, we propose TPC-CMA (Three-Phase Curriculum for Cross-Modal Alignment), a fine-tuning framework that explicitly reduces both components. The proposed CMA jointly mitigates centroid offsets and reshapes the distributional structure, while a three-phase curriculum with gradient-aware scheduling progressively introduces alignment during training to enable stable optimization. Experiments demonstrate that our method significantly improves cross-modal alignment. With αtarget=0.05α_{\text{target}}{=}0.05, the modality gap is reduced by 66.6% with only 4.84% accuracy drop. Under stronger alignment (αtarget=0.5α_{\text{target}}{=}0.5), the gap is reduced by 82.3%, clustering ARI improves from 0.318 to 0.516, and captioning CIDEr increases by 57.1% over the original model. Our code and pre-trained models will be made publicly available upon acceptance.

Hongyuan Liu, Qinli Yang, Wen Li +6

University of Electronic Science and Technology of China · University of Bristol

Cross-Modal AlignmentModality Gap in VLMsVLM Adaptation
AskPDF
Mar 30, 2026

Is the Modality Gap a Bug or a Feature? A Robustness Perspective

Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality gap: the distribution of images is well-separated from the distribution of texts in the shared embedding space. Despite a series of recent papers on this topic, it is still not clear why this gap exists nor whether closing the gap in post-processing will lead to better performance on downstream tasks. In this paper we show that under certain conditions, minimizing the contrastive loss yields a representation in which the two modalities are separated by a global gap vector that is orthogonal to their embeddings. We also show that under these conditions the modality gap is monotonically related to robustness: decreasing the gap does not change the clean accuracy of the models but makes it less likely that a model will change its output when the embeddings are perturbed. Our experiments show that for many real-world VLMs we can significantly increase robustness by a simple post-processing step that moves one modality towards the mean of the other modality, without any loss of clean accuracy.

Rhea Chowers, Oshri Naparstek, Udi Barzelay +1

Hebrew University, Jerusalem, Israel · IBM Research, Haifa, Israel

Modality Gap in VLMsMultimodal EmbeddingVLM RobustnessMultimodal Contrastive Learning
AskPDF
Mar 22, 2026

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1% of the data, RoboAlign achieves performance improvements of 17.5%, 18.9%, and 106.6% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.

Dongyoung Kim, Sumin Park, Woomin Song +6

KAIST · RLWRLD · Yonsei University +1

Vision-Language-Action ModelsReasoning for VLA ModelsModality Gap in VLMsRL for VLMs
AskPDF
Mar 20, 2026

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment

Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applied to inherently intra-modal tasks like image-to-image retrieval, their performance suffers from the intra-modal misalignment. In this paper we study intra-modal misalignment in CLIP with a focus on the role of the projectors that map pre-projection image and text embeddings into the shared embedding space. By analyzing the form of the cosine similarity applied to projected features, and its interaction with the contrastive CLIP loss, we show that there is an inter-modal operator responsible for aligning the two modalities during training, and a second, intra-modal operator that only enforces intra-modal normalization but does nothing to promote intra-modal alignment. Via spectral analysis of the inter-modal operator, we identify an approximately isotropic subspace in which the two modalities are well-aligned, as well as anisotropic directions specific to each modality. We demonstrate that this aligned subspace can be directly obtained from the projector weights and that removing the anisotropic directions improves intra-modal alignment. Our experiments on intra-modal retrieval and classification benchmarks show that our training-free method reduces intra-modal misalignment, greatly lowers latency, and outperforms existing approaches across multiple pre-trained CLIP-like models. The code is publicly available at: https://github.com/simomagi/IsoCLIP.

Simone Magistri, Dipam Goswami, Marco Mistretta +3

Media Integration and Communication Center (MICC), University of Florence, Italy · Department of Computer Science, Universitat Aut`onoma de Barcelona, Spain · Computer Vision Center, Barcelona, Spain +1

Latent Space AlignmentModality Gap in VLMsImage RetrievalVision-Language Pretraining
AskPDF
Mar 18, 2026

On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings

Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contributing to cross-modal separation known as the modality gap. While this phenomenon has been widely observed, its practical impact on supervised multimodal learning -- particularly in medical domains -- remains unclear. In this work, we introduce a lightweight post-hoc mechanism that keeps pretrained VLM encoders frozen while continuously controlling cross-modal separation through a single hyperparameter {λ}. This enables systematic analysis of how the modality gap affects downstream multimodal performance without expensive retraining. We evaluate generalist (CLIP, SigLIP) and medically specialized (BioMedCLIP, MedSigLIP) models across diverse medical and natural datasets in a supervised multimodal settings. Results consistently show that reducing excessive modality gap improves downstream performance, with medical datasets exhibiting stronger sensitivity to gap modulation; however, fully collapsing the gap is not always optimal, and intermediate, task-dependent separation yields the best results. These findings position the modality gap as a tunable property of multimodal representations rather than a quantity that should be universally minimized.

David Restrepo, Miguel L Martins, Chenwei Wu +5

CentraleSupélec, Université Paris-Saclay, France · University of Porto, Portugal · University of Michigan, USA +3

Modality Gap in VLMsMultimodal LearningMedical VLMs
AskPDF
Mar 16, 2026

Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection

Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on general visual-grounded reasoning tasks. In this work, we investigate whether safety and utility are inherently antagonistic objectives. We focus on a modality induced bias direction consistently observed across datasets, which arises from suboptimal coupling between the Large Language Model backbone and visual encoders. We further demonstrate that this direction undermines performance on both tasks. Leveraging this insight, we propose Two Birds, One Projection, an efficient inference time jailbreak defence that projects cross-modal features onto the null space of the identified bias direction to remove the corresponding components. Requiring only a single forward pass, our method effectively breaks the conventional tradeoff, simultaneously improving both safety and utility across diverse benchmarks.

Yewon Han, Yumin Seol, EunGyung Kong +2

Graduate School of Data Science, Seoul National University · Mobilint

VLM SafetyVLM RobustnessModality Gap in VLMs
AskPDF
Mar 14, 2026

SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis

Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically meaningful components. However, existing methods are largely restricted to images and overlook the cross-modal interactions. Text-image embeddings, such as those produced by CLIP, suffer from a modality gap, where visual and textual features follow distinct distributions, limiting interpretability. Canonical Correlation Analysis (CCA) offers a principled way to align features from different distributions, but has not been leveraged for multi-modal concept-level analysis. We show that the objectives of CCA and InfoNCE are closely related, such that optimizing CCA implicitly optimizes InfoNCE, providing a simple, training-free mechanism to enhance cross-modal alignment without affecting the pre-trained InfoNCE objective. Motivated by this observation, we couple concept-based explainability with CCA, introducing Concept CCA (CoCCA), a framework that aligns cross-modal embeddings while enabling interpretable concept decomposition. We further extend it and propose Sparse Concept CCA (SCoCCA), which enforces sparsity to produce more disentangled and discriminative concepts, facilitating improved activation, ablation, and semantic manipulation. Our approach generalizes concept-based explanations to multi-modal embeddings and achieves state-of-the-art performance in concept discovery, evidenced by reconstruction and manipulation tasks such as concept ablation.

Ehud Gordon, Meir Yossef Levi, Guy Gilboa

Viterbi Faculty of Electrical and Computer Engineering, Technion – Israel Institute of Technology, Haifa, Israel

Canonical Correlation AnalysisMultimodal Model InterpretabilityConcept-Based ExplanationsModality Gap in VLMsCross-Modal Alignment
AskPDF
Mar 11, 2026

Towards Cognitive Defect Analysis in Active Infrared Thermography with Vision-Text Cues

Active infrared thermography (AIRT) is currently witnessing a surge of artificial intelligence (AI) methodologies being deployed for automated subsurface defect analysis of high performance carbon fiber-reinforced polymers (CFRP). Deploying AI-based AIRT methodologies for inspecting CFRPs requires the creation of time consuming and expensive datasets of CFRP inspection sequences to train neural networks. To address this challenge, this work introduces a novel language-guided framework for cognitive defect analysis in CFRPs using AIRT and vision-language models (VLMs). Unlike conventional learning-based approaches, the proposed framework does not require developing training datasets for extensive training of defect detectors, instead it relies solely on pretrained multimodal VLM encoders coupled with a lightweight adapter to enable generative zero-shot understanding and localization of subsurface defects. By leveraging pretrained multimodal encoders, the proposed system enables generative zero-shot understanding of thermographic patterns and automatic detection of subsurface defects. Given the domain gap between thermographic data and natural images used to train VLMs, an AIRT-VLM Adapter is proposed to enhance the visibility of defects while aligning the thermographic domain with the learned representations of VLMs. The proposed framework is validated using three representative VLMs; specifically, GroundingDINO, Qwen-VL-Chat, and CogVLM. Validation is performed on 25 CFRP inspection sequences with impacts introduced at different energy levels, reflecting realistic defects encountered in industrial scenarios. Experimental results demonstrate that the AIRT-VLM adapter achieves signal-to-noise ratio (SNR) gains exceeding 10 dB compared with conventional thermographic dimensionality-reduction methods, while enabling zero-shot defect detection with intersection-over-union values reaching 70%.

Mohammed Salah, Eman Ouda, Giuseppe Dell'Avvocato +6

Fault DetectionThermal ImagingZero-Shot Anomaly DetectionModality Gap in VLMs
AskPDF
Mar 10, 2026

Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs

Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs across seven benchmarks in five input modes, spanning both synthetically rendered text and realistic document images from arXiv PDFs to Wikipedia pages. We find that the gap is highly sensitive to rendering choices such as font and resolution, and that natural document images often exhibit much smaller gaps, suggesting the performance difference partly reflects evaluation artifacts rather than fundamental limitations. Through a grounded-theory error analysis of over 4,000 examples, we identify the primary cause: image input alone suppresses reasoning effort, with models producing 5--19x shorter outputs that skip step-by-step computation or reasoning. The reluctance to reason, not a failure of perception or knowledge retrieval, drives the performance gap, particularly on tasks requiring multi-step reasoning. We show that a simple, lightweight on-policy self-distillation method by fine-tuning models on their own text-mode reasoning traces paired with image inputs closes this gap, raising image-mode accuracy to match or exceed text-mode performance with over 50% improvement, and the gains transfer to unseen benchmarks without catastrophic forgetting. Overall, our results and analyses provide a systematic understanding of the modality gap and suggest a practical path toward improving visual text understanding in multimodal language models.

Kaiser Sun, Xiaochuang Yuan, Hongjun Liu +4

Johns Hopkins University · Amazon · New York University +1

Multimodal Large Language ModelsModality Gap in VLMsMultimodal ReasoningDocument Image UnderstandingMultimodal Model Evaluation
AskPDF
Mar 6, 2026

K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging

Large-scale biomedical vision-language models (VLMs) adapted on high-end imaging (e.g., CT) often fail to transfer to frontline low-end modalities (e.g., radiography), collapsing into modality-specific shortcuts. We propose K-MaT (Knowledge-Anchored Manifold Transport), a prompt-learning framework that transfers decision structures to low-end modalities without requiring low-end training images. K-MaT factorizes prompts, anchors them to clinical text descriptions, and aligns the low-end prompt manifold to the visually-grounded high-end space using Fused Gromov-Wasserstein optimal transport. We evaluate K-MaT on four cross-modal benchmarks, including dermoscopy, mammography to ultrasound, and CT to chest X-ray. K-MaT achieves state-of-the-art results, improving the average harmonic mean of accuracy to 44.1% (from BiomedCoOp's 42.0%) and macro-F1 to 36.2%. Notably, on the challenging breast imaging task, it mitigates the catastrophic forgetting seen in standard methods like CoOp (which drops to 27.0% accuracy on the low-end), preserving robust performance across modalities. Aligning prompt manifolds via optimal transport provides a highly effective route for the zero-shot cross-modal deployment of medical VLMs.

Jiajun Zeng, Shadi Albarqouni

University of Bonn, University Hospital Bonn, Clinic for Diagnostic and Interventional Radiology, 53127 Bonn, Germany

Cross-Modal LearningMedical VLMsModality Gap in VLMs
AskPDF
Mar 5, 2026

Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment

Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding consistency to achieve semantic consistency, ignoring the non-semantic information present in the embedding. An intuitive approach is to decouple the embeddings into semantic and modality components, aligning only the semantic component. However, this introduces two main challenges: (1) There is no established standard for distinguishing semantic and modal information. (2) The modality gap can cause semantic alignment deviation or information loss. To align the true semantics, we propose a novel cross-modal alignment algorithm via Constrained Decoupling and Distribution Sampling (CDDS). Specifically, (1) A dual-path UNet is introduced to adaptively decouple the embeddings, applying multiple constraints to ensure effective separation. (2) A distribution sampling method is proposed to bridge the modality gap, ensuring the rationality of the alignment process. Extensive experiments on various benchmarks and model backbones demonstrate the superiority of CDDS, outperforming state-of-the-art methods by 6.6% to 14.2%.

Xiang Ma, Lexin Fang, Litian Xu +1

Shandong University, Jinan, China · The University of Exeter, Exeter, United Kingdom

Cross-Modal AlignmentVision-Language AlignmentModality Gap in VLMsMultimodal Disentangled Representation Learning
AskPDF
Mar 2, 2026

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However, measuring information loss during modality conversion is inherently challenging due to the modal gap between visual content and text output. In this paper, we argue that the quality of an image caption is positively correlated with the similarity between images retrieved via text search using that caption. Based on this insight, we further propose Cross-modal Identity Mapping (CIM), a reinforcement learning framework that enhances image captioning without requiring additional annotations. Specifically, the method quantitatively evaluates the information loss from two perspectives: Gallery Representation Consistency and Query-gallery Image Relevance. Supervised under these metrics, LVLM minimizes information loss and aims to achieve identity mapping from images to captions. The experimental results demonstrate the superior performance of our method in image captioning, even when compared with Supervised Fine-Tuning. Particularly, on the COCO-LN500 benchmark, CIM achieves a 20% improvement in relation reasoning on Qwen2.5-VL-7B.

Haonan Jia, Shichao Dong, Xin Dong +6

Taobao & Tmall Group of Alibaba · The University of Hong Kong

Image CaptioningModality Gap in VLMsRL for VLMs
AskPDF
Feb 27, 2026

3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection

Vision-language models (VLMs) show strong potential for complex diagnostic tasks in medical imaging. However, applying VLMs to multi-organ medical imaging introduces two principal challenges: (1) modality-specific vision-language alignment and (2) cross-modal feature fusion. In this work, we propose MedMAP, a Medical Modality-Aware Pretraining framework that enhances vision-language representation learning in 3D MRI. MedMAP comprises a modality-aware vision-language alignment stage and a fine-tuning stage for multi-organ abnormality detection. During the pre-training stage, the modality-aware encoders implicitly capture the joint modality distribution and improve alignment between visual and textual representations. We then fine-tune the pre-trained vision encoders (while keeping the text encoder frozen) for downstream tasks. To this end, we curated MedMoM-MRI3D, comprising 7,392 3D MRI volume-report pairs spanning twelve MRI modalities and nine abnormalities tailored for various 3D medical analysis tasks. Extensive experiments on MedMoM-MRI3D demonstrate that MedMAP significantly outperforms existing VLMs in 3D MRI-based multi-organ abnormality detection. Our code is available at https://github.com/RomantiDr/MedMAP.

Haowen Zhu, Ning Yin, Xiaogen Zhou

School of Computer Science and Engineering, Southeast University, China · Department of Medical Imaging, Suzhou Traditional Chinese Medicine Hospital, China · School of Electronic, Electrical Engineering and Physics, Fujian University of Technology

Medical VLMsVision-Language PretrainingMedical Image Anomaly DetectionModality Gap in VLMs3D Medical Imaging
AskPDF
Feb 26, 2026

ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport

Image-text retrieval has become a fundamental component in intelligent multimedia systems; however, most existing vision-language models are optimized for highresource languages and remain suboptimal for low-resource settings such as Vietnamese. This work introduces ViCLIP-OT, a foundation vision-language model specifically designed for Vietnamese image-text retrieval. The proposed framework integrates CLIP-style contrastive learning with a Similarity-Graph Regularized Optimal Transport (SIGROT) loss to enhance global cross-modal consistency and mitigate modality gap issues. Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in both in-domain and zero-shot settings. On UIT-OpenViIC, the model achieves an average Recall@K of 67.34%, improving upon CLIP by 5.75 percentage points. In zero-shot evaluation on Crossmodal-3600, ViCLIPOT surpasses CLIP by 11.72 percentage points. Embedding-space analysis further confirms improved alignment and reduced modality gap. The results indicate that integrating SIGROT provides an effective and scalable strategy for cross-modal retrieval in low-resource languages, offering practical implications for intelligent multimedia retrieval systems in Vietnamese and other underrepresented linguistic contexts.

Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang Pham

Can Tho University, Can Tho, Vietnam

Vision-Language RetrievalCross-Modal RetrievalVision-Language AlignmentModality Gap in VLMs
AskPDF
Feb 23, 2026

Closing the gap in multimodal medical representation alignment

In multimodal learning, CLIP has emerged as the de-facto approach for mapping different modalities into a shared latent space by bringing semantically similar representations closer while pushing apart dissimilar ones. However, CLIP-based contrastive losses exhibit unintended behaviors that negatively impact true semantic alignment, leading to sparse and fragmented latent spaces. This phenomenon, known as the modality gap, has been partially mitigated for standard text and image pairs but remains unknown and unresolved in more complex multimodal settings, such as the medical domain. In this work, we study this phenomenon in the latter case, revealing that the modality gap is present also in medical alignment, and we propose a modality-agnostic framework that closes this gap, ensuring that semantically related representations are more aligned, regardless of their source modality. Our method enhances alignment between radiology images and clinical text, improving cross-modal retrieval and image captioning.

Eleonora Grassucci, Giordano Cicchetti, Danilo Comminiello

Dept. of Information Engineering, Electronics, and Telecommunications, Sapienza University of Rome, Italy

Modality Gap in VLMsVision-Language AlignmentMedical VLMsMultimodal Contrastive LearningMedical Image Representation LearningCross-Modal Retrieval
AskPDF
Feb 22, 2026

CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion

Modality gap significantly restricts the effectiveness of multimodal fusion. Previous methods often use techniques such as diffusion models and adversarial learning to reduce the modality gap, but they typically focus on one-to-one alignment without exposing the data points of the source modality to the global distribution information of the target modality. To this end, leveraging the characteristic of rectified flow that can map one distribution to another via a straight trajectory, we extend rectified flow for modality distribution mapping. Specifically, we leverage the one-to-many mapping' strategy in rectified flow that allows each data point of the source modality to observe the overall target distribution. This also alleviates the issue of insufficient paired data within each sample, enabling a more robust distribution transformation. Moreover, to achieve more accurate distribution mapping and address the ambiguous flow directions in one-to-many mapping, we design adaptive relaxed alignment', enforcing stricter alignment for modality pairs belonging to the same sample, while applying relaxed mapping for pairs not belonging to the same sample or category. Additionally, to prevent information loss during distribution mapping, we introduce `cyclic rectified flow' to ensure the transferred features can be translated back to the original features, allowing multimodal representations to learn sufficient modality-specific information. After distribution alignment, our approach achieves very competitive results on multiple tasks of multimodal affective computing even with a simple fusion method, and visualizations verify that it can effectively reduce the modality gap.

Sijie Mai, Shiqin Han

South China Normal University

Multimodal FusionCross-Modal AlignmentModality Gap in VLMsRectified FlowAffective Computing
AskPDF
Feb 21, 2026

Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or logic errors. Existing VLMs often produce plausible yet ungrounded answers, and even when prompted to "reflect", their corrections may remain detached from the image evidence. To address this, we propose the MIRROR framework for Multimodal Iterative Reasoning via Reflection On visual Regions. By embedding visual reflection as a core mechanism, MIRROR is formulated as a closed-loop process comprising draft, critique, region-based verification, and revision, which are repeated until the output is visually grounded. To facilitate training of this model, we construct ReflectV, a visual reflective dataset for multi-turn supervision that explicitly contains reflection triggers, region-based verification actions, and answer revision grounded in visual evidence. Experiments on both general vision-language benchmarks and representative vision-language reasoning benchmarks show that MIRROR improves correctness and reduces visual hallucinations, demonstrating the value of training reflection as an evidence-seeking, region-aware verification process rather than a purely textual revision step.

Haoyu Zhang, Yuwei Wu, Pengxiang Li +6

Beijing Institute of Technology · Shenzhen MSU-BIT University

Self-Correction in VLMsVision-Language ModelsVLM Hallucination MitigationVisually Grounded ReasoningModality Gap in VLMs
AskPDF
Feb 21, 2026

MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment

Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or distinguishing cultural proxies, where correct interpretation hinges on subtle visual or linguistic clues and where minor misinterpretations can lead to significant real-world consequences. We present MiSCHiEF, a set of two benchmarking datasets based on a contrastive pair design in the domains of safety (MiS) and culture (MiC), and evaluate four VLMs on tasks requiring fine-grained differentiation of paired images and captions. In both datasets, each sample contains two minimally differing captions and corresponding minimally differing images. In MiS, the image-caption pairs depict a safe and an unsafe scenario, while in MiC, they depict cultural proxies in two distinct cultural contexts. We find that models generally perform better at confirming the correct image-caption pair than rejecting incorrect ones. Additionally, models achieve higher accuracy when selecting the correct caption from two highly similar captions for a given image, compared to the converse task. The results, overall, highlight persistent modality misalignment challenges in current VLMs, underscoring the difficulty of precise cross-modal grounding required for applications with subtle semantic and visual distinctions.

Sagarika Banerjee, Tangatar Madi, Advait Swaminathan +4

Algoverse AI Research · PocketFM

Cultural Safety Evaluation of VLMsVLM EvaluationText-Image AlignmentVision-Language ModelsModality Gap in VLMs
AskPDF
Feb 17, 2026

Can Vision-Language Models See Squares? Text-Recognition Mediates Spatial Reasoning Across Three Model Families

We present a simple experiment that exposes a fundamental limitation in vision-language models (VLMs): the inability to accurately localize filled cells in binary grids when those cells lack textual identity. We generate fifteen 15x15 grids with varying density (10.7%-41.8% filled cells) and render each as two image types -- text symbols (. and #) and filled squares without gridlines -- then ask three frontier VLMs (Claude Opus, ChatGPT 5.2, and Gemini 3 Thinking) to transcribe them. In the text-symbol condition, Claude and ChatGPT achieve approximately 91% cell accuracy and 84% F1, while Gemini achieves 84% accuracy and 63% F1. In the filled-squares condition, all three models collapse to 60-73% accuracy and 29-39% F1. Critically, all conditions pass through the same visual encoder -- the text symbols are images, not tokenized text. The text-vs-squares F1 gap ranges from 34 to 54 points across models, demonstrating that VLMs behave as if they possess a high-fidelity text-recognition pathway for spatial reasoning that dramatically outperforms their native visual pathway. Each model exhibits a distinct failure mode in the squares condition -- systematic under-counting (Claude), massive over-counting (ChatGPT), and template hallucination (Gemini) -- but all share the same underlying deficit: severely degraded spatial localization for non-textual visual elements.

Yuval Levental

Rochester Institute of Technology

Vision-Language ModelsVLM ReasoningVLM EvaluationSpatial Reasoning in Language ModelsModality Gap in VLMs
AskPDF
Jan 10, 2026

BabyVision: Visual Reasoning Beyond Language

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

Liang Chen, Weichu Xie, Yiyan Liang +27

1UniPat AI · 6Peking University · 3Alibaba Group +8

VLM EvaluationVisual ReasoningMultimodal Large Language ModelsModality Gap in VLMsVisually Grounded ReasoningMultimodal Foundation Models+1
AskPDF
Jul 26, 2025

Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models

The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared representation space. In continual learning, CLIP-based vision-language models (VLMs) not only suffer catastrophic forgetting but also experience modality gap drift that disrupts the shared embedding geometry. Such drift degrades cross-modal alignment and generalization. We propose FPCD, an efficient framework combining Fast Null-space Projection (FNP) and Contrastive Distillation (CD). FNP accumulates compact Gram matrices of previous tasks' activations and projects gradients onto layer-adaptive approximate null spaces to reduce interference with learned representations. By replacing singular value decomposition with symmetric eigendecomposition, FNP accelerates projection-basis construction by a factor of 5-9. CD uses a small reference set to align the bidirectional image-to-text and text-to-image similarity distributions of the fine-tuned model with CLIP, thereby preserving pretrained cross-modal relations. On the 11-task MTIL benchmark, FPCD achieves 87.6% Last, 76.4% Average, and 65.2% Transfer. It also maintains more stable modality gaps and stronger zero-shot retrieval performance on COCO Captions and Flickr30k than competing methods. These results highlight the importance of controlling modality gap drift during continual adaptation of VLMs.

Tiantian Peng, Yuyang Liu, Shuo Yang +2

Peking University, Shenzhen Graduate School · Peng Cheng Laboratory

Continual Learning for VLMsModality Gap in VLMs
AskPDF