Vision-Language Alignment

Ask about this topic

Overview

Vision-language alignment studies how models connect visual information with words, phrases, and longer descriptions, enabling tasks such as image-text retrieval, visual grounding, segmentation, and captioning. Common approaches include contrastive learning, prompt and adapter tuning, optimal transport, and fine-grained alignment between text tokens and image regions or video frames. Work also applies these methods to medical images, remote sensing, robotics, and multilingual settings, while developing benchmarks and diagnostics for compositional understanding and cross-modal correspondence. A central tension is that stronger semantic alignment can improve matching but may blur local details, amplify language bias, or weaken generalization across domains and tasks.

Latest papers

CardsList

361 papers33 papers in the last four weeks, up 22% on the four weeks before. 0.2% of all new papers.

Apr 20, 2026

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for fine-grained visual representations, which limits scalability to long videos. This work addresses both limitations. We propose T-REN (Text-aligned Region Encoder Network), an efficient encoder that maps visual data to a compact set of text-aligned region-level representations (or region tokens). T-REN achieves this through a lightweight network added on top of a frozen vision backbone, trained to pool patch-level representations within each semantic region into region tokens and align them with region-level text annotations. With only 3.7% additional parameters compared to the vision-language backbone, this design yields substantially stronger dense cross-modal understanding while reducing the token count by orders of magnitude. Specifically, T-REN delivers +5.9 mIoU on ADE20K open-vocabulary segmentation, +18.4% recall on COCO object-level text-image retrieval, +15.6% recall on Ego4D video object localization, and +17.6% mIoU on VSPW video scene parsing, all while reducing token counts by more than 24x for images and 187x for videos compared to the patch-based vision-language backbone. The code and model are available at https://github.com/savya08/T-REN.

Savya Khosla, Sethuraman T, Aryan Chadha +2

University of Illinois Urbana-Champaign

VLM AdaptationOpen-Vocabulary Semantic SegmentationVision-Language AlignmentVisual Token Compression
AskPDF
Apr 20, 2026

S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models

Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images remains challenging. We identify a critical capability gap in existing multi-image alignment approaches: current methods focus primarily on localized reasoning with pre-specified image indices (``Look at Image 3 and...''), bypassing the essential skills of global visual search and autonomous cross-image comparison. To address this limitation, we introduce a Simple-to-Hard (S2H) learning framework that systematically constructs multi-image preference data across three hierarchical reasoning levels requiring an increasing level of capabilities: (1) single-image localized reasoning, (2) multi-image localized comparison, and (3) global visual search. Unlike prior work that relies on model-specific attributes, such as hallucinations or attention heuristics, to generate preference pairs, our approach leverages prompt-driven complexity to create chosen/rejected pairs that are applicable across different models. Through extensive evaluations on LLaVA and Qwen-VL models, we show that our diverse multi-image reasoning data significantly enhances multi-image reasoning performance, yielding significant improvements over baseline methods across benchmarks. Importantly, our approach maintains strong single-image reasoning performance while simultaneously strengthening multi-image understanding capabilities, thus advancing the state of the art for holistic visual preference alignment.

Nitish Shukla, Surgan Jandial, Arun Ross

Michigan State University · Carnegie Mellon University

Direct Preference OptimizationVisual ReasoningVLM ReasoningMulti-Image ReasoningCurriculum LearningVision-Language Alignment
AskPDF
Apr 20, 2026

Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation

In text-to-image person retrieval tasks, the diversity of natural language expressions and the implicitness of visual semantics often lead to the problem of Expression Drift, where semantically equivalent texts exhibit significant feature discrepancies in the embedding space due to phrasing variations, thereby degrading the robustness of image-text alignment. This paper proposes a semantic compensation framework (MVR) driven by Large Language Models (LLMs), which enhances cross-modal representation consistency through multi-view semantic reformulation and feature compensation. The core methodology comprises three components: Multi-View Reformulation (MVR): A dual-branch prompting strategy combines key feature guidance (extracting visually critical components via feature similarity) and diversity-aware rewriting to generate semantically equivalent yet distributionally diverse textual variants; Textual Feature Robustness Enhancement: A training-free latent space compensation mechanism suppresses noise interference through multi-view feature mean-pooling and residual connections, effectively capturing "Semantic Echoes"; Visual Semantic Compensation: VLM generates multi-perspective image descriptions, which are further enhanced through shared text reformulation to address visual semantic gaps. Experiments demonstrate that our method can improve the accuracy of the original model well without training and performs SOTA on three text-to-image person retrieval datasets.

Chao Yuan, Yujian Zhao, Haoxuan Xu +1

Beihang University

VLM RobustnessVision-Language RetrievalVision-Language Alignment
AskPDF
Apr 20, 2026

When Vision-Language Models Judge Without Seeing: Exposing Informativeness Bias

The reliability of VLM-as-a-Judge is critical for the automatic evaluation of vision-language models (VLMs). Despite recent progress, our analysis reveals that VLM-as-a-Judge often pays limited attention to the image when making decisions. Instead, they often blindly favor the more informative answer, even when they can recognize it conflicts with the image content. We call this problem informativeness bias, which significantly undermines judge reliability. To address it, we propose BIRCH (Balanced Informativeness and CoRrectness with a Truthful AnCHor), a judging paradigm that first corrects inconsistencies with the image content in candidate answers, and then compares the answers against this corrected version. This shifts the judge's focus from informativeness to image-grounded correctness. Experiments on multiple models and benchmarks show that BIRCH reduces informativeness bias by up to 17%, resulting in performance gains of up to 9.8%. Our work reveals an overlooked but fundamental flaw in current VLM-as-a-Judge systems and highlights the need for more principled designs.

Xiaohan Zou, Roshan Sridhar, Mohammadtaher Safarzadeh +1

The Pennsylvania State University · Oracle AI

VLM EvaluationVision-Language AlignmentVision-Language Model-as-a-Judge
AskPDF
Apr 20, 2026

Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we propose the Dynamic Visual-semantic Alignment (DVSA), a robust ZSL framework for learning from ambiguous labels. DVSA uses a bidirectional visual-semantic alignment module with attention to mutually calibrate visual features and attribute prototypes, and a contrastive optimization grounded in Mutual Information (MI) at the attribute level to strengthen discriminative, semantically consistent attributes. In addition, a dynamic label disambiguation mechanism iteratively corrects noisy supervision while preserving semantic consistency, narrowing the instance-label gap, and improving generalization. Extensive experiments on standard benchmarks verify that DVSA achieves stronger performance under ambiguous supervision.

Jiangnan Li, Linqing Huang, Xiaowen Yan +3

College of Computer Science and Technology, Qingdao University · School of Computer Science, Shanghai JiaoTong University · Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)

Zero-Shot LearningNoisy-Label LearningVision-Language Alignment
AskPDF
Apr 19, 2026

Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an adversarial evaluation framework that quantifies this cross-modal dependency by measuring accuracy degradation (Drop) when semantically conflicting text is paired with unchanged images. Four adversarial strategies -- shape_swap, color_swap, position_swap, and random_text -- are applied to a controlled geometric-shapes dataset (n=1,000n{=}1{,}000). We compare three configurations: Baseline CLIP (ViT-B/32), LoRA fine-tuning, and LoRA Optimized (integrating Hard Negative Mining, Label Smoothing, layer-wise learning rates, Cosine Restarts, curriculum learning, and data augmentation). The optimized model reduces average Drop from 27.5% to 9.8% (64.4% relative improvement, p<0.001p{<}0.001) while maintaining 97% normal accuracy. Attention visualization and embedding-space analysis confirm that the optimized model attends more to visual features and achieves tighter cross-modal alignment.

Lijie Zhou

School of Computer Science University of Nottingham Ningbo China Ningbo, China

Cross-Modal LearningVLM RobustnessAdversarial Attacks on VLMsVision-Language ModelsVLM AdaptationAttention Mechanisms+3
AskPDF
Apr 18, 2026

Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition

Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction. A Motion Separation Module (MSM) separates motion-sensitive and global-static features, while a Motion Aggregation Block (MAB) employs gated cross-attention to refine motion representation without re-coupling redundant information. To facilitate generalization to unseen categories, we enforce semantic alignment between video features and textual representations by aligning projected embeddings with positive textual prompts, while leveraging negative prompts to explicitly model "non-class" semantics. Experiments on standard benchmarks demonstrate that our method consistently outperforms prior CLIP-based approaches, achieving robust zero-shot action recognition across both coarse and fine-grained datasets.

Yiming Wang, Frederick W. B. Li, Jingyun Wang

Department of Computer Science, Durham University

Representation LearningVideo Action RecognitionVideo Representation LearningMotion Representation LearningVision-Language AlignmentZero-Shot Action Recognition
AskPDF
Apr 18, 2026

MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation

Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This often leads to a modality gap between visual text inputs and textual inputs/outputs for image translation. Existing methods, primarily relying on instruction fine-tuning, risk parameter redundancy of pre-trained knowledge, hindering generalization performance. To address this, we introduce modality neuron-aware fine-tuning (MNAFT), a novel approach that takes advantage of the specialized roles of individual neurons within MLLMs for enhanced image translation. MNAFT identifies language-agnostic and language-specific neurons in both vision and language modules through an instruction-driven activation analysis, evaluating their importance in various translation tasks. We then perform selective fine-tuning, updating only the parameters of language-specific and language-agnostic neurons within the selected layers relevant to the target task, while preserving the knowledge encoded in other neurons and layers. Our extensive experiments on multiple benchmarks demonstrate that MNAFT significantly outperforms state-of-the-art image translation methods, including cascaded models, standard full fine-tuning, and parameter-efficient tuning techniques. Furthermore, we provide comprehensive analysis, including visualizations of neuron activations and clustering patterns, to offer insights into the roles of different neuron groups in mediating cross-modal understanding and facilitating accurate language-specific translation.

Bo Li, Ningyuan Deng, Tianyu Dong +3

School of Software, Tsinghua University, Beijing, China · Baidu Inc., Beijing, China · School of Information Resource Management, Renmin University of China,Beijing, China +2

Image Text TranslationFine-TuningVLM AdaptationMultimodal Large Language ModelsVision-Language AlignmentMachine Translation
AskPDF
Apr 17, 2026

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the correct image region corresponding to the question, they do not necessarily produce the correct answers. In this work, we demonstrate that this misalignment could be attributed to suboptimal information flow within VLMs, where text tokens distribute too much attention to irrelevant visual tokens, leading to incorrect answers. Based on the observation, we show that modulating the information flow during inference can improve the perception capability of VLMs. The idea is that text tokens should only be associated with important visual tokens during decoding, eliminating the interference of irrelevant regions. To achieve this, we propose a token dynamics-based method to determine the importance of visual tokens, where visual tokens that exhibit distinct activation patterns during different decoding stages are viewed as important. We apply our approach to representative open-source VLMs and evaluate on various datasets, including visual question answering, visual grounding and counting, optical character recognition, and object hallucination. The results show that our approach significantly improves the performance of baselines. Project page: https://cxliu0.github.io/AIF/.

Chengxin Liu, Wonseok Choi, Chenshuang Zhang +1

KAIST · POSTECH

Vision-Language AlignmentVLM Inference
AskPDF
Apr 17, 2026

PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding

Accurate open-vocabulary 3D scene understanding requires semantic representations that are both language-aligned and spatially precise at the pixel level, while remaining scalable when lifted to 3D space. However, existing representations struggle to jointly satisfy these requirements, and densely propagating pixel-wise semantics to 3D often results in substantial redundancy, leading to inefficient storage and querying in large-scale scenes. To address these challenges, we present PLAF, a Pixel-wise Language-Aligned Feature extraction framework that enables dense and accurate semantic alignment in 2D without sacrificing open-vocabulary expressiveness. Building upon this representation, we further design an efficient semantic storage and querying scheme that significantly reduces redundancy across both 2D and 3D domains. Experimental results show that PLAF provides a strong semantic foundation for accurate and efficient open-vocabulary 3D scene understanding. The codes are publicly available at https://github.com/RockWenJJ/PLAF.

Junjie Wen, Junlin He, Fei Ma +1

Pengcheng Laboratory, Shenzhen, 518108, China · The School of Intelligent Engineering, Sun Yat-Sen University-ShenzhenCampus, Shenzhen, Guangdong, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.

3D Scene Representation3D Representation LearningVision-Language Alignment3D Scene Understanding
AskPDF
Apr 17, 2026

Concept-wise Attention for Fine-grained Concept Bottleneck Models

Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept modeling. Existing methods often suffer from pre-training biases, manifested as granularity misalignment or reliance on structural priors. Moreover, fine-tuning with Binary Cross-Entropy (BCE) loss treats each concept independently, which ignores mutual exclusivity among concepts, leading to suboptimal alignment. To address these limitations, we propose Concept-wise Attention for Fine-grained Concept Bottleneck Models (CoAt-CBM), a novel framework that achieves adaptive fine-grained image-concept alignment and high interpretability. Specifically, CoAt-CBM employs learnable concept-wise visual queries to adaptively obtain fine-grained concept-wise visual embeddings, which are then used to produce a concept score vector. Then, a novel concept contrastive optimization guides the model to handle the relative importance of the concept scores, enabling concept predictions to faithfully reflect the image content and improved alignment. Extensive experiments demonstrate that CoAt-CBM consistently outperforms state-of-the-art methods. The codes will be available upon acceptance.

Minghong Zhong, Guoshuai Zou, Kanghao Chen +2

Sun Yat-sen University · Peng Cheng Laboratory · Key Laboratory of Machine Intelligence and Advanced Computing, MOE +1

Concept Bottleneck ModelsVision-Language Alignment
AskPDF
Apr 16, 2026

Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers a viable way to improve model capabilities without increasing model size or data requirements, making deployment more efficient. However, applying KD to VLMs is challenged by modality-specific supervision: although multimodal knowledge in VLMs is fused within the language space, current methods supervise each modality separately without explicitly addressing multimodal alignment, leading to inconsistent multimodal knowledge transfer. To address this, we propose Switch-KD, a visual-switch distillation framework that unifies vision-language knowledge transfer within a shared text-probability space. Switch-KD comprises two key components: (1) Visual-Switch Distillation, which switches the student's visual outputs into the teacher's language pathway to construct cross-modal probabilistic references for implicit visual knowledge transfer; and (2) Dynamic Bi-directional Logits Difference (DBiLD) loss, which adaptively aligns informative probability regions while preserving the distributional structures of teacher and student through bidirectional supervision. Guided by Switch-KD, a 0.5B TinyLLaVA effectively distills rich multimodal knowledge from its 3B teacher, yielding an average improvement of 3.6 points across 10 multimodal benchmarks without any architectural modification.

Haoyi Sun, Xiaoxiao Wang, Ning Mao +5

Li Auto Inc.

Cross-Modal Knowledge DistillationVision-Language ModelsVLM DistillationVision-Language AlignmentKnowledge Distillation
AskPDF
Apr 15, 2026

MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images

In diagnostic reports, experts encode complex imaging data into clinically actionable information. They describe subtle pathological findings that are meaningful in their anatomical context. Reports follow relatively consistent structures, expressing diagnostic information with few words that are often associated with tiny but consequential image observations. Standard vision language models struggle to identify the associations between these informative text components and small locations in the images. Here, we propose "MApLe", a multi-task, multi-instance vision language alignment approach that overcomes these limitations. It disentangles the concepts of anatomical region and diagnostic finding, and links local image information to sentences in a patch-wise approach. Our method consists of a text embedding trained to capture anatomical and diagnostic concepts in sentences, a patch-wise image encoder conditioned on anatomical structures, and a multi-instance alignment of these representations. We demonstrate that MApLe can successfully align different image regions and multiple diagnostic findings in free-text reports. We show that our model improves the alignment performance compared to state-of-the-art baseline models when evaluated on several downstream tasks. The code is available at https://github.com/cirmuw/MApLe.

Felicia Bader, Philipp Seeböck, Anastasia Bartashova +2

Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria · Comprehensive Center for Artificial Intelligence in Medicine, Medical University of Vienna, Austria · Medical Anomaly Detection (MANO) Group, Computational Imaging Research (CIR), Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria +1

Radiology VLMsVision-Language AlignmentText-Image AlignmentMedical Image Grounding
AskPDF
Apr 14, 2026

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding

Vision-Language Models demonstrate remarkable capabilities but often struggle with compositional reasoning, exhibiting vulnerabilities regarding word order and attribute binding. This limitation arises from a scarcity of informative samples needed to differentiate subtle semantic variations during contrastive pretraining. Although hard negative mining offers a promising remedy, existing methods lack explicit mechanisms to dictate which linguistic elements undergo modification. Instead of engineering generative architectures, this study establishes lexical concreteness as a fundamental determinant of negative sample efficacy. Modifying highly concrete terms generates more pronounced structural and visual discrepancies, providing a substantially stronger learning signal. Leveraging this principle, ConcretePlant is proposed to systematically isolate and manipulate perceptually grounded concepts. Analyses of the InfoNCE further reveals a severe gradient imbalance, where easily distinguishable pairs disproportionately overwhelm the optimization process and restrict the bandwidth available for nuanced learning. To resolve this degradation, the Cement loss is formulated utilizing a margin-based approach. By correlating psycholinguistic scores with sample difficulty, this objective dynamically calibrates the penalization applied to individual training pairs. Comprehensive evaluations substantiate these theoretical claims. The integrated framework, designated as Slipform, achieves state-of-the-art accuracy across diverse compositional evaluation benchmarks, general cross-modal retrieval, single and multi label linear probing.

Eun Woo Im, Dhruv Madhwal, Vivek Gupta

Arizona State University

Compositional Reasoning in VLMsVLM ReasoningContrastive LearningCompositional Representation LearningVision-Language AlignmentHard Negative Mining
AskPDF
Apr 14, 2026

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents, from browser automation and computer-use systems to camera-equipped embodied agents. In practice, the attack surface is heterogeneous: adversarial text appears at varying font sizes and under diverse visual conditions, while the growing ecosystem of VLMs exhibits substantial variation in vulnerability, complicating defensive approaches. Evaluating 1,000 prompts from SALAD-Bench across four VLMs, namely, GPT-4o, Claude Sonnet 4.5, Mistral-Large-3, and Qwen3-VL-4B-Instruct under varying font sizes (6--28px) and visual transformations (rotation, blur, noise, contrast changes), we find: (1) font size significantly affects attack success rate (ASR), with very small fonts (6px) yielding near-zero ASR while mid-range fonts achieve peak effectiveness; (2) text attacks are more effective than image attacks for GPT-4o (36% vs 8%) and Claude (47% vs 22%), while Qwen3-VL and Mistral show comparable ASR across modalities; (3) text-image embedding distance from two multimodal embedding models (JinaCLIP and Qwen3-VL-Embedding) shows strong negative correlation with ASR across all four models (r = -0.71 to -0.93, p < 0.01); (4) heavy degradations increase embedding distance by 10--12% and reduce ASR by 34--96%, while rotation asymmetrically affects models (Mistral drops 50%, GPT-4o unchanged). These findings highlight that model-specific robustness patterns preclude one-size-fits-all defenses and offer empirical guidance for practitioners selecting VLM backbones for agentic systems operating in adversarial environments.

Ravikumar Balakrishnan, Sanket Mendapara, Ankit Garg

Cisco Systems

Adversarial Attacks on VLMsVLM RobustnessAdversarial Text AttacksVision-Language Alignment
AskPDF
Apr 13, 2026

TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability that these models still struggle with is aligning dense patch representations with text embeddings of corresponding concepts. In this work, we investigate this critical issue and propose novel techniques to enhance this capability in foundational vision-language models. First, we reveal that a patch-level distillation procedure significantly boosts dense patch-text alignment -- surprisingly, the patch-text alignment of the distilled student model strongly surpasses that of the teacher model. This observation inspires us to consider modifications to pretraining recipes, leading us to propose iBOT++, an upgrade to the commonly-used iBOT masked image objective, where unmasked tokens also contribute directly to the loss. This dramatically enhances patch-text alignment of pretrained models. Additionally, to improve vision-language pretraining efficiency and effectiveness, we modify the exponential moving average setup in the learning recipe, and introduce a caption sampling strategy to benefit from synthetic captions at different granularities. Combining these components, we develop TIPSv2, a new family of image-text encoder models suitable for a wide range of downstream applications. Through comprehensive experiments on 9 tasks and 20 datasets, we demonstrate strong performance, generally on par with or better than recent vision encoder models. Code and models are released via our project page at https://gdm-tipsv2.github.io/ .

Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis +16

Google DeepMind · xAI · Epsilon Health +1

Vision-Language PretrainingVision-Language AlignmentMasked Image ModelingVLM Distillation
AskPDF
Apr 13, 2026

Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations than from the standard inference protocol based on global cosine similarity. First, through controlled diagnostic experiments, we show that explicitly enforcing fine-grained region-segment alignment at inference dramatically improves compositional performance without updating pretrained encoders. We then introduce a lightweight transformer that learns such alignments directly from frozen patch and token embeddings. Comparing against full fine-tuning and prior end-to-end compositional training methods, we find that although these approaches improve in-domain retrieval, their gains do not consistently transfer under distribution shift. In contrast, learning localized alignment over frozen representations matches full fine-tuning on in-domain retrieval while yielding substantial improvements on controlled out-of-domain compositional benchmarks. These results identify global embedding matching as a key bottleneck in dual-encoder VLMs and highlight the importance of alignment mechanisms for robust compositional generalization.

Imanol Miranda, Ander Salaberria, Eneko Agirre +1

HiTZ Center – Ixa, University of the Basque Country (UPV/EHU)

Compositional Reasoning in VLMsVision-Language ModelsVLM InferenceVision-Language AlignmentVLM Robustness
AskPDF
Apr 13, 2026

Anthropogenic Regional Adaptation in Multimodal Vision-Language Model

While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedicated framework for assessing human-centric alignment in vision-language systems. We offer two contributions to address this gap. First, we introduce Anthropogenic Regional Adaptation: a novel paradigm that aims to optimize model relevance to specific regional contexts while ensuring the retention of global generalization capabilities. Second, we present a simple, but effective adaptation method named Geographical-generalization-made-easy (GG-EZ), which utilizes regional data filtering and model merging. Through comprehensive experiments on 3 VL architectures: large vision-language models, text-to-image diffusion models, and vision-language embedding models, and a case study in Southeast Asia (SEA) regional adaptation, we demonstrate the importance of Anthropogenic Regional Adaptation and the effectiveness of GG-EZ, showing 5-15% gains in cultural relevance metrics across SEA while maintaining over 98% of global performance and even occasionally surpassing it. Our findings establish Anthropogenic Regional Alignment as a foundational paradigm towards applicability of multimodal vision-language models in diverse regions and demonstrate a simple-yet-effective baseline method that optimizes regional value alignment while preserving global generalization.

Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong +45

VLM AdaptationVision-Language Alignment
AskPDF
Apr 13, 2026

MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration

Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates medical prior knowledge and designs a feature-level region prompt integration mechanism, enabling it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions. We pre-train the model on a meticulously constructed large-scale dataset (containing over 6.4 million medical images and 97.3 million region-level annotations), equipping it with cross-disease and cross-modality fine-grained spatial semantic understanding capabilities. Experiments demonstrate that MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.

Jiahui Peng, He Yao, Jingwen Li +9

aSichuan University, Chengdu, 610065, China · bXinjiang University, Urumqi, 830046, China · cAlibaba Group, Hangzhou, 310023, China +3

Promptable Image SegmentationMultimodal PretrainingMedical VLMsMedical Image GroundingVision-Language Alignment
AskPDF
Apr 12, 2026

Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization

Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes. While recent NGCG methods commonly rely on CLIP-style dual-encoder architectures, they often suffer from weak cross-modal generalization and require complex architectural designs. In contrast, Multimodal Large Language Models (MLLMs) offer powerful semantic reasoning capabilities but are not directly optimized for retrieval tasks. In this work, we present a simple yet effective framework to adapt MLLMs for NGCG via parameter-efficient finetuning. Our approach optimizes latent representations within the MLLM while preserving its pretrained multimodal knowledge, enabling strong cross-modal alignment without redesigning model architectures. Through systematic analysis of diverse variables, from model backbone to feature aggregation, we provide practical and generalizable insights for leveraging MLLMs in NGCG. Our method achieves SOTA on GeoText-1652 with a 12.2% improvement in Text-to-Image Recall@1 and secures top performance in 5 out of 12 subtasks on CVG-Text, all while surpassing baselines with far fewer trainable parameters. These results position MLLMs as a robust foundation for semantic cross-view retrieval and pave the way for MLLM-based NGCG to be adopted as a scalable, powerful alternative to traditional dual-encoder designs. Project page and code are available at https://yuqichen888.github.io/NGCG-MLLMs-web/.

Yuqi Chen, Xiaohan Zhang, Ahmad Arrabi +3

Vermont Artificial Intelligence Lab, Department of Computer Science, University of Vermont · Intelligent Machines Lab, Department of Artificial Intelligence, Information Technology University · Institute of Artificial Intelligence, University of Central Florida

Cross-View Geo-LocalizationVision-Language RetrievalMultimodal Large Language ModelsVision-Language Alignment
AskPDF
Apr 10, 2026

See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment

Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding is disproportionately drawn to visually dominant or frequently occurring content. We observe that this inequity in attention allocation is a root cause of object hallucination: when rare, small, or contextually peripheral objects receive insufficient attention, the model fails to ground its generation in the full visual scene. We argue that every object in an image, regardless of its size, frequency or visual salience, deserves equal representational opportunity during decoding. To this end, we propose DOP-OBC, a training-free and architecture-agnostic decoding strategy built on the principle of equitable attention. Two complementary object-aware signals work in tandem: a Dominant Object Penalty (DOP) that softly suppresses attention over-concentration on visually dominant regions, and an Outlier Boost Coefficient (OBC) that amplifies attention toward rare yet confidently detected objects. These signals are injected as per-row logit modulations within the causal attention mask, requiring no weight updates and preserving autoregressive decoding properties. Extensive experiments across image and video MLLMs demonstrate consistent reductions in object hallucination on CHAIR and POPE benchmarks, alongside improvements in GPT-4o assessed captioning quality across correctness, consistency, detail, context and temporal dimensions. DOP-OBC establishes that fairness in attention allocation is not merely a design principle but a practical and effective path toward more faithful multimodal generation.

Mohammad Anas Azeez, Ankan Deria, Zohaib Hasan Siddiqui +5

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia · Macquarie University, Sydney, Australia +2

VLM Hallucination MitigationObject Hallucination in VLMsVision-Language GroundingVision-Language Alignment
AskPDF
Apr 10, 2026

UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation

Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label supervision. We propose UniSemAlign, a dual-modal semantic alignment framework that enhances visual segmentation by injecting explicit class-level structure into pixel-wise learning. Built upon a pathology-pretrained Transformer encoder, UniSemAlign introduces complementary prototype-level and text-level alignment branches in a shared embedding space, providing structured guidance that reduces class ambiguity and stabilizes pseudo-label refinement. The aligned representations are fused with visual predictions to generate more reliable supervision for unlabeled histopathology images. The framework is trained end-to-end with supervised segmentation, cross-view consistency, and cross-modal alignment objectives. Extensive experiments on the GlaS and CRAG datasets demonstrate that UniSemAlign substantially outperforms recent semi-supervised baselines under limited supervision, achieving Dice improvements of up to 2.6% on GlaS and 8.6% on CRAG with only 10% labeled data, and strong improvements at 20% supervision. Code is available at: https://github.com/thailevann/UniSemAlign

Le-Van Thai, Tien Dat Nguyen, Hoai Nhan Pham +3

AI VIETNAM Lab, Vietnam · Hanoi University of Science and Technology, Vietnam

Histopathology Image SegmentationSemi-Supervised Medical Image SegmentationComputational PathologyPrototype-Based LearningVision-Language Alignment
AskPDF
Apr 9, 2026

InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding

Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions to specific spatial-temporal regions. To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions. On the InstVL benchmark, InstAP substantially outperforms existing VLP models on instance-level retrieval, and also surpasses a strong VLP baseline trained on the exact same data corpus, isolating the benefit of our instance-aware objective. Moreover, instance-centric pre-training improves global understanding: InstAP achieves competitive zero-shot performance on multiple video benchmarks, including MSR-VTT and DiDeMo. Qualitative visualizations further show that InstAP localizes textual mentions to the correct instances, while global-only models exhibit more diffuse, scene-level attention.

Ashutosh Kumar, Rajat Saini, Jingjing Pan +5

Woven by Toyota

Vision-Language PretrainingVision-Language AlignmentVision-Language Grounding
AskPDF
Apr 9, 2026

DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing

Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models (VLMs), because sequential edits can lead to degraded reasoning and cross modal misalignment. Existing VLM knowledge editing methods based on gated adapters, activation edits, and parameter merging techniques address catastrophic forgetting seen in full fine tuning; however, they still operate in the shared representation space of the VLM, where concepts are entangled, so edits interfere with other non relevant concepts. We hypothesize that this instability persists because current methods algorithmically control edits via optimization rather than structurally separating knowledge. We introduce Dynamic Subspace Concept Alignment (DSCA) which by design mitigates this limitation by decomposing the representation space into a set of orthogonal semantic subspaces and proposing edits only in those transformed spaces. These subspaces are obtained through incremental clustering and PCA on joint vision language representations. This process structurally isolates concepts, enabling precise, non interfering edits by turning isolation from a soft training objective into an architectural property. The surgical edits are guided by a multi term loss function for maintaining task fidelity, edit locality, and cross modal alignment. With the base model frozen, our method achieves 98 percent single edit success, remains over 95 percent after 1000 sequential edits, lowers hallucination by 3 to 5 percent, and achieves the best backward transfer (BWT) scores on continual instruction tuning benchmarks. Extensive experiments demonstrate DSCA state of the art stability and knowledge retention capability in continual lifelong editing across various datasets and benchmarks.

Gyanendra Das, Sai Satyam Jena

Zynix AI, FL, USA

Continual Learning for VLMsVision-Language Alignment
AskPDF
Apr 7, 2026

MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models

Medical Vision-Language Models (Med-VLMs) have achieved expert-level proficiency in interpreting diagnostic imaging. However, current models are predominantly trained on professional literature, limiting their ability to communicate findings in the lay register required for patient-centered care. While text-centric research has actively developed resources for simplifying medical jargon, there is a critical absence of large-scale multimodal benchmarks designed to facilitate lay-accessible medical image understanding. To bridge this resource gap, we introduce MedLayBench-V, the first large-scale multimodal benchmark dedicated to expert-lay semantic alignment. Unlike naive simplification approaches that risk hallucination, our dataset is constructed via a Structured Concept-Grounded Refinement (SCGR) pipeline. This method enforces strict semantic equivalence by integrating Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) with micro-level entity constraints. MedLayBench-V provides a verified foundation for training and evaluating next-generation Med-VLMs capable of bridging the communication divide between clinical experts and patients.

Han Jang, Junhyeok Lee, Heeseong Eum +1

Seoul National University · Department of Radiology, Seoul National University Hospital · The Advanced Imaging and Computational Neuroimaging (AICON) Laboratory +2

HealthcareMedical VLMsVision-Language AlignmentClinical NLPMedical Image Benchmarks
AskPDF
Apr 7, 2026

Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment

Achieving robot transparency is a critical step toward effective human-robot collaboration. To be transparent, a robot's natural language communication must be consistent with its actions and explicitly grounded in the task and environment. Existing hierarchical Vision-Language-Action (VLA) models can generate language (e.g., through chain-of-thought) and low-level actions. However, current work does not consider explicit alignment between these modalities during training. To address this crucial gap, we propose a novel training framework that explicitly grounds hierarchical VLA sub-task descriptions with respect to the visual observation and action space. Our framework uses a contrastive model to assess the alignment between generated language and corresponding action trajectories. This contrastive model enables direct ranking of different language-trajectory pairs based on their alignment, allowing us to refine the grounding of our hierarchical VLA through offline preference learning. We apply our framework to the LanguageTable dataset, a benchmark dataset of human language-annotated trajectories, and provide critical insights into multimodal grounding representations, all while establishing a strong baseline that achieves performance comparable to fully supervised fine-tuning and minimizing the need for costly data annotations.

Theodor Wulff, Federico Tavella, Rahul Singh Maharjan +2

The University of Manchester, Manchester, United Kingdom

Vision-Language-Action ModelsVision-Language Alignment
AskPDF
Apr 7, 2026

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling

Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque "black boxes." To bridge this gap, we propose VL-MDR (Vision-Language Multi-Dimensional Reward), a framework that dynamically decomposes evaluation into granular, interpretable dimensions. Instead of outputting a monolithic scalar, VL-MDR employs a visual-aware gating mechanism to identify relevant dimensions and adaptively weight them (e.g., Hallucination, Reasoning) for each specific input. To support this, we curate a dataset of 321k vision-language preference pairs annotated across 21 fine-grained dimensions. Extensive experiments show that VL-MDR consistently outperforms existing open-source reward models on benchmarks like VL-RewardBench. Furthermore, we show that VL-MDR-constructed preference pairs effectively enable DPO alignment to mitigate visual hallucinations and improve reliability, providing a scalable solution for VLM alignment.

Qiyuan Chen, Hongsen Huang, Jiahe Chen +6

Zhejiang University · Soochow Securities Co.,Ltd. · HKUST(GZ) +1

Multimodal Reward ModelingVision-Language AlignmentVLM Interpretability
AskPDF
Apr 6, 2026

Spatially-Weighted CLIP for Street-View Geo-localization

This paper proposes Spatially-Weighted CLIP (SW-CLIP), a novel framework for street-view geo-localization that explicitly incorporates spatial autocorrelation into vision-language contrastive learning. Unlike conventional CLIP-based methods that treat all non-matching samples as equally negative, SW-CLIP leverages Tobler's First Law of Geography to model geographic relationships through distance-aware soft supervision. Specifically, we introduce a location-as-text representation to encode geographic positions and replace one-hot InfoNCE targets with spatially weighted soft labels derived from geodesic distance. Additionally, a neighborhood-consistency regularization is employed to preserve local spatial structure in the embedding space. Experiments on a multi-city dataset demonstrate that SW-CLIP significantly improves geo-localization accuracy, reduces long-tail errors, and enhances spatial coherence compared to standard CLIP. The results highlight the importance of shifting from semantic alignment to geographic alignment for robust geo-localization and provide a general paradigm for integrating spatial principles into multimodal representation learning.

Ting Han, Fengjiao Li, Chunsong Chen +3

School of Geospatial Engineering and Science, Sun Yat-Sen University, Zhuhai, China · School of System Science and Engineering, Sun Yat-Sen University, Guangzhou, China

Geospatial Representation LearningVisual Place RecognitionContrastive LearningVision-Language Alignment
AskPDF
Apr 2, 2026

Steerable Visual Representations

Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representations, a new class of visual representations, whose global and local features can be steered with natural language. While most vision-language models (e.g., CLIP) fuse text with visual features after encoding (late fusion), we inject text directly into the layers of the visual encoder (early fusion) via lightweight cross-attention. We introduce benchmarks for measuring representational steerability, and demonstrate that our steerable visual features can focus on any desired objects in an image while preserving the underlying representation quality. Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination, exhibiting zero-shot generalization to out-of-distribution tasks.

Jona Ruthardt, Manu Gaur, Deva Ramanan +2

University of Technology Nuremberg · Carnegie Mellon University · International Institute of Information Technology, Hyderabad

Visual Representation LearningVision-Language Alignment
AskPDF
Apr 2, 2026

ProVG: Progressive Visual Grounding via Language Decoupling for Remote Sensing Imagery

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit fine-grained linguistic cues, such as spatial relations and object attributes, that are crucial for distinguishing objects with similar characteristics. Importantly, these cues play distinct roles across different grounding stages and should be leveraged accordingly to provide more explicit guidance. In this work, we propose ProVG, a novel RSVG framework that improves localization accuracy by decoupling language expressions into global context, spatial relations, and object attributes. To integrate these linguistic cues, ProVG employs a simple yet effective progressive cross-modal modulator, which dynamically modulates visual attention through a survey-locate-verify scheme, enabling coarse-to-fine vision-language alignment. In addition, ProVG incorporates a cross-scale fusion module to mitigate the large-scale variations in remote sensing imagery, along with a language-guided calibration decoder to refine cross-modal alignment during prediction. A unified multi-task head further enables ProVG to support both referring expression comprehension and segmentation tasks. Extensive experiments on two benchmarks, i.e., RRSIS-D and RISBench, demonstrate that ProVG consistently outperforms existing methods, achieving new state-of-the-art performance.

Ke Li, Ting Wang, Di Wang +4

Xidian University, China · UC San Diego, USA · SUST, China

Remote Sensing Visual GroundingRemote Sensing VLMsVision-Language AlignmentReferring Expression Segmentation
AskPDF