VLM Adaptation

VLM: Vision-Language Model

Ask about this topic

Overview

Vision-language model adaptation studies how to specialize pretrained models such as CLIP and instruction-tuned multimodal large language models when target data, labels, or compute are limited. Common approaches include prompt tuning, LoRA and lightweight adapters, domain-specific fine-tuning, and test-time methods that use unlabeled examples or prediction memories; newer work also adapts models for video, medical imaging, remote sensing, and robotics. Evaluation often tests few-shot transfer, base-to-novel classes, cross-dataset generalization, robustness to distribution shift, and retention of the model’s original abilities. A central tension is that stronger specialization can cause forgetting, miscalibration, or reliance on language shortcuts, while conservative updates may preserve generality but limit task gains.

Latest papers

CardsList

546 papers41 papers in the last four weeks, down 13% on the four weeks before. 0.2% of all new papers.

Mar 30, 2026

CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition

Personalization in emotion recognition (ER) is essential for accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs), such as CLIP, demonstrate strong potential for leveraging joint image-text representations in ER. However, existing CLIP-based methods either rely on CLIP's contrastive pretraining or use LLMs to generate descriptive text prompts, which can be noisy, computationally expensive, and often fail to capture fine-grained expressions, leading to degraded performance. In this work, Action Units (AUs) are leveraged as structured textual prompts within CLIP to model fine-grained facial expressions. AUs encode the subtle muscle activations underlying expressions, providing localized and interpretable semantic cues for more robust facial expression recognition (FER). We introduce CLIP-AU, a lightweight AU-guided temporal learning method that integrates interpretable AU semantics into CLIP. It learns generic, subject-agnostic representations by aligning AU prompts with facial dynamics, enabling fine-grained FER without CLIP fine-tuning or LLM-generated text supervision. Although CLIP-AU models fine-grained AU semantics, it does not adapt to subject-specific variability in subtle expressions. To address this limitation, we propose CLIP-AUTT, a video-based test-time personalization method that dynamically adapts AU prompts to videos from unseen subjects. By combining entropy-guided temporal window selection with prompt tuning, CLIP-AUTT enables subject-specific adaptation while preserving temporal consistency. Our experiments on three challenging video-based datasets, BioVid, StressID, and BAH, indicate that CLIP-AU and CLIP-AUTT outperform state-of-the-art CLIP-based FER and TTA methods.

Muhammad Osama Zeeshan, Masoumeh Sharafi, Benoit Savary +3

LIVIA, ILLS, Dept. of Systems Engineering, ETS Montreal, Canada · Dept. of Computer Science, École Polytechnique, Paris, France · LIVIA, Dept. of Software and IT Engineering, ETS Montreal, Canada

VLM AdaptationFacial Expression RecognitionTemporal Video Understanding
AskPDF
Mar 27, 2026

Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation

Supervised fine-tuning (SFT) on visual instruction data often improves perceptual capabilities in vision-language models (VLMs) while degrading reasoning performance, creating a persistent reasoning tax during post-training. We investigate whether this degradation is related to disrupted access to depth-wise representations, and find that even fixed cross-depth aggregation substantially restores reasoning, suggesting that preserved cross-depth access is an important missing factor in VLM fine-tuning. Building on this observation, we propose Input-Adaptive Depth Aggregation (IADA), a lightweight mechanism that makes cross-depth retrieval input-adaptive, modality-aware, and efficiently parameterized through a low-rank bottleneck. On Qwen3-VL-2B, IADA improves the average reasoning score by 9.5 points and the average perception score by 3.33.3 points over LoRA-only fine-tuning with only 0.14M additional parameters, with the strongest gains appearing in parameter-efficient low-rank settings.

Yiming Ren, Yujiu Yang, Junjie Wang

Tsinghua University

VLM AdaptationVLM ReasoningLarge Vision-Language ModelsPEFT of VLMs
AskPDF
Mar 26, 2026

SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding

Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific fine-tuning indispensable. This fine-tuning causes models to memorize dataset-specific shortcuts rather than faithfully grounding in the actual visual content, leading to poor Out-of-Domain (OOD) generalization. Object-centric learning offers a promising remedy by decomposing scenes into entity-level representations, but existing approaches require re-running the entire multi-stage training pipeline from scratch. We propose SlotVTG, a framework that steers MLLMs toward object-centric, input-grounded visual reasoning at minimal cost. SlotVTG introduces a lightweight slot adapter that decomposes visual tokens into abstract slots via slot attention and reconstructs the original sequence, where objectness priors from a self-supervised vision model encourage semantically coherent slot formation. Cross-domain evaluation on standard VTG benchmarks demonstrates that our approach significantly improves OOD robustness while maintaining competitive In-Domain (ID) performance with minimal overhead.

Jiwook Han, Geo Ahn, Youngrae Kim +1

Kyung Hee University · University of Southern California

Temporal Video GroundingVLM AdaptationOOD GeneralizationObject-Centric Representation Learning
AskPDF
Mar 25, 2026

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition

As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on activations, making them dataset-dependent, vulnerable to data bias, and often restricted to coarse head-level explanations. We introduce SITH (Semantic Inspection of Transformer Heads), a fully data-free, training-free framework that directly analyzes CLIP's vision transformer in weight space. For each attention head, we decompose its value-output matrix into singular vectors and interpret each one via COMP (Coherent Orthogonal Matching Pursuit), a new algorithm that explains them as sparse, semantically coherent combinations of human-interpretable concepts. We show that SITH yields coherent, faithful intra-head explanations, validated through reconstruction fidelity and interpretability experiments. This allows us to use SITH for precise, interpretable weight-space model edits that amplify or suppress specific concepts, improving downstream performance without retraining. Furthermore, we use SITH to study model adaptation, showing how fine-tuning primarily reweights a stable semantic basis rather than learning entirely new features.

Francesco Gentile, Nicola Dall'Asen, Francesco Tonini +3

University of Trento · University of Pisa · Fondazione Bruno Kessler

Transformer InterpretabilityVLM InterpretabilityNeural Network InterpretabilityConcept-Based ExplanationsVLM Adaptation
AskPDF
Mar 25, 2026

Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification

Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that exploiting few-shot image embeddings from a training set is effective for CLIP-based classification. In this work, we analyze mixing image and text prototypes from a bias-variance perspective and show that mixing prototypes acts like a variance shrinkage estimator. Naively mixing text and image prototypes combines two partially aligned spaces since the two modalities are not perfectly aligned. To address this, we project image prototypes onto the principal directions of the semantic text embedding space to obtain a task-semantic image subspace. Mixing the image prototypes with text embeddings in the task-semantic subspace improves few-shot classification. However, when the task-semantic subspace captures insufficient discriminative visual information, relying on this subspace alone can be suboptimal. On extensive experiments over several few-shot classification benchmarks, we show that combining a task-semantic mixed prototype classifier and an anisotropic image-specific classifier systematically outperforms existing methods.

Dipam Goswami, Simone Magistri, Gido M. van de Ven +4

Department of Computer Science, Universitat Autònoma de Barcelona, Spain · Computer Vision Center, Barcelona, Spain · Media Integration and Communication Center, University of Florence, Italy +3

Prototype-Based LearningVLM AdaptationVision-Language AlignmentFew-Shot Image Classification
AskPDF
Mar 25, 2026

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming against CLIP-based methods. Notably, this gap is surprising because many LVLMs use CLIP-pretrained vision encoders. Yet LVLMs are not inherently limited by CLIP's architecture with independent vision and text encoders. In CLIP, this separation biases classification toward class-name matching rather than joint visual-text reasoning. In this paper we show that, despite their poor raw performance, LVLMs can improve visual feature class separability at inference using prompt conditioning, and LVLMs' internal representations, especially attention heads, can outperform the model itself at zero-shot and few-shot classification. We introduce Head Ensemble Classifiers (HEC) to bridge the performance gap between CLIP-based and LVLM-based classification methods. Inspired by Gaussian Discriminant Analysis, HEC ranks the most discriminative vision and text heads and combines them into a training-free classifier. We show that HEC achieves state-of-the-art performance in few-shot and zero-shot classification across 12 datasets.

Adhemar de Senneville, Xavier Bou, Jérémy Anger +2

Université Paris-Saclay, CNRS, ENS Paris-Saclay, Centre Borelli, France · École Polytechnique, AMIAD, France · Institut Universitaire de France

Large Vision-Language ModelsZero-Shot Image ClassificationFew-Shot Image ClassificationVLM Adaptation
AskPDF
Mar 24, 2026

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new challenge: each window is processed independently, leading to semantic discrepancy across windows. To address this issue, we propose Global-Local Aligned CLIP~(GLA-CLIP), a framework that facilitates comprehensive information exchange across windows. Rather than limiting attention to tokens within individual windows, GLA-CLIP extends key-value tokens to incorporate contextual cues from all windows. Nevertheless, we observe a window bias: outer-window tokens are less likely to be attended, since query features are produced through interactions within the inner window patches, thereby lacking semantic grounding beyond their local context. To mitigate this, we introduce a proxy anchor, constructed by aggregating tokens highly similar to the given query from all windows, which provides a unified semantic reference for measuring similarity across both inner- and outer-window patches. Furthermore, we propose a dynamic normalization scheme that adjusts attention strength according to object scale by dynamically scaling and thresholding the attention map to cope with small-object scenarios. Moreover, GLA-CLIP can be equipped on existing methods and broad their receptive field. Extensive experiments validate the effectiveness of GLA-CLIP in enhancing training-free open-vocabulary semantic segmentation performance. Code is available at https://github.com/2btlFe/GLA-CLIP.

ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun +3

Sungkyunkwan University

Open-Vocabulary Semantic SegmentationSliding-Window AttentionAttention MechanismsVLM AdaptationVision-Language Alignment
AskPDF
Mar 24, 2026

Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation

Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transferable knowledge is limited to the predictions of a black-box source model. Existing approaches exploit such knowledge via pseudo-label refinement or by leveraging vision-language models (ViLs), but they often fail to reconcile the inherent discrepancy between task-specific knowledge from black-box models and language-aligned semantic priors of ViLs, resulting in suboptimal integration and degraded adaptation performance. To address this challenge, we propose adaptive Dual-Teacher Distillation with Subnetwork Rectification (DDSR), a framework that explicitly reconciles these complementary yet inconsistent knowledge sources. DDSR employs an adaptive prediction fusion strategy to integrate predictions from the black-box source model and a ViL, generating reliable pseudo-labels for the target domain. A subnetwork-based regularization mechanism mitigates overfitting to noisy supervision by enforcing output consistency and gradient divergency. Furthermore, progressively improved target predictions iteratively refine both pseudo-labels and ViL prompts, enhancing semantic alignment. Finally, class-wise prototypes are used to further optimize target predictions via self-training. Extensive experiments on multiple benchmark datasets demonstrate that DDSR consistently outperforms state-of-the-art methods, including those with access to source data or source model parameters.

Zhe Zhang, Jing Li, Wanli Xue +4

School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China. · School of Artificial Intelligence, Tianjin University, Tianjin 300350, China

Source-Free Domain AdaptationKnowledge DistillationVLM DistillationVLM Adaptation
AskPDF
Mar 22, 2026

CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language Models

Multimodal large language models (MLLMs) achieve remarkable progress in cross-modal perception and reasoning, yet a fundamental question remains unresolved: should the vision encoder be fine-tuned or frozen? Despite the success of models such as LLaVA and Qwen-VL, inconsistent design choices and heterogeneous training setups hinder a unified understanding of visual fine-tuning (VFT) in MLLMs. Through a configuration-aligned benchmark, we find that existing VFT methods fail to consistently outperform the frozen baseline across multimodal tasks. Our analysis suggests that this instability arises from visual preference conflicts, where the context-agnostic nature of vision encoders induces divergent parameter updates under diverse multimodal context. To address this issue, we propose the Context-aware Visual Fine-tuning (CoVFT) framework, which explicitly incorporates multimodal context into visual adaptation. By integrating a Context Vector Extraction (CVE) and a Contextual Mixture-of-Experts (CoMoE) module, CoVFT decomposes conflicting optimization signals and enables stable, context-sensitive visual updates. Extensive experiments on 12 multimodal benchmarks demonstrate that CoVFT achieves state-of-the-art performance with superior stability. Notably, fine-tuning a 7B MLLM with CoVFT surpasses the average performance of its 13B counterpart, revealing substantial untapped potential in visual encoder optimization within MLLMs.

Nan Zhou, Huiqun Wang, Yaoyan Zheng +1

State Key Laboratory of Complex and Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University

VLM AdaptationMultimodal Large Language ModelsMultimodal Learning
AskPDF
Mar 22, 2026

SkinCLIP-VL: Consistency-Aware Vision-Language Learning for Multimodal Skin Cancer Diagnosis

The deployment of vision-language models (VLMs) in dermatology is hindered by the trilemma of high computational costs, extreme data scarcity, and the black-box nature of deep learning. To address these challenges, we present SkinCLIP-VL, a resource-efficient framework that adapts foundation models for trustworthy skin cancer diagnosis. Adopting a frozen perception, adaptive reasoning paradigm, we integrate a frozen CLIP encoder with a lightweight, quantized Qwen2.5-VL via low-rank adaptation (LoRA). To strictly align visual regions with clinical semantics under long-tailed distributions, we propose the Consistency-aware Focal Alignment (CFA) Loss. This objective synergizes focal re-weighting, semantic alignment, and calibration. On ISIC and Derm7pt benchmarks, SkinCLIP-VL surpasses 13B-parameter baselines by 4.3-6.2% in accuracy with 43% fewer parameters. Crucially, blinded expert evaluation and out-of-distribution testing confirm that our visually grounded rationales significantly enhance clinical trust compared to traditional saliency maps.

Zhixiang Lu, Shijie Xu, Kaicheng Yan +6

Xi’an Jiaotong-Liverpool University, China · University of Liverpool, United Kingdom

Medical VLMsVLM AdaptationSkin Lesion ClassificationDermatologyVision-Language AlignmentVLM Calibration
AskPDF
Mar 20, 2026

Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning

Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization. To address this, we propose Chain-of-Adaptation (CoA), an adaptation framework designed to integrate domain knowledge while maintaining the model's inherent reasoning and perceptual capabilities. CoA introduces a structured reasoning format that enhances domain alignment without sacrificing general multimodal competence by reinforcement learning. Experiments on standard surgical benchmarks, under both in-distribution and out-of-distribution settings, demonstrate that CoA achieves higher accuracy, stronger generalization, and more stable behavior than supervised fine-tuning. Furthermore, ablation studies confirm that CoA effectively preserves the model's core visual-language abilities, providing a reliable pathway for domain specialization in VLMs.

Jiajie Li, Chenhui Xu, Meihuan Liu +1

University at Buffalo Buffalo, NY, USA

VLM AdaptationMedical VLMsVLM ReasoningRL for VLMs
AskPDF
Mar 19, 2026

CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models

Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored. Prior robustness evaluations often assume clean, curated inputs or study isolated corruptions, overlooking routine acquisition, reconstruction, display, and delivery operations that preserve clinical readability while shifting image statistics. To address this gap, we propose CoDA, a chain-of-distribution framework that constructs clinically plausible pipeline shifts by composing acquisition-like shading, reconstruction and display remapping, and delivery and export degradations. Under masked structural-similarity constraints, CoDA jointly optimizes stage compositions and parameters to induce failures while preserving visual plausibility. Across brain MRI, chest X-ray, and abdominal CT, CoDA substantially degrades the zero-shot performance of CLIP-style MVLMs, with chained compositions consistently more damaging than any single stage. We also evaluate multimodal large language models (MLLMs) as technical-authenticity auditors of imaging realism and quality rather than pathology. Proprietary multimodal models show degraded auditing reliability and persistent high-confidence errors on CoDA-shifted samples, while the medical-specific MLLMs we test exhibit clear deficiencies in medical image quality auditing. Finally, we introduce a post-hoc repair strategy based on teacher-guided token-space adaptation with patch-level alignment, which improves accuracy on archived CoDA outputs. Overall, our findings characterize a clinically grounded threat surface for MVLM deployment and show that lightweight alignment improves robustness in deployment.

Xiang Chen, Fangfang Yang, Chunlei Meng +6

Medical Image Quality AssessmentVLM RobustnessMedical VLMsAdversarial Attacks on VLMsMedical Image AnalysisVLM Adaptation
AskPDF
Mar 18, 2026

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important regions in source domains. Although current works have demonstrated CLIP's shortcomings in capturing local subtle patterns, in this paper, we find that the domain gap and scarce training data further exacerbate such shortcomings, much more than that of holistic patterns, which we call the local misalignment problem in CLIP-based CDFSL. To address this problem, due to the lack of supervision in aligning local visual features and text semantics, we turn to self-supervision information. Inspired by the translation task, we propose the CC-CDFSL method with cycle consistency, which translates local visual features into text features and then translates them back into visual features (and vice versa), and constrains the original features close to the translated back features. To reduce the noise imported by richer information in the visual modality, we further propose a Semantic Anchor mechanism, which first augments visual features to provide a larger corpus for the text-to-image mapping, and then shrinks the image features to filter out irrelevant image-to-text mapping. Extensive experiments on various benchmarks, backbones, and fine-tuning methods show we can (1) effectively improve the local vision-language alignment, (2) enhance the interpretability of learned patterns and model decisions by visualizing patches, and (3) achieve state-of-the-art performance.

Yaze Zhao, Yixiong Zou, Yuhua Li +1

School of Computer Science and Technology, Huazhong University of Science and Technology

Cycle ConsistencySource-Free Cross-Domain Few-Shot LearningFew-Shot LearningFew-Shot Domain AdaptationVLM AdaptationVision-Language Alignment+1
AskPDF
Mar 18, 2026

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters

Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity auxiliary Heterogeneous Graph Teacher that operates solely during training. This teacher (i) integrates multi-scale visual patches and text prompts into a unified graph, (ii) performs deep cross-modal reasoning via a Modality-aware Graph Transformer (MGT), and (iii) applies discriminative node filtering to extract high-fidelity class features. Crucially, we employ a cache-aware dual-objective strategy to supervise this relational knowledge directly into the Tip-Adapter's key-value cache, effectively upgrading the prototypes while the graph teacher is discarded at test time. Thus, inference remains identical to Tip-Adapter with zero extra latency or memory. Across standard 1-16-shot benchmarks, our method consistently establishes a new state-of-the-art. Ablations confirm that the auxiliary graph supervision, text-guided reasoning, and node filtering are the essential ingredients for robust few-shot adaptation. Code is available at https://github.com/MR-Sherif/TOGA.git.

Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan +2

Edge Hill University, Ormskirk, Lancashire, L39 4QP

Few-Shot Image ClassificationVLM AdaptationCross-Modal Knowledge Distillation
AskPDF
Mar 18, 2026

MedSAD-CLIP: Supervised CLIP with Token-Patch Cross-Attention for Medical Anomaly Detection and Segmentation

Medical anomaly detection (MAD) and segmentation play a critical role in assisting clinical diagnosis by identifying abnormal regions in medical images and localizing pathological regions. Recent CLIP-based studies are promising for anomaly detection in zero-/few-shot settings, and typically rely on global representations and weak supervision, often producing coarse localization and limited segmentation quality. In this work, we study supervised adaptation of CLIP for MAD under a realistic clinical setting where a limited yet meaningful amount of labeled abnormal data is available. Our model MedSAD-CLIP leverages fine-grained text-visual cues via the Token-Patch Cross-Attention(TPCA) to improve lesion localization while preserving the generalization capability of CLIP representations. Lightweight image adapters and learnable prompt tokens efficiently adapt the pretrained CLIP encoder to the medical domain while preserving its rich semantic alignment. Furthermore, a Margin-based image-text Contrastive Loss is designed to enhance global feature discrimination between normal and abnormal representations. Extensive experiments on four diverse benchmarks-Brain, Retina, Lung, and Breast datasets-demonstrate the effectiveness of our approach, achieving superior performance in both pixel-level segmentation and image-level classification over state-of-the-art methods. Our results highlight the potential of supervised CLIP adaptation as a unified and scalable paradigm for medical anomaly understanding. Code will be made available at https://github.com/thuy4tbn99/MedSAD-CLIP

Thuy Truong Tran, Minh Kha Do, Phuc Nguyen Duy +1

Singapore Management University · La Trobe University · Vietnam National University, Hanoi

Medical Image Anomaly DetectionMedical VLMsMedical Image SegmentationVLM AdaptationContrastive Learning
AskPDF
Mar 17, 2026

ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models

The success of CLIP-like vision-language models (VLMs) on natural images has inspired medical counterparts, yet existing approaches largely fall into two extremes: specialist models trained on single-domain data, which capture domain-specific details but generalize poorly, and generalist medical VLMs trained on multi-domain data, which retain broad semantics but dilute fine-grained diagnostic cues. Bridging this specialization-generalization trade-off remains challenging. To address this problem, we propose ACE-LoRA, a parameter-efficient adaptation framework for generalist medical VLMs that maintains robust zero-shot generalization. ACE-LoRA integrates Low-Rank Adaptation (LoRA) modules into frozen image-text encoders and introduces an Attention-based Context Enhancement Hypergraph Neural Network (ACE-HGNN) module that captures higher-order contextual interactions beyond pairwise similarity to enrich global representations with localized diagnostic cues, addressing a key limitation of prior Parameter-Efficient Fine-Tuning (PEFT) methods that overlook fine-grained details. To further enhance cross-modal alignment, we formulate a label-guided InfoNCE loss to effectively suppress false negatives between semantically related image-text pairs. Despite adding only 0.95M trainable parameters, ACE-LoRA consistently outperforms state-of-the-art medical VLMs and PEFT baselines across zero-shot classification, segmentation, and detection benchmarks spanning multiple domains. Our code is available at https://github.com/icon-lab/ACE-LoRA.

M. Arda Aydın, Melih B. Yilmaz, Aykut Koç +1

Bilkent University · National Magnetic Resonance Research Center (UMRAM)

VLM AdaptationMedical VLMsParameter-Efficient Fine-TuningVision-Language Alignment
AskPDF
Mar 17, 2026

HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models

Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue that this homogeneity ignores the distinct structural nature of the modalities -- spatial locality in images versus semantic density in text. To address this, we propose HeBA (Heterogeneous Bottleneck Adapter), a unified architectural framework that introduces modality-specific structural inductive biases. HeBA departs from conventional designs through three key architectural innovations: (1) Heterogeneity: It processes visual tokens via 2D depthwise-separable convolutions to preserve spatial correlations, while distinctively processing text tokens via dense linear projections to capture semantic relationships; (2) Bottleneck Regularization: Unlike standard expanding adapters, HeBA employs a compression bottleneck (D -> D/4) that explicitly forces the model to learn compact, robust features and acts as a structural regularizer; and (3) Active Gradient Initialization: We challenge the restrictive zero-initialization paradigm, utilizing a Kaiming initialization strategy that ensures sufficient initial gradient flow to accelerate convergence without compromising the frozen backbone's pre-trained knowledge. Extensive experiments demonstrate that HeBA's architecturally specialized design achieves superior stability and accuracy, establishing a new state-of-the-art on 11 few-shot benchmarks. Code is available at https://github.com/Jahid12012021/VLM-HeBA.

Md Jahidul Islam

Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh

VLM AdaptationAdapter TuningVLM Robustness
AskPDF
Mar 17, 2026

FlowComposer: Composable Flows for Compositional Zero-Shot Learning

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient fine-tuning (PEFT). They apply visual disentanglers for decomposition and manipulate token-level prompts or prefixes to encode compositions. However, such PEFT-based designs suffer from two fundamental limitations: (1) Implicit Composition Construction, where composition is realized only via token concatenation or branch-wise prompt tuning rather than an explicit operation in the embedding space; (2) Remained Feature Entanglement, where imperfect disentanglement leaves attribute, object, and composition features mutually contaminated. Together, these issues limit the generalization ability of current CZSL models. In this paper, we are the first to systematically study flow matching for CZSL and introduce FlowComposer, a model-agnostic framework that learns two primitive flows to transport visual features toward attribute and object text embeddings, and a learnable Composer that explicitly fuses their velocity fields into a composition flow. To exploit the inevitable residual entanglement, we further devise a leakage-guided augmentation scheme that reuses leaked features as auxiliary signals. We thoroughly evaluate FlowComposer on three public CZSL benchmarks by integrating it as a plug-and-play component into various baselines, consistently achieving significant improvements.

Zhenqi He, Lin Li, Long Chen

The Hong Kong University of Science and Technology

Zero-Shot LearningCompositional Representation LearningFlow MatchingVLM Adaptation
AskPDF
Mar 13, 2026

Rethinking VLMs for Image Forgery Detection and Localization

With the rapid rise of Artificial Intelligence Generated Content (AIGC), image manipulation has become increasingly accessible, posing significant challenges for image forgery detection and localization (IFDL). In this paper, we study how to fully leverage vision-language models (VLMs) to assist the IFDL task. In particular, we observe that priors from VLMs hardly benefit the detection and localization performance and even have negative effects due to their inherent biases toward semantic plausibility rather than authenticity. Additionally, the location masks explicitly encode the forgery concepts, which can serve as extra priors for VLMs to ease their training optimization, thus enhancing the interpretability of detection and localization results. Building on these findings, we propose a new IFDL pipeline named IFDL-VLM. To demonstrate the effectiveness of our method, we conduct experiments on 9 popular benchmarks and assess the model performance under both in-domain and cross-dataset generalization settings. The experimental results show that we consistently achieve new state-of-the-art performance in detection, localization, and interpretability.Code is available at: https://github.com/sha0fengGuo/IFDL-VLM.

Shaofeng Guo, Jiequan Cui, Richang Hong

Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education

Image Forgery DetectionImage Forgery LocalizationVLM Adaptation
AskPDF
Mar 13, 2026

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models

Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work, we revisit this trade-off by investigating a fundamental question: What makes VLMs robust? Through a detailed analysis of adversarially fine-tuned models, we examine how robustness mechanisms function internally and how they interact with clean accuracy. Our analysis reveals that adversarial robustness is not uniformly distributed across network depth. Instead, unexpectedly, it is primarily localized within the shallow layers, driven by a low-frequency spectral bias and input-insensitive attention patterns. Meanwhile, updates to the deep layers tend to undermine both clean accuracy and robust generalization. Motivated by these insights, we propose Adversarial Robustness Adaptation (R-Adapt), a simple yet effective framework that freezes all pre-trained weights and introduces minimal, insight-driven adaptations only in the initial layers. This design achieves an exceptional balance between adversarial robustness and clean accuracy. R-Adapt further supports training-free, model-guided, and data-driven paradigms, offering flexible pathways to seamlessly equip standard models with robustness. Extensive evaluations on 18 datasets and diverse tasks demonstrate our state-of-the-art performance under various attacks. Notably, R-Adapt generalizes efficiently to large vision-language models (e.g., LLaVA and Qwen-VL) to enhance their robustness. Our project page is available at https://summu77.github.io/R-Adapt.

Sen Nie, Jie Zhang, Zhongqi Wang +3

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China · University of Chinese Academy of Sciences, Beijing 100049, China

VLM RobustnessAdversarial RobustnessAdversarial Attacks on VLMsVLM Adaptation
AskPDF
Mar 13, 2026

AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network

Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptability of visual features. These issues are particularly significant in aerial scenes, which involve various visual appearances and fine-grained object distinctions. We propose AVION, a knowledge distillation framework tailored for remote sensing adaptation of vision-language models. The teacher module constructs semantically rich textual prototypes by collecting descriptions from a large language model and verifying validity using remote sensing image features. The student module integrates lightweight and learnable prompts into both vision and language encoders, guided by the teacher to align embeddings and their cross-modal relationships. Once trained, the student operates independently during inference. Experiments on six optical remote sensing benchmarks show that AVION improves few-shot classification and base-class accuracy without degrading generalization to novel categories. It also enhances mean recall for cross-modal retrieval, with minimal additional trainable parameters.

Yu Hu, Jianyang Gu, Hao Liu +4

The University of British Columbia, Okanagan, Kelowna, BC, Canada · The Ohio State University, Columbus, OH, USA · TerraSense Analytics, Kelowna, BC, Canada

VLM AdaptationRemote Sensing VLMsRemote SensingFew-Shot Image ClassificationCross-Modal Knowledge Distillation
AskPDF
Mar 12, 2026

Human Knowledge Integrated Multi-modal Learning for Single Source Domain Generalization

Generalizing image classification across domains remains challenging in critical tasks such as fundus image-based diabetic retinopathy (DR) grading and resting-state fMRI seizure onset zone (SOZ) detection. When domains differ in unknown causal factors, achieving cross-domain generalization is difficult, and there is no established methodology to objectively assess such differences without direct metadata or protocol-level information from data collectors, which is typically inaccessible. We first introduce domain conformal bounds (DCB), a theoretical framework to evaluate whether domains diverge in unknown causal factors. Building on this, we propose GenEval, a multimodal Vision Language Models (VLM) approach that combines foundational models (e.g., MedGemma-4B) with human knowledge via Low-Rank Adaptation (LoRA) to bridge causal gaps and enhance single-source domain generalization (SDG). Across eight DR and two SOZ datasets, GenEval achieves superior SDG performance, with average accuracy of 69.2% (DR) and 81% (SOZ), outperforming the strongest baselines by 9.4% and 1.8%, respectively.

Ayan Banerjee, Kuntal Thakur, Sandeep Gupta

Impact Lab, Arizona State University

Domain GeneralizationCross-Domain GeneralizationMultimodal Domain GeneralizationMedical VLMsVLM Adaptation
AskPDF
Mar 12, 2026

OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs

Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling pipelines address this gap by distilling knowledge from large frontier models, but this dependence on large teachers is costly, limits scalability, and caps achievable performance at the ceiling of the teacher. We propose OSMDA: a self-contained domain adaptation framework that eliminates this dependency. Our key insight is that a capable base VLM can serve as its own annotation engine: by pairing aerial images with rendered OpenStreetMap (OSM) tiles, we leverage optical character recognition and chart comprehension capabilities of the model to generate captions enriched by OSM's vast auxiliary metadata. The model is then fine-tuned on the resulting corpus with satellite imagery alone, yielding OSMDA-VLM, a domain-adapted VLM that requires no manual labeling and no stronger external VLM teacher. We conduct exhaustive evaluations spanning six zero-shot and five in-distribution benchmarks across vision-language tasks, where OSMDA leads to substantial improvement. We further compare against nine competitive baselines, demonstrating that our method achieves superior overall performance, while being substantially cheaper to train than teacher-dependent alternatives. These results suggest that, given a strong foundation model, alignment with crowd-sourced geographic data is a practical and scalable path towards remote sensing domain adaptation. Dataset and model weights will be made publicly available upon acceptance.

Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi +3

INSAIT, Sofia University "St. Kliment Ohridski" · INSAIT, Sofia University “St. Kliment Ohridski”

Remote Sensing VLMsVLM AdaptationVision-Language ModelsUnsupervised Domain Adaptation
AskPDF
Mar 12, 2026

ReHARK: Refined Hybrid Adaptive RBF Kernels for Robust One-Shot Vision-Language Adaptation

The adaptation of large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks with extremely limited data -- specifically in the one-shot regime -- is often hindered by a significant "Stability-Plasticity" dilemma. While efficient caching mechanisms have been introduced by training-free methods such as Tip-Adapter, these approaches often function as local Nadaraya-Watson estimators. Such estimators are characterized by inherent boundary bias and a lack of global structural regularization. In this paper, ReHARK (Refined Hybrid Adaptive RBF Kernels) is proposed as a synergistic training-free framework that reinterprets few-shot adaptation through global proximal regularization in a Reproducing Kernel Hilbert Space (RKHS). A multistage refinement pipeline is introduced, consisting of: (1) Hybrid Prior Construction, where zero-shot textual knowledge from CLIP and GPT-3 is fused with visual class prototypes to form a robust semantic-visual anchor; (2) Support Set Augmentation (Bridging), where intermediate samples are generated to smooth the transition between visual and textual modalities; (3) Adaptive Distribution Rectification, where test feature statistics are aligned with the augmented support set to mitigate domain shifts; and (4) Multi-Scale RBF Kernels, where an ensemble of kernels is employed to capture complex feature geometries across diverse scales. Superior stability and accuracy are demonstrated through extensive experiments on 11 diverse benchmarks. A new state-of-the-art for one-shot adaptation is established by ReHARK, which achieves an average accuracy of 65.83%, significantly outperforming existing baselines. Code is available at https://github.com/Jahid12012021/ReHARK.

Md Jahidul Islam

Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh

VLM AdaptationTest-Time Adaptation of VLMsKernel MethodsFew-Shot Domain Adaptation
AskPDF
Mar 11, 2026

A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters

Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language models into IL methods has marked a significant advancement. However, these methods face three primary challenges: (1) the need for improved training efficiency; (2) reliance on a memory bank to store previous data; and (3) the necessity of a strong backbone to augment the model's capabilities. In this paper, we propose SimE, a Simple and Efficient framework that employs a vision-language model with adapters designed specifically for the IL task. We report a remarkable phenomenon: there is a nonlinear correlation between the number of adaptive adapter connections and the model's IL capabilities. While increasing adapter connections between transformer blocks improves model performance, adding more adaptive connections within transformer blocks during smaller incremental steps does not enhance, and may even degrade the model's IL ability. Extensive experimental results show that SimE surpasses traditional methods by 9.6% on TinyImageNet and outperforms other CLIP-based methods by 5.3% on CIFAR-100. Furthermore, we conduct a systematic study to enhance the utilization of the zero-shot capabilities of CLIP. We suggest replacing SimE's encoder with a CLIP model trained on larger datasets (e.g., LAION2B) and stronger architectures (e.g., ViT-L/14).

Haihua Luo, Xuming Ran, Jiangrong Shen +4

Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland · Equal contribution · National University of Singapore, Singapore, Singapore +2

Incremental LearningContinual Learning for VLMsAdapter TuningVLM Adaptation
AskPDF
Mar 10, 2026

Ego: Embedding-Guided Personalization of Vision-Language Models

AI assistants that support humans in daily life are becoming increasingly feasible, driven by the rapid advancements in multimodal language models. A key challenge lies in overcoming the generic nature of these models to deliver personalized experiences. Existing approaches to personalizing large vision language models often rely on additional training stages, which limit generality and scalability, or on engineered pipelines with external pre-trained modules, which hinder deployment efficiency. In this work, we propose an efficient personalization method that leverages the model's inherent ability to capture personalized concepts. Specifically, we extract visual tokens that predominantly represent the target concept by utilizing the model's internal attention mechanisms. These tokens serve as a memory of that specific concept, enabling the model to recall and describe it when it appears in test images. We conduct a comprehensive and unified evaluation of our approach and SOTA methods across various personalization settings including single-concept, multi-concept, and video personalization, demonstrating strong performance gains with minimal personalization overhead.

Soroush Seifi, Simon Gardier, Vaggelis Dorovatas +2

Toyota Motor Europe

VLM AdaptationMemory-Augmented VLMs
AskPDF
Mar 10, 2026

Guided Prompt Evolution for Vision-Language Models Adaptation

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from catastrophic forgetting of pre-trained knowledge. Toward addressing this limitation, our work is grounded in the insight that governing the evolutionary path of prompts is essential for forgetting-free adaptation. To this end, we propose EvoPrompt, a novel framework designed to explicitly steer the prompt trajectory for knowledge-preserving fine-tuning. Specifically, our approach employs a Modality-Shared Prompt Projector (MPP) to generate hierarchical prompts from a unified embedding space. Critically, an evolutionary training strategy decouples low-rank updates into directional and magnitude components, preserving early-learned semantic directions while only adapting their magnitude, thus enabling prompts to evolve without discarding foundational knowledge. Extensive experiments demonstrate that EvoPrompt achieves state-of-the-art performance in few-shot learning while robustly preserving the original zero-shot capabilities of pre-trained VLMs.

Enming Zhang, Jiayang Li, Yanlong Wang +3

Tsinghua Shenzhen International Graduate School, Tsinghua University · Sun Yat-sen University · Chinese University of Hong Kong, Shenzhen

VLM AdaptationFew-Shot LearningVisual Prompt LearningCatastrophic Forgetting
AskPDF
Mar 9, 2026

BiCLIP: Domain Canonicalization via Structured Geometric Transformation

Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that independently trained VLMs are related by a canonical transformation, we extend this understanding to the concept of domains. We hypothesize that image features across disparate domains are related by a canonicalized geometric transformation that can be recovered using a small set of anchors. Few-shot classification provides a natural setting for this alignment, as the limited labeled samples serve as the anchors required to estimate this transformation. Motivated by this hypothesis, we introduce BiCLIP, a framework that applies a targeted transformation to multimodal features to enhance cross-modal alignment. Our approach is characterized by its extreme simplicity and low parameter footprint. Extensive evaluations across 11 standard benchmarks, including EuroSAT, DTD, and FGVCAircraft, demonstrate that BiCLIP consistently achieves state-of-the-art results. Furthermore, we provide empirical verification of existing geometric findings by analyzing the orthogonality and angular distribution of the learned transformations, confirming that structured alignment is the key to robust domain adaptation. Code is available at https://github.com/QuantitativeImagingLaboratory/BilinearCLIP

Pranav Mantini, Shishir K. Shah

University of Houston, Department of Computer Science · The University of Oklahoma, School of Computer Science

VLM AdaptationDomain AdaptationVision-Language AlignmentFew-Shot Domain Adaptation
AskPDF
Mar 9, 2026

Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM

Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon introduces a text-conditioned granularity Controller that dynamically adjusts the visual abstraction level according to the semantic scope of the textual input, and an Adaptive Token Aggregation module that performs granularity-guided pooling and relation-aware clustering to produce compact, semantically rich visual tokens. This design enables unified "pixel-to-fine-to-coarse" reasoning within a single forward pass. Extensive and interpretable experiments demonstrate that Granulon improves accuracy by ~30% and reduces hallucination by ~20%, outperforming all visual encoders under identical settings.

Junyuan Mao, Qiankun Li, Linghao Meng +5

National University of Singapore · Nanyang Technological University

Large Vision-Language ModelsFine-Grained Visual PerceptionVLM AdaptationVisual Representation LearningVisual Token Compression
AskPDF
Mar 9, 2026

FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Models

CLIP-based prompt tuning enables pretrained Vision-Language Models (VLMs) to efficiently adapt to downstream tasks. Although existing studies have made significant progress, they pay limited attention to changes in the internal attention representations of VLMs during the tuning process. In this paper, we attribute the failure modes of prompt tuning predictions to shifts in foreground attention of the visual encoder, and propose Foreground View-Guided Prompt Tuning (FVG-PT), an adaptive plug-and-play foreground attention guidance module, to alleviate the shifts. Concretely, FVG-PT introduces a learnable Foreground Reliability Gate to automatically enhance the foreground view quality, applies a Foreground Distillation Compensation module to guide visual attention toward the foreground, and further introduces a Prior Calibration module to mitigate generalization degradation caused by excessive focus on the foreground. Experiments on multiple backbone models and datasets show the effectiveness and compatibility of FVG-PT. Codes are available at: https://github.com/JREion/FVG-PT

Haoyang Li, Liang Wang, Siyu Zhou +5

University of Technology Sydney, NSW 2007, Australia · Shanghai University, Shanghai 200444, China

Attention-Guided DistillationVLM AdaptationPrompt Learning for VLMsPrompt TuningAttention Mechanisms
AskPDF