Vision-Language Alignment

Follow this topic Ask about this topic

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

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

May 27, 2026

LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment

We take a Gromov-Wasserstein perspective on Vision-Language-Action (VLA) learning, where the goal is to make the relational geometry of action representations compatible with the semantic geometry of VL embeddings. However, this alignment is non-trivial due to the mathematical heterogeneity between the domains: the semantic space of vision-language is topologically linear and isotropic, whereas the physical manifold of robotic action is non-Euclidean and anisotropic. Their disjoint metric structures render direct regression ill-posed. To resolve this incompatibility, we introduce LAST (Lie-algebraic Action Space Tokenizer), which reconstructs the action space to establish local metric compatibility with the VL modality via a two-stage transformation: (1) Global Topological Linearization: linearizing the action manifold via Lie-algebraic mapping, converting trajectories into a fixed-length, physically additive representation. (2) Local Metric Discretization: hierarchically discretizing the representation into schemas and whitened residuals, yielding approximately isotropic local charts that are statistically aligned with the semantic metric. By resolving the structural mismatch at both global and local levels, LAST enables VLA models with superior convergence and generalizability.

Huaihai Lyu, Chaofan Chen, Yuheng Ji +4

1MAIS, Institute of Automation, Chinese Academy of Sciences. · 2Beijing Academy of Artificial Intelligence. · 3Peking University..

Cross-Modal Learning Vision-Language-Action Models Vision-Language Alignment

May 27, 2026

Rethinking Video-Language Model from the Language Input Perspective

Driven by the wave of large language models, Video-Language Models (VLMs) have become a significant yet challenging technology to bridge the gap between videos and texts. Although previous VLM works have made significant progress, almost all of them implicitly assume that all the texts are predefined by the specific template. In real-world applications, such a strict assumption is impossible to satisfy since 1) predefining all the texts is extremely time-consuming and labor-intensive. 2) these predefined text inputs are too restrictive and user-unfriendly, limiting their applications. It is observed that given a video input, texts with similar semantics but different templates lead to various performances. To this end, in this paper, we propose a novel plug-and-play framework for various VLM-based methods to fully bridge videos and texts. Specifically, we first generate positive and negative texts from the original ones to target specific text components. Then, we propose an attribute-based text reasoning strategy to mine fine-grained textual semantics of generated texts. Finally, we utilize videos as guidance to conduct cross-modal bridging by designing a self-weighted loss. Extensive experiments show that the proposed method can serve as the plug-and-play module to effectively improve the performance of state-of-the-art VLMs.

Xiang Fang, Wanlong Fang, Changshuo Wang +2

School of Software Engineering, Huazhong University of Science and Technology · Nanyang Technological University, Singapore · University College London +2

Prompt Sensitivity VLM Adaptation Video-Language Models Vision-Language Alignment

May 27, 2026

Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning

Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging its strong representations, recent studies improve task adaptation under insufficient local data while preserving generalization. However, these methods emphasize fully local optimization with simple parameter aggregation,which can amplify inter-client optimization inconsistency and intra-client over-specialization under heterogeneous and full-data FL settings, making it difficult to balance global task adaptation and generalization. To address these challenges, we propose FedDTL, a novel federated VLM framework that decouples the image encoder and text encoder across clients and the server. Through decoupled encoder training with server-client modality alignment, FedDTL promotes coherent global semantic update and reduces inter-client optimization inconsistency, improving global task adaptation.To further mitigate intra-client over-specialization,we introduce a two-stage local fine-tuning, where a supervised fine-tuning stage enables rapid and reliable warm-start, followed by a reinforcement learning stage that enhances generalization. Extensive experiments on multiple benchmarks, including label skew and feature shift, demonstrate that FedDTL achieves an effective balance between global task adaptation and generalization under various FL data distributions in both few-shot and full-data regimes.

Yuting Ma, Lechao Cheng, Xiaohua Xu

School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China · School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China.

VLM Adaptation Vision-Language Alignment Federated Fine-Tuning Federated Learning Heterogeneous Federated Learning

May 26, 2026

FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL (Fast and Efficient Global-local Object Alignment Learning), an efficient fine-tuning method that enhances ability of CLIP to handle lengthy text through global-local semantic alignment. Our method consists of two key components. First, Fast Local Image-Sentence Matching (FLISM) efficiently extracts local image regions through object detection and spatial division, then matches them with corresponding sentences. Second, Token Similarity-based Learning (TSL) maximizes the similarity between patch tokens from specific regions in the image and their corresponding region embeddings, applying the same principle to text, which enhances the ability of the model to capture detailed correspondences. Additionally, we introduce GLIT100k, a dataset that provides both global image-lengthy caption pairs and context-derived local pairs, where local descriptions are extracted from global captions to maintain semantic coherence. Through extensive experiments on long caption datasets (DOCCI, DCI) and short caption datasets (MSCOCO, Flickr30k), we demonstrate that FAST-GOAL achieves significant improvements over baselines, enabling effective adaptation of CLIP to detailed textual descriptions while maintaining computational efficiency.

Hyungyu Choi, Young Kyun Jang, Chanho Eom

Department of Virtual Convergence, Graduate School of Advanced Imaging Science, Multimedia & Films (GSAIM), Chung-Ang University, Seoul, South Korea

VLM Adaptation Text-Image Alignment Vision-Language Alignment

May 25, 2026

Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models

Vision Language Models adapt well to downstream tasks but are highly vulnerable to adversarial perturbations that disrupt cross-modal semantic alignment. Existing defenses are largely unidirectional or structural, failing to exploit bidirectional cross-modal complementarity and instance-wise adaptive protection. To overcome the limitations of unidirectional and static defenses in adversarial settings, we propose Closed-Loop Bidirectional Prompting, casting robust adaptation as cross-modal agreement recovery via a dynamic feedback loop on frozen encoders. A Semantic Anchor is introduced as a stable prior to constrain cyclic updates and mitigate perturbation-induced feature corruption. Through anchor-based bootstrapping, textual semantics denoise visual representations, while the refined visuals enable instance-adaptive prompt updating, yielding a rectified and robust consensus. Extensive evaluations across 11 datasets validate state-of-the-art robustness and strong base-to-new generalization, while maintaining a favorable trade-off between computational cost and accuracy.

Xiao Liu, Jiaxiang Liu, Boci Peng +6

University of Macau · Guangdong Institute of Intelligence Science and Technology · Peking University +4

VLM Robustness Prompt Learning VLM Adaptation Adversarial Robustness Vision-Language Alignment Prompt Learning for VLMs

May 24, 2026

Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the tendency of LVLMs to over-rely on text while neglecting visual inputs. Yet most analyses remain empirical without uncovering its underlying cause. In this paper, we provide a systematic study of language bias and identify its root in modality misalignment during training. Our analysis shows that both Visual Instruction Tuning (VIT) and Direct Preference Optimization (DPO) often prioritize textual improvements, which may cause LVLMs to overly lean toward language modeling rather than balanced multimodal understanding. To address this, we propose two simple yet effective methods: Language Bias Regularization (LBR) which mitigates language bias through regularization during instruction tuning, and Language Bias Penalty (LBP), which penalizes language bias in the DPO training process. Extensive experiments across diverse models and benchmarks demonstrate the effectiveness of our approach. LBR consistently improves performance on over ten general benchmarks, while LBP significantly reduces hallucination and improves trustworthiness. Together, these methods not only mitigate language bias but also advance the overall alignment of LVLMs, all without introducing any additional data or auxiliary models. Our code is publicly available at https://github.com/lab-klc/LVLM-Language-Bias.

Yangneng Chen, Jing Li

1Harbin Institute of Technology, Shenzhen, China.

Vision-Language Models VLM Adaptation Object Hallucination in VLMs Vision-Language Alignment

May 24, 2026

Interpretability Transfer from Language to Vision via Sparse Autoencoders

Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model by constraining a visual projector to map visual tokens into an LLM's pre-existing, labeled textual SAE space. This approach enables visual interpretability without training dedicated vision SAEs. By regularizing the projector using the LLM's SAE reconstruction loss, VISTA achieves a threefold increase in the matching rate, which measures how accurately the most activating textual concepts in the SAE space correspond to semantic elements in the image. Using this framework, we further analyze spatial localization properties of different vision encoders and show that DINOv2 features have stronger localization abilities than other encoders. Leveraging this precision, we validate VISTA's cross-modal alignment through fine-grained, localized concept interventions, where specific objects are removed or replaced in the model's perception while preserving the surrounding scene. This results in improvements of 35% in object removal and 47% in object replacement tasks over vision-only baselines, providing causal evidence that visual tokens inhabit the text SAE manifold. These contributions are validated across multiple LLM architectures.

Alexey Kravets, Da Li, Chuan Li +2

University of Bath, UK · Samsung AI Centre Cam- bridge · Lambda, Inc..

VLM Interpretability Sparse Autoencoders Vision-Language Alignment

May 22, 2026

Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition

Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The similarity volume is refined by spatial aggregation, which contextualizes local similarity patterns to improve intra-frame consistency. Motion-aware modulation further injects inter-frame variation cues, highlighting dynamically changing regions. Mamba-based temporal aggregation then models the evolution of class-conditioned similarity patterns across frames. By maintaining dense visual-text correspondence, SimVA effectively transfers CLIP to video action recognition, achieving competitive performance across zero-shot, few-shot, and base-to-novel benchmarks.

Yerim So, Jiyeong Kim, Jiwon Yoon +1

Ewha Womans University, South Korea

Video Action Recognition Vision-Language Alignment

May 21, 2026

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end yet opaque "black boxes". Conversely, textual localization readout is merely readable, not truly interpretable, often functioning as an unconstrained post-hoc step. To bridge this interpretability gap, we propose SegCompass, an end-to-end model that leverages a Sparse Autoencoder (SAE) to forge an explicit, interpretable, and differentiable alignment pathway. Given an image-instruction pair, SegCompass first generates a chain-of-thought (CoT) trace. The core of our method is an SAE that maps both the CoT and visual tokens into a shared, high-dimensional sparse concept space. A query codebook selects salient concepts from this space, which are then spatially grounded by a slot mapper into a multi-slot heatmap that guides the final mask decoder. The entire model is trained jointly, unifying reinforcement learning for the reasoning path with standard segmentation supervision. This SAE-driven interface provides a "white-box" connection that is significantly more traceable than latent queries and more coherent than textual readouts. Extensive experiments on five challenging benchmarks demonstrate that SegCompass matches or surpasses state-of-the-art performance. Crucially, our visual and quantitative analyses show a strong correlation between the quality of the learned sparse concepts and final mask accuracy, confirming that SegCompass achieves superior results through its enhanced and inspectable alignment. Code is available at https://github.com/ZhenyuLU-Heliodore/SegCompass.

Zhenyu Lu, Liupeng Li, Jinpeng Wang +4

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Peng Cheng Laboratory · University of Chinese Academy of Sciences +3

Image Segmentation Text-Guided Image Segmentation VLM Interpretability Visually Grounded Reasoning Vision-Language Alignment Reasoning Segmentation

May 21, 2026

Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling

Vision-Language Models (VLMs) excel at tasks like zero-shot classification and cross-modal retrieval by mapping images and text to a shared space, but this requires expensive end-to-end training with massive paired datasets. Current post-hoc alignment methods reduce computational costs by connecting pretrained encoders through lightweight mappings, yet still demand substantial paired data. In this work, we investigate the potential of repurposing the classification heads of pretrained vision models as semantic prototypes. The recycling of these weights, typically discarded after pretraining, unlocks two distinct capabilities: it enables zero-shot alignment by using weights as semantic anchors, and serves as a robust data augmentation strategy by mixing these prototypes with real image-text pairs. We demonstrate that integrating our approach with several state-of-the-art post-hoc alignment techniques consistently boosts accuracy in cross-modal retrieval, zero- and few-shot classification tasks.

David Méndez, Roberto Confalonieri, Natalia Díaz Rodríguez

Department of Computer Science and Artificial Intelligence, DaSCI Institute, University of Granada, Granada, Spain · Department of Mathematics “Tullio Levi-Civita”, University of Padova, Padova, Italy.

Cross-Modal Learning VLM Adaptation Vision-Language Retrieval Zero-Shot Image Classification Vision-Language Alignment Few-Shot Image Classification

May 20, 2026

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing

Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevailing assumption underlying this paradigm is that a connector module can seamlessly align the VLM's rich multi-modal reasoning with the original text embedding space of DiTs. However, we hypothesize that this alignment acts as a severe semantic bottleneck, degrading fine-grained structural variables. Verifying this is challenging, as end-to-end evaluations conflate alignment failures with generation errors, and natural datasets lack disentangled annotations. To rigorously investigate this, we propose a controlled data processing pipeline based on video composition that results in TRACE-Edit, a diagnostic dataset focusing on relation-based editing. Leveraging this dataset, we propose a comprehensive diagnostic protocol to analyze two important designs of meta-query and connector in the existing video editing models. Systematic evaluation of four representative model cases reveals that fine-grained structural semantics can be severely degraded during alignment. Our findings overturn the assumption of lossless semantic transfer, identifying the VLM-to-DiT alignment as a major bottleneck and providing a new diagnostic foundation for future multi-modal alignment architectures.

Hangyu Lin, Chao Wen, Chengming Xu +4

HKUST · FDU · ZJU +1

Video Diffusion Models Video Editing Instruction-Based Video Editing Vision-Language Alignment Video Generation Evaluation

May 20, 2026

Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics

Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However, it often leads to overfitting to the training dataset, corrupts pre-trained image priors, and degrades alignment or aesthetics. To break this bottleneck, we propose a feature supervision paradigm for Multimodal Diffusion Transformers (MM-DiT). Specifically, we introduce a lightweight cross-modal alignment mechanism that implicitly extracts multi-granularity vision-aligned text representations from SigLIP 2 and applies supervision to the image branch of MM-DiT during the training stage, with zero extra inference overhead. Our method injects vision-aligned text guidance while preserving the base model's original generalization, avoiding degradation caused by SFT. Furthermore, our method directly mines implicit multi-granularity aesthetic signals from pre-trained vision foundation models to optimize human-perceived aesthetics. Extensive experiments on MM-DiTs show that our method pushes the Pareto frontier and achieves synergistic improvements across text-image alignment, photorealism, and human-perceived aesthetics.

Yunlong Wang, Jinjin Shi, Wenbin Gao +3

Xiaomi Corporation Nanjing, China · Xiaomi Corporation Beijing, China

Diffusion Model Alignment Diffusion Transformer Image Generation Vision-Language Alignment T2I Diffusion Models

May 18, 2026

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models

In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual features into textual sequence, enabling unified multimodal alignment and reasoning within a generative architecture. However, our experiments reveal two key limitations: (1) Although visual information serves as the core evidential modality in MLLMs, it is treated on par with textual tokens, diminishing the unique contribution of the visual modality; (2) As generation length increases, particularly within a limited context window, the model's dependence on visual information progressively weakens, resulting in deteriorated vision-language alignment and reduced consistency between generated content and visual semantics. To address these challenges, we propose the Vision Inference Former (VIF), a lightweight architectural module that establishes a direct bridge between pure visual representations and the model's output space. Specifically, VIF continuously injects visual semantics throughout the decoding phase of the inference process, ensuring that the model remains firmly grounded in visual content during generation. We conduct experiments on 14 benchmark tasks covering general reasoning, OCR, table understanding, vision-centric evaluation, and hallucination. Experimental results show that VIF consistently improves model performance across diverse architectures while introducing minimal additional overhead. The code for this work is available at https://github.com/Dong-Xinpeng/VIF.

Xinpeng Dong, Min Zhang, Kairong Han +3

Zhejiang University · East China Normal University · Zhejiang University of Science and Technology

Object Hallucination in VLMs Multimodal Large Language Models Vision-Language Grounding Vision-Language Alignment VLM Inference

May 18, 2026

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual prompts, such as masks or points, SWIM leverages mask supervision only during training to guide cross-modal attention, allowing the model to automatically attend to the user-specified object at inference. Our cross-attention analysis of pretrained multimodal large languagemodels (MLLMs) reveals a systematic discrepancy: Attribute words produce sharp, localized activations in the visual modality, whereas object nouns yield diffuse and scattered patterns due to semantic reference bias and distributed high-level representations. To address this misalignment, we construct NL-Refer, an enriched dataset, in which each object mask is paired with a precise natural language referring expression. SWIM extracts multi-layer cross-attention maps from object nouns and enforces spatial consistency with ground-truth masks. Experimental results demonstrate that SWIM substantially improves text-visual alignment and achieves superior performance over visual-prompt-based methods on fine-grained object understanding benchmarks. The code and data are available at https://github.com/HumanMLLM/SWIM.

Boyuan Sun, Bowen Yin, Yuanming Li +2

VCIP, CS, Nankai University · Tongyi Lab, Alibaba Group · NKIARI, Shenzhen Futian

Cross-Modal Learning Video Object Segmentation VLM Adaptation Referring Video Object Segmentation Vision-Language Grounding Vision-Language Alignment+2

May 18, 2026

GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations

Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption meaning, but they expose these signals through a fixed-length vector interface. We study whether embedding length can be turned into a controllable semantic access interface. We propose GraSP-VL, which learns a shared near-orthogonal prefix transform over frozen VLM embeddings. GraSP-VL instantiates a Semantic Matryoshka interface: short prefixes are assigned coarse semantic roles, while longer prefixes progressively expose finer language-grounded distinctions. Because the transform is shared across image and text embeddings and preserves full-dimensional geometry, prefix behavior changes without rewriting the original VLM space. On a 20,147-example COCO/Flickr30K annotation pool, GraSP-VL reaches a staircase score of 53.01 and hard-negative selectivity of 89.76, while keeping full-space drift below

10^{-6}

. It also transfers to SugarCrepe-clean with 86.03 object accuracy and 11.96 mean external emergence, and preserves full-dimensional zero-shot CIFAR-100 accuracy. These results show that frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed.

Zesheng Li, Chengchang Pan, Honggang Qi

University of the Chinese Academy of Sciences, China

Vision-Language Models Representation Learning Matryoshka Representation Learning Vision-Language Alignment

May 16, 2026

SHED: Style-Homogenized Embedding Alignment for Domain Generalization

Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios. To address this, we propose Style-Homogenized Embedding alignment for Domain-generalization (SHED), a novel CLIP-based method that aligns style-homogenized embeddings instead of raw representations from encoders in CLIP. During training, SHED removes domain-specific style centroids from both image embeddings computed per source domains and text embeddings which are averaged across diverse prompt templates and stripped of a global centroid. For inference, considering the lack of target domain information, SHED projects diverse textual domain centroids into the visual space and aggregates predictions via membership weighting. Extensive experiments on five benchmarks show SHED achieves state-of-the-art performance, outperforming prior methods significantly (e.g., +4.0% on DomainNet vs. standard fine-tuning).

Kai Gan, Tong Wei

School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China

VLM Robustness VLM Adaptation Domain Generalization Vision-Language Alignment Invariant Representation Learning

May 15, 2026

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the visual pathway may compress or discard critical 3D structural cues during feature extraction, so the language model receives image representations that are already insufficient for reliable spatial judgment. We introduce GeoWorld-VLM, a VLM-side distillation framework that transfers geometric structure from frozen camera-conditioned video world models into VLMs. GeoWorld-VLM fine-tunes only the image encoder and multimodal projector, aligning post-projector image features with intermediate world-model representations while leaving the main backbone frozen. Given images, a prompt, and a sampled camera trajectory, the world-model teacher converts static visual input into a synthetic multi-view spatial signal. Training combines spatial answer supervision, teacher-student feature alignment, and a preservation anchor to the original VLM. Since the language model remains frozen, GeoWorld-VLM preserves the original model's linguistic capabilities while attributing spatial improvements to the enhanced visual pathway. To evaluate the effectiveness and generality of the proposed method, we apply GeoWorld-VLM to two distinct VLM architectures and observe consistent improvements across both backbones. GeoWorld-VLM improves performance by approximately 4 percent on both the What'sUp and VSR benchmarks, suggesting that world-model-guided visual alignment generalizes across model structures and spatial reasoning datasets.

Renjie Gu, Kaichen Zhou, Yan Luo +1

Harvard AI and Robotics Lab · Kempner Institute for the Study of Natural and Artificial Intelligence · Harvard University

Visual Spatial Reasoning VLM Adaptation VLM Distillation Visually Grounded Reasoning Vision-Language Alignment Knowledge Distillation

May 15, 2026

Res $^2$ CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment

Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenarios with scarce samples and rapidly changing categories. Existing CLIP-based methods face two major challenges: coarse-grained unified text prompts struggle to adapt to fine-grained foreground-background differences, causing cross-granularity mismatch; and fine-tuning on auxiliary datasets disrupts CLIP's inherent open-world generalization due to domain shift, leading to cross-category generalization degradation. To address these, we propose to shift multimodal alignment entirely into a unified residual space, where residual representations naturally eliminate fine-grained normal feature differences across regions and class-specific biases, simultaneously resolving both problems. Based on this insight, Res

^2

CLIP, the first residual-to-residual alignment framework that symmetrically bridges visual and text modalities within CLIP's residual space, is designed. The framework is developed from a residual perspective into three branches: a text prompt-based branch, a visual prompt-based branch, and a novel residual-to-residual alignment branch. All learnable optimizations are constrained within the residual domain, and the residual alignment optimization objectives are designed to force the model to focus on relative anomaly deviations rather than optimizing class-specific features. Experiments on multiple datasets demonstrate the effectiveness of our architecture. The code is available at https://github.com/hito2448/Res2CLIP.

Xinyue Liu, Jianyuan Wang, Biao Leng +1

Beihang University · University of Science and Technology Beijing · Beijing Jiaotong University

Few-Shot Anomaly Detection VLM Adaptation Residual Learning Multimodal Anomaly Detection Vision-Language Alignment Anomaly Detection

May 15, 2026

Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation

Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic units. We propose a Decomposed Vision-Language Alignment framework that explicitly factorizes textual prompts into a concept token and multiple attribute tokens, enabling separate cross-modal interactions for each semantic unit. At the feature level, we introduce a Feature-Gated Cross-Attention module that generates attribute-specific gating maps to fuse information in a multiplicative manner, effectively enforcing compositional semantics. At the scoring level, per-token similarities are aggregated in log-space, producing a stable and interpretable compositional matching. The method can be seamlessly integrated into existing transformer-based segmentation architectures and significantly improves generalization to unseen attribute-category compositions in fine-grained open-vocabulary segmentation benchmarks.

Chenhao Wang, Yingrui Ji, Yu Meng +1

Aerospace Information Research Institute, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Zhejiang University

Image Segmentation Open-Vocabulary Semantic Segmentation Vision-Language Alignment Semantic Segmentation Compositional Generalization Fine-Grained Semantic Segmentation

May 15, 2026

BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation

Biomedical Vision--Language Models (VLMs) have shown remarkable promise in few-shot medical diagnosis but face a critical bottleneck: fragility to prompt variations.Existing adaptation frameworks typically optimize visual and textual prompts as independent streams, relying on ideal ``Golden Prompts''. In clinical reality, where descriptions are often noisy and heterogeneous, this modality isolation leads to unstable cross-modal alignment. To address this, we propose BiomedAP, a vision-informed dual-anchor framework with gated cross-modal fusion.BiomedAP enforces synergistic alignment through two mechanisms: (1) Gated Cross-Modal Fusion, which enables layer-wise interaction between modalities, acting as a dynamic noise regulator to suppress irrelevant textual cues; and (2) a Dual-Anchor Constraint that regularizes learnable prompts toward stable semantic centroids derived from both expert templates (High Anchors) and few-shot visual prototypes (Low Anchors). Extensive experiments across 11 benchmarks demonstrate that BiomedAP consistently surpasses baselines, achieving competitive few-shot accuracy and markedly enhanced robustness under prompt perturbations. Our code is available at: https://github.com/tongdiedie/BiomedAP. Keywords: Vision-Language Models; Prompt Learning; Parameter-Efficient Fine-Tuning; Few-shot Learning

Huanyang Tong, Kai Liu, Fangjun Kuang +1

Wenzhou University · Wenzhou Business College

VLM Robustness Prompt Learning Healthcare VLM Adaptation Medical VLMs Vision-Language Alignment

May 14, 2026

Deep Pre-Alignment for VLMs

Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain distant from the text space in the initial layers of the LLM, forcing the model to waste critical depth~\cite{zhang-etal-2024-investigating,artzy-schwartz-2024-attend} on superficial modality alignment rather than deep understanding and complex reasoning. In this work, we propose Deep Pre-Alignment (DPA), a novel architecture that replaces the standard ViT encoder with a small VLM as perceiver, ensuring visual features are deeply aligned with the text space of the target large language model. Comprehensive experiments demonstrate the effectiveness of DPA. On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale. Moreover, by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks. We further demonstrate that these gains are consistent across different LLM families including Qwen3 and LLaMA 3.2, highlighting the generality of our approach. Beyond performance, DPA also offers a seamless upgrade path for current VLM development, requiring only a modular replacement for the visual encoder with marginal computation overhead.

Tianyu Yu, Kechen Fang, Zihao Wan +5

1Tsinghua University · 2Taobao & Tmall Group of Alibaba · 3Shanghai Qi Zhi Institute.

Vision-Language Models Large Vision-Language Models Vision-Language Alignment

May 13, 2026

Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning

Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkable generalization of CLIP, leveraging pre-trained vision-language models has become a dominant paradigm in CIL. However, current work primarily focuses on aligning global image embeddings (i.e., [CLS] token) with their corresponding text prompts (i.e., [EOS] token). Despite their good performance, we find that they discard the rich patch-level semantic information inherent in CLIP's encoders. For instance, when recognizing a rabbit, local patches may encode its distinctive cues, such as long ears and a fluffy tail, which can provide complementary evidence for recognition. Based on the above observation, we propose SPA (Semantic-guided Patch-level Alignment) for CLIP-based CIL, which aims to awaken long-neglected local representations within CLIP. Specifically, for each class, we first construct representative and diverse visual samples and feed them to GPT-5 as visual guidance to generate class-wise semantic descriptions. These descriptions are used to guide the selection of discriminative patch-level visual features. Building upon these selected patches, we further employ optimal transport to align selected patch tokens with semantic tokens from class-wise descriptions, yielding a structured cross-modal alignment that improves recognition. Furthermore, we introduce task-specific projectors for effective adaptation to downstream incremental tasks, and sample pseudo-features from stored class-wise Gaussian statistics to calibrate old-class representations, thereby mitigating catastrophic forgetting. Extensive experiments demonstrate that SPA achieves state-of-the-art performance.

Hao Sun, Zi-Jun Ding, Da-Wei Zhou

School of Artificial Intelligence, Nanjing University · State Key Laboratory for Novel Software Technology, Nanjing University

Class-Incremental Learning VLM Adaptation Incremental Learning Vision-Language Alignment

May 13, 2026

Revealing the Gap in Human and VLM Scene Description through Counterfactual Semantic Saliency

Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects by measuring the semantic shift induced by their causal ablation from a scene. To evaluate AI-human semantic alignment, we tested prominent VLMs against a human psychophysics baseline comprising 16,603 valid responses across 307 complex natural scenes and 1,306 high-fidelity counterfactual variants. Our analysis reveals a pervasive scene comprehension gap: models exhibit an overreliance (relative to humans) on large objects (size bias), objects at the center of the image (center bias), and high-saliency objects. In contrast, models rely less on people in the scenes than our human participants do to describe the images. A model's size bias is a primary driver explaining variations in model-human semantic divergence. Code and data are available at https://github.com/starsky77/Counterfactual-Semantic-Saliency-Data .

Ziqi Wen, Parsa Madinei, Miguel P. Eckstein

Department of Computer Science, University of California, Santa Barbara · Department of Psychological and Brain Sciences, University of California, Santa Barbara

VLM Evaluation Vision-Language Models Counterfactual Explanations VLM Interpretability Vision-Language Alignment

May 12, 2026

VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference

Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond the CLIP-based paradigm and harnesses the recent spatially-aware dino

.

txt framework to facilitate more efficient and high-quality dense prediction. While dino

.

txt exhibits robust spatial awareness, we find that the semantic ambiguity of text queries gives rise to severe mismatch within its dense cross-modal interactions. To address this, we introduce Visual-guided Prompt evolution (VIP) to rectify the semantic expressiveness of text queries in dino

.

txt, unleashing its potential for fine-grained object perception. Towards this end, VIP integrates alias expansion with a visual-guided distillation mechanism to mine valuable semantic cues, which are robustly aggregated in a saliency-aware manner to yield a high-fidelity prediction. Extensive evaluations demonstrate that VIP: 1. surpasses the top-leading methods by 1.4%-8.4% average mIoU, 2. generalizes well to diverse challenging domains, and 3. requires marginal inference time and memory overhead.

Hao Zhu, Shuo Jin, Wenbin Liao +4

Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · XJTLU +1

Image Segmentation Vision-Language Models Efficient VLM Inference Prompt Optimization Open-Vocabulary Semantic Segmentation Vision-Language Alignment

May 12, 2026

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models

Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as discrete categories not aligned with natural language. We propose ClipSum, a framework that leverages frozen CLIP vision-language features with explicit temporal modeling and dimension-adaptive fusion for instructional video summarization. CLIP's contrastive pre-training on 400M image-text pairs yields visual features semantically aligned with the linguistic concepts that text decoders generate, bridging the vision-language gap at the representation level. On YouCook2, ClipSum achieves 33.0% ROUGE-1 versus 30.5% for ResNet-152 with 4x lower dimensionality (512 vs. 2048), demonstrating that semantic alignment matters more than feature capacity. Frozen CLIP (33.0%) surpasses fine-tuned CLIP (32.3%), showing that preserving pre-trained alignment is more valuable than task-specific adaptation. https://github.com/aqeeelmirza/clipsum

Maham Nazir, Muhammad Aqeel, Richong Zhang +1

Beihang University, Beijing, China · University of Verona, Italy

Video Summarization Video-Language Models Vision-Language Alignment

May 12, 2026

Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning

Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual representations. Instead of optimizing messages through a shared external communicative objective, our agents exchange only discrete token sequences and update their own models using local perceptual evidence. This setting focuses on an underexplored aspect of emergent communication, examining whether common symbols can arise without shared perceptual access, and how the similarity between private visual spaces constrains the content and symmetry of the resulting language. We instantiate this setting in the Metropolis-Hastings Captioning Game (MHCG), where two agents collaboratively form shared captions by exchanging proposed token sequences that a listener accepts or rejects using an MH-style criterion evaluated against its own visual features. We compare three pairings of frozen visual encoders, with agents starting from randomly initialized text modules. Experiments on MS-COCO show that MHCG produces visually informative shared token sequences that outperform a no-communication baseline in cross-agent alignment, visual-feature prediction, and image-text retrieval; all cross-agent metrics decline as encoder mismatch increases. Moderate encoder heterogeneity reduces the number of shared sequences while preserving per-sequence visual specificity, whereas stronger encoder heterogeneity yields fewer, coarser, and more asymmetric sequences. Ablations show that listener-side MH acceptance is critical for avoiding degenerate token formation. These results suggest that shared symbols can arise from local perceptual evaluation alone, with visual representational similarity across encoders shaping both the content and symmetry of the resulting language.

Mikako Ochiai, Masatoshi Nagano, Tadahiro Taniguchi

Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan

Multi-Agent Systems Vision-Language Alignment Multi-Agent Communication Emergent Communication

May 12, 2026

Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning

Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot fine-tuning of vision-language models like CLIP remains underexplored. By establishing multiple fine-tuning baselines of CLIP for CDFSL, we find adapter-based methods (e.g., LoRA) consistently outperform prompt-based ones (e.g., MaPLe), contrary to in-domain scenarios. To make those effective in-domain methods competitive again in CDFSL, we analyze this phenomenon and discover LoRA's superiority stems from rectifying the collapsed attention of visual CLS token, enhancing modality alignment and class separation by focusing on text-related visual regions. Further, we find textual EOS token exhibit much better attention to visual samples, and CLIP's standard contrastive loss weakly constrains modality alignment. Based on these insights, we propose Semantic Probe, a plug-and-play attention rectification framework for both adapter- and prompt-based methods. Extensive experiments on four CDFSL benchmarks validate our rationale, achieving state-of-the-art performance and benefiting both fine-tuning paradigms. Codes will be released.

Yaze Zhao, Yicong Liu, Yixiong Zou +2

Source-Free Cross-Domain Few-Shot Learning Source-Free Domain Adaptation Few-Shot Domain Adaptation VLM Adaptation Few-Shot Learning Vision-Language Alignment+1

May 11, 2026

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models

Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision, resulting in representations that lack accurate spatial awareness. Existing implicit spatial grounding methods partially address this by aligning VLA features with those of 3D-aware foundation models, but they rely on empirical layer search and perform alignment on LLM-level visual tokens where spatial structure has already been entangled with linguistic semantics, limiting both generalizability and geometric interpretability. We propose VEGA (Visual Encoder Grounding Alignment), a simple yet effective framework that directly aligns the output of the VLA's visual encoder with spatially-aware features from DINOv2-FiT3D, a DINOv2 model fine-tuned with multi-view consistent 3D Gaussian Splatting supervision. By performing alignment at the visual encoder output level, VEGA grounds spatial awareness before any linguistic entanglement occurs, offering a more interpretable and principled alignment target. The alignment is implemented via a lightweight projector trained with a cosine similarity loss alongside the standard action prediction objective, and is discarded at inference time, introducing no additional computational overhead. Extensive experiments on simulation benchmark and real-world manipulation tasks demonstrate that VEGA consistently outperforms existing implicit spatial grounding baselines, establishing a new state-of-the-art among implicit spatial grounding methods for VLA models.

Hao Wang, Xiaobao Wei, Jingyang He +10

1Peking University, Beijing, China · 2Beijing Innovation Center of Humanoid Robotics, Beijing, China

3D Spatial Reasoning Spatial Grounding for VLA Models Robotic Manipulation Vision-Language-Action Models Visually Grounded Reasoning Vision-Language Alignment

May 11, 2026

Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection

Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge RGB-based semantics. We present Thermal-Det, the first large language model (LLM) supervised open-vocabulary detector tailored for thermal images. To enable large-scale training, we develop a synthetic dataset by converting GroundingCap-1M into the thermal domain and filtering captions to remove RGB-specific terms, yielding over one million thermally aligned samples with bounding boxes, grounding texts, and detailed captions. Thermal-Det jointly optimizes detection, captioning, and cross-modal distillation objectives. A frozen RGB teacher provides geometric and semantic pseudo-supervision for paired but unlabeled RGB-thermal data, transferring open-vocabulary knowledge without manual annotation. The model further employs a Thermal-Text Alignment Head for text calibration and a Modality-Fused Cross-Attention module for dual-modality reasoning. Unlike prior domain-adaptation methods, the detector is fully fine-tuned to internalize thermal contrast patterns while preserving language alignment. Experiments on public benchmarks show consistent 2-4% AP gains over existing open-vocabulary detectors, establishing a strong foundation for scalable, language-driven thermal perception.

Yasiru Ranasinghe, Elim Schenck, Florence Yellin +3

Johns Hopkins University · Kitware · DEVCOM Army Research Laboratory

Open-Vocabulary Object Detection Cross-Modal Knowledge Distillation VLM Adaptation Infrared Object Detection Vision-Language Alignment

May 9, 2026

DAPE: Dynamic Non-uniform Alignment and Progressive Detail Enhancement Techniques for Improving the Performance of Efficient Visual Language Models

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly distributed. Existing methods often overlook the inherent and dynamic differences in information density and semantic scope between text tags and image blocks. These common uniform alignment strategies result in coarse-grained cross-modal interactions and loss of fine semantic details. Moreover, pursuing finer alignment typically requires substantial computational overhead, limiting practical model deployment. To address this challenge, this paper proposes a novel framework for dynamic cross-modal alignment with continuous detail introduction. First, we design a dynamically adaptive cross-modal matching mechanism that uses a learnable matching function to dynamically assign varying numbers and sizes of image tags to text tags of the same size but different information density, enabling more precise attention interaction. Second, we develop a continuous detail introduction module to progressively incorporate high-resolution visual feature enhancement into the alignment process. Extensive experiments across multiple benchmarks demonstrate significant improvements in the accuracy of various downstream tasks while reducing computational overhead.

Mengyuan Tian, Qiyan Zhao, Yanan Wang +1

The Wang Yanan Institute for Studies in Economics, Xiamen University, Xiamen 361005, China · Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China

VLM Adaptation Efficient VLM Inference Vision-Language Alignment