Vision-Language Alignment

Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions. Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement. In this work, we revisit image-text alignment through the lens of cycle consistency: given an image and a caption generated by an image-to-text model, the backward mapping through a text-to-image model should reconstruct an image that closely matches the original. In our setup, a VLM serves as the image-to-text component, while a pre-trained text-to-image model closes the loop by reconstructing the image from the generated caption. Building on this, we introduce CycleCap, a fine-tuning scheme to improve image captioning using Group Relative Policy Optimization (GRPO) with a reward based on the similarity between the original and reconstructed images, computed on-the-fly. Unlike previous work that uses cycle consistency loss for preference dataset construction, our method leverages cycle consistency directly as a self-supervised training signal. This enables the use of raw images alone, eliminating the need for curated image-text datasets, while steering the VLM to produce more accurate and grounded text descriptions. Applied to four VLMs ranging from 1B to 7B parameters, CycleCap yields consistent improvements across captioning and hallucination benchmarks, surpassing state-of-the-art methods that rely on supervised cycle consistency training.

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.

Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial structure of spatial and class aggregations, leading to knowledge interference between class-level semantics and spatial context. Therefore, this paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the above challenge, enabling the model to capture richer vision-language alignment information from cost volumes. Specifically, we design an expert-driven perceptual learning (EPL) module that efficiently integrates semantic and contextual streams. It incorporates a multi-expert parser to extract complementary features from multiple perspectives. In addition, a coefficient mapper is designed to adaptively learn pixel-specific weights for each feature, enabling the integration of complementary knowledge into a unified and robust feature embedding. Furthermore, we propose a feature orthogonalization decoupling (FOD) strategy to mitigate redundancy between the semantic and contextual streams, which allows the EPL module to learn diverse knowledge from orthogonalized features. Extensive experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.

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.

Domain Generalized person Re-identification (DG Re-ID) is a challenging task, where models are trained on source domains but tested on unseen target domains. Although previous pure vision-based models have achieved significant progress, the performance remains further improved. Recently, Vision-Language Models (VLMs) present outstanding generalization capabilities in various visual applications. However, directly adapting a VLM to Re-ID shows limited generalization improvement. This is because the VLM only produces with global features that are insensitive to ID nuances. To tacle this problem, we propose a CLIP-based multi-grained vision-language alignment framework in this work. Specifically, several multi-grained prompts are introduced in language modality to describe different body parts and align with their counterparts in vision modality. To obtain fine-grained visual information, an adaptively masked multi-head self-attention module is employed to precisely extract specific part features. To train the proposed module, an MLLM-based visual grounding expert is employed to automatically generate pseudo labels of body parts for supervision. Extensive experiments conducted on both single- and multi-source generalization protocols demonstrate the superior performance of our approach. The implementation code will be released at https://github.com/RikoLi/MUVA.

Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion. We observe that the most pronounced drift tends to concentrate in vulnerable neighborhoods near the old-new semantic interface, where shared visual patterns are easily re-explained by new textual semantics. To address this under an exemplar-free constraint, we propose Semantic Geometry Preservation for Continual Learning (SeGP-CL). SeGP-CL first probes the drift-prone region by constructing a compact set of adversarial anchors with dual-targeted projected gradient descent (DPGD), which drives selected new-task seeds toward old-class semantics while remaining faithful in raw visual space. During training, we preserve cross-modal structure by anchor-guided cross-modal geometry distillation (ACGD), and stabilize the textual reference frame across tasks via a lightweight text semantic-geometry regularization (TSGR). After training, we estimate anchor-induced raw-space drift to transfer old visual prototypes and perform dual-path inference by fusing cross-modal and visual cues. Extensive experiments on five continual learning benchmarks demonstrate that SeGP-CL consistently improves stability and forward transfer, achieving state-of-the-art performance while better preserving semantic geometry of VLMs. Code is available at: https://github.com/chiyuan-IVIPLab/SeGP-CL.

Vision-language models offer strong few-shot capability through prompt tuning but remain vulnerable to noisy labels, which can corrupt prompts and degrade cross-modal alignment. Existing approaches struggle because they often lack the ability to model fine-grained semantic cues and to adaptively separate clean from noisy signals. To address these challenges, we propose NA-MVP, a framework for Noise-Aware few-shot learning through bi-directional Multi-View Prompt alignment. NA-MVP is built upon a key conceptual shift: robust prompt learning requires moving from global matching to region-aware alignment that explicitly distinguishes clean cues from noisy ones. To realize this, NA-MVP employs (1) multi-view prompts combined with unbalanced optimal transport to achieve fine-grained patch-to-prompt correspondence while suppressing unreliable regions; (2) a bi-directional prompt design that captures complementary clean-oriented and noise-aware cues, enabling the model to focus on stable semantics; and (3) an alignment-guided selective refinement strategy that uses optimal transport to correct only mislabeled samples while retaining reliable data. Experiments on synthetic and real-world noisy benchmarks demonstrate that NA-MVP consistently outperforms state-of-the-art baselines, confirming its effectiveness in enabling robust few-shot learning under noisy supervision.

Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent generative methods tailored for VER demonstrate strong performance but incur high computational costs, limiting their scalability and practical deployment. In this work, we revisit the contrastive paradigm for VER and introduce WikiCLIP, a simple yet effective framework that establishes a strong and efficient baseline for open-domain VER. WikiCLIP leverages large language model embeddings as knowledge-rich entity representations and enhances them with a Vision-Guided Knowledge Adaptor (VGKA) that aligns textual semantics with visual cues at the patch level. To further encourage fine-grained discrimination, a Hard Negative Synthesis Mechanism generates visually similar but semantically distinct negatives during training. Experimental results on popular open-domain VER benchmarks, such as OVEN, demonstrate that WikiCLIP significantly outperforms strong baselines. Specifically, WikiCLIP achieves a 16% improvement on the challenging OVEN unseen set, while reducing inference latency by nearly 100 times compared with the leading generative model, AutoVER. The project page is available at https://artanic30.github.io/project_pages/WikiCLIP/

Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language. However, existing approaches often fail to effectively integrate multi-granular visual and textual information, relying primarily on global image-text alignment. This limitation hinders the model's ability to accurately capture fine-grained details in images, thus restricting its performance in complex, fine-grained tasks. To address this, we propose GeoAlignCLIP, a unified framework that achieves fine-grained alignment in remote sensing tasks by learning multi-granular semantic alignments and incorporating intra-modal consistency, enabling more precise visual-semantic alignment between image regions and text concepts. Additionally, we construct RSFG-100k, a fine-granular remote sensing dataset containing scene descriptions, region-level annotations, and challenging hard-negative samples, providing hierarchical supervision for model training. Extensive experiments conducted on multiple public remote-sensing benchmarks demonstrate that GeoAlignCLIP consistently outperforms existing RS-specific methods across diverse tasks, exhibiting more robust and accurate fine-grained vision-language alignment.

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

Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating local image-text alignment to capture fine-grained visual cues, yet these approaches often select local regions independently for each prompt, leading to redundant local feature usage and prompt overlap. We propose SOT-GLP, which introduces a shared sparse patch support and balanced optimal transport allocation to explicitly partition salient visual regions among class-specific local prompts while preserving global alignment. Our method learns shared global prompts and class-specific local prompts. The global branch maintains standard image-text matching for robust category-level alignment. The local branch constructs a class-conditioned sparse patch set using V-V attention and aligns it to multiple class-specific prompts via balanced entropic optimal transport, yielding a soft partition of patches that prevents prompt overlap and collapse. We evaluate our method on two complementary objectives: (i) few-shot classification accuracy on 11 standard benchmarks and (ii) out-of-distribution (OOD) detection. On the standard 11-dataset benchmark with 16-shot ViT-B/16, SOT-GLP achieves 85.1% average accuracy, outperforming prior prompt-learning methods. We identify a distinct accuracy-robustness trade-off in prompt learning: while learnable projections optimize in-distribution fit, they alter the foundational feature space. We demonstrate that a projection-free local alignment preserves the native geometry of the CLIP manifold, yielding state-of-the-art OOD detection performance (94.2% AUC) that surpasses fully adapted models. Implementation available at: https://github.com/Deniz2304988/SOT-GLP

Caption quality has emerged as a critical bottleneck in training high-quality text-to-image (T2I) and text-to-video (T2V) generative models. While visual language models (VLMs) are commonly deployed to generate captions from visual data, they suffer from hallucinations, poor compositional reasoning, and limited fine-grained understanding, resulting in misaligned image-caption pairs that degrade downstream model performance. This technical report introduces VIVECaption, a systematic two-sided approach to caption quality improvement. We first establish a comprehensive taxonomy of caption evaluation metrics, distinguishing between "universal" and "instance-grounded" metrics, with the ultimate goal of showcasing the use-cases and tradeoffs between different caption quality metrics. We then use this language to describe our two-sided approach to caption quality improvement: (1) a gold-standard dataset creation methodology using stratified sampling and (2) a model alignment strategy encompassing context alignment and parameter-level finetuning using SFT. We demonstrate our methodology on open-source models, focusing on structured caption formats that enable better parsing and downstream utilization. We ultimately show that using a finetuned character detection model in an image captioning pipeline significantly improves holistic image-caption alignment quality. Our work addresses the growing need for high-quality "vegan" training data in enterprise AI development, providing practical solutions for teams seeking to improve caption-image alignment without relying on potentially copyright-protected web-scraped content.

High-performing vision language models still produce incorrect answers, yet their failure modes are often difficult to explain. To make model internals more accessible and enable systematic debugging, we introduce VisualScratchpad, an interactive interface for visual concept analysis during inference. We apply sparse autoencoders to the vision encoder and link the resulting visual concepts to text tokens via text-to-image attention, allowing us to examine which visual concepts are both captured by the vision encoder and utilized by the language model. VisualScratchpad also provides a token-latent heatmap view that suggests a sufficient set of latents for effective concept ablation in causal analysis. Through case studies, we reveal three underexplored failure modes: limited cross-modal alignment, misleading visual concepts, and unused hidden cues. Project page: https://hyesulim.github.io/visual_scratchpad_projectpage/

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown promising results. Current works in traditional visual models suggest that improving visual discriminability enhances performance. However, in VLM-based SF-CDFSL tasks, we find that strengthening visual-modal discriminability actually suppresses VLMs' performance. In this paper, we aim to delve into this phenomenon for an interpretation and a solution. By both theoretical and experimental proofs, our study reveals that fine-tuning with the typical cross-entropy loss ($\mathcal{L}_{\mathrm{vlm}}$) inherently includes a visual learning part and a cross-modal learning part, where the cross-modal part is crucial for rectifying the heavily disrupted modality misalignment in SF-CDFSL. However, we find that the visual learning essentially acts as a shortcut that encourages the model to reduce $\mathcal{L}_{\mathrm{vlm}}$ without considering the cross-modal part, therefore hindering the cross-modal alignment and harming the performance. Based on this interpretation, we further propose an approach to address this problem: first, we perturb the visual learning to guide the model to focus on the cross-modal alignment. Then, we use the visual-text semantic relationships to gradually align the visual and textual modalities during the fine-tuning. Extensive experiments on various settings, backbones (CLIP, SigLip, PE-Core), and tasks (4 CDFSL datasets and 11 FSL datasets) show that we consistently set new state-of-the-art results. Code is available at https://github.com/zhenyuZ-HUST/CVPR26-Mind-the-Discriminability-Trap.

When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We observe that this degradation is related to the deterioration of cross-modal information structure, where dependencies among visual observations, language instructions, and actions progressively diffuse during continual adaptation. But existing continual learning methods fail to preserve such cross-modal information dependencies. Thus, we propose Info-VLA, an information-preserving continual learning framework that maintains cross-modal information structure through two complementary constraints. Replay Anchor Contrastive Learning constructs stable alignment anchors from a frozen teacher model, preserving cross-modal alignment in the representation space. Cross-Modal Mutual Information Maximization further preserves dependency structure between visual and language representations through mutual information constraints. By jointly preserving historical alignment and cross-modal dependency information, Info-VLA balances stability and plasticity during continual learning. Furthermore, experiments on the LIBERO show that Info-VLA significantly outperforms existing methods in both task retention and adaptation.

Generative zero-shot learning (ZSL) synthesizes visual features for unseen classes by learning a semantic-conditioned generator from seen classes. Since semantic conditions determine the knowledge transfer from seen to unseen classes, their effectiveness is critical for generating plausible features. However, existing class-level semantic prototypes lack semantic diversity to capture intra-class variations, while exhibiting inconsistent inter-class structures with the visual space due to the semantic-visual gap. To address these issues, we propose Adaptive Attribute Distribution and Visual Structure Alignment (AAVS), a unified semantic condition learning framework for generative ZSL. Specifically, the Adaptive Attribute Distribution (AAD) learns dimension-adaptive attribute distributions with discriminability-guided variation calibration to capture transferable semantic diversity, while Visual Structure Alignment (VSA) aligns the diverse attributes with refined visual prototypes to learn visual inter-class structures. By jointly modeling semantic diversity and visual structural consistency, AAVS provides more effective generation conditions for unseen classes to generate visual features. Extensive quantitative and qualitative evaluations on three benchmarks demonstrate that AAVS outperforms existing generative ZSL methods and validate the effectiveness of the learned generation conditions.

Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (region-text) and intra-modal (region-region) alignments. This multimodal degradation is a unique challenge that prior quantization methods for closed-vocabulary detectors fail to resolve. To overcome this, we propose Quantization-Aware Training with Multimodal Alignment (QATMA), the first multimodal-aware and architecture-agnostic QAT framework tailored for OVOD. QATMA integrates two key components: (i) Curriculum QAT, which partitions the detector by functional roles and progressively expands the quantization scope to suppress error accumulation and ensure stable optimization; and (ii) Text-anchored Pairwise Similarity Distillation, which transfers both region-text and region-region alignments from a full-precision teacher model via pairwise cosine similarities in the joint embedding space. Experimental results on LVIS and COCO zero-shot benchmarks demonstrate that QATMA significantly outperforms existing QAT baselines under extremely low-bit settings, achieving gains of up to 4.3 and 7.6 AP, respectively.

To address the limitations of existing open-vocabulary object recognition methods, including high system complexity, substantial training costs, and limited generalization capability, this paper proposes a novel Open-Vocabulary Object Recognition (OVOR) framework based on a streamlined two-stage strategy: object segmentation followed by recognition. The proposed framework eliminates the need for complex retraining procedures and labor-intensive annotation. After extracting object regions, object-level image embeddings and category-level text embeddings are generated using CLIP, enabling recognition over arbitrary vocabularies. To reduce dependence on CLIP and enhance encoding flexibility, we further introduce a CNN/MLP-based approach that extracts convolutional neural network (CNN) feature maps and employs a multilayer perceptron (MLP) to align visual features with text embeddings. The resulting embeddings are then concatenated for cross-modal matching. Finally, object recognition is performed through similarity matching between image and text embeddings. Experiments on COCO, Pascal VOC, and ADE20K demonstrate that CLIP-based image encoding achieves the highest average AP, outperforming current state-of-the-art methods. Meanwhile, the results reveal the potential of CLIP-independent image encoding as a promising alternative for OVOR.

Temporal Sentence Grounding in Videos (TSGV) aims to temporally localize segments of a video that correspond to a given natural language query. Despite recent progress, most existing TSGV approaches operate under closed-vocabulary settings, limiting their ability to generalize to real-world queries involving novel or diverse linguistic expressions. To bridge this critical gap, we introduce the Open-Vocabulary TSGV (OV-TSGV) task and construct the first dedicated benchmarks--Charades-OV and ActivityNet-OV--that simulate realistic vocabulary shifts and paraphrastic variations. These benchmarks facilitate systematic evaluation of model generalization beyond seen training concepts. To tackle OV-TSGV, we propose HERO(Hierarchical Embedding-Refinement for Open-Vocabulary grounding), a unified framework that leverages hierarchical linguistic embeddings and performs parallel cross-modal refinement. HERO jointly models multi-level semantics and enhances video-language alignment via semantic-guided visual filtering and contrastive masked text refinement. Extensive experiments on both standard and open vocabulary benchmarks demonstrate that HERO consistently surpasses state-of-the-art methods, particularly under open-vocabulary scenarios, validating its strong generalization capability and underscoring the significance of OV-TSGV as a new research direction.

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where CLIP has recently shown promising results due to its generalizability to downstream tasks. Current works indicate CLIP's text encoder is more suitable for cross-domain tasks, however, we find that removing certain middle layers of the text encoder can effectively improve performance in SF-CDFSL, which we call the Lost Layers. In this paper, we delve into this phenomenon for a deeper understanding. We discover that instead of being harmful for the SF-CDFSL task, the information in these layers is actually beneficial, but visual gaps prevent this useful information from being fully utilized, making these layers seem redundant. Based on this understanding, unlike current works that simply remove these layers, we propose a method to teachs the model to re-utilize information in these lost layers at both the layer and encoder levels, guiding the re-learning of the visual branch under domain shifts. Our approach effectively addresses the issue of underutilized information in the text encoder. Extensive experiments across various settings, backbones (CLIP, SigLip, PE-Core), and tasks (4 CDFSL datasets and 10 Meta-dataset datasets) demonstrate the effectiveness of our method. Code is available at https://github.com/zhenyuZ-HUST/CVPR26-VtT.

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

Large Multimodal Models (LMMs) have achieved strong performance in vision-language understanding, yet many existing approaches rely on large-scale architectures and coarse supervision, which limits their ability to generate detailed image captions. In this work, we present VisionPangu, a compact 1.7B-parameter multimodal model designed to improve detailed image captioning through efficient multimodal alignment and high-quality supervision. Our model combines an InternVL-derived vision encoder with the OpenPangu-Embedded language backbone via a lightweight MLP projector and adopts an instruction-tuning pipeline inspired by LLaVA. By incorporating dense human-authored descriptions from the DOCCI dataset, VisionPangu improves semantic coherence and descriptive richness without relying on aggressive model scaling. Experimental results demonstrate that compact multimodal models can achieve competitive performance while producing more structured and detailed captions. The code and model weights will be publicly available at https://www.modelscope.cn/models/asdfgh007/visionpangu.

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective discrepancies and serving efficiency bottlenecks. This paper introduces PinCLIP, a large-scale visual representation learning approach developed to enhance retrieval and ranking models at Pinterest by leveraging VLMs to learn image-text alignment. We propose a novel hybrid Vision Transformer architecture that utilizes a VLM backbone and a hybrid fusion mechanism to capture multi-modality content representation at varying granularities. Beyond standard image-to-text alignment objectives, we introduce a neighbor alignment objective to model the cross-fusion of multi-modal representations within the Pinterest Pin-Board graph. Offline evaluations show that PinCLIP outperforms state-of-the-art baselines, such as Qwen, by 20% in multi-modal retrieval tasks. Online A/B testing demonstrates significant business impact, including substantial engagement gains across all major surfaces in Pinterest. Notably, PinCLIP significantly addresses the "cold-start" problem, enhancing fresh content distribution with a 15% Repin increase in organic content and 8.7% higher click for new Ads.

Despite the growing interest in open-vocabulary object detection in recent years, most existing methods rely heavily on manually curated fine-grained training datasets as well as resource-intensive layer-wise cross-modal feature extraction. In this paper, we propose HDINO, a concise yet efficient open-vocabulary object detector that eliminates the dependence on these components. Specifically, we propose a two-stage training strategy built upon the transformer-based DINO model. In the first stage, noisy samples are treated as additional positive object instances to construct a One-to-Many Semantic Alignment Mechanism(O2M) between the visual and textual modalities, thereby facilitating semantic alignment. A Difficulty Weighted Classification Loss (DWCL) is also designed based on initial detection difficulty to mine hard examples and further improve model performance. In the second stage, a lightweight feature fusion module is applied to the aligned representations to enhance sensitivity to linguistic semantics. Under the Swin Transformer-T setting, HDINO-T achieves 49.2 mAP on COCO using 2.2M training images from two publicly available detection datasets, without any manual data curation and the use of grounding data, surpassing Grounding DINO-T and T-Rex2 by 0.8 mAP and 2.8 mAP, respectively, which are trained on 5.4M and 6.5M images. After fine-tuning on COCO, HDINO-T and HDINO-L further achieve 56.4 mAP and 59.2 mAP, highlighting the effectiveness and scalability of our approach. Code and models are available at https://github.com/HaoZ416/HDINO.

Vision-language models like CLIP have achieved remarkable progress in cross-modal representation learning, yet suffer from systematic misclassifications among visually and semantically similar categories. We observe that such confusion patterns are not random but persistently occur between specific category pairs, revealing the model's intrinsic bias and limited fine-grained discriminative ability. To address this, we propose CAPT, a Confusion-Aware Prompt Tuning framework that enables models to learn from their own misalignment. Specifically, we construct a Confusion Bank to explicitly model stable confusion relationships across categories and misclassified samples. On this basis, we introduce a Semantic Confusion Miner (SEM) to capture global inter-class confusion through semantic difference and commonality prompts, and a Sample Confusion Miner (SAM) to retrieve representative misclassified instances from the bank and capture sample-level cues through a Diff-Manner Adapter that integrates global and local contexts. To further unify confusion information across different granularities, a Multi-Granularity Difference Expert (MGDE) module is designed to jointly leverage semantic- and sample-level experts for more robust confusion-aware reasoning. Extensive experiments on 11 benchmark datasets demonstrate that our method significantly reduces confusion-induced errors while enhancing the discriminability and generalization of both base and novel classes, successfully resolving 50.72 percent of confusable sample pairs. Code will be released at https://github.com/greatest-gourmet/CAPT.

We introduce V-SONAR, a vision-language embedding space extended from the text-only embedding space SONAR (Omnilingual Embeddings Team et al., 2026), which supports 1500 text languages and 177 speech languages. To construct V-SONAR, we propose a post-hoc alignment pipeline that maps the representations of an existing vision encoder into the SONAR space. We thoroughly evaluate V-SONAR and show that its embeddings achieve competitive performance on text-to-video retrieval. Equipped with the OMNISONAR text decoder, V-SONAR further surpasses state-of-the-art vision-language models on video captioning tasks, including DREAM-1K (BLEU 23.9 vs. 19.6) and PE-VIDEO (BLEU 39.0 vs. 30.0). Leveraging V-SONAR, we first demonstrate that the Large Concept Model (LCM; LCM team et al. 2024) operating in SONAR and trained with English text only, can perform both single- and multi-visual concept understanding in a zero-shot manner. Finally, we introduce V-LCM, which extends the LCM with vision-language instruction tuning. V-LCM encodes vision and language inputs into an unified sequence of latent embeddings via V-SONAR and SONAR, and it is trained with the same latent diffusion objective for next-embedding prediction as in LCM's text-only pre-training. Experiments on a large-scale multilingual and -modal instruction-tuning data mixture highlight the potential of V-LCM: V-LCM matches state-of-the-art vision-language models on tasks covering image/video captioning and question answering, while significantly outperforming them across 61 rich- to low-resource languages out of all 62 tested languages.

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This reliance leads to high false-positive rates on semantically normal background regions such as sky or vegetation, and poor recall of true Out-of-distribution (OOD) instances, thereby posing safety risks for robotic perception and decision-making. To address these challenges, we propose VL-Anomaly, a vision-language anomaly segmentation framework that incorporates semantic priors from pre-trained Vision-Language Models (VLMs). Specifically, we design a prompt learning-driven alignment module that adapts Mask2Forme's visual features to CLIP text embeddings of known categories, effectively suppressing spurious anomaly responses in background regions. At inference time, we further introduce a multi-source inference strategy that integrates text-guided similarity, CLIP-based image-text similarity and detector confidence, enabling more reliable anomaly prediction by leveraging complementary information sources. Extensive experiments demonstrate that VL-Anomaly achieves state-of-the-art performance on benchmark datasets including RoadAnomaly, SMIYC and Fishyscapes.Code is released on https://github.com/NickHezhuolin/VL-aligner-Road-anomaly-segment.

Visual-Language Models (VLMs), with their strong capabilities in image and text understanding, offer a solid foundation for intelligent communications. However, their effectiveness is constrained by limited token granularity, overlong visual token sequences, and inadequate cross-modal alignment. To overcome these challenges, we propose TaiChi, a novel VLM framework designed for token communications. TaiChi adopts a dual-visual tokenizer architecture that processes both high- and low-resolution images to collaboratively capture pixel-level details and global conceptual features. A Bilateral Attention Network (BAN) is introduced to intelligently fuse multi-scale visual tokens, thereby enhancing visual understanding and producing compact visual tokens. In addition, a Kolmogorov Arnold Network (KAN)-based modality projector with learnable activation functions is employed to achieve precise nonlinear alignment from visual features to the text semantic space, thus minimizing information loss. Finally, TaiChi is integrated into a multimodal and multitask token communication system equipped with a joint VLM-channel coding scheme. Experimental results validate the superior performance of TaiChi, as well as the feasibility and effectiveness of the TaiChi-driven token communication system.

The development of 3D Vision-Language Models (VLMs), crucial for applications in robotics, autonomous driving, and augmented reality, is severely constrained by the scarcity of paired 3D-text data. Existing methods rely solely on next-token prediction loss, using only language tokens for supervision. This results in inefficient utilization of limited 3D data and leads to a significant degradation and loss of valuable geometric information in intermediate representations. To address these limitations, we propose {\mname}, a novel feature-level alignment regularization method. {\mname} explicitly supervises intermediate point cloud tokens to preserve fine-grained 3D geometric-semantic information throughout the language modeling process. Specifically, we constrain the intermediate point cloud tokens within the LLM to align with visual input tokens via a consistency loss. By training only a lightweight alignment projector and LoRA adapters, {\mname} achieves explicit feature-level supervision with minimal computational overhead, effectively preventing geometric degradation. Extensive experiments on ModelNet40 and Objaverse datasets demonstrate that our method achieves 2.08 pp improvement on average for classification tasks, with a substantial 7.50 pp gain on the challenging open-vocabulary Objaverse classification task and 4.88 pp improvement on 3D object captioning evaluated by Qwen2-72B-Instruct, validating the effectiveness of {\mname}. Code is publicly available at https://github.com/yharoldsu0627/PointAlign.

When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or relation to an otherwise correct description can increase the similarity score. We call such cases half-truths. On COCO, CLIP prefers the correct shorter description only 34.0% of the time, and performance drops to 27.8% when the added detail is a relation. We trace this vulnerability to weak supervision on caption parts: contrastive training aligns full sentences but does not explicitly enforce that individual entities and relations are grounded. We propose CS-CLIP (Component-Supervised CLIP), which decomposes captions into entity and relation units, constructs a minimally edited foil for each unit, and fine-tunes the model to score the correct unit above its foil while preserving standard dual-encoder inference. CS-CLIP raises half-truth accuracy to 76.4% and improves average performance on established compositional benchmarks by 5.8 points, suggesting that reducing half-truth errors aligns with broader gains in compositional understanding.