CVPR 2026 Papers

Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Synthetic data offers a cost-effective and perfectly labeled alternative. However, its performance often lags behind, revealing a significant domain gap between real and current synthetic data. In this work, we systematically analyze mainstream rendering-based synthetic datasets and identify their key limitations: insufficient diversity in corpus, font, and layout, which restricts their realism in complex scenarios. To address these issues, we introduce UnionST, a strong data engine synthesizes text covering a union of challenging samples and better aligns with the complexity observed in the wild. We then construct UnionST-S, a large-scale synthetic dataset with improved simulations in challenging scenarios. Furthermore, we develop a self-evolution learning (SEL) framework for effective real data annotation. Experiments show that models trained on UnionST-S achieve significant improvements over existing synthetic datasets. They even surpass real-data performance in certain scenarios. Moreover, when using SEL, the trained models achieve competitive performance by only seeing 9% of real data labels. Code is available at https://github.com/YesianRohn/UnionST.

Recent advancements in text-to-image synthesis have been largely propelled by diffusion-based models, yet achieving precise alignment between text prompts and generated images remains a persistent challenge. We find that this difficulty arises primarily from the limitations of conventional diffusion loss, which provides only implicit supervision for modeling fine-grained text-image correspondence. In this paper, we introduce Cross-Timestep Self-Calibration (CTCal), founded on the supporting observation that establishing accurate text-image alignment within diffusion models becomes progressively more difficult as the timestep increases. CTCal leverages the reliable text-image alignment (i.e., cross-attention maps) formed at smaller timesteps with less noise to calibrate the representation learning at larger timesteps with more noise, thereby providing explicit supervision during training. We further propose a timestep-aware adaptive weighting to achieve a harmonious integration of CTCal and diffusion loss. CTCal is model-agnostic and can be seamlessly integrated into existing text-to-image diffusion models, encompassing both diffusion-based (e.g., SD 2.1) and flow-based approaches (e.g., SD 3). Extensive experiments on T2I-Compbench++ and GenEval benchmarks demonstrate the effectiveness and generalizability of the proposed CTCal. Our code is available at https://github.com/xiefan-guo/ctcal.

Vision-and-Language Navigation (VLN) requires the agent to navigate based on natural instructions. This task is challenging due to partial observability, which makes it difficult to align perception with language. Recent methods mitigate this by imagining future scenes, yet they rely on vision-based synthesis, leading to high computational cost and redundant details. To this end, we propose to adaptively imagine key environmental semantics via language form, enabling a more reliable and efficient strategy. Specifically, we introduce Adaptive Text Dreamer (ATD), a dual-branch self-guided imagination policy built upon a large language model (LLM). ATD is designed with a human-like left-right brain architecture, where the left brain focuses on logical integration, and the right brain is responsible for imaginative prediction of future scenes. To achieve this, we fine-tune only the Q-former within both brains to efficiently activate domain-specific knowledge in the LLM, enabling dynamic updates of logical reasoning and imagination during navigation. Furthermore, we propose a cross-interaction mechanism that regularizes the imagined latent-space outputs and integrates them with the navigation expert module via a decoder-free latent interface, thereby enabling ATD to jointly harness the reasoning ability of the LLM and the task-specific knowledge of the navigation model. We conduct extensive experiments across the R2R, REVERIE, and R4R benchmarks, demonstrating that ATD achieves competitive performance with significantly fewer parameters. The code will be available.

Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards have become the standard, relying on anonymized model outputs for fairness. In this work, we show that such anonymity can be easily broken. We find that generations from each T2I model form distinctive clusters in the image embedding space, enabling accurate deanonymization without prompt control or training data. Using 22 models and 280 prompts (150K images), our centroid-based method achieves high accuracy and reveals systematic model-specific signatures. We further introduce a prompt-level distinguishability metric and conduct large-scale analyses showing how certain prompts can lead to near-perfect distinguishability. Our findings expose fundamental security flaws in T2I leaderboards and motivate stronger anonymization defenses.

Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on proxy-loss optimization instead of the true end-to-end objective, or depend on large-scale and costly RL-trained generators. Motivated by these limitations, we propose JANUS , a lightweight framework that formulates jailbreak as optimizing a structured prompt distribution under a black-box, end-to-end reward from the T2I system and its safety filters. JANUS replaces a high-capacity generator with a low-dimensional mixing policy over two semantically anchored prompt distributions, enabling efficient exploration while preserving the target semantics. On modern T2I models, we outperform state-of-the-art jailbreak methods, improving ASR-8 from 25.30% to 43.15% on Stable Diffusion 3.5 Large Turbo with consistently higher CLIP and NSFW scores. JANUS succeeds across both open-source and commercial models. These findings expose structural weaknesses in current T2I safety pipelines and motivate stronger, distribution-aware defenses. Warning: This paper contains model outputs that may be offensive.

The recent successes of Vision-Language models raise the question of how to equivalently imbue a pretrained speech model with vision understanding, an important milestone towards building a multimodal speech model able to freely converse about images. Building such a conversational Vision-Speech model brings its unique challenges: (i) paired image-speech datasets are much scarcer than their image-text counterparts, (ii) ensuring real-time latency at inference is crucial thus bringing compute and memory constraints, and (iii) the model should preserve prosodic features (e.g., speaker tone) which cannot be inferred from text alone. In this work, we introduce MoshiVis, augmenting a recent dialogue speech LLM, Moshi, with visual inputs through lightweight adaptation modules. An additional dynamic gating mechanism enables the model to more easily switch between the visual inputs and unrelated conversation topics. To reduce training costs, we design a simple one-stage, parameter-efficient fine-tuning pipeline in which we leverage a mixture of image-text (i.e., "speechless") and image-speech samples. We evaluate the model on downstream visual understanding tasks with both audio and text prompts, and report qualitative samples of interactions with MoshiVis.

Text-to-image models are increasingly utilized in design workflows, but articulating nuanced design intentions solely through text remains a challenge. This work proposes a method that extracts visual attributes from a reference image and injects them directly into the generation pipeline. Specifically, the method optimizes a text token to selectively represent the target attribute using a custom training prompt and two novel embeddings, termed distilled and residual. A wide range of attributes can be extracted through this approach, including shape, material, pose, and camera shot and angle. The effectiveness of the method is validated on various target attributes and text prompts drawn from a newly constructed dataset. The method outperforms existing approaches in selectively extracting and applying target attributes across diverse contexts. Ultimately, the proposed method enables intuitive and controllable text-to-image generation, streamlining the design process.

The rapid advancement of generative AI enables the creation of highly realistic text images, posing significant security risks from fraud and disinformation. However, research into robust detection is critically hampered by existing datasets that lack scale, diversity, and updated counterfeit techniques, as well as by models that fail to generalize. To address these deficiencies, we introduce DanceText, a large-scale, comprehensive dataset for AI-counterfeited text image detection. Constructed using our novel Creative Proposer pipeline, which automates the generation of diverse and realistic counterfeits, DanceText surpasses previous works by over 100-fold in multiple dimensions. It is the first to include counterfeits from multimodal large models, commercial software, and mobile apps, covering all major paradigms, including full-image generation, regional removal, and editing. Building on this dataset, we propose DS-Net, a novel and effective detection model. It features two key components: a Forensic Decoupling Encoder to extract generator-agnostic artifact features, and a Synergy Denoising Decoder that synergizes image-level classification with instance-level localization. Extensive experiments demonstrate that DS-Net achieves state-of-the-art performance, advancing the field toward robust and unified detection of AI-counterfeited text images in real-world scenarios. Both our code and dataset will be released publicly.

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations--such as translating, rotating, or resizing objects--due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations.Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.

Contrastive Language-Image Pre-training (CLIP) offers a new paradigm for Weakly Supervised Semantic Segmentation (WSSS) by generating Class Activation Maps (CAMs) from text-image alignment. Existing methods primarily rely on hand-crafted templates or general attribute descriptions generated by a large language model to construct text prototypes for querying visual features. However, these strategies faces two major limitations: the inherent modality gap in CLIP prevents text prototypes achieving tight alignment with visual features; and their static text prototypes cannot adaptively respond to target instances that exhibit diverse visual attributes. To address these challenges, our key insight is to directly construct instance-specific visual description prototype as query, thereby bypassing the suboptimal static text description optimization. To this end, we propose the Visual Description Assembly (VDA) framework. It employs a probabilistic model to map complex CLIP visual features into a structured latent space. This latent space allows us to explicitly disentangle and aggregate varied visual attributes, and then dynamically assemble them into instance-specific visual prototypes. Furthermore, to enhance the robustness of this prototype, we adaptively incorporate the semantically stable text prototype into it as the final query for generating superior CAMs. Experimental results show our method outperforms existing baselines, achieving state-of-the-art performance on WSSS benchmarks.

Fine-tuning large-scale Vision-Language Models (VLMs) is crucial for specialized tasks, but their performance is often undermined by the label noise prevalent in real-world datasets. Traditional approaches to learning with noisy labels typically rely on a self-referential loop, using a model's own predictions to correct errors. While recent VLM-specific methods have begun to leverage cross-modal information to aid in noise detection, we explore an alternative direction: using the text modality not just to identify noise, but to establish a source of ground truth that is fully independent of the training data's potentially corrupt labels. To this end, we propose Text-ANchored Guided Optimization (TANGO), a framework centered on "semantic anchors"--a set of pure, immutable reference points generated from diverse text descriptions. Building upon these anchors, our approach reframes two key aspects of learning with noisy labels. First, we replace the conventional linear classifier with a parameter-free Text-Anchored Classifier, making predictions a direct, weighted consensus of the clean anchors. Second, we introduce an Anchor-Guided Refinement mechanism that validates each sample's given label against this external ground truth, providing a more robust signal for sample selection and label correction. Extensive experiments demonstrate that this approach achieves competitive and often state-of-the-art performance. Our code will be publicly available.

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment (Null-TTA), which aligns diffusion models by optimising the unconditional embedding in classifier-free guidance, rather than manipulating latent or noise variables. Due to the structured semantic nature of the text embedding space, this ensures alignment occurs on a semantically coherent manifold and prevents reward hacking (exploiting non-semantic noise patterns to improve the reward). Since the unconditional embedding in classifier-free guidance serves as the anchor for the model's generative distribution, Null-TTA directly steers model's generative distribution towards the target reward rather than just adjusting the samples, even without updating model parameters. Thanks to these desirable properties, we show that Null-TTA achieves state-of-the-art target test-time alignment while maintaining strong cross-reward generalisation. This establishes semantic-space optimisation as an effective and principled novel paradigm for TTA.

Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process calibration data from different modalities in a unified manner, overlooking modality-specific behaviors. This raises a critical challenge: how to address the divergent behaviors of textual and visual tokens for accurate pruning of LVLMs. To this end, we systematically investigate the sensitivity of visual and textual tokens to the pruning operation by decoupling their corresponding weights, revealing that: (i) the textual pathway should be calibrated via text tokens, since it exhibits higher sensitivity than the visual pathway; (ii) the visual pathway exhibits high redundancy, permitting even 50% sparsity. Motivated by these insights, we propose a simple yet effective Asymmetric Text-Visual Weight Pruning method for LVLMs, dubbed ATV-Pruning, which establishes the importance metric for accurate weight pruning by selecting the informative tokens from both textual and visual pathways. Specifically, ATV-Pruning integrates two primary innovations: first, a calibration pool is adaptively constructed by drawing on all textual tokens and a subset of visual tokens; second, we devise a layer-adaptive selection strategy to yield important visual tokens. Finally, extensive experiments across standard multimodal benchmarks verify the superiority of our ATV-Pruning over state-of-the-art methods.

Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable. It further underexploits complementary cues across views (e.g., drone, satellite, and street) and modalities (e.g., language and image). To address these challenges, we propose GeoBridge, a novel model that performs bidirectional matching across views and supports language-to-image retrieval. Going beyond traditional satellite-centric formulations, GeoBridge builds on a novel semantic-anchor mechanism that bridges multi-view features through textual descriptions for robust, flexible localization. In support of this task, we construct GeoLoc, the first large-scale, cross-modal, and multi-view aligned dataset comprising over 50,000 pairs of drone, street-view panorama, and satellite images as well as their textual descriptions, collected from 36 countries, ensuring both geographic and semantic alignment. We performed broad evaluations across multiple tasks. Experiments confirm that GeoLoc pre-training markedly improves geo-location accuracy for GeoBridge while promoting cross-domain generalization and cross-modal knowledge transfer. Code, dataset, and pretrained models will be released at https://github.com/MiliLab/GeoBridge.

3D visual grounding (VG) aims to localize target objects in 3D scenes based on free-form textual descriptions. Existing 3D VG models predominantly employ point-based backbones for point cloud feature extraction. Such methods require aggressive downsampling of the input point cloud, which sacrifices the fine-grained spatial details crucial for precise localization. This paper proposes PV-Ground, a novel 3D VG architecture based on effective text-guided point-voxel feature interaction. Our method leverages the complementary strengths of both voxels and keypoints: it employs a voxel-based feature extraction backbone to preserve high-resolution spatial details, while utilizing compact keypoints to aggregate these features for efficient, deep interaction with the textual query. Furthermore, we propose a text-guided keypoint sampling module to adaptively concentrate the keypoint distribution around the text-described object, enabling task-specific feature aggregation and significantly boosts model performance. Extensive qualitative and quantitative experiments demonstrate the superiority of our proposed method. Our method achieves a performance improvement of 5.1% on the ScanRefer dataset and 5.6% on the ReferIt3D dataset, while also achieves over 4% improvement in the segmentation task. The code will be made publicly available.

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent layouts, which are then rendered by graphic engines to produce final images. However, they are blind to the rendered visual outcome, making it difficult to guarantee readability and aesthetics. In this paper, we identify visual feedback as a critical factor in layout generation and propose Visual Feedback Layout Model (VFLM), a self-improving framework that leverages visual feedback iterative refinement. VFLM is capable of performing adaptive reflective generation, which leverages visual information to reflect on previous issues and iteratively generates outputs until satisfactory quality is achieved. It is achieved through reinforcement learning with a visually grounded reward model that incorporates OCR accuracy. By rewarding only the final generated outcome, we can effectively stimulate the model's iterative and reflective generative capabilities. Experiments across multiple benchmarks show that VFLM consistently outperforms advanced MLLMs, existing layout models, and code-only baselines, establishing visual feedback as critical for design-oriented MLLMs. Our code and data are available at https://github.com/FolSpark/VFLM.

Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations.

For video-text retrieval, the use of CLIP has been a de facto standard. However, as CLIP provides only image and text encoders, this consensus has led to a biased paradigm that entirely ignores the sound track of videos. While several attempts have been made to reintroduce audio -- typically by incorporating an audio encoder and fusing its output with visual features -- these methods face two challenges: ineffective representation of speech content and suboptimal vision-audio fusion. To address these issues jointly, we propose SAVE, a Speech Aware Video rEpresentation learning method. SAVE improves upon AVIGATE, a SOTA audiovisual method, with a dedicated speech branch for more effective speech embedding. Furthermore, we introduce soft-ALBEF for early vision-audio alignment that facilitates fusion. Extensive experiments on five benchmarks show that SAVE compares favorably against the SOTA, outperforming AVIGATE by +4.1% on MSRVTT-1k, +1.9% on MSRVTT-3k, +2.5% on VATEX, +9.8% on Charades, and +2.1% on LSMDC, in light of the SumR metric.

Text-Image Person Re-Identification (TI-ReID) is widely deployed in intelligent surveillance. Built on deep neural networks and vision-language models, TI-ReID models inherit vulnerabilities to adversarial attacks, posing security risks. Yet its security remains less explored than retrieval accuracy, and its robustness to adversarial attacks is largely unexplored. To fill this gap, we propose Reconstruction-residual based Targeted and Untargeted Attack (R^2TUA), which generates perturbations from an image and adversarial prompt that mislead TI-ReID into matching the perturbed image with the adversarial identity. To precisely inject identity attributes into perturbations and achieve fine-grained targeted attack, R^2TUA proposes Transformer-based Gradual Multimodal Fusion (TGMF) that fuses image and adversarial prompt progressively across layers with tunable cross-modal weight. In addition, we propose a fully differentiable Soft Clamp Function (SCF), ensuring perturbations remain inconspicuous while avoiding local gradient vanishing effects that would trap training into suboptimal local minima. To further align perturbed images with the adversarial text descriptions while leading them to mismatch their original descriptions, R^2TUA employs (PPLs) and matching losses during training. Extensive evaluations across multiple datasets and models demonstrate the superior untargeted attack and targeted attack performance of R^2TUA. It also exhibits strong adaptability and transferability against black-box models, outperforming all related attacks across multiple tasks.