Despite recent advances in text-to-image (T2I) generation, models still struggle to accurately render prompt-specified text with correct spatial layout—especially in multi-span, structured settings. This challenge is driven not only by the lack of datasets that align prompts with the exact text and layout expected in the image, but also by the absence of effective metrics for evaluating layout quality. To address these issues, we introduce TextGround4M, a large-scale dataset of over 4 million prompt-image pairs, each annotated with span-level text grounded in the prompt and corresponding bounding boxes. This enables fine-grained supervision for layout-aware, prompt-grounded text rendering. Building on this, we propose a lightweight training strategy for autoregressive T2I models that appends layout-aware span tokens during training, without altering model architecture or inference behavior. We further construct a benchmark with stratified layout complexity to evaluate both open-source and proprietary models in a zero-shot setting. In addition, we introduce two layout-aware metrics to address the long-standing lack of spatial evaluation in text rendering. Our results show that models trained on TextGround4M outperform strong baselines in text fidelity, spatial accuracy, and prompt consistency, highlighting the importance of fine-grained layout supervision for grounded T2I generation.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
The widespread deployment of large vision models such as Stable Diffusion raises significant legal and ethical concerns, as these models can memorize and reproduce copyrighted content without authorization. Existing detection approaches often lack robustness and fail to provide rigorous theoretical underpinnings. To address these gaps, we formalize the concept of copyright infringement and its detection from the perspective of Differential Privacy (DP), and introduce the conditional sensitivity metric, a concept analogous to sensitivity in DP, that quantifies the deviation in a diffusion model's output caused by the inclusion or exclusion of a specific training data point. To operationalize this metric, we propose D-Plus-Minus (DPM), a novel post-hoc detection framework that identifies copyright infringement in text-to-image diffusion models. Specifically, DPM simulates inclusion and exclusion processes by fine-tuning models in two opposing directions: learning or unlearning. Besides, to disentangle concept-specific influence from the global parameter shifts induced by fine-tuning, DPM computes confidence scores over orthogonal prompt distributions using statistical metrics. Moreover, to facilitate standardized benchmarking, we also construct the Copyright Infringement Detection Dataset (CIDD), a comprehensive resource for evaluating detection across diverse categories. Our results demonstrate that DPM reliably detects infringement content without requiring access to the original training dataset or text prompts, offering an interpretable and practical solution for safeguarding intellectual property in the era of generative AI.
The deployment of large, black-box foundation models for medical image classification is often hindered by the high cost of acquiring large, task-specific labeled datasets for fine-tuning. While active learning (AL) presents a promising solution, many state-of-the-art AL methods are computationally expensive or require full access to internal model parameters. We present VALIANT (Visual Adaptation and Learning Integration for Active learNing Tasks), a new active learning framework designed to efficiently adapt black-box foundation models by overcoming these limitations. VALIANT introduces a lightweight Visual Prompt Decoder (VIPD), trained via unsupervised Zero-Order Optimization (ZOO), to generate task-specific visual prompts without internal model access. Our core contribution is a perturbation-based ranking strategy that leverages this VIPD to formulate a computationally efficient, gradient-aware informativeness metric. This metric, which we term prompt instability, identifies the most impactful samples for the labeling budget. VALIANT further enhances this process by incorporating anatomical information from unsupervised segmentation maps to generate more discriminative visual prompts. Extensive evaluations on multiple medical datasets demonstrate VALIANT’s superior performance and significant reduction in labeling costs compared to a range of existing active learning techniques, positioning it as a scalable and practical solution for medical image analysis.
Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning
PDF ↗Large Multimodal Models (LMMs) have shown promising in-context learning (ICL) capabilities, but scaling to many-shot settings remains difficult due to limited context length and high inference cost. To address these challenges, task-vector-based methods have been explored by inserting compact representations of many-shot in-context demonstrations into model activations. However, existing task-vector-based methods either overlook the importance of where to insert task vectors or struggle to determine suitable values for each location. To this end, we propose a novel Sensitivity-aware Task Vector insertion framework (STV) to figure out where and what to insert. Our key insight is that activation deltas across query-context pairs exhibit consistent structural patterns, providing a reliable cue for insertion. Based on the identified sensitive-aware locations, we construct a pre-clustered activation bank for each location by clustering the activation values, and then apply reinforcement learning to choose the most suitable one to insert. We evaluate STV across a range of multimodal models (e.g., Qwen-VL, Idefics-2) and tasks (e.g., VizWiz, OK-VQA), demonstrating its effectiveness and showing consistent improvements over previous task-vector-based methods with strong generalization.
Auto-regressive (AR)-based decoders, owing to their flexibility in handling variable-length outputs and their strong capability in modeling character-level dependencies, have emerged as the predominant decoding paradigm in the field of scene text recognition (STR). However, AR-based decoders suffer from attention drift, slow decoding speed, and difficulty capturing global dependencies, restricting their performance in various scenarios. In this paper, we propose a novel paradigm for AR-based decoding, called One-Token to Sequence (One2Seq), to address the above issues. Unlike existing methods, we encode the semantic features into a single context token and design a One-Token Wise Decoder to perform the decoding, which alleviates the attention drift caused by the accumulation of semantic information. Moreover, we proposed Positioal-aware Hash Embedding to embed the decoded characters, ensuring the order information is obtained in the context token. By continuously updating this token, One2Seq fully leverages the decoded semantic information while avoiding the computational overhead associated with the growing query sequence. Furthermore, to leverage global information for decoding, we propose Dynamic Global Infusion to dynamically integrates global visual features into the context token. Equipped with the enriched context token, the model has an enhanced ability to extract discriminative local features under the guidance of global context, thereby enhancing recognition accuracy. Extensive experiments reveal that, with its ingenious design, One2Seq exhibits marked superiority on both accuracy and decoding speed compared to existing STR models.
HyperDiag: Temporal–Regional Hypergraph Learning via Topology-Enhanced State Propagation for Brain Disease Diagnosis
PDF ↗Dynamic brain networks provide a powerful representation for capturing temporal variations in functional brain connectivity and have gained increasing attention in brain disease diagnosis. However, most existing methods extract features from isolated time windows, making it difficult to capture the high-order dynamic evolution of brain activity. Moreover, these methods often neglect the functional heterogeneity among brain regions, thereby limiting diagnostic performance. To address these limitations, we propose HyperDiag, a novel temporal-regional Hypergraph learning via topology-enhanced state propagation for brain disease Diagnosis. Specifically, we first design a dual-level hypergraph learning strategy: a temporally-evolving hypergraph message passing strategy to capture dynamic high-order dependencies within and across time windows, and meanwhile, a region-wise functional hypergraph learning strategy to capture regional dependencies. Subsequently, we construct a topology-enhanced selective state-space propagation network to integrate complementary information from both the temporally-evolving and region-wise features. Extensive experiments on four brain disorder datasets (ABIDE-I, ADNI, REST-meta-MDD, and Epilepsy) demonstrate that HyperDiag not only outperforms state-of-the-art methods but also identifies biologically meaningful abnormal connections, offering potential biomarkers for clinical interpretation.
StyleFM: Frequency Manipulation Empowered by Recursive Attention on Diffusion Models for Arbitrary Style Transfer
PDF ↗Given the remarkable performance of diffusion models in image generation, recent research has been exploring their adaptation to style transfer. However, current diffusion-based approaches encounter persistent challenges, such as style distortions and the reliance on textual prompts for content preservation. To address these limitations, we introduce StyleFM, a novel training-free diffusion-based style transfer approach that incorporates optimization strategies into both the frequency and temporal domains. The proposed method provides two core innovations: (1) Tripartite Frequency Manipulation: To more precisely tailor frequency manipulation, StyleFM introduces a tripartite frequency design with a buffer band accounting for the overlap of content and style representations. In addition, StyleFM designs a frequency superposition editing method to achieve frequency enhancement. (2) Recursive Attention: StyleFM proposes the recursive attention strategy within the diffusion process, which facilitates the progressive and consistent injection of style information throughout the temporal process without reliance on text guidance. Experiments demonstrate that StyleFM outperforms state-of-the-art methods. It effectively preserves content fidelity while achieving sufficient style embedding.
PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning
PDF ↗In recent years, face anti-spoofing (FAS) has made notable progress in multimodal fusion, cross-domain generalization, and interpretability. With the development of large language models and reinforcement learning (RL), strategy-based training paradigms offer new opportunities for jointly modeling multimodality, generalization, and interpretability. However, compared to unimodal reasoning, multimodal reasoning introduces more complex logic, such as accurate feature representation and cross-modal verification, which significantly increases reasoning complexity and labeling difficulty. Due to the lack of high-quality annotations in existing multimodal FAS datasets, directly applying RL strategies is sub-optimal, hindering robust multimodal reasoning. In this paper, we find two key issues of supervised fine-tuning combined with reinforcement learning (SFT+RL) paradigms in multimodal FAS reasoning: 1) limited multimodal reasoning paths not only hinder the full utilization of multimodal information but also constrain the model’s exploration space after SFT, thereby affecting the effectiveness of subsequent RL; and 2) the mismatch between single-task supervision and the diversity of multimodal reasoning paths leads to reasoning confusion, where models may exploit shortcuts by directly mapping input images to answers, bypassing the intended reasoning process. These issues further increase the complexity of multimodal reasoning and hinder the effective application of RL strategies. To address these challenges, we propose the PA-FAS framework with a reasoning path enhancement strategy for high-quality extended reasoning sequences construction based on limited annotated data to enrich the reasoning paths and alleviate exploration constraints. Additionally, we introduce an answer shuffling mechanism during SFT for comprehensive multimodal analysis rather than mining superficial cues, thus encouraging deeper reasoning and avoiding shortcut learning. Our method significantly improves multimodal reasoning accuracy and generalization, and successfully unifies multimodal fusion, cross-domain generalization, and interpretability towards trustworthy multimodal FAS.
3D scene graph prediction aims to abstract complex 3D environments into structured graphs consisting of objects and their pairwise relationships. Existing approaches typically adopt object-centric graph neural networks, where relation edge features are iteratively updated by aggregating messages from connected object nodes. However, this design inherently restricts relation representations to pairwise object context, making it difficult to capture high-order relational dependencies that are essential for accurate relation prediction. To address this limitation, we propose a Link-guided Edge-centric relational reasoning framework with Object-aware fusion, namely LEO, which enables progressive reasoning from relation-level context to object-level understanding. Specifically, LEO first predicts potential links between object pairs to suppress irrelevant edges, and then transforms the original scene graph into a line graph where each relation is treated as a node. A line graph neural network is applied to perform edge-centric relational reasoning to capture inter-relation context. The enriched relation features are subsequently integrated into the original object-centric graph to enhance object-level reasoning and improve relation prediction. Our framework is model-agnostic and can be integrated with any existing object-centric method. Experiments on the 3DSSG dataset with two competitive baselines show consistent improvements, highlighting the effectiveness of our edge-to-object reasoning paradigm.
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and then introduce a CLIP-based framework to construct a visual attribute dictionary, enabling automatic evaluation of image attributes. By systematically analyzing both single-attribute imbalance and compositional attribute imbalance, we reveal how the rarity of attributes affects model performance. To tackle these challenges, we propose adjusting the sampling probability of samples based on the rarity of their compositional attributes. This strategy is further integrated with various data augmentation techniques (such as CutMix, Fmix, and SaliencyMix) to enhance the model's ability to represent rare attributes. Extensive experiments on benchmark datasets demonstrate that our method effectively mitigates attribute imbalance, thereby improving the robustness and fairness of deep neural networks. Our research highlights the importance of modeling visual attribute distributions and provides a scalable solution for long-tail image classification tasks.
Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models
PDF ↗Image Aesthetics Assessment (IAA) evaluates visual quality through user-centered perceptual analysis and can guide various applications. Recent advances in Multimodal Large Language Models (MLLMs) have sparked interest in adapting them for IAA. However, two critical limitations persist in applying MLLMs to IAA: 1) the tokenization strategy leads to insensitivity to scores, and 2) the classification-based decoding mechanisms introduce score quantization errors. Current MLLM-based IAA methods treat the task as coarse rating classification followed by probability-to-score mapping, which loses fine-grained information. To address these challenges, we propose ROC4MLLM, offering complementary solutions from two perspectives:1) Representation: We separate scores from the word token space to avoid tokenizing scores as text. An independent position token bridges these spaces, improving the sensitivity of the model to score positions in text. 2) Computation: We apply distinct loss functions for text and score predictions to enhance the sensitivity of the model to score gradients. Decoupling scores from text ensures effective supervision while preventing interference between scores and text in the loss computation. Extensive experiments across five datasets demonstrate that ROC4MLLM achieves state-of-the-art performance without requiring additional training data. Additionally, its plug-and-play design ensures seamless integration with existing MLLMs, boosting their IAA performance.
Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback
PDF ↗Recent advances in diffusion models have significantly improved audio-driven human video generation, surpassing traditional methods in both quality and controllability. However, existing approaches still face challenges in lip-sync accuracy, temporal coherence for long video generation, and multi-character animation. In this work, we propose a diffusion transformer (DiT)-based framework for generating lifelike talking videos of arbitrary length, and introduce a training-free method for multi-character audio-driven animation. First, we employ a LoRA-based training strategy combined with a position shift inference approach, which enables efficient long video generation while preserving the capabilities of the foundation model. Moreover, we combine partial parameter updates with reward feedback to enhance both lip synchronization and natural body motion. Finally, we propose a training-free approach, Mask Classifier-Free Guidance (Mask-CFG), for multi-character animation, which requires no specialized datasets or model modifications and supports audio-driven animation for three or more characters. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving high-quality, temporally coherent, and multi-character audio-driven video generation in a simple, efficient, and cost-effective manner.
Vision language models (VLMs) that enable natural language interaction with satellite imagery can democratize Earth observation by accelerating expert workflows, making data accessible to non-specialists, and enabling planet-scale automation. However, existing datasets focus mainly on short-term, high-resolution imagery from a limited number of satellites, overlooking low-resolution, multi-satellite, long-term archives, such as Landsat, that are essential for affordable and bias-robust global monitoring. We address this gap with Landsat30-AU, a large-scale vision-language dataset built from 30-meter resolution imagery collected by four Landsat satellites (5, 7, 8, and 9) over Australia, spanning more than 36 years. The dataset includes two components: Landsat30-AU-Cap, containing 196,262 image-caption pairs, and Landsat30-AU-VQA, comprising 17,725 human-verified visual question answering (VQA) samples across eight remote sensing domains. Both datasets are curated through a bootstrapped pipeline that leverages generic VLMs with iterative refinement and human verification to ensure quality. Our evaluation of eight VLMs on our benchmark reveals that off-the-shelf models struggle to understand satellite imagery. The open-source remote-sensing VLM EarthDial achieves only 0.07 SPIDEr in captioning and a VQA accuracy of 0.48, highlighting the limitations of current approaches. Encouragingly, lightweight fine-tuning of Qwen2.5-VL-7B on Landsat30-AU improves captioning performance from 0.11 to 0.31 SPIDEr and boosts VQA accuracy from 0.74 to 0.87.
MFINet: Multi-view Fusion and 2D–3D Interaction Enhancement for Real-Time LiDAR Semantic Segmentation
PDF ↗LiDAR semantic segmentation is a key task in advanced autonomous driving systems. Projection-based methods exhibit real-time potential due to their efficiency, but suffer from inevitable 3D information loss and rely on time-consuming post-processing, limiting overall performance. To address this, we propose MFINet, a real-time semantic segmentation network based on multi-view fusion and 2D-3D interaction enhancement. It adopts a three-branch architecture that integrates 3D Point View (3D-PV), 2D Bird’s Eye View (2D-BEV) and 2D Range View (2D-RV) to make full use of 2D and 3D representation. From 3D to 2D, we design a 3D Point Feature Projector (3DPFP), which injects 3D features into the 2D BEV and RV pseudo-images to retain effective 3D information. From 2D to 3D, a Feature Enhancement (FE) module is designed to leverage the advantages of 2D information in extracting geometric and semantic features. We also introduce a 2D-3D Fusion Head (FH) to aggregate point features from multiple views. Besides, we incorporate a Multi-Scale Dilated Attention (MSDA) module with a sliding window strategy to enhance feature discrimination. Extensive experiments on the SemanticKITTI and NuScenes benchmarks demonstrate that MFINet outperforms existing methods on the SemanticKITTI, NuScenes val set and achieves competitive results on the NuScenes test set.
With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.
Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids
PDF ↗Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks—such as dispensing, aspiration, and mixing—must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks.
Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos
PDF ↗Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.
X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning
PDF ↗Existing open-source datasets for arbitrary-instruction image editing remain suboptimal, while a plug-and-play editing module compatible with community-prevalent generative models is notably absent. In this paper, we first introduce the X2Edit Dataset, a comprehensive dataset covering 14 diverse editing tasks, including subject-driven generation. We utilize the industry-leading unified image generation models and expert models to construct the data. Meanwhile, we design reasonable editing instructions with the VLM and implement various scoring mechanisms to filter the data. As a result, we construct 3.7 million high-quality data with balanced categories. Second, to better integrate seamlessly with community image generation models, we design task-aware MoE-LoRA training based on FLUX.1, with only 8% of the parameters of the full model. To further improve the final performance, we utilize the internal representations of the diffusion model and define positive/negative samples based on image editing types to introduce contrastive learning. Extensive experiments demonstrate that the model's editing performance is competitive among many excellent models. Additionally, the constructed dataset exhibits substantial advantages over existing open-source datasets.
CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving
PDF ↗End-to-end planning methods are the de-facto standard of the current autonomous driving system, while the robustness of the data-driven approaches suffers due to the notorious long-tail problem (i.e., rare but safety-critical failure cases). In this work, we explore whether recent diffusion-based video generation methods (a.k.a. world models), paired with structured 3D layouts, can enable a fully automated pipeline to self-correct such failure cases. We first introduce an agent to simulate the role of product manager, dubbed PM-Agent, which formulates data requirements to collect data similar to the failure cases. Then, we use a generative model that can simulate both data collection and annotation. However, existing generative models struggle to generate high-fidelity data conditioned on 3D layouts. To address this, we propose DriveSora, which can generate spatiotemporally consistent videos aligned with the 3D annotations requested by PM-Agent. We integrate these components into our self-correcting agentic system, CorrectAD. Importantly, our pipeline is end-to-end model agnostic and can be applied to improve any end-to-end planner. Evaluated on both nuScenes and a more challenging in-house dataset across multiple end-to-end planners, CorrectAD corrects 62.5% and 49.8% of failure cases, reducing collision rates by 39% and 27%, respectively.
While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in disentanglement is often unrealistic when target and sensitive factors are naturally correlated. To address this challenge, we propose CAD-VAE(Correlation-Aware Disentangled VAE), which introduces a correlated latent code to capture the information shared between the target and sensitive attributes. Given this correlated latent, our method effectively separates overlapping factors without extra domain knowledge by directly minimizing the conditional mutual information between target and sensitive codes. A relevance-driven optimization strategy refines the correlated code by efficiently capturing essential correlated features and eliminating redundancy. Extensive experiments on benchmark datasets demonstrate that CAD-VAE produces fairer representations, realistic counterfactuals, and improved fairness-aware image editing.