We present Infinite-Story, a training-free framework for consistent text-to-image (T2I) generation tailored for multi-prompt storytelling scenarios. Built upon a scale-wise autoregressive model, our method addresses two key challenges in consistent T2I generation: identity inconsistency and style inconsistency. To overcome these issues, we introduce three complementary techniques: Identity Prompt Replacement, which mitigates context bias in text encoders to align identity attributes across prompts; and a unified attention guidance mechanism comprising Adaptive Style Injection and Synchronized Guidance Adaptation, which jointly enforce global style and identity appearance consistency while preserving prompt fidelity. Unlike prior diffusion-based approaches that require fine-tuning or suffer from slow inference, Infinite-Story operates entirely at test time, delivering high identity and style consistency across diverse prompts. Extensive experiments demonstrate that our method achieves state-of-the-art generation performance, while offering over 6x faster inference (1.72 seconds per image) than the existing fastest consistent T2I models, highlighting its effectiveness and practicality for real-world visual storytelling.
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
We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) within a single coherent framework. To tackle UMS-ReID, we introduce image-text knowledge modeling (ITKM) -- a three-stage framework that effectively exploits the representational power of vision-language models. We start with a pre-trained CLIP model with an image encoder and a text encoder. In Stage I, we introduce a scenario embedding in the image encoder and fine-tune the encoder to adaptively leverage knowledge from multiple scenarios. In Stage II, we optimize a set of learned text embeddings to associate with pseudo-labels from Stage I and introduce a multi-scenario separation loss to increase the divergence between inter-scenario text representations. In Stage III, we first introduce cluster-level and instance-level heterogeneous matching modules to obtain reliable heterogeneous positive pairs (e.g., a visible image and an infrared image of the same person) within each scenario. Next, we propose a dynamic text representation update strategy to maintain consistency between text and image supervision signals. Experimental results across multiple scenarios demonstrate the superiority and generalizability of ITKM; it not only outperforms existing scenario-specific methods but also enhances overall performance by integrating knowledge from multiple scenarios.
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual generation tasks. In this work, we rethink the NTP for autoregressive image generation and extend it to a novel Next Patch Prediction (NPP) paradigm. Our key idea is to group and aggregate image tokens into patch tokens with higher information density. By using patch tokens as a more compact input sequence, the autoregressive model is trained to predict the next patch, significantly reducing computational costs. To further exploit the natural hierarchical structure of image data, we propose a multi-scale coarse-to-fine patch grouping strategy. With this strategy, the training process begins with a large patch size and ends with vanilla NTP where the patch size is 1x1, thus maintaining the original inference process without modifications. Extensive experiments across a diverse range of model sizes demonstrate that NPP could reduce the training cost to around 0.6 times while improving image generation quality by up to 1.0 FID score on the ImageNet 256x256 generation benchmark. Notably, our method retains the original autoregressive model architecture without introducing additional trainable parameters or specifically designing a custom image tokenizer, offering a flexible and plug-and-play solution for enhancing autoregressive visual generation.
Contrastive Language-Image Pretraining (CLIP) has demonstrated impressive generalization on vision-language tasks by aligning images and short texts. However, its inherent 77-token length limits the capacity of capturing complex semantics in long captions. Existing long-text adaptations for CLIP typically rely on either multi-stage training or truncation-based alignment, both inevitably resulting in semantic degradation and cumbersome tuning. Therefore, we propose OneLIP, a unified framework that extends CLIP to understand long captions within a single training stage, eliminating the need for brittle truncation or multi-stage pipelines. OneLIP addresses semantic degradation by introducing two key innovations: (1) Token Refinement and Importance-guided Modeling (TRIM) module, which selects and refines informative tokens via SVD-based contribution scoring and cross-modal relevance modeling; (2) Per-sample Online Hard Negative Mining (PO-HNM) strategy dynamically maintains sample-specific negatives based on dual-consistency difficulty tracking, which is superior in long-text scenarios where key semantics are distributed in scattered positions. Extensive experiments on long-text image retrieval, short-text image retrieval, zero-shot classification, and text-to-image generation demonstrate OneLIP's robustness and versatility across diverse input lengths, offering a faithful solution for long-text representation learning of CLIP.
Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
PDF ↗Multimodal large language models (MLLMs) have achieved significant results in various tasks, but their practical application is still severely constrained by hallucination issues, which are particularly prominent in reinforcement learning (RL) optimization processes. This paper systematically analyzes the causes of hallucinations in MLLM under RL training, identifying three key factors: (1) The model relies heavily on chained visual reasoning to guide decision-making during RL training. Thus, error and irrelevant information in visual reasoning can easily cause hallucinations, including inaccurate initial visual descriptions that anchor subsequent inferences to incorrect information, as well as redundant and broad inferential information; (2) Insufficient exploration diversity during the policy optimization phase, causing the model to output overly confident results; (3) The destructive conflict between different samples during optimization is a key factor that leads to false associations and unstable parameter updates. To address these issues, we propose a solution framework comprising three core modules. First, to improve the accuracy of visual localization, we add planning and caption stages before thinking and answer stages. To enhance initial visual descriptions ability, we allow LLMs to respond based solely on the caption and provide corresponding caption reward based on the quality of the response. Second, to enhance exploration capabilities, we classify samples based on the mean and variance of the reward distribution and select samples with high reward variance for training, thereby increasing the model's focus on diverse samples. Finally, to mitigate conflicts between training samples, we identify neural tangent kernel (NTK) similarity as the key factor. Rather than minimizing it uniformly, we regulate NTK similarity by grouping sample pairs based on a similarity threshold. An InfoNCE loss is then applied to pull dissimilar pairs closer and push overly similar ones apart, guiding interactions toward a balanced range. The experimental results demonstrate that the proposed method significantly reduces the hallucination rate and effectively improves the inference accuracy of MLLMs.
Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational requirements by caching similar features in the inference process of the diffusion model. In this paper, we analyze existing feature caching methods from the perspective of information utilization, and point out that relying solely on historical information will lead to constrained accuracy and speed performance. And we propose a novel paradigm that introduces future information via self-speculation based on the information similarity at the same time step across different iteration times. Based on this paradigm, we present SpecDiff, a training-free multi-level feature caching strategy including a cached feature selection algorithm and a multi-level feature classification algorithm. (1) Feature selection algorithm based on self-speculative information. SpecDiff determines a dynamic importance score for each token based on self-speculative information and historical information, and performs cached feature selection through the importance score. (2) Multi-level feature classification algorithm based on feature importance scores.SpecDiff classifies tokens by leveraging the differences in feature importance scores and introduces a multi-level feature calculation strategy. Extensive experiments show that SpecDiff achieves average 2.80×, 2.74×, and 3.17× speedup with negligible quality loss in Stable Diffusion 3, 3.5, and FLUX compared to RFlow on NVIDIA A800-80GB GPU. By merging speculative and historical information, SpecDiff overcomes the speedup-accuracy trade-off bottleneck, pushing the Pareto frontier of speedup and accuracy in the efficient diffusion model inference.
Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal Attack), a novel adversarial framework on Continuous-Time Dynamic Graphs, which degrades TGNN performance by an average of 29.47% across 4 widely benchmark datasets and 4 State-of-the-Art (SotA) models. LoReTTA operates through a two-stage approach: (1) sparsify the graph by removing high-impact edges using any of the 16 tested temporal importance metrics, (2) strategically replace removed edges with adversarial negatives via LoReTTA’s novel degree-preserving negative sampling algorithm. Our plug-and-play design eliminates the need for expensive surrogate models while adhering to realistic unnoticeability constraints. LoReTTA degrades performance by upto 42.0% on MOOC, 31.5% on Wikipedia, 28.8% on UCI, and 15.6% on Enron. LoReTTA outperforms 11 attack baselines, remains undetectable to 4 leading anomaly detection systems, and is robust to 4 SotA adversarial defense training methods, establishing its effectiveness, unnoticeability, and robustness.
Image restoration has made great progress with the rise of deep learning, but its energy consumption limits its real-world applications. Spiking Neural Networks (SNNs) are seen as energy-efficient alternatives to Artificial Neural Networks (ANNs). Applying SNNs to image restoration (IR) remains challenging, primarily due to the limited information capacity of spike-based signals. This limitation leads to quantization errors and information loss, while IR tasks are highly sensitive to output precision and error. Thus, the restoration performance suffers significantly. To address this challenge, we propose SpikingIR, an ANN-to-SNN conversion framework for IR that reduces information loss and quantization error. SpikingIR mainly consists of two components: Convolutional Pixel Mapping (CPM) and Membrane Potential Reuse Neuron (MPRN), which are designed to alleviate quantization errors and information loss in the output and intermediate layers, respectively. Specifically, CPM maps discrete outputs into a continuous space, better aligning with pixel-level details. From the perspective of information entropy, we show that outputs of CPM contain more information than the original outputs. MPRN introduces a post-processing step with relaxed firing conditions to extract residual membrane potential, reducing information waste. Furthermore, we fine-tune the converted model to jointly optimize both accuracy and energy efficiency. Experimental results demonstrate that SpikingIR achieves performance comparable to ANN counterparts across various IR benchmarks while reducing energy consumption by up to 50%.
Taming the Phantom: Token-Asymmetric Filtering for Hallucination Mitigation in Large Vision-Language Models
PDF ↗Hallucination in Large Vision-Language Models (LVLMs) remains a critical challenge, undermining their reliability in real-world applications. Existing studies have investigated the causes of hallucination at the modality level and proposed effective strategies. However, interaction patterns beyond the modality level remain insufficiently explored. In this paper, we conduct a token-level analysis and identify two key phenomena: (1) a small subset of textual tokens in LVLMs exert disproportionate influence in the visual-active layers, surpassing that of the visual modality and potentially misleading visual understanding; (2) while LVLMs can correctly identify key visual information, insufficient focus on these cues can sometimes lead to hallucinations. Based on such observation, we attribute hallucinations in LVLMs to two token-level causes: the disproportionate influence of certain textual tokens (phantom tokens) and the underutilization of critical visual cues (anchor tokens). To mitigate these issues, we introduce Token-Asymmetric Filtering (TAF)—a training-free, plug-and-play method that modulates intermediate attention maps in LVLMs. TAF isolates the influence of phantom tokens and emphasizes the influence of anchor tokens in the visual-active layers. Experimental results across multiple benchmarks demonstrate that TAF significantly mitigates hallucinations across a range of state-of-the-art LVLMs.
Remote sensing (RS) image–text retrieval faces significant challenges in real-world datasets due to the presence of Pseudo-Matched Pairs (PMPs), semantically mismatched or weakly aligned image–text pairs, which hinder the learning of reliable cross-modal alignments. To address this issue, we propose a novel retrieval framework that leverages Cross-Modal Gated Attention and a Positive–Negative Awareness Attention mechanism to mitigate the impact of such noisy associations. The gated module dynamically regulates cross-modal information flow, while the awareness mechanism explicitly distinguishes informative (positive) cues from misleading (negative) ones during alignment learning. Extensive experiments on three benchmark RS datasets, i.e., RSICD, RSITMD, and RS5M, demonstrate that our method consistently achieves state-of-the-art performance, highlighting its robustness and effectiveness in handling real-world mismatches and PMPs in RS image–text retrieval tasks.
DeLightMono: Enhancing Self-Supervised Monocular Depth Estimation in Endoscopy by Decoupling Uneven Illumination
PDF ↗Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in low-intensity regions. Existing low-light enhancement techniques fail to effectively guide the depth network. Furthermore, solutions from other fields, like autonomous driving, require well-lit images, making them unsuitable and increasing data collection burdens. To this end, we present DeLightMono - a novel self-supervised monocular depth estimation framework with illumination decoupling. Specifically, endoscopic images are represented by a designed illumination-reflectance-depth model, and are decomposed with auxiliary networks. Moreover, a self-supervised joint-optimizing framework with novel losses leveraging the decoupled components is proposed to mitigate the effects of uneven illumination on depth estimation. The effectiveness of the proposed methods was rigorously verified through extensive comparisons and an ablation study performed on two public datasets.
Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these methods have baked-in static environments and only allow for limited scene control -- they are functionally constrained in scene and trajectory diversity by the captures from which they are reconstructed. In contrast, generating driving data with recent image or video diffusion models offers control, however, at the cost of geometry grounding and causality. In this work, we aim to bridge this gap and present a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal novel view synthesis with object permanence and explicit 3D geometry estimation. The proposed method combines the generation of a proxy geometry and environment representation with score distillation from learned 2D image priors. We find that this approach allows for high controllability, enabling the prompt-guided geometry and high-fidelity texture and structure that can be conditioned on map layouts -- producing realistic and geometrically consistent 3D generations of complex driving scenes.
Virtual Multiplex Staining for Histological Images Using a Marker-Wise Conditioned Diffusion Model
PDF ↗Multiplex imaging is revolutionizing pathology by enabling the simultaneous visualization of multiple biomarkers within tissue samples, providing molecular-level insights that traditional hematoxylin and eosin (H&E) staining cannot provide. However, the complexity and cost of multiplex data acquisition have hindered its widespread adoption. Additionally, most existing large repositories of H&E images lack corresponding multiplex images, limiting opportunities for multi-modal analysis. To address these challenges, we leverage recent advances in latent diffusion models (LDMs), which excel at modeling complex data distributions by utilizing their powerful priors for fine-tuning to a target domain. In this paper, we introduce a novel framework for virtual multiplex staining that utilizes pretrained LDM parameters to generate multiplex images from H&E images using a conditional diffusion model. Our approach enables marker-by-marker generation by conditioning the diffusion model on each marker, while sharing the same architecture across all markers. To tackle the challenge of varying pixel value distributions across different marker stains and to improve inference speed, we fine-tune the model for single-step sampling, enhancing both color contrast fidelity and inference efficiency through pixel-level loss functions. We validate our framework on two publicly available datasets, notably demonstrating its effectiveness in generating up to 18 different marker types with improved accuracy, a substantial increase over the 2-3 marker types achieved in previous approaches. This validation highlights the potential of our framework, pioneering virtual multiplex staining. Finally, this paper bridges the gap between H&E and multiplex imaging, potentially enabling retrospective studies and large-scale analyses of existing H&E image repositories.
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
PDF ↗Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.
Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation
PDF ↗Wide-angle cameras, despite their popularity for content creation, suffer from distortion-induced facial stretching—especially at the edge of the lens—which degrades visual appeal. To address this issue, we propose a structure-to-detail portrait correction model named ImagePC. It integrates the long-range awareness of the transformer and multi-step denoising of diffusion models into a unified framework, achieving global structural robustness and local detail refinement. Besides, considering the high cost of obtaining video labels, we then repurpose ImagePC for unlabeled wide-angle videos (termed VideoPC), by spatiotemporal diffusion adaption with spatial consistency and temporal smoothness constraints. For the former, we encourage the denoised image to approximate pseudo labels following the wide-angle distortion distribution pattern, while for the latter, we derive rectification trajectories with backward optical flows and smooth them. Compared with ImagePC, VideoPC maintains high-quality facial corrections in space and mitigates the potential temporal shakes sequentially in blind scenarios. Finally, to establish an evaluation benchmark and train the framework, we establish a video portrait dataset with a large diversity in the number of people, lighting conditions, and background. Experiments demonstrate that the proposed methods outperform existing solutions quantitatively and qualitatively, contributing to high-fidelity wide-angle videos with stable and natural portraits.
One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half.
Identical twin face verification represents an extreme fine-grained recognition challenge where even state-of-the-art systems fail due to overwhelming genetic similarity. Current face recognition methods achieve over 99.8% accuracy on standard benchmarks but drop dramatically to 88.9% when distinguishing identical twins, exposing critical vulnerabilities in biometric security systems. The difficulty lies in learning features that capture subtle, non-genetic variations that uniquely identify individuals. We propose the Asymmetric Hierarchical Attention Network (AHAN), a novel architecture specifically designed for this challenge through multi-granularity facial analysis. AHAN introduces a Hierarchical Cross-Attention (HCA) module that performs multi-scale analysis on semantic facial regions, enabling specialized processing at optimal resolutions. We further propose a Facial Asymmetry Attention Module (FAAM) that learns unique biometric signatures by computing cross-attention between left and right facial halves, capturing subtle asymmetric patterns that differ even between twins. To ensure the network learns truly individuating features, we introduce Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor. Extensive experiments on the ND TWIN dataset demonstrate that AHAN achieves 92.3% twin verification accuracy, representing a 3.4 percentage point improvement over state-of-the-art methods.
The evolution of Visual Large Language Models (VLLMs) has revolutionized the automatic understanding of Visually Rich Documents (VRDs), which contain both textual and visual elements. Although VLLMs excel in Visual Question Answering (VQA) on multi-page VRDs, their ability to detect unanswerable questions is still an open research question. Our research delves into the robustness of the VLLMs to plausible yet unanswerable questions, i.e., questions that appear valid but cannot be answered due to subtle corruptions caused by swaps between related concepts or plausible question formulations. Corruptions are generated by replacing the original natural language entities with other ones of the same type, belonging to different document elements, and in different layout positions or pages of the related document. To this end, we present VRD-UQA (VISUALLY RICH DOCUMENT UNANSWERABLE QUESTION ANSWERING), a benchmark for evaluating VLLMs' resilience to plausible yet unanswerable questions across multiple dimensions. It automatically alters the questions of existing VQA datasets consisting of multi-page VRDs, verifies their unanswerability using a VLLM-as-a-judge approach, and then thoroughly evaluates VLLMs' performance. Experiments, run on 12 models, analyze: (1) The VLLMs' accuracy in detecting unanswerable questions at both page and document levels; (2) The effect of different types of corruption (NLP entity, document element, layout); (3) The effectiveness of different knowledge injection strategies based on in-context learning (OCR, multi-page selection, or the possibility of unanswerability). Our findings reveal VLLMs' limitations and demonstrate that VRD-UQA can serve as an evaluation framework for developing resilient document VQA systems.
FantasyHSI: Video-Generation-Centric 4D Human Synthesis in Any Scene Through a Graph-Based Multi-Agent Framework
PDF ↗Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level tasks and generalizing to unseen scenes. To address these limitations, we introduce FantasyHSI, a novel HSI framework centered on video generation and multi-agent systems that operates without paired data. We model the complex interaction process as a dynamic directed graph, upon which we build a collaborative multi-agent system. This system comprises a scene navigator agent for environmental perception and high-level path planning, and a planning agent that decomposes long-horizon goals into atomic actions. Critically, we introduce a critic agent that establishes a closed-loop feedback mechanism by evaluating the deviation between generated actions and the planned path. This allows for the dynamic correction of trajectory drifts caused by the stochasticity of the generative model, thereby ensuring long-term logical consistency. To enhance the physical realism of the generated motions, we leverage Direct Preference Optimization (DPO) to train the action generator, significantly reducing artifacts such as limb distortion and foot-sliding. Extensive experiments on our custom SceneBench benchmark demonstrate that FantasyHSI significantly outperforms existing methods in terms of generalization, long-horizon task completion, and physical realism.
Promptable segmentation models such as SAM have established a powerful paradigm, enabling strong generalization to unseen objects and domains with minimal user input, including points, bounding boxes, and text prompts. Among these, bounding boxes stand out as particularly effective, often outperforming points while significantly reducing annotation costs. However, current training and evaluation protocols typically rely on synthetic prompts generated through simple heuristics, offering limited insight into real-world robustness. In this paper, we investigate the robustness of promptable segmentation models to natural variations in bounding box prompts. First, we conduct a controlled user study and collect thousands of real bounding box annotations. Our analysis reveals substantial variability in segmentation quality across users for the same model and instance, indicating that SAM-like models are highly sensitive to natural prompt noise. Then, since exhaustive testing of all possible user inputs is computationally prohibitive, we reformulate robustness evaluation as a white-box optimization problem over the bounding box prompt space. We introduce BREPS, a method for generating adversarial bounding boxes that minimize or maximize segmentation error while adhering to naturalness constraints. Finally, we benchmark state-of-the-art models across 10 datasets, spanning everyday scenes to medical imaging.