Papers

Scene text editing (STE) has achieved remarkable progress in accurately rendering target text through diffusion-based methods. However, we identify a critical yet overlooked problem: edit spillover – when editing a target text region, existing methods inadvertently modify non-target regions, particularly neighboring text. Through systematic evaluation on 50 real-world scenes across four categories, we reveal that state-of-the-art diffusion editing models exhibit a spillover rate of 94%, meaning nearly all non-target text regions are altered during editing. To address this, we propose the Edit Fidelity Field (EFF), a semantics-aware continuous field that controls per-pixel editing fidelity. Unlike binary masks, EFF leverages OCR-detected text regions to construct a four-zone field: Edit Core (fully editable), Transition Zone (smooth decay), Protected Zone (non-target text, explicitly locked), and Background (strictly preserved). EFF operates as a training-free, model-agnostic post-processing module applicable to any diffusion-based STE method. We further propose per-region spillover quantification, a novel evaluation protocol that measures edit leakage at each non-target text region individually. Experiments demonstrate that EFF reduces spillover rate from 94% to 25% while improving non-target region preservation by +91.4 dB PSNR.

Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic features extracted from pre-trained visual encoders. However, existing approaches rely on a fixed representation space, constructed independently of the generative objective and kept unchanged during training. We argue that the representation space guiding diffusion should itself adapt to the generative task. To this end, we propose Coevolving Representation Diffusion (CoReDi), a framework in which the semantic representation space evolves during training by learning a lightweight linear projection jointly with the diffusion model. While naively optimizing this projection leads to degenerate solutions, we show that stable coevolution can be achieved through a combination of stop-gradient targets, normalization, and targeted regularization that prevents feature collapse. This formulation enables the semantic space to progressively specialize to the needs of image synthesis, improving its complementarity with image latents. We apply CoReDi to both VAE latent diffusion and pixel-space diffusion, demonstrating that adaptive semantic representations improve generative modeling across both settings. Experiments show that CoReDi achieves faster convergence and higher sample quality compared to joint diffusion models operating in fixed representation spaces.

Manual annotation of high-quality visual question answering with grounding (VQA-G) datasets, which pair visual questions with evidential grounding, is crucial for advancing vision-language models (VLMs), but remains unscalable. Existing automated methods are often hindered by two key issues: (1) inconsistent data fidelity due to model hallucinations; (2) brittle verification mechanisms based on simple heuristics. To address these limitations, we introduce AutoVQA-G, a self-improving agentic framework for automated VQA-G annotation. AutoVQA-G employs an iterative refinement loop where a Consistency Evaluation module uses Chain-of-Thought (CoT) reasoning for fine-grained visual verification. Based on this feedback, a memory-augmented Prompt Optimization agent analyzes critiques from failed samples to progressively refine generation prompts. Our experiments show that AutoVQA-G generates VQA-G datasets with superior visual grounding accuracy compared to leading multimodal LLMs, offering a promising approach for creating high-fidelity data to facilitate more robust VLM training and evaluation. Code: https://github.com/rohnson1999/AutoVQA-G

Advanced deepfake technologies are blurring the lines between real and fake, presenting both revolutionary opportunities and alarming threats. While it unlocks novel applications in fields like entertainment and education, its malicious use has sparked urgent ethical and societal concerns ranging from identity theft to the dissemination of misinformation. To tackle these challenges, feature analysis using frequency features has emergedas a promising direction for deepfake detection. However, oneaspect that has been overlooked so far is that existing methodstend to concentrate on one or a few specific frequency domains,which risks overfitting to particular artifacts and significantlyundermines their robustness when facing diverse forgery patterns. Another underexplored aspect we observe is that different features often attend to the same forged region, resulting in redundant feature representations and limiting the diversity of the extracted clues. This may undermine the ability of a model to capture complementary information across different facets, thereby compromising its generalization capability to diverse manipulations. In this paper, we seek to tackle these challenges from two aspects: (1) we propose a triple-branch network that jointly captures spatial and frequency features by learning from both original image and image reconstructed by different frequency channels, and (2) we mathematically derive feature decoupling and fusion losses grounded in the mutual information theory, which enhances the model to focus on task-relevant features across the original image and the image reconstructed by different frequency channels. Extensive experiments on six large-scale benchmark datasets demonstrate that our method consistently achieves state-of-the-art performance. Our code is released at https://github.com/injooker/Unveiling Deepfake.

Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive computational overhead, limiting scalability. We introduce a framework, Privatar, to offload avatar reconstruction from headset to untrusted devices within the same local network while safeguarding attacks against adversaries capable of intercepting offloaded data. Privatar's key insight is that domain-specific knowledge of avatar reconstruction enables provably private offloading at minimal cost. (1) System level. We observe avatar reconstruction is frequency-domain decomposable via BDCT with negligible quality drop, and propose Horizontal Partitioning (HP) to keep high-energy frequency components on-device and offloads only low-energy components. HP offloads local computation while reducing information leakage to low-energy subsets only. (2) Privacy level. For individually offloaded, multi-dimensional signals without aggregation, worst-case local Differential Privacy requires prohibitive noise, ruining utility. We observe users' expression statistical distribution are slowly changing over time and trackable online, and hence propose Distribution-Aware Minimal Perturbation. DAMP minimizes noise based on each user's expression distribution to significantly reduce its effects on utility, retaining formal privacy guarantee. Combined, HP provides empirical privacy against expression identification attacks. DAMP further augments it to offer a formal guarantee against arbitrary adversaries. On a Meta Quest Pro, Privatar supports 2.37x more concurrent users at 6.5% higher reconstruction loss and 9% energy overhead, providing a better throughout-loss Pareto frontier over quantization, sparsity and local construction baselines. Privatar provides both provable privacy guarantee and stays robust against both empirical and NN-based attacks.

Vision-Language Navigation(VLN) requires an agent to navigate through 3D environments by following natural language instructions. While recent Video Large Language Models(Video-LLMs) have largely advanced VLN, they remain highly susceptible to State Drift in long scenarios. In these cases, the agent's internal state drifts away from the true task execution state, leading to aimless wandering and failure to execute essential maneuvers in the instruction. We attribute this failure to two distinct cognitive deficits: Progress Drift, where the agent fails to distinguish completed sub-goals from remaining ones, and Memory Drift, where the agent's history representations degrade, making it lose track of visited landmarks. In this paper, we propose a Dual-Anchoring Framework that explicitly anchors the instruction progress and history representations. First, to address progress drift, we introduce Instruction Progress Anchoring, which supervises the agent to generate structured text tokens that delineate completed versus remaining sub-goals. Second, to mitigate memory drift, we propose Memory Landmark Anchoring, which utilizes a Landmark-Centric World Model to retrospectively predict object-centric embeddings extracted by the Segment Anything Model, compelling the agent to explicitly verify past observations and preserve distinct representations of visited landmarks. Facilitating this framework, we curate two extensive datasets: 3.6 million samples with explicit progress descriptions, and 937k grounded landmark data for retrospective verification. Extensive experiments in both simulation and real-world environments demonstrate the superiority of our method, achieving a 15.2% improvement in Success Rate and a remarkable 24.7% gain on long-horizon trajectories. To facilitate further research, we will release our code, data generation pipelines, and the collected datasets.

Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D generation (e.g., synthesis, completion, and editing). However, these tasks are often tackled in isolation, resulting in fragmented architectures and representations that hinder knowledge transfer and holistic scene modeling. To address these challenges, we propose UniMesh, a unified framework that jointly learns 3D generation and understanding within a single architecture. First, we introduce a novel Mesh Head that acts as a cross model interface, bridging diffusion based image generation with implicit shape decoders. Second, we develop Chain of Mesh (CoM), a geometric instantiation of iterative reasoning that enables user driven semantic mesh editing through a closed loop latent, prompting, and re generation cycle. Third, we incorporate a self reflection mechanism based on an Actor Evaluator Self reflection triad to diagnose and correct failures in high level tasks like 3D captioning. Experimental results demonstrate that UniMesh not only achieves competitive performance on standard benchmarks but also unlocks novel capabilities in iterative editing and mutual enhancement between generation and understanding. Code: https://github.com/AIGeeksGroup/UniMesh. Website: https://aigeeksgroup.github.io/UniMesh.

Visual prompting has emerged as a powerful method for adapting pre-trained models to new domains without updating model parameters. However, existing prompting methods typically optimize a single prompt per domain and apply it uniformly to all inputs, limiting their ability to generalize under intra and inter-domain variability, which is especially critical in the medical field. To address this, we propose APEX, an Adaptive Prompt EXtraction framework that retrieves input-specific prompts from a learnable prompt memory. The memory stores diverse, domain-discriminative prompt representations and is queried via domain features extracted from the Fourier spectrum. To learn robust and discriminative domain features, we introduce a novel Low-Frequency Feature Contrastive (LFC) learning framework that clusters representations from the same domain while separating those from different domains. Extensive experiments on two medical segmentation tasks demonstrate that APEX significantly improves generalization across both seen and unseen domains. Furthermore, it complements any existing backbones and consistently enhances performance, confirming its effectiveness as a plug-and-play prompting solution in medical fields. The code is available at https://github.com/cetinkayaevren/apex/

Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. To address this, we propose Hyperbolic Scene Graph (HSG), which learns scene graph embeddings in hyperbolic space where hierarchical relationships are naturally encoded through geometric distance. Our results show that HSG improves hierarchical structure quality while maintaining strong retrieval performance. The largest gains are observed in graph level metrics: HSG achieves a PP IoU of 33.17 and the highest Graph IoU of 33.51, outperforming the best AoMSG variant (25.37) by 8.14, highlighting the effectiveness of hyperbolic representation learning for scene graph modeling. Code: https://github.com/AIGeeksGroup/HSG.

Being one of the oldest and most basic problems in image processing, image denoising has seen a resurgence spurred by rapid advances in deep learning. Yet, most modern denoising architectures make limited use of the technical knowledge acquired researching the classical denoisers that came before the mainstream use of neural networks, instead relying on depth and large parameter counts. This poses a challenge not only for understanding the properties of such networks, but also for deploying them on real devices which may present resource constraints and diverse noise profiles. Tackling both issues, we propose an architecture dedicated to RAW-to-RAW denoising that incorporates the interpretable structure of classical self-similarity-based denoisers into a fully learnable neural network. Our design centers on a novel nonlocal block that parallels the established pipeline of neighbor matching, collaborative filtering and aggregation popularized by nonlocal patch-based methods, operating on learned multiscale feature representations. This built-in nonlocality efficiently expands the receptive field, sufficing a single block per scale with a moderate number of neighbors to obtain high-quality results. Training the network on a curated dataset with clean real RAW data and modeled synthetic noise while conditioning it on a noise level map yields a sensor-agnostic denoiser that generalizes effectively to unseen devices. Both quantitative and visual results on benchmarks and in-the-wild photographs position our method as a practical and interpretable solution for real-world RAW denoising, achieving results competitive with state-of-the-art convolutional and transformer-based denoisers while using significantly fewer parameters. The code is available at https://github.com/MIA-UIB/nonlocal-matchfilter .

Increasingly advanced data augmentation techniques have greatly aided clinical medical research, increasing data diversity and improving model generalization capabilities. Although most current basic models exhibit strong generalization abilities, image quality varies due to differences in equipment and operators. To address these challenges, we present SegTTA, a framework that improves medical image segmentation without model retraining by combining four augmentations (Gamma correction, Contrast enhancement, Gaussian blur, Gaussian noise) with weighted voting across multiple MedSAM2 checkpoints. Experiments demonstrate consistent improvements across three diverse datasets: healthy uterus segmentation, uterine myoma detection, and multi class hepatic structure segmentation. Ablation studies reveal that large organs benefit from intensity augmentations while small lesions require noise augmentations. The voting threshold controls the coverage precision trade off, enabling task specific optimization for different clinical requirements. Ultimately, on a multiclass hepatic vessel dataset, compared to MedSAM2 baselines, our method achieves an increase of 1.6 in mIoU and 1.9 in aIoU, along with a reduction of approximately 2.0 in HD95. Code will be available at https://github.com/AIGeeksGroup/SegTTA.

Purpose: 3D reconstruction in minimally invasive surgery (MIS) enables enhanced surgical guidance through improved visualisation, tool tracking, and augmented reality. However, traditional RGB-based keypoint detection and matching pipelines struggle with surgical challenges, such as poor texture and complex illumination. We investigate whether using snapshot hyperspectral imaging (HSI) can provide improved results on keypoint detection and matching surgical scenes. Methods: We developed HyKey, a HYperspectral KEYpoint detection and description model made up of a hybrid 3D-2D convolutional neural network that jointly extracts spatial-spectral features from HSI. The model was trained using synthetic homographic augmentation and epipolar geometry constraints on a robotically-acquired dual-camera RGB-HSI laparoscopic dataset of ex-vivo organs with calibrated camera poses. We benchmarked performance against established RGB-based methods, including SuperPoint and ALIKE. Results: Our HSI-based model outperformed RGB baselines on registered RGB frames, achieving 96.62% mean matching accuracy and 67.18% mean average accuracy at 10 degree on pose estimation, demonstrating consistent improvements across multiple evaluation metrics. Conclusion: Integrating spectral information from an HSI cube offers a promising approach for robust monocular 3D reconstruction in MIS, addressing limitations of texture-poor surgical environments through enhanced spectral-spatial feature discrimination. Our model and dataset are available at https://github.com/alexsaikia/HyKey-Hyperspectral-Keypoint-Detection

Recently computer vision has seen advancements mainly thanks to Transformer-based models. However many non-Transformer methods are still doing well being a direct competition of Transformer-based models. This review tries to present a comprehensive taxonomy of such methods and organize these methods into categories like convolution-based models, MLP-based models, state-space-based and more. These methods are looked at in terms of how efficient they are, how well they scale, how easy they are to understand and how robust they are. A total of 40 papers were chosen for this study. The goal is to give a view of non-Transformer methods and find out what challenges and opportunities exist for future computer vision research.

This study presents a Shape from Shading (SfS) framework to enhance sub-metre resolution lunar digital elevation models (DEMs) using imagery from the Orbiter High Resolution Camera (OHRC) aboard Chandrayaan-2. The framework applies SfS to an independent OHRC image of the same region, enabling SfS not just as a refinement tool, but as a source of new topographic data, unconstrained by stereo baseline limitations. The method is applied across three lunar sites, including the Cyrillus crater, the Vikram landing region, and the lunar south pole (Mons Mouton), with a systematic three-stage parameter sweep on the SfS smoothness weight. Results show measurable topographic enhancement, particularly in surface slope statistics, revealing fine-scale crater morphology previously unresolved. A limiting case is also characterized, where large pitch angle separation between the shading image and stereo pair reduces SfS sensitivity, and partial footprint coverage of the shading image is identified as a factor influencing spatially variable enhancement quality.

As video generation models achieve unprecedented capabilities, the demand for robust video evaluation metrics becomes increasingly critical. Traditional metrics are intrinsically tailored for short-video evaluation, predominantly assessing frame-level visual quality and localized temporal smoothness. However, as state-of-the-art video generation models scale to generate longer videos, these metrics fail to capture essential long-range characteristics, such as narrative richness and global causal consistency. Recognizing that short-term visual perception and long-context attributes are fundamentally orthogonal dimensions, we argue that long-video metrics should be disentangled from short-video assessments. In this paper, we focus on the rigorous justification and design of a dedicated framework for long-video evaluation. We first introduce a suite of long-video attribute corruption tests, exposing the critical limitations of existing hort-video metrics from their insensitivity to structural inconsistencies, such as shot-level perturbations and narrative shuffling. To bridge this gap, we design a novel long-video metric based on shot dynamics, which is highly sensitive to the long-range testing framework. Furthermore, we introduce Long-CODE (Long-Context as an Orthogonal Dimension for video Evaluation), a specialized dataset designed to benchmark long-video evaluation, with human annotations isolated specifically to genuine long-range characteristics. Extensive experiments show that our proposed metrics achieve state-of-the-art correlation with human judgments. Ultimately, our metric and benchmark seamlessly complement existing short-video standards, establishing a holistic and unbiased evaluation paradigm for video generation models.

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive cost of processing dense frame sequences. Prevailing keyframe-selection methods rely on either a single visual-centric metric (e.g., CLIP similarity) or a static fusion of heuristic scores. This "one-size-fits-all" paradigm frequently fails: visual-only metrics are ineffective for plot-driven narrative queries, while indiscriminately adding textual scores introduces severe "modal noise" for purely visual tasks. To break this bottleneck, we propose Q-Gate, a plug-and-play, training-free framework that treats keyframe selection as a dynamic modality routing problem. We decouple retrieval into three lightweight expert streams: Visual Grounding for local details, Global Matching for scene semantics, and Contextual Alignment for subtitle-driven narratives. Crucially, Q-Gate introduces a Query-Modulated Gating Mechanism that uses the in-context reasoning of an LLM to assess query intent and dynamically allocate weights across the experts, activating necessary modalities while "muting" irrelevant ones to maximize the signal-to-noise ratio. Extensive experiments on LongVideoBench and Video-MME across multiple MLLM backbones show that Q-Gate outperforms representative keyframe-selection baselines in most settings, with particularly strong gains on long and medium videos, providing a robust and interpretable solution for scalable video reasoning.

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show that many can be written under a common framework, which we call reward score matching (RSM). Under this view, alignment becomes score matching against a value-guided target, and the main differences across methods reduce to the construction of the value-guidance estimator and the effective optimization strength across timesteps. This unification clarifies the bias-variance-compute tradeoffs of existing designs, and distinguishes core optimization components from auxiliary mechanisms that add complexity without clear benefit. Guided by this perspective, we develop simpler, more efficient redesigns across representative differentiable and black-box reward alignment tasks. Overall, RSM turns a seemingly fragmented collection of reward-based fine-tuning methods into a smaller, more interpretable, and more actionable design space. Code is available at https://github.com/jaylee2000/rsm.

Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of accelerating inference. Whether speculative decoding, the dominant acceleration strategy for large language models, can be effectively adapted to autoregressive video generation remains an open question, because video blocks are continuous spatiotemporal tensors with no token-level distribution for exact rejection sampling. We introduce SDVG, which brings speculative decoding to block-based autoregressive video diffusion by replacing token verification with an image-quality router. A 1.3B drafter proposes candidate blocks via four denoising steps; each block is VAE-decoded and scored by ImageReward using worst-frame aggregation–taking the minimum per-frame reward to catch single-frame artifacts that averaging would mask. Blocks scoring above a fixed threshold tau are accepted into the 14B target's KV cache; the rest are regenerated by the target. Two additional design choices prove critical: the first block is always force-rejected to anchor scene composition, and tau serves as a single knob that traces a smooth quality-speed Pareto frontier. On 1003 MovieGenVideoBench prompts (832x480), SDVG retains 98.1% of target-only VisionReward quality (0.0773 vs. 0.0788) at a 1.59x speedup with tau=-0.7, and reaches 2.09x at 95.7% quality retention–while consistently outperforming draft-only generation by over +17%. The framework is training-free, requires no architectural changes, and can be seamlessly integrated into existing autoregressive video generation pipelines.

Ancient inscriptions frequently suffer missing or corrupted regions from fragmentation, erosion, or other damage, hindering reading, and analysis. We review prior image restoration methods and their applicability to inscription image recovery, then introduce MESA (Multi-Exemplar, Style-Aware) -an image-level restoration method that uses well-preserved exemplar inscriptions (from the same epigraphic monument, material, or similar letterforms) to guide reconstruction of damaged text. MESA encodes VGG19 convolutional features as Gram matrices to capture exemplar texture, style, and stroke structure; for each neural network layer it selects the exemplar minimizing Mean-Squared Displacement (MSD) to the damaged input. Layer-wise contribution weights are derived from Optical Character Recognition-estimated character widths in the exemplar set to bias filters toward scales matching letter geometry, and a training mask preserves intact regions so synthesis is restricted to damaged areas. We also summarize prior network architectures and exemplar and single-image synthesis, inpainting, and Generative Adversarial Network (GAN) approaches, highlighting limitations that MESA addresses. Comparative experiments demonstrate the advantages of MESA. Finally, we provide a practical roadmap for choosing restoration strategies given available exemplars and metadata.

Soft-tissue deformation remains a major limitation in image-guided neurosurgery, where intra-operative anatomy can deviate substantially from pre-operative imaging due to brain shift, compromising navigation accuracy and surgical safety. Existing compensation methods often rely on intra-operative MRI, CT, or ultrasound, which are disruptive and difficult to integrate repeatedly into the surgical workflow. In contrast, partial 3D cortical surfaces can be reconstructed as point clouds from stereoscopic microscopes or laser range scanners (LRS), capturing only a limited portion of the exposed cortex. This makes point cloud registration a practical alternative without interrupting surgery; however, such partial and noisy observations make deformation estimation highly challenging. In this study, we propose a deep learning-based framework for non-rigid volume-to-surface registration, enabling dense displacement field estimation from sparse intra-operative surface observations without explicit point correspondences or volumetric intra-operative imaging. The network leverages multi-scale point-based feature extraction and a hierarchical deformation decoder to capture both global and local deformations. The key contribution lies in integrating partial intra-operative surface information into the full pre-operative point cloud domain, enabling implicit correspondence learning and dense deformation recovery under limited visibility. Quantitative results demonstrate accurate recovery of fine-scale deformations, achieving an Endpoint Error (EPE) of 1.13 +/- 0.75 mm and RMSE of 1.33 +/- 0.81 mm under challenging partial-surface conditions. The proposed approach supports automatic, workflow-compatible brain-shift compensation from sparse surface observations.

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs. Effective spatial reasoning requires low-level geometric structure to be faithfully preserved and updated throughout the reasoning process, whereas textual representations tend to abstract away precisely these critical details. To address this issue, we propose SpatialImaginer, a unified multimodal generation framework that integrates textual reasoning with visual imagination. Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation. To support this capability, we further introduce a difficulty-aware data engine with closed-loop verification to train the model to invoke visual imagination selectively when stable spatial state tracking is required. Extensive experiments on diverse spatial intelligence benchmarks show that SpatialImaginer achieves state-of-the-art performance and substantially improves robustness on complex multi-step spatial reasoning tasks.

In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemble of fine-tuned vision transformers like DINOv2, AIMv2 and OpenCLIP's ViT-L/14 to create generalizable method to detect deepfakes. We use the DF-Wild dataset released as part of the IEEE SP Cup 2025, because it uses a challenging and diverse set of manipulations and generation techniques. We started our experiments with CNN classifiers trained on spatial features. Experimental results show that our ensemble outperforms individual models and strong CNN baselines, achieving an AUC of 96.77% and an Equal Error Rate (EER) of just 9% on the DF-Wild test set, beating the state-of-the-art deepfake detection algorithm Effort by 7.05% and 8% in AUC and EER respectively. This was the winning solution for SP Cup, presented at ICASSP 2025.

Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1–L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks.

Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction, we introduce DIVA, a controlled benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings. We further propose Semantic Alignment Gap ($\Delta$), an architecture-agnostic metric that quantifies divergence between literal and idiomatic visual grounding. We additionally introduce a directional signed bias $b(t)$ to separately measure the direction and strength of literal preference. Evaluating 8 recent VLMs, we reveal a consistent Literal Superiority Bias: model scale alone does not resolve literal preference, and increased visual fidelity is associated with weaker symbolic alignment, suggesting cognitive interference from hyper-realistic imagery. Our findings suggest that improving compositional understanding requires iconographic abstraction of visual input and anchoring interpretation and generation in intended meaning.

Diabetic retinopathy (DR) is a leading cause of preventable blindness, and automated grading could extend screening capacity. However, most reported DR models are validated only on the dataset they were trained on, leaving their behaviour under real screening variability unmeasured. This study presents a dual-resolution grading framework and quantifies how far performance falls when the imaging domain shifts. Two EfficientNet backbones process complementary views of each fundus image: B0 receives Ben Graham-normalised input at 224x224, emphasising vascular structure, while B3 receives CLAHE-enhanced input at 300x300, emphasising focal lesions. A learnable attention gate fuses the branches per image, and an ordinal binary-decomposition head models severity as an ordered scale rather than as unordered categories. Training used a combined set of 4,149 images (APTOS 2019, n = 2,929; Messidor-2 training portion, n = 1,220); evaluation used a held-out APTOS split (n = 733) and a Messidor-2 test set (n = 524) excluded from training and from all model selection. Quadratic weighted kappa was 0.882 (95% CI 0.853-0.906) on APTOS and 0.679 (95% CI 0.613-0.735) on Messidor-2 for this run, a significant gap of 0.202 (95% CI 0.142-0.273); across three random seeds the held-out kappa was 0.689 +/- 0.021. Critically, accuracy fell 19.3 points while 93.7% of predictions stayed within one grade of reference: ordering survives domain shift, threshold placement does not. Referable-DR sensitivity fell from 0.879 to 0.620.

Face morphing attacks pose a substantial risk to the reliability of face recognition systems used in passport issuance, border control, and digital identity verification. Detecting morphing attacks from a single facial image remains challenging owing to the lack of a trusted reference and the diversity of attack generation methods. This paper presents a new Single-Image Face Morphing Attack Detection (S-MAD) framework that integrates high-frequency Laplacian residual statistics with representations from a frozen, foundation-scale vision transformer. The approach employs residual-statistic-gated low-rank adapters (R-FLoRA) and feature-wise residual fusion (Res-FiLM) to enhance sensitivity to local morphing artefacts while preserving the semantic context of the backbone. A novel residual-contrastive alignment loss further regularises the fused token space, improving discrimination under unseen morphing conditions. Comprehensive experiments on four ICAO-compliant datasets, encompassing seven morph generation techniques, demonstrate that the proposed method consistently surpasses nine recent state-of-the-art S-MAD algorithms in detection accuracy and cross-domain (or dataset) generalisation. With a frozen backbone and minimal trainable parameters, the model achieves real-time efficiency and interpretability, making it suitable for real-life scenarios in biometric verification systems.

Deploying Vision-Language Models (VLMs) under aggressive low-bit inference remains challenging because inference cost is dominated by the long visual-token prefix during prefill and the growing KV cache during autoregressive decoding. Token pruning and low-bit quantization are complementary for reducing these costs, yet naive stage-wise combinations are often brittle due to a mismatch between quantization calibration and pruning execution. We present a collaborative quantization-and-pruning framework that unifies low-bit inference and deterministic visual-token pruning in a single deployable pipeline. The framework introduces the Quantization Unified Offline Token Allocator (QUOTA), which converts low-bit calibration signals into a layer-wise token allocation schedule and materializes it as a pruning recipe. Token importance is evaluated under deployed W4A4 operators with a quantized KV cache by combining activation magnitude, attention cues, and an explicit low-bit risk signal, enabling consistent budgeted top-$k$ selection. Experiments on standard VLM benchmarks show improved robustness over stage-wise baselines under the same low-bit regime, achieving 95.65% average retention while retaining only 30% of visual tokens, compared with about 94.3% retention for representative stage-wise combinations. The code will be released.

Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground each entity to a corresponding visual region in an associated image. Existing approaches predominantly adopt pipeline-based architectures that decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization. In this paper, we propose E2E-GMNER, a fully end-to-end generative framework that unifies entity recognition, semantic typing, visual grounding, and implicit knowledge reasoning within a single multimodal large language model. We formulate GMNER as an instruction-tuned conditional generation task and incorporate chain-of-thought reasoning to enable the model to adaptively determine when visual evidence or background knowledge is informative, reducing reliance on noisy cues. To further address the instability of generative bounding box prediction, we introduce Gaussian Risk-Aware Box Perturbation (GRBP), which replaces hard box supervision with probabilistically perturbed soft targets to improve robustness against annotation noise and discretization errors. Extensive experiments on the Twitter-GMNER and Twitter-FMNERG benchmarks demonstrate that E2E-GMNER achieves highly competitive performance compared with state of the art methods, validating the effectiveness of unified end-to-end optimization and noise-aware grounding supervision. Code is available at:https://github.com/Finch-coder/E2E-GMNER

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address this, we propose MedFocusLeak, a highly transferable black-box multimodal attack that induces incorrect yet clinically plausible diagnoses while keeping perturbations imperceptible. The method injects coordinated perturbations into non-diagnostic background regions and employs an attention distraction mechanism to shift the model's focus away from pathological areas. Extensive evaluations across six medical imaging modalities show that MedFocusLeak achieves state-of-the-art performance, generating misleading yet realistic diagnostic outputs across diverse VLMs. We further introduce a unified evaluation framework with novel metrics that jointly capture attack success and image fidelity, revealing a critical weakness in the reasoning capabilities of modern clinical VLMs.

Detecting face forgeries using CLIP has recently emerged as a promising direction. However, most existing methods focus on adapting its visual encoder, leaving the potential of the textual encoder largely underexplored. In this paper, we propose Separable Prompt Learning (SePL) to better exploit the text modality, which further enhances the detection capacity. Specifically, SePL distills the forgery knowledge from CLIP via two separate learnable prompts, supported by a cross-modality alignment strategy and dedicated objectives. Extensive experiments demonstrate that our method achieves superior performance under both cross-dataset and cross-method evaluation. The code has been released at https://github.com/OUC-YER/SePL-DeepfakeDetection.