Authors: Krisanu Sarkar
Abstract: Current synthetic data pipelines for computer vision generate images without diagnosing what the downstream model actually needs. This open-loop paradigm treats synthetic data as cheap real data, randomly sampling the generator's output space and hoping to cover the model's failure modes. We argue this fundamentally misuses synthetic data's unique property: the controllable, independent variation of scene factors.Drawing on the statistical theory of Design of Experiments (DoE), we propose Synthetic Designed Experiments for Representational Sufficiency (SDRS). SDRS treats the downstream model as a black-box system and the synthetic generator as an experimental apparatus. Using fractional factorial designs, SDRS efficiently audits a model's factor-sensitivity profile via ANOVA decomposition. It classifies failures into two actionable types: Type I gaps (coverage failures on underrepresented factor levels) and Type II gaps (reliance on spurious nuisance dependencies). The audit then prescribes targeted synthetic data to address each gap type. We validate SDRS on three experiments: (1) a controlled diagnostic on dSprites with planted biases, where the audit correctly identifies both gap types and targeted data improves accuracy from 49.9% to 79.0%; (2) a dense segmentation task on procedural scenes, where detecting background-complexity shortcuts and applying targeted data improves mIoU from 0.948 to 0.998; and (3) an entanglement detection experiment showing that the ANOVA audit identifies cross-factor contamination in imperfect generators. Finally, we show that per-factor invariance penalties can transfer sensitivity between factors, identifying an open problem for representation-level correction.
Authors: Alizishaan Khatri, Chiquita Prabhu
Abstract: The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to adult and sexually explicit material. Existing detection methods operate on either prompts or decoded pixel-space outputs. Therefore, both approaches are blind to the rich internal representations formed during generation. In this paper, we propose a novel latent space probing framework that intercepts the denoised latent representations produced by the CogVideoX video diffusion model during inference and attaches lightweight classifiers to perform real-time adult content detection. To support this work, we construct a large-scale binary dataset of 11039 ten-second video clips (5086 violating, 5953 non-violating) sourced from adult websites and YouTube respectively. We introduce two lightweight probing classifier architectures. We train and evaluate it on the dataset. Our work demonstrates that latent-space signals encode strong discriminative features for harmful content detection, achieving 97.29% F1 on our held-out test set with an overhead in the 4-6ms range. Our results suggest that probing the latent space results in improvements in both detection performance as well as cost.
Authors: Dustin M. Haggett
Abstract: Technical traders have long relied on visual analysis of candlestick charts to identify market patterns and predict price movements. While deep learning has achieved remarkable success in image classification, its application to financial chart images remains underexplored. This paper presents a systematic study comparing different visual representations for cryptocurrency regime prediction. We evaluate three image encoding methods (raw candlestick charts, Gramian Angular Fields, and multi-channel GAF), five chart component configurations, four neural network architectures (CNN, ResNet18, EfficientNet-B0, and Vision Transformer), and the impact of ImageNet transfer learning. Through eight controlled experiments on Bitcoin, Ethereum, and S&P 500 data spanning 2018-2024, we identify optimal configurations for visual regime classification. Our results show that a simple 4-layer CNN on raw candlestick charts achieves 0.892 AUC-ROC, outperforming larger pretrained models. Surprisingly, simpler representations (price-only charts, 128x128 resolution) consistently outperform more complex alternatives. We provide interpretability analysis using GradCAM and demonstrate that transfer learning improves performance by 4-16% despite the domain gap between natural images and financial charts.
Authors: Manish Kumar, Rajendra K. Ray
Abstract: In real-world scenarios, image defogging is an inverse problem due to unknown scene depth, atmospheric scattering, and the common absence of ground truth . To resolve the issue, we propose a hybrid defogging model that integrates a fourth-order nonlinear PDE with a physical haze formation model. We used Dark Channel Prior to estimate atmospheric parameters and to generate a guidance image, while the final restoration is performed via a fourth-order PDE-based evolution. A fourth-order PDE of the type telegraph is then evolved, incorporating an edge-adaptive diffusion coefficient and a fidelity term weighted by the transmission map. Fourth-order diffusion effectively suppresses haze while preserving structural details, and the hyperbolic formulation improves numerical stability and convergence behavior. We use relative error norm criteria for the convergence of our PDE. The proposed method is compared with Dark Channel prior, modified Dark Channel prior, and variational-based single-image defogging techniques. When we have ground truth available, we use MSE and SSIM for quantitative evaluation, whereas no-reference metrics, including FADE, Contrast Restoration Index, Average Gradient, and Entropy, are applied to real-world foggy images. Experimental results demonstrate that the proposed hybrid PDE-based method provides comparable visual quality and maintains structural details.
Authors: Xinyu Zeng, Xiangkun He, Lei Tao, Chen Lv, Hong Cheng
Abstract: Autonomous driving (AD) is evolving towards end-to-end (E2E) frameworks through two primary paradigms: monolithic models exemplified by Vision-Language-Action (VLA), and specialized modular architectures. Despite their divergent designs, both paradigms increasingly rely on Transformer backbones for complex reasoning, potentially causing a shared vulnerability: visually imperceptible perturbations can manipulate E2E AD models into hazardous maneuvers by targeting the Transformer module. Most existing adversarial attack approaches against AD systems operate under white-box or black-box settings; yet, they typically necessitate full model transparency, or suffer from either prohibitive query latency or limited attack transferability. In this paper, we propose Adversarial Flow Matching (AFM), a novel gray-box attack framework that exploits Transformer structural vulnerabilities in E2E AD models. AFM enables efficient one-step generation of adversarial examples via a neural average velocity field. Additionally, the proposed technique yields effective and visually imperceptible attacks by synergistically perturbing the generative latent space and the neural average velocity field. Extensive experiments demonstrate that AFM achieves a superior trade-off between attack effectiveness and imperceptibility: it substantially degrades the performance of both VLA and modular AD agents across various scenarios compared to baselines, while maintaining state-of-the-art visual imperceptibility. Furthermore, adversarial examples generated by AFM exhibit robust cross-model transferability, indicating that AFM closely approximates a black-box attack setting while requiring only the prior knowledge that the target AD model incorporates a Transformer-based module.
Authors: Zhiyi Niu, Xiaoguang Tu, Bo Zhao, Junzhe Cao, Dan Guo, Zitong Yu
Abstract: Remote Photoplethysmography (rPPG) enables convenient non-contact physiological measurement. Existing Self-Supervised Learning (SSL) methods commonly fall into a correlation trap: they tend to learn the most dominant periodic signals in the data, such as high-energy motion or illumination noise, rather than the faint, true rPPG signal, leading to poor model generalization. To address this, we propose a new SSL paradigm, Physiological Causal Probing (PCP), which treats the latent rPPG signal as the underlying physical source and the resulting pixel chrominance variations as its visual manifestation. Its core idea is to shift from passive correlation learning to active, precise intervention: it intervenes on the video based on a proposed rPPG hypothesis, and verifies whether the post-intervention changes match physical expectations. We propose the Interv-rPPG framework to implement PCP: an rPPG extractor named PhysMambaFormer hypothesizes the rPPG signal, while a Controllable Physiological Signal Editor conducts precise chrominance-domain interventions on videos based on this hypothesis. Interv-rPPG validates the physical realism of the hypothesis through `Falsifiability via Nulling' and `Axiomatic Equivariance'. Our editor achieves precise editing of the rPPG signal by intervening in the low-frequency chrominance components of the video. Our method improves both in-domain and cross-domain performance on challenging datasets such as VIPL-HR and MMPD. Furthermore, it surpasses the supervised baseline in complex cross-dataset settings, while remaining competitive on clean datasets where the intervention mechanism may introduce slight residual chrominance noise. Extensive experiments, including diagnostic analysis of nuisance sensitivity, demonstrate that the PCP paradigm effectively resists motion and illumination artifacts.
Authors: Qi Li, Weining Wang, Shuangjun Du, Bo Peng, Jing Dong, Kun Wang, Zhenan Sun, Ming-Hsuan Yang
Abstract: Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models.Despite these advances, existing methods remain fragmented across different paradigms, and their evaluation is highly inconsistent due to the lack of standardized datasets and protocols. Moreover, prior surveys primarily focus on broader deepfake generation or detection, leaving face swapping insufficiently studied as a standalone problem. In this paper, we present a comprehensive survey and benchmark for face swapping. We provide a structured review of existing methods, organizing them into five major paradigms and systematically analyzing their design principles, strengths, and limitations. To enable fair and controlled evaluation, we introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic distributions and explicit attribute variations, and establish standardized protocols to assess the robustness of different face swapping methods. Extensive experiments on representative approaches yield new insights into the performance characteristics and limitations of current techniques. Overall, our work provides a unified perspective and a principled evaluation framework to facilitate the development of more robust and controllable face swapping methods. More results can be found at https://github.com/CASIA-NLPRAI/face-swapping-survey.
Authors: Justn williams, Kishor Datta Gupta, Roy George, Mrinmoy Sarkar
Abstract: Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low-latency closed-loop guidance under strict onboard compute and communication constraints. We present LiteVLA-H, a compact 256M-parameter VLA system designed for dual-rate operation on an NVIDIA Jetson AGX Orin: a fast outer-loop guidance mode for short action-token outputs and a slower semantic mode for scene understanding, hazard description, and operator-facing narration. The central empirical observation is that, in this compact edge regime, end-to-end latency is dominated by multimodal pre-fill rather than by the marginal cost of decoding a few extra tokens. This motivates a scheduler that issues reactive action tokens at 50.65,ms (19.74,Hz) while still supporting sentence-level semantic outputs at 149.90--164.57\ms (6.08--6.67,Hz) on the same embedded platform. To specialize the model without collapsing its descriptive competence, we use a knowledge-preserving fine-tuning recipe that mixes reactive flight data, aerial semantic data, and generic caption/VQA supervision. Beyond reporting current latency measurements, we position the system against recent state-of-the-art architectures, including AnywhereVLA, FutureVLA, and ReMem-VLA, showing that the measured action branch reaches a higher edge inference rate under our deployment conditions while retaining periodic semantic awareness.
Authors: Yingming Zhang, Wuqi Su, Qing Xiao, Yonggang Yang
Abstract: Existing single image dehazing methods have demonstrated satisfactory performance on homogeneous thin-haze images; however, they often struggle with non-homogeneous hazy images that exhibit spatially varying haze concentrations and abrupt density transitions across different regions. To address this fundamental limitation, we propose a novel multi-branch deep neural network framework, termed Concentration Partitioning and Image Fusion Network (CPIFNet), which decomposes the challenging non-homogeneous dehazing problem into a set of tractable homogeneous sub-problems. Our key insight is that a single non-homogeneous hazy image can be viewed as a composite of multiple local regions, each exhibiting approximately homogeneous haze characteristics. CPIFNet employs a two-stage architecture consisting of an Image Enhancement Network (IENet) stage and an Image Fusion Network (IFNet) stage. In the first stage, multiple IENet branches are independently trained on homogeneous haze datasets of different concentration levels, producing enhancement models that excel at restoring regions matching their respective haze densities. In the second stage, the IFNet intelligently aggregates the advantageous regions from all enhancement outputs through deep feature stacking and merging, yielding a unified high-quality dehazed result. Furthermore, we introduce a comprehensive loss function incorporating reconstruction, perceptual, structural, and color losses to jointly supervise both stages.
Authors: Yingming Zhang, Wuqi Su, Qing Xiao, Yonggang Yang
Abstract: Infrared small target detection (IRSTD) plays a pivotal role in a broad spectrum of mission-critical applications, including maritime surveillance, military search and rescue, early warning systems, and precision-guided strikes, all of which demand the precise identification of dim, sub-pixel targets amid highly cluttered infrared backgrounds. Despite significant progress driven by deep learning methods, fundamental challenges persist: infrared small targets occupy extremely limited spatial extents (often only a few pixels), exhibit low signal-to-clutter ratios, and are easily confused with structurally complex backgrounds that frequently induce false alarms. Existing encoder-decoder architectures suffer from two key limitations - an information bottleneck in early convolutional stages that undermines fine-grained target perception, and static skip connections that lack the dynamic adaptability required to discriminate between genuine targets and pseudo-target regions. To address these challenges, we propose SANet, a Selective Attention-based Network built upon the classical U-Net framework and augmented with two novel components: (1) a \emph{Dual-path Semantic-aware Module} (DSM) that integrates standard convolutions for local spatial detail preservation with pinwheel-shaped convolutions for expanded, direction-sensitive receptive fields, followed by a Convolutional Block Attention Module (CBAM) for fine-grained spatial-channel feature recalibration; and (2) a \emph{Selective Attention Fusion Module} (SAFM) that replaces conventional static skip connections with a spatially adaptive, learnable weighting mechanism to perform context-aware, cross-scale feature fusion.
Authors: Paarth Prasad, Ruchika Malhotra
Abstract: We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-ray disease detection in low-data settings. Traditional contrastive learning methods rely on dense attention mechanisms, which are computationally expensive and often process redundant regions in medical images. To resolve this, SparseContrast introduces a sparse attention mechanism that selectively concentrates on diagnostically pertinent areas, markedly decreasing computational burden without compromising accuracy. The framework adaptively trims attention maps in the training phase, directed by a compact saliency predictor which concurrently optimizes sparsity and feature quality. This method not only speeds up training and inference by as much as 40% relative to dense attention benchmarks but also boosts diagnostic accuracy by focusing on areas of clinical importance. Moreover, the approach remains indifferent to the selection of backbone architecture, which permits its application to both convolutional and transformer-based models. Experiments show SparseContrast attains comparable or better performance in disease identification tasks with greater efficiency relative to current approaches. The proposed framework delivers a practical approach for implementing contrastive learning in medical imaging settings with limited resources, where computational efficiency and diagnostic accuracy are paramount.
Authors: Eun Som Jeon, Jisoo Lee, Huisu Lim, Omik M. Save, Hyunglae Lee, Pavan Turaga
Abstract: Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. Specifically, ground reaction force (GRF) provides essential insights into the body's interaction with the ground during movement and is typically measured using instrumented treadmills equipped with force plates. However, such equipment is expensive and restricted to laboratory environments. To enable a more portable solution, wearable insole sensors have been used to measure GRF. These sensors, however, are prone to noise and external interference, which reduces measurement accuracy. Deep learning methodologies could be adopted to address these issues, but they often require significant computing resources to achieve high accuracy, limiting their applicability for real-time analysis on portable devices. To overcome these limitations, we propose Selective Correlation Based Knowledge Distillation (SCKD) for estimating GRF from data collected by insole sensors. Our proposed method utilizes selected features considering temporal characteristics in the process of extracting correlation maps for knowledge transfer, enhancing interpretability and mitigating issues in high dimensional data processing. We demonstrate the effectiveness of the compact models generated by our distillation framework through comparison with existing methods. Various configurations of teacher-student architectures and training approaches are examined based on multiple evaluation criteria, utilizing data collected at different walking speeds and with different window sizes. Experimental results confirm that our approach outperforms existing methods in estimating GRF from wearable insole sensor data. Therefore, our approach offers a reliable and resource-efficient solution for human gait analysis.
Authors: Ikhlas Enaieh (S2A, LTCI), Olivier Fercoq (S2A, LTCI), Garc\'ia \'Angel (DATSI, UPM)
Abstract: We investigate the explanability properties of the recently proposed linear-min-max neural networks. At initialization, they can be interpreted as k-medoids with the infinity norm as a distance. Then, they are trained using subgradient descent to better fit the data. The model has been shown to be a universal approximator. Yet, we can trace the decision process because a single most activated neuron is responsible for the value of the output. Using this property, we designed a pixel fragility measure that determines whether changes to a single pixel may be responsible to a change in the classification output. Experiments on the PneumoniaMnist dataset show that this explanation for the output of the neural network compares favorably to SHAP and Integrated Gradient.
Authors: Sergio D. Sierra M., Monica Sinha, Marcela M\'unera, Carlos A. Cifuentes
Abstract: Falls among older adults are a significant public health concern, leading to severe injuries, loss of independence, and increased healthcare costs. This study evaluates the effectiveness of various models, including a Geometric approach, XGBoost, SVM, and several deep learning architectures, in classifying walker usage, standing vs. sitting, and posture for smart walkers used. Geometric and XGBoost were the top performers. XGBoost achieved near-perfect training accuracy in binary classification tasks, with 99.84% for walker choice and 99.69% for standing vs. sitting. For posture classification, Geometric approach attained 89.9% accuracy for 8 postures, and XGBoost obtained 99.24% during training for 17 postures. Deep learning models such as the 4-layer CNN and Encoder-Decoder CNN also demonstrated strong performance in binary classification, with accuracies above 98%. This study underscores the potential of machine learning to enhance human-robot interaction in smart walkers, particularly for fall prevention.
Authors: Hao Wang, Limeng Qiao, Chi Zhang, Lin Ma, Guanglu Wan, Xiangyuan Lan, Xiaodan Liang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM series produce high-quality masks, but they rely on low-level visual prompts and cannot natively interpret complex conversational instructions. Existing segmentation MLLMs narrow this gap, but are usually specialized for either images or videos and rarely support both textual and visual prompts in one interface. We introduce X2SAM, a unified segmentation MLLM that extends any-segmentation capabilities from images to videos. Given conversational instructions and visual prompts, X2SAM couples an LLM with a Mask Memory module that stores guided vision features for temporally consistent video mask generation. The same formulation supports generic, open-vocabulary, referring, reasoning, grounded conversation generation, interactive, and visual grounded segmentation across image and video inputs. We further introduce the Video Visual Grounded (V-VGD) segmentation benchmark, which evaluates whether a model can segment object tracks in videos from interactive visual prompts. With a unified joint training strategy over heterogeneous image and video datasets, X2SAM delivers strong video segmentation performance, remains competitive on image segmentation benchmarks, and preserves general image and video chat ability.
Authors: Chamani Shiranthika, Parvaneh Saeedi
Abstract: Federated learning enables collaborative model training across medical institutions without sharing raw data, but its performance is often limited by domain heterogeneity across clients. Existing approaches to address this challenge fall into two main paradigms: model-side personalization, which adapts model parameters to each client, and data-side harmonization, which reduces inter-client variation at the input level. Despite their widespread use, these strategies have not been systematically compared. In this work, we conduct a comprehensive study across six medical imaging settings-colon polyp, skin lesion, and breast tumor segmentation, and tuberculosis CXR, brain tumor, and breast tumor classification-covering diverse types of domain shift. We evaluate a broad set of state-of-the-art harmonization and personalization methods under a unified framework. Our results reveal a conditional trade-off driven by the nature of heterogeneity: harmonization is more effective when variation is primarily appearance-based (e.g., CXR classification), while personalization performs better when differences are structural (e.g., colon polyp segmentation). When inter-client variation is limited, both strategies perform similarly. These findings demonstrate that the effectiveness of adaptation in federated medical imaging depends on the type and magnitude of domain shift rather than the strategy alone. We provide practical guidelines for selecting between harmonization and personalization and highlight directions for future hybrid approaches that combine both paradigms. Code is available at https://github.com/ChamaniS/WhenToAdapt.
Authors: Md. Enamul Hoq, Wataru Uegami, Saghir Alfasly, Ghazal Alabtah, Sahar Rahimi Malakshan, Armita Kazemi, Alex T. Schmitgen, Fred Prior, H. R. Tizhoosh
Abstract: Generative vision-language models can produce fluent medical image captions but remain prone to hallucination, over-specific diagnostic claims, and factual inconsistency-serious issues in pathology. We investigate retrieval-guided generation (RGG) as a safer alternative, where captions are formed by summarizing expert text from visually similar cases rather than generated de novo. On the ARCH histopathology dataset, RGG improves semantic alignment with ground truth, achieving cosine similarity of $\approx$0.60 versus $\approx$0.47 from MedGemma, with non-overlapping confidence intervals indicating a robust gain. A pathologist-led qualitative review shows better preservation of morphology-relevant terminology and fewer unsupported diagnoses, while revealing failure modes such as concept mixing and inherited over-specific labeling. Overall, retrieval-guided captioning offers a more transparent and reliable approach with clearer opportunities for auditing than fully generative methods.
Authors: Tianyang Wang, Ziyu Su, Abdul Rehman Akbar, Usama Sajjad, Usman Afzaal, Lina Gokhale, Charles Rabolli, Wei Chen, Anil Parwani, Muhammad Khalid Khan Niazi
Abstract: Vision foundation models (VFMs), such as DINOv3, provide rich semantic representations that are promising for computational pathology. However, many current adaptations pair frozen VFMs with lightweight decoders, creating a capacity mismatch that often limits boundary fidelity for infiltrative tumor bulk segmentation. This paper presents Dino-NestedUNet, a framework that couples a pre-trained DINOv3 encoder with a Nested Dense Decoder. Instead of sparse skip connections and linear upsampling, the proposed decoder forms a dense grid of intermediate pathways to enable continuous feature reuse and multi-scale recalibration, aligning high-level semantics with low-level morphological textures during reconstruction. We evaluate Dino-NestedUNet on three histopathology cohorts (multi-center CHTN, institutional OSU, and CAMELYON16) and observe consistent improvements over UNet++ and standard Dino-UNet variants, particularly under cross-domain shift. To further assess external generalization, we perform zero-shot evaluation by training on CHTN and directly testing on unseen TIGER WSIBULK and OSU CRC cohorts without fine-tuning. These results suggest that dense decoding is a key ingredient for unlocking foundation encoders in boundary-sensitive pathology segmentation.
Authors: Prabhjot Singh, Manmeet Singh
Abstract: Operational phase unwrapping is the primary computational bottleneck in InSAR-based volcanic and seismic monitoring. We challenge the industry trend of adopting high-complexity computer vision architectures, such as attention mechanisms, without validating their suitability for physics-constrained geophysical regression. We present the first large-scale architectural ablation study on a global LiCSAR benchmark (20 frames, 39,724 patches, 651M pixels). Our results reveal a significant "complexity penalty": a vanilla U-Net (7.76M parameters) achieves $R^2=0.834$ and RMSE $= 1.01$ cm, outperforming 11.37M-parameter attention-based models by 34% in $R^2$ and 51% in RMSE. Power Spectral Density (PSD) analysis provides the physical justification: while attention excels at capturing sharp semantic edges in natural images, it injects unphysical high-frequency artifacts ($>0.3$ cycles/pixel) into geophysical fields, violating the fundamental smoothness constraints of elastic surface deformation. With a 2.92ms inference latency (a $2.5\times$ speedup), the vanilla U-Net is the only candidate to comfortably meet the sub-100ms requirement for operational early-warning systems. This work bridges the "publication-to-practice" gap by proving that convolutional locality outperforms modern complexity for smooth-field regression, advocating for physics-informed simplicity in ML4RS. Code available at https://github.com/prabhjotschugh/When-Less-is-More-InSAR-Phase-Unwrapping
URLs: https://github.com/prabhjotschugh/When-Less-is-More-InSAR-Phase-Unwrapping
Authors: James Flora, Kowshik Thopalli, Akshay R. Kulkarni, Weng-Keen Wong, Shusen Liu
Abstract: We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencoder-based divergence testing with density ratio estimation, LatentDiff identifies interpretable semantic differences between datasets at a fraction of the computational cost of caption-based alternatives. We also introduce Noisy-Diff, a benchmark capturing realistic sparse distribution shifts that cause existing methods to struggle. Experiments demonstrate that LatentDiff achieves superior accuracy while remaining robust to settings where an extremely small fraction of images (from 5% to <1% ) differ semantically.
Authors: Md Shifatul Ahsan Apurba, Md Selim, Jin Chen
Abstract: The use of CT imaging is important for screening, diagnosis, therapy planning, and prognosis of lung cancers. Unfortunately, due to differences in imaging protocols and scanner models, CT images acquired by different means may show large differences in noise statistics, contrast, and texture. In this study, we develop a novel conditional MeanFlow pipeline for CT image reconstruction. We introduce a conditional MeanFlow network that models the enhancement trajectory by predicting image-conditioned flow fields given intermediate image states. The image enhancement network is trained with a MeanFlow consistency loss along with the image reconstruction loss. In order to provide an adaptive refinement process in terms of spatial location of enhancements, we integrate a regional reinforcement learning-driven policy network into our approach. The policy network receives information about the MeanFlow rollouts and provides predictions in terms of tile-wise refinement budgets, stopping criteria, and total budget allocation of enhancement processes. Our policy network is trained through reinforcement learning in a policy gradient framework, where the goal of the training reward is to maximize improvement of enhancements while minimizing unnecessary computations and avoiding instabilities. In this way, our approach combines conditional flow-based enhancement with reinforcement learning-based spatial enhancement control. This allows our approach to focus more attention on enhancing difficult areas while stabilizing areas already showing sufficient quality. Our results show high accuracy in the tumor ROI, with the average radiomic feature CCC being 0.96, an average PSNR of 31.30 $\pm$ 4.16, and average SSIM of 0.94 $\pm$ 0.07. Moreover, there is an improvement in the overall quality of images, with an average PSNR of 34.23 $\pm$ 1.71 and average SSIM of 0.95 $\pm$ 0.01.
Authors: Tianhao Lei, Parsa Esmaeilkhani, Saghir Alfasly, Wataru Uegami, Judy C. Boughey, Matthew P. Goetz, Krishna R. Kalari, H. R. Tizhoosh
Abstract: Foundation models are reshaping computational histopathology, yet their value for whole-slide image retrieval relative to strong patch-based and supervised aggregation baselines remains unclear. We benchmarked ten pipelines on 9,387 diagnostic slides spanning 17 organs and 60 diagnoses from The Cancer Genome Atlas (TCGA) using patient-level leave-one-patient-out evaluation. Methods included four pre-trained slide foundation models, a supervised attention-based multiple instance learning (ABMIL) aggregator on patch embeddings, and patch-level retrieval across five sampling densities. Performance varied more across organs and diagnoses than across architectures. Although the slide foundation model TITAN achieved the strongest overall results, its advantage was modest; ABMIL and patch-based methods reached comparable Top-1 and Top-3 accuracy, with no model consistently dominant. Morphologically distinctive entities approached ceiling performance, while rare, heterogeneous, and closely related subtypes remained challenging. Misclassifications aligned with organs exhibiting known inter-observer variability, suggesting an intrinsic ceiling for morphology-only retrieval. Performance was driven primarily by patch-level feature representations, with limited benefit from slide-level aggregation, indicating aggregation may be unnecessary in many settings. These findings argue against a universally optimal architecture and instead support organ-resolved benchmarking, diagnosis-aware or ensemble strategies, stronger feature representations, and multimodal retrieval frameworks. Notably, even the best model achieved only $\approx 68\% \pm 21\%$ retrieval accuracy on TCGA, and some subtypes showed $0\%$ accuracy across all methods, highlighting fundamental limitations of morphology-based representations and the need for substantial progress before reliable clinical deployment.
Authors: Muhammad Kaleem Ullah Khan
Abstract: Agriculture is a key sector of the economies of developing countries. It serves as a primary source of income and employment for rural populations. However, each year, a large portion of crops is wasted because of pests and diseases. Well-timed prediction of plant diseases is crucial to sustainable, high-quality agricultural production. Detection of plant diseases through conventional methods is both labour-intensive and time-consuming. Researchers have developed image classification based automated techniques for this purpose. Most accurate methods are based on deep convolutional neural networks, which are computationally intensive, with many layers and millions of trainable parameters. In resource-constrained settings, especially in rural areas, it is difficult to deploy deep convolutional neural network models for efficient plant disease identification. To address these issues, an efficient and light-weight Multi-View Convolutional Neural Network is proposed. These additional features aid the proposed model to identify the plant diseases accurately and efficiently with less number of parameters. The proposed model is tested on a benchmark Plantvillage dataset and achieves an improvement of $ 2.9\%$ in classification accuracy compared to the baseline convolutional neural network model, which was trained only on Red, Green, and Blue (RGB) plant images. Compared with state-of-the-art deep convolutional neural network models, the proposed model is less computationally expensive and achieves comparable accuracy for plant disease identification on the PlantVillage dataset.
Authors: Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim, Kundan Thind, Dongxiao Zhu
Abstract: Learning-based fluence map prediction offers a fast alternative to iterative inverse planning in intensity-modulated radiation therapy (IMRT), but its robustness under realistic distribution shifts remains unclear. We study a two-stage transformer pipeline that maps anatomy (CT and contours) to dose and then to beamlet fluence maps. We compare fluence-stage transformer backbones with hierarchical, global, and hybrid attention, trained with a physics-informed loss enforcing energy consistency. Robustness is evaluated under geometric perturbations, radiometric noise, reduced training data, and domain shifts using a prostate IMRT dataset, with additional evaluation of the dose stage on public datasets. Results show smooth degradation under moderate perturbations but sharp failures under severe rotations and noise. Hierarchical transformers (e.g., SwinUNETR) exhibit slower growth in upper-quartile energy error, indicating improved robustness. We further show that SSIM alone fails to capture clinically relevant errors, highlighting the need for physics-informed evaluation.
Authors: Hongjun Wang, Po Hu, Kai Han
Abstract: Generalized Category Discovery (GCD) aims to categorize unlabelled instances from both known and unknown classes by transferring knowledge from labelled data of known classes. Existing methods assume all data comes from a single domain, yet real-world unlabelled data often exhibits domain shifts alongside semantic shifts. We study GCD under domain shifts and propose three frameworks that adapt foundation models, ranging from self-supervised vision models to vision-language models. (i) HiLo disentangles domain and semantic features through multi-level feature extraction and mutual information minimization, combined with PatchMix augmentation and curriculum sampling. (ii) HLPrompt extends HiLo with semantic-aware spatial prompt tuning to suppress background and domain noise. (iii) VLPrompt leverages vision-language models via factorized textual prompts and cross-modal consistency regularization. The three methods share core design principles while operating on different foundation backbones, making them suitable for different deployment scenarios. Extensive experiments on synthetic corruptions and real-world multi-domain shifts demonstrate consistent improvements over strong baselines. Project page: https://visual-ai.github.io/hilo/
Authors: Han Gong, Zhen Zhou, Yunyang Shi, Yan Tan, Jinbiao Huo, Qi Hong, Zhiyuan Liu
Abstract: Large language models (LLMs) and multimodal large models (MLLMs) are increasingly used for transportation tasks such as regulation question answering, traffic management support, engineering review, and autonomous-driving scene reasoning. Yet transportation workflows are rule-intensive, computation-intensive, safety-critical, and inherently multimodal. Existing general benchmarks provide limited evidence of whether a model can apply regulations correctly, perform verifiable engineering calculations, or interpret traffic scenes reliably, while the small number of public transportation benchmarks remain narrow in scope and rarely support fine-grained diagnosis across text, images, and point-cloud data. To address this gap, we present TRIP-Evaluate, an open multimodal benchmark for large models in transportation. The benchmark organizes 837 items using a role-task-knowledge taxonomy that covers vehicle, traffic-management, traveler, and planning-and-design functions. Each item is annotated with capability, modality, and difficulty labels, enabling diagnosis from overall accuracy down to specific failure modes. The current release includes 596 text items, 198 image items, and 43 point-cloud items. TRIP-Evaluate also standardizes item construction, quality control, prompting, decoding, and scoring to improve cross-model comparability. Results on a diverse panel of models show that text-based performance is improving, but substantial weaknesses remain in multi-step engineering calculation, rule-constrained reasoning, multimodal scene understanding, and point-cloud understanding. Overall, TRIP-Evaluate provides a reproducible, diagnosable, and engineering-aligned evaluation baseline for model selection, regression testing, and safer deployment in transportation applications.
Authors: Alcides Toledo Espinosa, Gerardo Antonio \'Alvarez Hern\'andez, \'Angel Eduardo Zamora-Su\'arez, Miguel Bola\~nos, Juan Irving V\'asquez
Abstract: This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in realistic scenarios. Representative models from each paradigm are considered, including YOLOv26-nano, a recent variant of the YOLO family, and transformer-based approaches such as RTDETR and RF-DETR. Experiments were conducted on the GROUNDBASED_ WEED dataset, allowing performance to be evaluated in terms of detection accuracy and computational efficiency using metrics such as precision, recall, average precision, and inference speed. The results highlight a clear trade-off between efficiency and contextual modeling: CNN-based detectors achieve high performance at a lower computational cost, while transformer-based approaches offer better global context capture at the expense of higher resource demands. These results provide practical criteria for model selection in precision agriculture applications.
Authors: Lin Sun, Wang Dexian, Jingang Huang, Linglin Zhang, Change Jia, Zhengwei Cheng, Xiangzheng Zhang
Abstract: Industrial Retrieval-Augmented Generation (RAG) systems depend on optical character recognition (OCR) to transform visual documents into text. Existing OCR benchmarks rely on character-level metrics, which inadequately measure downstream RAG effectiveness under real-world conditions. We introduce an OCR benchmark for industrial RAG systems covering 11 challenging document types, including extreme layouts, high-resolution pages, complex or watermarked backgrounds, historical documents with non-standard reading orders, visually decorated text, and documents containing tables and mathematical formulas. Evaluating recent SOTA OCR models under a controlled OCR-first RAG pipeline shows clear performance degradation on realistic industrial documents despite strong conventional benchmark scores. We find that high OCR accuracy does not necessarily translate into strong downstream RAG performance: structural and semantic errors can cause substantial retrieval failures even when WER/CER remains low. Further analysis shows that this mismatch is category-dependent, arises through both retrieval-side and downstream generation-side failures, and remains stable across representative OCR-first pipeline choices. The benchmark is publicly available at https://github.com/Qihoo360/InduOCRBench.
Authors: Emilie Durrieu, Christophe Hurter, Philippe Muller, Victor Boutin
Abstract: When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to infer where an image was captured. Whether image geolocation models rely on similar object-level evidence remains difficult to determine, as attribution methods like Grad-CAM typically highlight diffuse regions rather than coherent visual entities, making it difficult to link model predictions to specific objects or perceptible patterns. In this work, we propose an object-centric analysis pipeline to investigate the visual evidence used by geolocation models. Starting from attribution maps, we extract salient regions and segment them into object-like elements. We evaluate their predictive relevance through deletion and insertion tests, comparing attributionguided crops to randomly selected regions with similar coverage. Experiments on a three-country benchmark show that attribution-guided crops consistently retain more information for the model's prediction than random crops. These results suggest that attribution maps can be decomposed into interpretable, perceptible elements, providing a step toward object-level analysis of geolocation models.
Authors: Jiangtao Fan, Anish Jindal, Amir Atapour-Abarghouei
Abstract: Sensor-based Human Activity Recognition (HAR) has attracted increasing attention in medical and healthcare monitoring, particularly with the growth of Internet of Medical Things (IoMT). However, in real-world wearable sensing scenarios, IoMT signals are often corrupted by missing measurements, sensor failures, and environmental noise, which significantly degrade the performance of conventional deep learning models that assume clean and complete inputs. To address this challenge, we propose a Manifold-Consistent Spatio-Temporal Network (MCSTN) for robust HAR under imperfect sensing conditions. The proposed framework introduces a dual-level corruption modeling mechanism that simulates realistic sensor imperfections through both physical-level corruption and diffusion-driven continuous corruption. By enforcing representation consistency across multiple corrupted views, the model learns stable and corruption-invariant semantic representations. Furthermore, we design a dual-stream spatio-temporal architecture that explicitly decouples temporal dynamics modeling and spatial correlation learning. The temporal stream captures long-term activity dynamics, while the spatial stream models inter-sensor relationships, enabling more effective spatio-temporal representation learning. Extensive experiments on three widely used HAR benchmark datasets, PAMAP2, Opportunity, and WISDM, demonstrate that the proposed MCSTN achieves competitive performance compared with existing state-of-the-art methods, particularly under imperfect sensing conditions. These results validate the effectiveness and robustness of the proposed framework for real-world wearable IoMT sensing applications.
Authors: Zice Wang
Abstract: Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tokens, treating patch representations as an unstructured bag-of-words. We challenge this paradigm by demonstrating that token order is a critical, exploitable dimension in frozen visual representations (e.g., MAE, BEiT, DINOv2, and ViT as CLS-ablation extreme). We propose SSMProbe, a probing framework driven by a State Space Model (SSM). Operating as discrete Linear Time-Invariant (LTI) dynamical systems, SSMs act as permutation-sensitive probes where sequence order strictly dictates the final state due to inherent memory decay. Formulating token ordering as an information scheduling problem, we compare fixed scan heuristics against a differentiable soft permutation (Sinkhorn-based) learned from downstream supervision. Evaluations on standard and fine-grained classification benchmarks reveal a striking order gap: while fixed scans fail dramatically on highly localized patch features, our learned soft permutation successfully extracts highly competitive performance from otherwise heavily localized patch sequences. We find that pre-training objectives fundamentally shape token structure: DINOv2 concentrates global semantics in optimized CLS tokens leaving patches hyperspecialized, pure MAE preserves distributed representations with heterogeneous patch informativeness, and ViT represents a supervised CLS-dominated extreme. BEiT occupies middle ground. This heterogeneity is order-dependent -- meaning the SSM probe's performance depends critically on which tokens are placed at which temporal positions -- and is not merely a topological property of the spatial grid. SSMProbe's learned routing effectively discovers and exploits this heterogeneity, offering a powerful new diagnostic lens for visual representation analysis.
Authors: Rui Zhang, Xianzhi Song, Linqi Zhu, Branko Bijeljic, Gensheng Li, Martin J. Blunt
Abstract: Reliable segmentation of multiphase pore-scale X-ray images of rocks is necessary to quantify fluid saturation, connectivity, and interfacial geometry. However, current 3D segmentation methods are typically dataset-specific, requiring retraining or extensive fine-tuning whenever rock type, fluid pattern, scanner, or acquisition conditions change. Foundation models such as the Segment Anything Model (SAM) provide strong 2D boundary priors, but they are not directly applicable to 3D data. We present SAMamba3D, a parameter-efficient framework that adapts a largely frozen SAM encoder to generalizable 3D pore-scale segmentation by coupling it with Mamba-based volumetric context modeling and progressive cross-scale feature interaction. For sandstone and carbonate datasets, with different fluids, wettability, and scanning conditions, SAMamba3D matches or outperforms current 3D baselines while reducing the need for case-specific retraining. The resulting segmented images preserve physically meaningful descriptors, including fluid saturation, connectivity, and interface morphology, enabling more reliable and rapid analysis of large 3D multiphase images.
Authors: Chirag Shinde
Abstract: We introduce energy-based constraint networks -- a modality-agnostic architecture that learns structural coherence from contrastive pairs. The system processes frozen encoder embeddings through a state-space model with dual-head attention, producing a scalar energy measuring structural consistency alongside per-position energy scores that localize violations. Multiple independently trained branches detect different violation types and compose at inference without interference. We demonstrate the framework in two domains. In text, the system achieves 93.4% accuracy on trained corruption types and 87.2% on 9 unseen types, using frozen BERT and 7.4M trainable parameters. In vision, the same architecture achieves competitive deepfake detection: 0.959 AUC on FaceForensics++ Deepfakes and 0.870 on Celeb-DF without any Celeb-DF training data, using frozen DINOv2 and 3.6M parameters per branch. The framework supports flexible training: branches learn from designer-specified corruptions, real-world paired data, or both. Composable branches require representation compatibility -- a finding validated through extensive experimentation where five incompatible approaches failed before the compatible one succeeded. The architecture is encoder-agnostic and domain-agnostic: changing the domain requires only new corruption strategies; changing the encoder requires only a new input projection layer. To our knowledge, this is the first architecture to learn within-modality structural coherence as an explicit energy landscape with per-position decomposition, and to demonstrate that the same architecture transfers across modalities via corruption respecification alone.
Authors: Michael Zhang, Elise Wang, Charlotte Whatley, Seth Strickland, Dylan Bannon
Abstract: The record of the beginning of the most widespread legal system in the world is contained in millions of pages of handwritten text. Most of the records of the first centuries of the Anglo-American legal system are hand-written in a highly abbreviated form of medieval Latin which only a few dozen scholars in the world are trained to read. In this interdisciplinary project, we construct a dataset of 4029 lines of text across 193 medieval criminal and civil cases. We then use the dataset to train an open-source end-to-end pipeline for transcribing these manuscripts. We first train standard neural network architectures for line segmentation and handwriting recognition (R-Blla and CNN+LSTM with CTC decoding, respectively) and show that they can already achieve 79% word accuracy, despite the relatively small training set and the challenge of expanding abbreviations. We then demonstrate that simple post-processing significantly boosts accuracy: adding an n-gram language model to the CTC decoder improves word accuracy to 82%, while asking Gemini Pro 3 to correct mistakes boosts accuracy to 88%. Finally, we compare the CNN+LSTM architecture with TrOCR, a transformer-based OCR architecture, demonstrating that TrOCR shows comparable word accuracy but worse character accuracy due to its over-willingness to guess, making it harder for humans to infer the correct reading. We incorporated our pipeline into a web portal (glyphmachina.com), opening up the English legal tradition to legal scholars, medievalists, and students.
Authors: Junzhe Huang, Xiaoxiao Sun, Yan Yang, Yuxuan Hou, Ruotian Zhang, Sirui Li, Hehe Fan, Serena Yeung-Levy, Xin Yu
Abstract: Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its importance, current evaluations rely largely on structured-text tables or clean rendered images, leaving the visual complexity of in-the-wild table images underexplored. Such images feature varied layouts and diverse domains that demand sophisticated structural perception and numerical reasoning. To bridge this gap, we introduce WildTableBench, the first question-answering benchmark for naturally occurring table images from real-world settings. WildTableBench comprises 402 high-information-density table images collected from online forums and websites across diverse domains, together with 928 manually annotated and verified questions spanning 17 subtypes across five categories. We evaluate 21 frontier proprietary and open-source multimodal foundation models on this benchmark. Only one model exceeds 50% accuracy, while all remaining models range from 4.1% to 49.9%. We further conduct diagnostic analyses to characterize model failures and reveal persistent weaknesses in structural perception and reasoning. These results and analyses provide useful insights into current model capabilities and establish WildTableBench as a valuable diagnostic benchmark for table image understanding.
Authors: Yueru Sun, Yimeng Zhang, Haoyu Gu, Nuo Chen, Dong She, Xianrong Yao, Yang Gao, Zhanpeng Jin
Abstract: Multimodal Emotion Recognition (MER) is critical for interpreting real-world interactions. While Multimodal Large Language Models (MLLM) have shown promise in MER, their internal decision-making mechanisms under modality conflict and missingness remain largely underexplored. In this paper, to systematically investigate these behaviors, we introduce EmoMM, a comprehensive benchmark featuring modality-aligned, conflict, and missing subsets. Through extensive evaluation, we uncover a Video Contribution Collapse (VCC) phenomenon, where MLLM marginalize video evidence due to high token redundancy and modality preferences. To address this, we propose Conflict-aware Head-level Attention Steering (CHASE), a lightweight mechanism that detects modality conflicts and performs inference-time attention steering, effectively mitigating decision bias without retraining the backbone. Experimental results demonstrate that CHASE consistently improves performance across various settings, significantly enhancing the reliability of MLLM in complex affective scenarios.
Authors: Chaoyue Xing, Wei Mao, Miaomiao Liu
Abstract: This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in this paper, we introduce a physics-aware human motion generation framework that explicitly models the full spectrum of human-related forces, including human-object, human-scene, and internal body dynamics.~Our method imposes soft physical constraints to maintain force and torque balance, ensuring physically grounded motion synthesis. We further propose a novel continuous distance-based force model that generalizes contact modeling to arbitrary surfaces, capturing interactions not only with static environments but also with dynamic, moving objects. Extensive experiments show that our approach significantly improves physical plausibility and generalizes well to complex scenes, setting a new benchmark for physically consistent human motion generation.
Authors: Johannes B. Thalhammer, Lorenzo D'Amico, Lucy Costello, Sebastian Peterhansl, Daniel Frey, Tina Dorosti, Florian Schaff, Jannis Ahlers, Ronan Smith, Marcus Kitchen, Franz Pfeiffer, Martin Donnelley, Daniela Pfeiffer, Kaye S. Morgan
Abstract: Propagation-based X-ray phase-contrast imaging (PBI) enables high-contrast visualization of lung structures and holds strong medical potential. However, safe translation to the clinic will require a substantial radiation dose reduction, which inevitably increases image noise. Supervised convolutional-neural-network-based denoising can restore image quality but depends on paired low- and high-dose datasets, which are rarely available in practice. Self-supervised methods avoid this limitation, yet most are not well adapted to the inverse problem of PBI computed tomography (CT). We introduce Neighbor2Inverse, a self-supervised denoising framework designed for low-dose PBI-CT that generalizes to clinical CT. Building on the Neighbor2Neighbor principle, each noisy projection is subsampled into two variants that preserve structural information but contain independent noise realizations. These are reconstructed separately, and the resulting pairs are used to train a denoising network directly in the image domain. We benchmark the proposed method against established analytical and self-supervised denoising approaches. In region-of-interest PBI CT experiments, Neighbor2Inverse achieves superior noise suppression while preserving fine structural details, as demonstrated by improved contrast-to-noise ratio, spatial resolution, and composite image quality metrics. Competitive performance is also observed on clinical CT data under simulated low-dose conditions. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Code, data, and interactive figures are available at https://github.com/J-3TO/Neighbor2Inverse.
Authors: Hamed Khatounabadi, Xiaohu Lu, Hayder Radha
Abstract: The performance of state-of-the-art object detectors degrades significantly under adverse weather, causing a safety-critical domain shift problem for autonomous vehicles. Recent efforts address this problem by relying on synthetic data to train the object detectors, which limits their real-world applicability. Meanwhile, pseudo-labeling is widely used for cross-dataset domain adaptation problems. However, these methods have not been exploited by weather-based domain adaptation approaches due to the noisy nature of such labels generated under harsh weather conditions. In this paper, we propose two new approaches to mitigate this weather-induced domain shift. First, we propose a Weather-Induced pseudo Label Denoising (WILD) framework that filters noisy pseudo labels generated by real data captured under adverse weather conditions. Second, we develop a novel hybrid training methodology, WILD SAM, that exploits both pseudo-label denoising and simulation-based training solutions while using real-data from the target harsh-weather domain. We validate both proposed approaches, WILD and WILD SAM, on the recently released Four Seasons dataset across rainy and snowy scenarios. Experiments show that the proposed frameworks improve Average Precision (AP) up to 13\% and significantly reduce the weather-induced performance gap relative to the baseline. The code is available at: https://github.com/Kh-Hamed/WILD-SAM
Authors: Hamidreza Aftabi, John E. Lloyd, Amanda Ding, Benedikt Sagl, Eitan Prisman, Antony Hodgson, Sidney Fels
Abstract: Mandibular reconstruction with vascularized bone grafts is complicated by donor-host nonunion, and current virtual surgical planning produces a geometric plan rather than a configuration that explicitly promotes bone union. We present OsteoOpt++, an image-to-decision planning loop for patient-specific mandibular reconstruction. A pre-operative computed tomography (CT) is converted into a personalized digital twin through template-to-patient registration and CT-derived updates of the muscle and temporomandibular-joint parameters. Bayesian optimization with an expected-improvement-plus acquisition rule then searches six clinically controllable cut-plane and donor-positioning variables under an apposition-driven objective and a safety-factor-regularized variant. The workflow was evaluated on three generic defects (body, symphysis, and ramus-body) and a total of 3+1 patient-specific cases, with 3 used for optimization and 1 for validation. In the generic cases, against a common surgical approach, cycle-averaged donor-mandible apposition increased by up to 29 percentage points (329% relative); in the patient-specific cases, against the surgeon-implemented day-5 post-operative configuration, by up to 26 percentage points. A 10% sensitivity analysis over eleven modeling parameters capped the change in the apposition-driven objective at 3% for generic cases and 4% for patient-specific cases, and the longitudinal case showed Dice overlap of 0.70 and 0.76 between predicted apposition and year-1 bone formation. Clinically, this provides surgeons with a pre-operative, image-driven recommendation for cut-plane orientation and donor placement that is predicted to improve union conditions over the configurations currently delivered in the operating room. The optimization and patient-specific modeling code is open source at https://github.com/hamidreza-aftabi/OsteoOpt.
Authors: Chi Zhang, Changjia Zhu, Xiaowen Li, Yao Liu, Zhuo Lu
Abstract: Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing safety filters typically rely on text-based classifiers or image-based checkers that completely block the output upon detecting a threat, issuing an explicit allow/block feedback signal to the user. This binary strategy leaves models vulnerable to adversarial attacks that alter keywords to bypass detection, and it causes high false-alarm rates that degrade the experience for benign users. To address such vulnerabilities, we propose Disciplined Diffusion (DDiffusion), a novel robust text-to-image diffusion that counters Not Safe For Work (NSFW) generation by uncovering implicit malicious semantics in prompt embeddings. DDiffusion leverages a semantic retrieval mechanism to evaluate prompts against concept distributions rather than relying on brittle pairwise similarity. Furthermore, it employs a localization method during the diffusion process to selectively edit only the harmful regions of the generated image. By returning locally sanitized images instead of applying uniform blocking, DDiffusion suppresses malicious content while preserving generation fidelity for benign prompts and avoiding the binary allow-deny signal on which existing probing attacks rely.
Authors: Anya Ji, George Ma, T\'ea Wright, Yiming Zhang, David M. Chan, Alane Suhr, Somayeh Sojoudi
Abstract: Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often struggle to communicate both exact spatial layouts and specific semantic details simultaneously. While natural language instructions effectively convey high-level semantics like texture and color, they lack spatial specificity. Conversely, freehand scribbles provide rough spatial boundaries but cannot express detailed visual attributes. Consequently, achieving precise control requires combining both modalities. However, existing models struggle to jointly interpret abstract scribbles alongside text due to a lack of specialized training data. In this work, we introduce ScribbleEdit, a large-scale synthetic dataset designed to bridge this gap by combining natural language instructions with freehand scribble inputs for more accurate, controllable edits. We construct this dataset through a synthetic pipeline that automatically generates source-target image pairs via inpainting, which are then paired with human-drawn scribbles and VLM-generated text instructions. Using ScribbleEdit, we evaluate and finetune both diffusion-based and autoregressive unified multimodal image editing models. Our experiments reveal that while off-the-shelf models struggle with abstract scribble inputs, finetuning on our synthetic dataset significantly improves their ability to generate spatially aligned and semantically consistent edits.
Authors: Suryakant Singh, Saarthak Kapse, Joel Saltz, Prateek Prasanna
Abstract: Whole-slide images (WSIs) present a fundamental challenge for computational pathology due to their extreme resolution, multi-scale heterogeneity, and the requirement for clinically reliable interpretation. Although recent pathology foundation models have enabled fluent report generation, they often lack clinical grounding, failing to accurately represent key diagnostic concepts and relationships observed by pathologists. This limitation arises from the difficulty of integrating heterogeneous visual evidence spanning fine-grained cellular patterns, slide-level tissue architecture, and high-level diagnostic concepts, while maintaining interpretability and clinical coherence. Here we present SCOUT: Semantic Context-aware mOdality fUsion Transformer, a context-aware concept-grounded multimodal framework for pathology report generation that enables progressive conditioning of image representations by global slide information and explicit diagnostic concepts. The method integrates local histological patterns, whole-slide context, and expert-curated semantic descriptors within a unified learning paradigm, allowing visual features to be dynamically refined throughout the encoding process. By combining depth-aware contextual modulation with adaptive multimodal fusion during text generation, the framework produces clinically coherent reports while preserving complementarity across representational scales. Using CONCH1.5 features, we evaluate SCOUT against WSI-Caption, HistGen, and BiGen on TCGA-BRCA, MICCAI REG, and HistAI. SCOUT achieves the best BLEU-1 to BLEU-4 and METEOR scores on all datasets, plus the best ROUGE-L on TCGA-BRCA and MICCAI REG. On TCGA-BRCA, it reaches 0.436/0.303/0.202/0.156 BLEU-1/2/3/4 and 0.204 METEOR; on REG 2025, it achieves 0.865/0.834/0.805/0.780 and 0.568. These results support progressive contextual conditioning for grounded pathology report generation.
Authors: Valter Estevam, Rayson Laroca, Helio Pedrini, David Menotti
Abstract: This paper proposes a novel Zero-Shot Action Recognition~(ZSAR) method based on contrastive learning. In ZSAR, we aim to classify examples from classes that were missing during training. Two well-known problems remain in ZSAR: the semantic gap and the domain shift. A semantic gap occurs because label representations come from the textual domain (i.e., language models) and must be associated with visual representations (i.e., CNNs, RNNs, transformer-based). This multimodal nature implies that the semantic properties of the two spaces are not identical. On the other hand, the domain shift arises from differences between the training and test sets and is inherent to ZSAR once the test set is unknown. One of the most promising methods to address both issues is learning joint embedding spaces. Therefore, we propose a new model that encodes videos and sentences in a joint embedding space, trained by aligning videos with their natural-language descriptions. We design an automatic negative sampling procedure to augment the training dataset and generate unpaired data, i.e., visual appearance and unrelated descriptions. Our results are state-of-the-art on the UCF-101 and Kinetics-400 datasets under several split configurations. Our code is available at https://github.com/valterlej/cezsar.
Authors: Ghadi Nehme, Eamon Whalen, Faez Ahmed
Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering.
Authors: M. Berk Sahin, Dilek Yalcinkaya, Abolfazl Hashemi, Behzad Sharif
Abstract: Accelerated magnetic resonance imaging (MRI) enabled by the training of deep learning (DL)-based image recon. models requires large and diverse raw k-space datasets. In most clinical MRI applications, due to storage and patient privacy concerns, raw k-space data is discarded and magnitude-only images are the only component saved. Consequently, a large portion of the DL-based MRI recon. literature has either relied on small training datasets or has used one of the few available open-source k-space datasets. At the same time, the growing number of anonymized magnitude-only image registries/databases motivates the development of techniques that can use them as training datasets for generalizable DL-based recon. models. Here we propose to address this challenge by employing a generative approach based on conditional score-based diffusion models (SBDMs): given a magnitude-only MR image, it synthesizes a phase map (in the image domain) that realistically corresponds to the magnitude-only image. We evaluate its generative capabilities in a downstream DL-based recon. task whereby a large k-space dataset is generated by combining the SBDM-synthesized phase-maps and the corresponding magnitude-only images, and this k-space dataset is then used to train a DL model for accelerated MRI recon. We compare the performance of the resulting DL model versus those trained according to (a) a naive approach that uses smooth phase, (b) a k-space training dataset generated using synthesized phase maps derived from a generative adversarial network, and (c) the ground truth k-space data. Our results suggest that the DL model trained from SBDM-synthesized k-space data outperforms the other approaches in terms of quantitative metrics as well as qualitatively observed recon. fidelity, i.e., whether the reconstructed images include erroneous or hallucinated features that could adversely impact diagnostic accuracy.
Authors: Jiabei Zhang, Ziyuan Yang, Andrew Beng Jin Teoh, Yi Zhang
Abstract: Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space perturbations to obfuscate identity information, yet their protection can degrade when adversaries learn restoration or purification mappings that partially invert the transformation. We study this setting as an asymmetric adversarial attack, in which reverse manipulation becomes feasible because existing defense paradigms do not control reversibility. To address this problem, we propose Asymmetric Reversible Face Protection (ARFP), a restoration-aware extension of personalized face cloaking that integrates privacy protection, keyed recovery, and tamper indication in a single framework. ARFP consists of three components: Key-Conditioned Manifold Binding, which ties the protection transformation to a user-provided key; Adversarial Restoration-Aware Training, which introduces a surrogate restoration adversary during training to improve robustness against evaluated inverse purification attacks; and Authorized Reversible Restoration, which supports recovery with the correct key while providing nonce-based tamper indication. Extensive experiments under the threat models considered in this work show that ARFP improves resistance to the evaluated restoration attacks while preserving authorized recovery utility. These results provide empirical evidence of key-sensitive recovery behavior and tamper awareness in the tested settings.
Authors: Pengfei Jiang, Jixiang Luo, Luxi Lin, Zhaohong Huang, Xuelong Li
Abstract: Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and inflate memory at high resolutions. We introduce Visual Implicit Autoregressive Modeling (VIAR), a next-scale autoregressive generator that embeds an implicit equilibrium layer between shallow pre/post blocks. The implicit layer is trained with Jacobian-Free Backpropagation, yielding constant training memory, while inference exposes a per-scale iteration knob that enables compute control. On ImageNet 256x256 benchmark, VIAR attains FID 2.16, and sFID 8.07 with only 38.4% parameters of VAR, matching or surpassing strong AR baselines and remaining competitive with large diffusion models. By controlling the per-scale knob, VIAR can reduce peak memory from 19.24 GB to 8.53 GB and doubles throughput from 15.16 to 32.08 images/s on a single RTX 4090, without retraining. Ablations show that fewer steps are sufficient for fixed-point iterations to converge and that VIAR consistently dominates VAR across quality efficiency operating points. In zero shot in-painting and class-conditional editing, VIAR produces sharper details and smoother boundaries while preserving global structure, validating the benefits of implicit equilibria and per-scale compute control for practical, deployable visual generation.
Authors: Nima Rahmanian, Daniel Kienzle, Thomas Gossard, Dvij Kalaria, Rainer Lienhart, Shankar Sastry
Abstract: We present TT4D, a large-scale, high-fidelity table tennis dataset. It provides $140+$ hours of reconstructed singles and doubles gameplay from monocular broadcast videos, featuring multimodal annotations like high-quality camera calibrations, precise 3D ball positions, ball spin, time segmentation, and 3D human meshes over time. This rich data provides a new foundation for virtual replay, in-depth player analysis, and robot learning. The dataset's combination of scale and precision is achieved through a novel reconstruction pipeline. Prior methods first partition a game sequence into individual shot segments based on the 2D ball track, and only then attempt reconstruction. However, 2D-based time segmentation collapses under occlusion and varied camera viewpoints, preventing reliable reconstruction. We invert this paradigm by first lifting the entire unsegmented 2D ball track to 3D through a learned lifting network. This 3D trajectory then allows us to reliably perform time segmentation. The learned lifting network also infers the ball's spin, handles unreliable ball detections, and successfully reconstructs the ball trajectory in cases of high occlusion. This lift-first design is necessary, as our pipeline is the only method capable of reconstructing table tennis gameplay from general-view broadcast monocular videos. We demonstrate the dataset's fidelity through two downstream tasks: estimating the racket's pose \& velocity at impact, and training a generative model of competitive rallies.
Authors: Lei He, Jielei Chu, Fengmao Lv, Weide Liu, Tianrui Li, Jun Cheng, Yuming Fang
Abstract: Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation characteristics to dynamically modulate feature representations. Our method constructs degradation-aware contextual representations from the input to modulate attention distribution, frequency-domain features, and feature aggregation. Specifically, a lightweight multi-scale degradation-aware module extracts coarse degradation information and generates layer-wise prompts. These prompts guide attention temperature and output gating in encoder and decoder blocks for adaptive feature extraction. Additionally, a spatial-channel dual-gated adaptive fusion mechanism refines encoder features, suppressing noise propagation from shallow to deep layers. This design effectively suppresses degradation-induced noise while preserving informative structures. Experiments show DACG-IR outperforms state-of-the-art methods in single-task, all-in-one, adverse weather removal, and composite degradation settings. Code: https://github.com/HlHomes/DACG-IR-code
Authors: Suraj Pai, Thibault Heintz, Cosmin Ciausu, Marion Tonneau, Hugo Aerts, Raymond Mak
Abstract: Zero-shot vision-language models (VLMs) offer a promptable alternative to task-specific training for gross tumor volume (GTV) delineation in non-small-cell lung cancer (NSCLC), but the prompt dimensions that govern their spatial behavior remain poorly understood. We study this question by probing alignment directions in VoxTell on a held-out internal NSCLC tumor dataset through sub-prompt decomposition into diagnosis, demographic, staging, anatomical, generic, and irrelevant controls; attribute-wise perturbation robustness; specificity ladders; and cross-case prompt swaps, while benchmarking against fine-tuned and zero-shot baselines using the Dice Similarity Coefficient (DSC) with Wilcoxon signed-rank tests and Benjamini-Hochberg correction. Alignment analyses revealed that anatomical location is the dominant driver of VoxTell's spatial attention: 63.4 percent of location perturbations caused catastrophic drops, prompt specificity improved from generic to full descriptions except for diagnosis-only prompts, irrelevant prompts correctly yielded zero segmentation, and cross-case prompt swaps confirmed patient-specific conditioning (matched DSC 0.906 vs. mismatched 0.406). Histology and stage substitutions had minimal effect, indicating that the model prioritizes "where to look" over "what to look for." In this context, VoxTell, operating fully zero-shot, achieved a mean DSC of 0.613, statistically indistinguishable from nnUNet (0.690, adjusted p = 0.156) and Ahmed et al. (0.675, adjusted p = 0.679), while significantly outperforming all other zero-shot models. Together, these findings argue that segmentation VLMs should be evaluated not only by Dice, but also by the prompt dimensions to which they align.
Authors: Rajesh Sureddi, Shreshth Saini, Avinab Saha, Alan C. Bovik
Abstract: The development of video game streaming has grown rapidly, with major platforms such as YouTube and Twitch using different codecs. To support quality assessment models that work consistently across any codec, it is necessary to have access to large, diverse subjective gaming quality datasets. Currently, there are only a few available, each having limitations. To address this gap, we present the largest gaming video quality dataset to date, incorporating both user-generated content (UGC) and professional-generated content (PGC) with extensive visual diversity. Our dataset covers the most widely used codecs - H.264, H.265, and AV1 - and consists of 4,048 video samples, each annotated by an average of 37 mean opinion score (MOS) ratings. In addition to overall quality scores, we collect coarse-grained quality attributes, enabling a better understanding of perceptual factors. We study the performance of leading video quality assessment methods on this dataset, including a vision language model that outperforms all the benchmarks. To the best of our knowledge, this is the first dataset that comprehensively addresses gaming video quality assessment across multiple codecs and content types with quality attributes. Our dataset is publicly available at https://rajeshsureddi.github.io/GameScope/.
Authors: Hyeonseok Jin
Abstract: Recently, Convolutional Neural Network (CNN) or Transformer architecture based models have been proposed to overcome the limitations of Recurrent Neural Network (RNN) based models in spatiotemporal prediction. These models prevent the inefficiency of parallelization limitation due to the sequential properties and stacked error due to the recursive method, and show high performance. Novertheless, there are still some challengies. First, CNN based models have difficulty considering global information due to the local properties of the kernel, and their performance is limited. In addition, information is mixed because the time axis is combined with the channel axis of the image for processing. Models based on Transformer architecture have high complexity due to the self-attention calcuation and take a long training time. In this paper, we propose a new structure model called CNN-based Multi-In-Multi-Out model for Efficient Spatiotemporal Prediction (MIMO-ESP) to overcome these limitations. MIMO-ESP considers global information and significantly improves complexity by configuring a Transformer architecture based on CNN. In addition, it treats the time axis as an independent axis without combining it, and effectively considers spatiotemporal information together by applying dilation. This structure makes MIMO-ESP efficient and high performance. Extensive experiment results on three promising benchmark datasets which including video, traffic, and precipitation prediction tasks demonstrate that the usefulness of MIMO-ESP due to the achieved competitive efficiency while outperforming existing models. Furthermore, the ablation study results demonstrate the usefulness of the components of MIMO-ESP, emphasizing the potential of the proposed approaches.
Authors: David J. Richter
Abstract: Plants, crops and their yields are essential to our very existence, but diseases and pests cause large losses every year. As such it is vital to ensure that diseases can be spotted early and treated accordingly and stopping the spread while still possible. Manual and traditional methods require personal to walk through the field and check for symptoms 'by hand'. This is very laborious and very time consuming, so ML methods have been applied as a result and they have garnered promising results. CNN models are especially efficient as they can automatically extract features from images without any manual feature construction before then feeding the features to a classifier. Datasets are largely influential to the final performance of the model. Despite the importance that datasets pose to the field, there still seems to be somewhat of a discrepancy between what is publicly available for use and what would be required to sufficiently train fully capable models. To overcome these shortcomings, as part of this thesis open datasets for the field of plant leaf disease classification have been identified as well as models that can be trained on them and extensive benchmarks have been carried out to identify their suitability. Then a new dataset was constructed based on those findings as well as on the findings of a augmentation applicability study, which will be used to train a new Base Model based on the DenseNet201 architecture, which managed to outperform the baseline model on said new dataset as well as outperforming it on plant leaf disease classification domain specific Transfer-Learning experiments on another new dataset. This new model manages to train models through Transfer-Learning (TL) faster, more robust, more stable, and with less data than general model would, overcoming a large number of issues that the field still suffers from.
Authors: Peiyang Liu, Ziqiang Cui, Xi Wang, Di Liang, Wei Ye
Abstract: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external documents. However, current systems predominantly operate on parsed text, which creates two critical bottlenecks: (1) \textit{Coarse-grained attribution}, where users are burdened with manually locating evidence within lengthy documents based on vague text-level citations; and (2) \textit{Visual semantic loss}, where the conversion of visually rich documents (e.g., slides, PDFs with charts) into text discards spatial logic and layout cues essential for reasoning. To bridge this gap, we present \textbf{Chain of Evidence (CoE)}, a retriever-agnostic visual attribution framework that leverages Vision-Language Models to reason directly over screenshots of retrieved document candidates. CoE eliminates format-specific parsing and outputs precise bounding boxes, visualizing the complete reasoning chain within the retrieved candidate set. We evaluate CoE on two distinct benchmarks: \textbf{Wiki-CoE}, a large-scale dataset of structured web pages derived from 2WikiMultiHopQA, and \textbf{SlideVQA}, a challenging dataset of presentation slides featuring complex diagrams and free-form layouts. Experiments demonstrate that fine-tuned Qwen3-VL-8B-Instruct achieves robust performance, significantly outperforming text-based baselines in scenarios requiring visual layout understanding, while establishing a retriever-agnostic solution for pixel-level interpretable iRAG. Our code is available at https://github.com/PeiYangLiu/CoE.git.
Authors: Kosuke Takemoto, Takafumi Koshinaka
Abstract: Diffusion-based virtual try-on methods achieve photorealistic synthesis through cross-attention mechanisms that transfer garment features to target body regions. However, these approaches rely on implicit learning of spatial correspondences, struggling to preserve fine details such as text and illustrations. We propose a novel approach, which we call SIFT-VTON, that utilizes SIFT keypoint matching to provide explicit geometric guidance for diffusion-based virtual try-on. Our method applies domain-specific filtering to SIFT keypoint matches between garment and person images, then converts these correspondences into spatial probability distributions that supervise cross-attention layers during training. This explicit supervision guides the model to learn precise spatial alignment, concentrating attention on geometrically consistent garment regions. Experiments on the VITON-HD dataset demonstrate significant improvements on unpaired metrics while maintaining competitive paired reconstruction metrics. Qualitative comparisons show superior preservation of text clarity and pattern alignment. Attention visualizations confirm that our method produces sharply focused attention on relevant garment details. This work demonstrates that classical geometric correspondence methods can effectively enhance modern diffusion models for conditional synthesis tasks. The source code will be available at https://github.com/takesukeDS/SIFT-VTON.
Authors: Ruichi Zhang, Chikai Shang, Jiacheng Yang, Mengke Li, Yang Zhou, Junlong Gao, Yang Lu
Abstract: Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few. Recently, fine-tuning foundation models for long-tailed learning has gained attention due to their excellent performance. However, most existing methods focus solely on mitigating long-tailed distribution bias while overlooking concept confusion caused by the long-tailed distribution. In this paper, we study this problem and attribute it to the mutual exclusivity of single-label supervision under long-tailed distributions, which suppresses feature sharing among related classes and amplifies the dominance of head classes, leading to disrupted inter-class discriminability. To address this, we propose CUE, Concept-aware mUlti-label Expansion, which introduces multi-label concept signals to preserve disrupted inter-class relationships. Specifically, CUE constructs concept sets by (i) extracting instance-level visual cues from zero-shot CLIP and (ii) generating class-level semantic cues with LLM; the two cues are incorporated via separately weighted Binary Logit-Adjustment (BLA) auxiliary losses and jointly optimized with the baseline Logit-Adjustment (LA) loss. Experiments on several long-tailed benchmarks, CUE achieves balanced and strong performance, surpassing recent state-of-the-art methods. Code is available at: https://github.com/zhangruichi/CUE.
Authors: Jiahao Zhu, Kang You, Dandan Ding, Zhan Ma
Abstract: LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yields high compression gains, it faces two critical bottlenecks: 1) prohibitive latency, particularly during decoding, caused by causal, multi-stage context modeling; and 2) a rigid performance-latency trade-off, preventing a single model from adapting to varying constraints. These limitations stem from the tight coupling between context aggregation backbone and probability prediction. To address this, we propose PACE, a new framework that reformulates ancestral context aggregation as a non-causal backbone and confines causality to a lightweight, stage-scalable predictor, eliminating repetitive backbone executions and reducing computational overhead. The predictor supports an arbitrary number of prediction stages, supporting seamless adaptation across diverse performance-latency trade-offs without reloading parameters. Experiments demonstrate that PACE sets a new state-of-the-art in compression efficiency, achieving notable BD-BR savings and reducing decoding latency by over 90% in autoregressive mode, highly attractive for practical applications.
Authors: Jingze Wu, Quan Zhang, Hongfei Suo, Zeqiang Cai, Hongbo Chen
Abstract: Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue, we leverage causal analysis and experiment to reveal the underlying phenomenon of perceptual bias, demonstrating that RL-based fine-tuning compels lightweight models to preferentially adopt perceptual shortcuts induced by data biases, rather than developing genuine reasoning abilities. Motivated by this insight, we propose VideoThinker, a causal-inspired framework that cultivates robust reasoning in lightweight models through a two-stage debiasing process. First, the Bias Aware Training stage forges a dedicated "bias model" to embody these shortcut behaviors. Then, the Causal Debiasing Policy Optimization (CDPO) algorithm fine-tunes the primary model, employing an innovative repulsive objective to actively push it away from the bias model's flawed logic while simultaneously pulling it toward correct, generalizable solutions. Our model, VideoThinker-R1, establishes a new state-of-the-art in video reasoning efficiency. For same-scale comparison, requiring no Supervised Fine-Tuning (SFT) and using only 1 of the training data for RL, it surpasses VideoRFT-3B with a 3.2% average gain on widely-used benchmarks and a 7% lead on VideoMME. For cross-scale comparison, it outperforms the larger Video-UTR-7B model on multiple benchmarks, including a 2.1% gain on MVBench and a 3.8% gain on TempCompass. Code is available at https://github.com/falonss703/VideoThinker.
Authors: Muyang Li, Yucheng Liu, Jianbo Ma, Elliot Osborne, Bo Han, Tongliang Liu
Abstract: Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders. While recent works have explored various combinations of vision encoders and LLMs, there still lacks a principled understanding of what makes a vision encoder suitable for VLM alignment. In this paper, we systematically investigate this question via comprehensive experiments on a curated collection of 19 pre-trained vision encoders from diverse sources. We first demonstrate that common practices, such as choosing encoders with the largest size or highest zero-shot accuracy, consistently fail to identify optimal models. In fact, these metrics show only weak to moderate correlation with VLM performance. This intriguing finding begs a fundamental question: What factors of vision-encoders matter in VLM? Through comprehensive analysis, we identify that the structural similarity across modalities plays a crucial but previously overlooked role in vision-encoder selection, which we measure using the Gromov-Wasserstein distance as a proxy. From a theoretical perspective, we show that the learnability of cross-modality mapping can be provably associated with the Gromov-Wasserstein distance. Empirical verification on 60+ full VLM training runs shows that our proposed inference-only metric performs significantly better than alternative model selection strategies and exhibits a much stronger correlation with final VLM performance, thereby enabling efficient and effective prediction of VLM performance before full training.
Authors: Jin Tong, Guang Liang, Peilin Sun, Jianxin Wu
Abstract: Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either handle quantization post-training or suppress large activations during training; however, aggressively restricting outliers in vision models can lead to a poorer trade-off between full-precision and quantized accuracy. We argue that rather than simply suppressing outliers, the training objective should control the structural amplification that makes them harmful. To this end, we introduce Colinearity-Decay (CD), a structural regularizer for ordered matrix pairs within Transformer blocks. CD penalizes detrimental cross-matrix alignment and mitigates extreme activations without altering the architecture or task loss. Applied as a decoupled update, CD is non-invasive and introduces minimal training overhead. Across ImageNet-1K pre-training, COCO detection, and downstream fine-tuning, CD consistently boosts quantized accuracy across multiple pipelines while preserving, or even improving, full-precision performance. Ultimately, our results demonstrate that structural regularization effectively prepares vision Transformers for low-bit deployment with zero inference-time overhead.
Authors: Hao Wang, Yiming Yao, Yaguang Xie, Tong Qiao, Zhidong Zhao
Abstract: Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security of steganography methods, especially the emerging invertible image hiding approaches. However, prior studies merely classify input images into two categories (i.e., stego or cover) and typically conduct steganalysis under the constraint that training and testing data must follow similar distribution, thereby hindering their application in real-world scenarios. To overcome these shortcomings, we propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting. Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images. Additionally, we elaborate a simple yet effective residual augmentation strategy for generating stego images to further enhance the generalizability of the steganalyzer in cross-dataset and cross-architecture scenarios. Extensive experiments on benchmark datasets demonstrate that our proposed approach significantly outperforms the existing steganalysis techniques for invertible image hiding schemes.
Authors: Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei
Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevitably sacrifices the fine-grained details necessary for complex reasoning. Inspired by the classical paradigms of active vision and information foraging, we frame overcoming this limitation as a sequential decision-making process. We formalise this process through the lens of the sequential Bayesian optimal experimental design (S-BOED) problem. While exact Bayesian inference is intractable in continuous gigapixel spaces, we derive principled yet tractable approximations that balance spatial coverage against resolution. To validate this framework, we present a training-free inference strategy as a practical instantiation of the S-BOED objective for agents equipped with multiple vision tools. Designed as a flexible template, this strategy accommodates arbitrary optimisation algorithms, ranging from efficient greedy sampling to look-ahead planning, to approximate the optimal design. Empirical evaluations on gigapixel-level benchmarks demonstrate that our approach further boosts the performance of state-of-the-art models, significantly outperforming standard baselines and effectively narrowing the gap towards human-annotated oracles.
Authors: Kartik Jhawar, Yuhao Geng, Atul N. Parikh, Lipo Wang
Abstract: Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertainty estimation, these approaches often struggle under partial observability, where local temporal evidence can be contradictory and standard confidence scores become misleading. We introduce CHASE (Competing Hypotheses for Ambiguity-Aware Selective Prediction), a selective prediction framework that explicitly compares structured temporal explanations to determine whether to commit to a decision or abstain. Because genuine ambiguity causes the score gap between competing hypotheses to collapse, CHASE optimizes a ranking-aware selector over these hypothesis margins to globally separate safe commitments from fundamentally uncertain ones. We evaluate this framework on the problem of hidden connectivity inference, utilizing a controlled, physically grounded simulator inspired by the dynamics of giant unilamellar vesicles (GUVs), alongside zero-shot qualitative transfer (without retraining or fine tuning) to representative real GUV videos. Our experiments demonstrate that explicitly reasoning over competing hypotheses provides a superior balance of metrics. Compared to canonical uncertainty baselines, CHASE achieves statistically significant gains in overall no-abstain accuracy, three-way accuracy, and overall ambiguity-aligned abstention (at 80% coverage). Specifically, it yields up to an 11.0% relative mean improvement in overall alignment, alongside up to an 8.8% relative boost in three-way accuracy in the very-high ambiguity regime. By maintaining a selective risk boundary strictly at par with the best baselines at 80% coverage, and reducing overall risk by 9.9% at 90% coverage, this framework offers a more reliable approach to decision-making under structured ambiguity.
Authors: Minh-Dung Le, Minh-Duc Hoang, Hoang-Vu Truong, Thi-Thu-Hong Phan
Abstract: Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) provide strong representation capability by modeling long-range dependencies and inter-class relationships; however, their high computational cost makes them impractical for deployment on edge devices. As a result, existing approaches struggle to effectively transfer these rich representations to lightweight models. This paper introduces AgriKD, a cross-architecture knowledge distillation framework for efficient edge deployment, which transfers knowledge from a Vision Transformer (ViT) teacher to a compact convolutional student model. To bridge the representational gap between Transformer and CNN architectures, the proposed approach integrates multiple distillation objectives at the output, feature, and relational levels, where each objective captures a different aspect of the teacher knowledge. This enables the student model to better preserve and utilize transformer-derived global representations. Experiments on multiple leaf disease datasets show that the distilled student achieves performance comparable to the teacher while significantly improving efficiency, reducing model parameters by approximately 172 times, computational cost by 47.57 times, and inference latency by 18-22 times. Furthermore, the optimized model is deployed across multiple runtime formats, including ONNX, TFLite Float16, and TensorRT FP16, achieving consistent predictive performance with negligible accuracy degradation. Real-world deployment on NVIDIA Jetson edge devices and a mobile application demonstrates reliable real-time inference, highlighting the practicality of AgriKD for AI-powered agricultural applications in resource-constrained environments.
Authors: Haowen Sun, Shaolong Zhang, Mingyang Li, Chengzhong Ma, Xinzhe Chen, Qiongjie Cui, Xingyu Chen, Zeyang Liu, Xuguang Lan
Abstract: Open-vocabulary 3D affordance detection requires localizing interaction regions on point clouds given novel affordance descriptions. Recent methods extend multimodal large language models (MLLMs) with special output tokens that are decoded into segmentation masks. However, these tokens are produced through autoregressive generation, which models sequential dependencies rather than spatial neighborhood relations, leaving them semantically rich but spatially impoverished for 3D localization. We propose Voxel-enhanced Affordance detection (VoxAfford), which bypasses this bottleneck by injecting multi-scale geometric features from a frozen pre-trained 3D VQVAE encoder into the output tokens after generation. Each output token uses its affordance semantics as a query to retrieve relevant geometric patterns from its paired voxel scale via cross-attention, with a learned compatibility gate controlling the injection strength. The enhanced tokens are then aggregated into a spatially-aware affordance prompt through semantic-conditioned attention and propagated alongside per-point features to generate the final mask. Experiments on open-vocabulary affordance detection tasks show that VoxAfford achieves state-of-the-art performance with approximately an 8% improvement in mIoU, and real robot experiments confirm zero-shot transfer to novel objects.
Authors: Chinmay Prabhakar, Bastian Wittmann, Paul B\"uschl, Hongwei Bran Li, Bjoern Menze, Suprosanna Shit
Abstract: Analyzing human vasculature and vessel-like, tubular structures, such as airways, is crucial for disease diagnosis and treatment. Current methods often rely on small sub-regions or simplified tree-like structures, rendering analysis of entire organ-level networks at clinical resolution computationally challenging. To this end, we propose VAEsselSparse, an efficient encoder-decoder model to obtain a meaningful yet compact representation of the entire organ-level vascular network at sub-millimeter resolution. VAEsselSparse leverages the inherent sparsity of 3D vascular structures via sparse convolutions and attention mechanisms, achieving substantial spatial compression rates of 8 x 8 x 8. We demonstrate superior reconstruction performance compared to dense counterparts and previous methods. Importantly, the resulting latent space retains clinically relevant discriminative features readily usable for classification tasks, such as aneurysm/stenosis or subvariants of the circle of Willis. Moreover, the compact latent space of VAEsselSparse serves as an effective representation for learning vessel-specific priors through generative models, enabling the synthesis of realistic vasculature.
Authors: Alejandro Aparcedo, Akash Kumar, Aaryan Garg, Dalton Pham, Wen-Kai Chen, Anirudh Bharadwaj, Aman Chadha, Yogesh Rawat
Abstract: Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action interactions between diverse entities which characterize real-world video understanding. Furthermore, the lack of a systematic framework for analyzing model failures across complementary spatio-temporal axes hinders comprehensive evaluation. To address these gaps, we introduce VISTA, a Video Interaction Spatio-Temporal Analysis benchmark designed for open-set, multi-entity and multi-action spatio-temporal understanding in VLMs. VISTA decomposes videos into interpretable entities, their associated actions, and relational dynamics, enabling multi-axis diagnostics and unified assessment of relational, spatial, and temporal understanding. Our benchmark integrates multiple datasets into a single interaction-aware taxonomy and comprises ~12K curated video-query pairs spanning diverse scenes and complexities. We systematically evaluate 11 state-of-the-art VLMs on VISTA, and break down aggregate performance across our taxonomy to reveal shortcomings and pronounced spatio-temporal biases obscured by traditional metrics. By providing detailed, taxonomy-driven diagnostics on a challenging dataset, VISTA offers a nuanced framework to guide advances in model design, pretraining strategies, and evaluation protocols. Overall, VISTA is the first, large-scale, interaction-aware diagnostic benchmark for spatio-temporal understanding in VLMs.
Authors: Abhishek Vivekanandan, Ahmed Abouelazm, J. Marius Z\"ollner
Abstract: Motion forecasting often requires trading interpretability for predictive accuracy. Standard anchor-based architectures rely on opaque latent queries that are highly prone to latent collapse, or naive trajectory sampling that limits multi-modal diversity. We propose an end-to-end differentiable framework that grounds predictions in a comprehensive "motion bank", a structured embedding space of physically realizable trajectories constructed via contrastive learning. Rather than regressing paths from a blank slate, our architecture dynamically retrieves explicit motion priors using a novel Anchor Retrieval Layer. This module adapts orthogonally initialized queries via a Dual-Level Gated Cross-Attention mechanism and executes discrete trajectory selection using a Straight-Through Gumbel-Softmax estimator to preserve continuous gradient flow. The retrieved semantically grounded anchors are then geometrically refined by a DETR-style decoder, optimized jointly with a Winner-Takes-All (WTA) kinematic Gaussian Mixture Model (GMM), a latent diversity penalty, and a soft-min weighted endpoint loss. By strictly conditioning the decoding phase on diverse, interpretable motion primitives, our approach eliminates the "black box" of standard latent queries while achieving competitive multi-modal accuracy on the Argoverse 2 and Waymo Open Motion datasets. Code is available at: https://github.com/abviv/recall2predict
Authors: Panagiotis P. Filntisis, George Retsinas, Radek Dan\v{e}\v{c}ek, Vanessa Sklyarova, Petros Maragos, Timo Bolkart
Abstract: Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic correspondence directly from calibrated multi-view images. However, these learning-based methods rely on the slow, manual registration pipelines they aim to replace for their training supervision. We overcome this limitation with MOCHI (Multi-view Optimizable Correspondence of Heads from Images), a multi-view 3D face prediction framework trained without requiring registered training data. MOCHI eliminates the registration data dependency by enforcing topological consistency through a pseudo-linear inverse kinematic solver. Semantic alignment is guided by dense keypoints from a 2D landmark predictor trained exclusively on synthetic data. Our analysis further reveals that standard point-to-surface distances induce training instabilities and visual artifacts in registration-free settings. We propose pointmap- and normal-based losses instead, which provide smoother gradients and superior reconstruction fidelity. Finally, we introduce a test-time optimization scheme that refines network weights over a few dozen iterations. This approach bridges the gap between feed-forward efficiency and iterative optimization precision, allowing MOCHI to outperform traditional labor-intensive pipelines in both reconstruction accuracy and visual quality. Code and model are public at: https://filby89.github.io/mochi.
Authors: Roberto Isai Navaro-Avi\~na, Eduardo Said Merin-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello
Abstract: Single-Image Super-Resolution (SISR) aims to reconstruct a High-Resolution (HR) image from a Low-Resolution (LR) observation, a fundamentally ill-posed problem where high-frequency details are severely degraded at large upscaling factors. Recent advances have been driven by transformer-based architectures and diffusion models improve global context modeling and perceptual quality at the cost of increased computational complexity. In contrast, this work focuses on enhancing the expressivity of local operators under minimal resources. We propose SRGAN--CKAN, a hybrid super-resolution framework that integrates Convolutional Kolmogorov--Arnold Networks (CKAN) into an adversarial learning setting reformulating convolution as a nonlinear patch-based transformation. The proposed operator replaces linear local mappings with spline-based functional representations, allowing expressive modeling of complex local structures and high-frequency textures using minimal hardware resources. Experimental results demonstrate that the proposed approach improves perceptual quality while preserving reconstruction fidelity, achieving a favorable balance between distortion-based and perceptual metrics. These results are obtained under constrained computational settings, highlighting the efficiency of the proposed formulation. Overall, this work introduces a complementary direction to existing approaches by improving the representational power of local transformations, providing an efficient and scalable alternative to globally intensive architectures.
Authors: Zhaoyang Li, Zhichao You, Tianrui Li
Abstract: Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.
Authors: Jiacheng Yang, Ruichi Zhang, Chikai Shang, Mengke Li, Xinyi Shang, Junlong Gao, Yonggang Zhang, Yang Lu
Abstract: Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer helps balance the decision space of the classifier, it also induces latent non-local feature mixing that entangles inter-class features, causing decision boundary overlap and tail class distribution shift. To address this, we first identify the problem of boundary ambiguity and then propose Decision Boundary-aware Generation (DBG) framework, which promotes near-boundary representation learning by generating informative near-boundary samples. Overall, DBG rebalances the long-tailed dataset while yielding more separable decision space for long-tailed learning. Across standard long-tailed benchmarks, DBG consistently improves tail class and overall accuracy with less inter-class overlap. The code of DBG is available at https://github.com/keepdigitalabc-svg/DBG.
Authors: Kanak Mazumder, Fabian B. Flohr
Abstract: Online High-Definition (HD) map construction is a key component of autonomous driving. Recent methods rely on multi-view camera images for cost-effective HD map segmentation, but cameras lack depth information for accurate scene geometry. In contrast, LiDAR provides precise 3D measurements but lacks dense semantic cues. In this work, we propose LIE, LiDAR-only semantic map construction method that employ Knowledge Distillation (KD) to handle the lack of dense semantic and texture cues. Specifically, the teacher branch fuses student LiDAR features and the corresponding 2D intensity map tile to provide dense supervision for segmenting map elements using online distillation scheme. Experimental results show that our method outperforms all single-modality approaches, achieving 8.2% higher mIoU than the state-of-the-art camera-based model on nuScenes. LIE is robust over long ranges and under challenging weather and lighting, and efficiently adapts to Argoverse2 with only 10% fine-tuning, surpassing camera-based models trained on the full dataset. Source code will be available \href{https://iv.ee.hm.edu/lie/}{here}.
Authors: Jiewei Lai, Lan Zhang, Chen Tang, Pengcheng Sun, Zhaopeng Zhang, Yunhao Wang, Hui Jin
Abstract: Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these methods exhibit a critical vulnerability to the forgery attack, attackers can extract the watermark by inverting the watermarked image and re-generating it with an arbitrary prompt, thereby enabling false attribution on malicious content. In this paper, we propose the CSGuard, the first forgery-resistant watermarking schema that leverages compressed sensing to bind the watermarked image generation and verification to a secret matrix. This ensures that only users possessing the secret matrix can correctly embed or verify the image watermark, prevents the illegal users from forgery without compromising generation quality and watermark integrity. Experimental results demonstrate that CSGuard achieves strong forgery resistance, reduces the attack success rate from 100.0\% to 28.12\%, and achieve 100\% detection rate on benign watermarked images without compromising watermarking effectiveness.
Authors: Guandong Li, Mengxia Ye
Abstract: We study training-free image editing on Qwen-Image-Edit-2511, a 60-block multi-modal diffusion transformer (MMDiT) that concatenates noise and source-image tokens within a single attention stream. We make three contributions. (i) We introduce KVInject, a single-forward attention manipulation that alpha-blends source-half key/value projections into the noise-half within a localized layer/step band. KVInject is simpler than the classical two-pass MasaCtrl recipe and avoids the prompt-mismatch failure mode that disables MasaCtrl on MMDiT (composite score drops 31% versus baseline). (ii) We show that no single attention operation dominates across edit types, motivating AttnRouter, a per-category routing table that dispatches edits to the operation that best preserves source structure for that type. With ground-truth categories the router improves the CLIP-T+DINO-I composite by 6.4% over the editing baseline; an automatic CLIP zero-shot classifier closes 98% of this gap despite only 55% category accuracy. (iii) Through layer-, step-, and alpha-band ablations we localize the editing-effective attention sub-circuit: K/V injection in early denoising steps (S0-7) recovers nearly all of the gain of full-step injection, while injection in early (L0-15) or late (L45-60) layer bands fails to drive editing entirely; alpha in [0.3, 0.5] is a stable sweet spot. We also report negative results that highlight what does not transfer from the UNet folklore: simple K/V rescaling never beats baseline and aggressive variants collapse generation entirely (composite 0.084). We release code, pre-computed routing tables, and a 100-sample stratified subset of ImgEdit-Bench used in all ablations.
Authors: Ping Li, Bartlomiej Brzozka
Abstract: A hierarchical cross-modal fusion model is proposed for vision-language question answering (VLQA) in industrial robotics, targeting the challenges of semantic ambiguity, complex environmental layouts, and domain-specific terminology common in modern manufacturing. The framework integrates advanced object detection, multi-scale visual encoding, syntactic parsing, and task-aware semantic attention to unite vision and language signals into a joint reasoning space. Region-based deep networks extract visual features, weighted embeddings aggregate, and recurrent neural parsing encodes sentence structures. Through fine-grained semantic alignment driven by adaptive fusion and cross-attention mechanisms, the system can handle operational queries, instruction steps, and anomaly detection with higher reliability. Compared to the existing VLQA benchmarks, validation experiments conducted on the IVQA and RIF benchmarks indicate improvements in semantic alignment, Top-1 accuracy, and robustness to ambiguous or procedural task queries. Ablation studies further quantify the impact of each architectural module, confirming the necessity of multi-level feature integration and context-driven gating for dependable industrial deployment. The technical advancements reported here provide core methodologies to improve the interpretability and operational effectiveness of industrial robots faced with diverse human-robot interaction tasks.
Authors: Zijian Zhou, Jianing Zhang, Kai Sun, Xiangyu Zhao, Chunxia Zhang, Xiangyong Cao
Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images. However, the current mainstream frequency-based pansharpening methods employ fixed frequency filters, which cannot precisely adapt to complex and spatially diversified frequency distributions in PAN and MS images. Furthermore, existing denoising strategies insufficiently exploit frequency components for denoising and struggle to suppress various noise types accurately. To address these challenges, we propose CGFformer, a cluster-guidance frequency Transformer that focuses on varying frequency distribution and interactions between frequency and spatial components. Specifically, we design an adaptive separation module that integrates local features and non-local information through K-means clustering, enabling more precise separation of high- and low-frequency components. Subsequently, we introduce a dual-stream refinement module combined with Transformer-based cross-attention to remove various noise, allowing the network to jointly suppress frequency-relevant and irrelevant disturbances. In addition, we develop a frequency-spatial fusion module designed to enhance detail and facilitate spatial-frequency interaction, ensuring more effective reconstruction of spatial structures in the fused results. Extensive experiments on multiple benchmark datasets demonstrate that the proposed CGFformer achieves notable improvements over existing pansharpening approaches.
Authors: Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, Ivan Laptev
Abstract: This report presents the results and findings of the first edition of the Short-Films 20K (SF20K) Competition, held in conjunction with the SLoMO Workshop at ICCV 2025. The competition is designed to advance story-level video understanding beyond short-clip action recognition, introducing an open-ended video question-answering task built on a corpus of amateur short films. This setup ensures that models must rely on multimodal understanding rather than memorization of popular movies. Evaluation is conducted using the SF20K-Test benchmark (95 movies, 979 question-answer pairs) and scored via LLM-QA-Eval, an automated judge based on GPT-4.1-nano. The competition attracted 22 teams and 286 submissions across two tracks: a Main Track with unrestricted model size and a Special Track limited to models under 8 billion parameters. The winning team achieved 65.7% accuracy on the Main Track and 48.7% on the Special Track, against a human performance ceiling of 91.7%. Our analysis reveals several key findings: narrative-aware, shot-level processing consistently outperforms uniform frame sampling; well-designed multi-stage pipelines using smaller models can match or exceed end-to-end inference with models over 30x larger; and subtitle quality is a dominant factor in performance. These results highlight that the primary bottleneck in long-form video QA lies in information selection and reasoning structure rather than raw model capacity, and that a substantial gap remains between current methods and human-level narrative comprehension.
Authors: Liang Peng, Bohan Tan, Zhipeng Zhang, Haobo Li, Yifan Jiao, Xingping Dong, Libo Zhang
Abstract: Visual query localization (VQL) aims to predict the spatio-temporal response of the most recent occurrence in a sequence given a query. Currently, most research focuses on visual query localization in 2D videos, while its counterpart in 3D space has received little attention. In this paper, we make the first attempt to address visual query localization in the 3D world by introducing a novel benchmark, dubbed 3DVQL. Specifically, 3DVQL contains 2,002 sequences with around 170,000 frames and 6.4K response track segments from 38 object categories. Each sequence in 3DVQL is provided with multiple modalities, including point clouds, RGB images, and depth images, to support flexible research. To ensure high-quality annotations, each sequence is manually annotated with multiple rounds of verification and refinement. To the best of our knowledge, 3DVQL is the first benchmark for 3D multimodal visual query localization. To facilitate comparison in subsequent research, we implement a series of representative 3D multimodal VQL baselines using point clouds and RGB images. The experimental results show that existing methods exhibit significant performance variations across different fusion modules. To encourage future research, we propose a lift-and-attention fusion algorithm named LaF, which significantly outperforms existing baseline models. Our benchmark and model will be publicly released at https://github.com/wuhengliangliang/3DVQL.
Authors: William Stevens, Mohit Prabhushankar, Ghassan AlRegib
Abstract: Epistemic uncertainty estimation is essential for identifying regions where deep learning system outputs may be unreliable. However, existing approaches require computationally expensive ensemble methods or multiple stochastic forward passes, limiting their scalability to dense prediction tasks like segmentation. We propose Resolution-Aggregated Decoder Mutual Information (RADMI), a single-pass method that estimates prediction uncertainty by measuring mutual information (MI) between consecutive decoder layers in segmentation networks. We observe that elevated inter-layer MI correlates with prediction uncertainty, as the network must integrate conflicting contextual information at ambiguous regions such as class boundaries. Evaluating on a seismic facies segmentation benchmark, RADMI achieves the highest correlation with deep ensemble uncertainty among all single-pass methods, outperforming the next-best baselines by 5.5% in Pearson and 10.7% in Spearman correlation coefficients. Compared to baselines that either lack spatial precision or demand significant computational overhead, RADMI yields sharp, boundary-localized uncertainty maps without architectural modifications. Our results suggest that linear aggregation of normalized information flow provides a principled and efficient proxy for prediction uncertainty in encoder-decoder architectures.
Authors: Detao Bai, Shimin Yao, Weixuan Chen, Chengen Lai, Yuanming Li, Zhiheng Ma, Xihan Wei
Abstract: Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design -- sampling visual frames at 1--2 fps while processing audio waveforms at 25 fps -- resulting in systems that perceive video \emph{frame by frame, modality by modality} rather than holistically as humans do. Such a discrepancy leaves models with impoverished cross-modal interaction during encoding and an inability to capture fine-grained visual motion. To bridge this gap, we present \textbf{Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps} within a shared latent space. This architecture leverages three core innovations -- the Omni-Encoder Token Template, Omni-RoPE, and Temporal Window Shifting -- to effectively reconcile the dual challenges of modality disentanglement and computational efficiency. Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5-Omni under the same input token budget to the LLM decoder, Omni-Encoder delivers substantial gains on visual continuous understanding tasks -- such as sign language recognition and fine-grained sports action analysis -- while maintaining competitive performance on established audio-visual benchmarks such as AVQA and Speaker Identification and Localization. These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models that more closely reflect the integrated nature of human perception.
Authors: Huy Duong, Trong-Tung Nguyen, Cuong Pham, Anh Tran, Khoi Nguyen, Minh Hoai
Abstract: Diffusion models have achieved remarkable success in high-quality image synthesis, sparking interest in image-guided generation tasks such as subject-driven image personalization. Despite their impressive personalization results, existing methods typically rely on computationally intensive fine-tuning, iterative optimization, or multi-step denoising processes, which significantly hinder their deployment and interactive capability in real-time applications. In this work, we present SwiftPie, the first one-step diffusion image personalization tool that enables lightning-fast generation of personalized images. SwiftPie introduces a novel dual-branch identity injection mechanism that effectively integrates subject identity into a one-step diffusion model. In addition, we incorporate a mask-guided rescaling strategy to further enhance subject contextualization within a single diffusion step. Extensive experiments demonstrate that SwiftPie not only delivers superior image personalization speed but also achieves comparable performance with multi-step approaches in both identity fidelity and prompt alignment. This work opens new opportunities for real-time, high-quality personalized image generation, paving the way for interactive visual synthesis.
Authors: Jiantang Huang
Abstract: Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited, yet accurate joint localization in time, space, and collision type is required. We present a no-fine-tuning pipeline that elicits this joint output from frozen vision-language models through two ideas. First, a coarse-to-fine two-pass decomposition: a full-video pass at 1 fps produces a coarse (t, x, y, c) tuple, then a second pass at 5 fps within a +/- 3 s window refines time and location, with two deterministic confidence gates that revert to the coarse estimate on boundary hedges or edge-clamped coordinates. Second, a specialist role assignment: Qwen3-VL-Plus handles grounding, Gemini 3.1 Flash-Lite handles typing on a centered video clip. On the ACCIDENT@CVPR 2026 benchmark (2,027 real CCTV videos) we reach ACC^S = 0.539 (95% CI [0.525, 0.553]): +0.127 over the benchmark paper's best-of-baselines oracle (0.412), +0.143 over the strongest single-VLM baseline (Molmo-7B, 0.396), and +0.250 over the naive baseline (0.289). The VLM path uses up to three API calls per video (17% fall back to physics on API failures); the full run costs ~$20.
Authors: Guotao Liang, Zhangcheng Wang, Chuang Wang, Juncheng Hu, Haitao Zhou, Junhua Liu, Jing Zhang, Dong Xu, Qian Yu
Abstract: Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains challenging as it requires bridging discrete code representations with continuous visual dynamics. Existing optimization-based methods often destroy topological consistency, while general-purpose LLMs rely on rigid CSS/SMIL transformations, failing to model geometry-level non-rigid deformations. To address these limitations, we present VAnim, the first LLM-based framework for open-domain text-to-SVG animation. We reconceptualize animation not as sequence generation, but as Sparse State Updates (SSU) on a persistent SVG DOM tree. This paradigm compresses sequence length by over 9.8x while preserving the SVG DOM structure and non-participating elements by construction. To enable precise control, we propose an Identification-First Motion Planning mechanism that grounds textual instructions in explicit visual entities. Furthermore, to overcome the non-differentiable nature of SVG rendering, we employ Rendering-Aware Reinforcement Learning via Group Relative Policy Optimization (GRPO). By leveraging a hybrid reward from a state-of-the-art video perception encoder, we align discrete code updates with high-fidelity visual feedback. We also introduce SVGAnim-134k, the first benchmark for vector animation. Extensive experiments demonstrate that VAnim significantly outperforms state-of-the-art baselines in semantic alignment and structural validity, with additional appendix metrics further validating motion quality and identity preservation.
Authors: Joy Dhar, Song Xia, Manish Kumar Pandey, Maryam Haghighat, Azadeh Alavi, Ferdous Sohel, Wenyu Zhang, Nayyar Zaidi
Abstract: We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robustness under L2 certificates and empirical robustness against strong L attacks, while preserving strong generalization across diverse imaging benchmarks. HyCAS unifies deterministic and randomized principles by coupling 1-Lipschitz, spectrally normalized convolutions with two stochastic components, spectral normalized random, projection filters and a randomized attention-noise mechanism, to realize a randomized defense. Injecting smoothing randomness inside the architecture yields an overall <= 2-Lipschitz network with formal certificates. Exten-sive experiments on diverse imaging benchmarks, including CIFAR-10/100, ImageNet-1k, NIH Chest X-ray, HAM10000, show that HyCAS surpasses prior leading certified and empirical defenses, boosting certified accuracy by up to 7.3% (on NIH Chest X-ray) and empirical robustness by up to 3.1% (on HAM10000), without sacrificing clean accuracy. These results show that a randomized Lipschitz constrained architecture can simultaneously improve both certified L2 and empirical L adversarial robustness, thereby supporting safer deployment of deep models in high-stakes applications. Code: https://github.com/misti1203/HyCAS
Authors: Yin Zhang, Jiaxuan Zhao, Zonghan Wu, Zengxiang Li, Junfeng Fang, Kun Wang, Qingsong Wen, Yilei Shao
Abstract: Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution by optimizing policies using answer correctness signals. Despite their effectiveness, prevailing RLVR methods face two critical limitations. First, much of the sampling budget is wasted on trajectories doomed to fail due to early visual description errors. Second, sparse rewards cannot distinguish whether failures stem from visual perception or reasoning stages. We introduce MIRL, a decoupled framework that addresses both limitations by leveraging mutual information (MI) between generated descriptions and visual inputs as a cheap pre-screening signal. This enables intelligent budget allocation toward high-potential trajectories via forking, while decoupled training provides independent MI-based rewards for visual perception optimization, resolving reward blindness. Experiments on six vision-language reasoning benchmarks demonstrate that MIRL achieves 70.22% average accuracy and successfully surpasses the performance of sampling 16 complete trajectories using only 10 pre-samples with top-6 selection (25% fewer complete trajectories). Our code is available at: https://anonymous.4open.science/r/mirl-main/.
Authors: Bao-Long Tran, Per-Erik Forss\'en, Fredrik Viksten
Abstract: In this paper, we introduce a challenging task: extracting a fundamental matrix from a single motion blurred image. For a camera moving in 3D during exposure, the smear paths in the blurry image contain cues and constraints on this motion. We demonstrate the feasibility of establishing correspondences between two time instances within the camera exposure window, and that these can be used to robustly infer a fundamental matrix, which summarizes the motion of the camera during the exposure time. The inferred fundamental matrix is unique up to a transpose, corresponding to an ambiguity of the direction of time. Due to this per-smear ambiguity, classic methods, such as the 8-point algorithm, are no longer usable. The proposed method modifies the estimation to work on time-direction ambiguous correspondences. To improve the robustness of the fundamental matrix estimation, we also propose to incorporate an uncertainty measurement in smear pattern prediction and use it in the sampling process of the estimator. Experiments on synthetic and real-world motion-blur datasets demonstrate that our approach is able to estimate the fundamental matrix encoding the 3D camera motion, from single frames. Practical applicability is demonstrated on the downstream task of motion segmentation.
Authors: Ceausescu Ciprian-Mihai, Anghelina Ion-Marian, Alexe Dumitru-Bogdan
Abstract: We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach employs a teacher-student paradigm in which a joint teacher model aggregates domain-invariant representations learned from diverse source datasets, while a task-specific student model is trained via multi-level knowledge distillation. Originally developed for medical image segmentation, the framework is extended to support image-level classification and object-level detection, enabling a general multi-task formulation for medical image analysis. We evaluate our method on a broad suite of datasets, including six segmentation benchmarks, BrainMetShare, ISLES, BraTS (MRI) and Lung MSD, LiTS, KiTS (CT), as well as multiple classification datasets for pulmonary disease and dementia, and detection datasets with native bounding-box annotations. Across all tasks and modalities, the proposed approach yields consistent improvements over strong dataset-specific and multi-head baselines, demonstrating enhanced robustness to distributional shifts and superior generalization. These findings highlight the potential of multi-dataset knowledge distillation as a scalable and task-agnostic approach for enhancing segmentation, classification, and object detection performance across heterogeneous medical imaging domains.
Authors: Wojciech Koz{\l}owski, Rados{\l}aw Kuczba\'nski, Kamil Adamczewski, Karol Szczypkowski, Maciej Zi\k{e}ba
Abstract: Deep stochastic processes have recently become a central paradigm for image enhancement, with many methods explicitly conditioning the stochastic trajectory on the degraded input. However, the relationship between these conditional processes and standard diffusion models remains unclear. In this work, we introduce a unified perspective on stochastic image enhancement by classifying recent methods into three families of continuous-time processes: unconditional diffusion models, Ornstein-Uhlenbeck (OU) processes, and diffusion bridges. We show that all of these approaches arise from a common stochastic differential equation (SDE) formulation. This framework makes explicit that seemingly disparate methods differ primarily in their drift and diffusion terms, terminal distributions, and boundary conditions, while schedulers and samplers constitute orthogonal design choices. Leveraging this unification, we conduct a controlled empirical study across multiple image enhancement tasks using identical architectures and training protocols. Our results reveal no consistently dominant method; instead, we identify and disentangle the specific design choices that most strongly influence performance. Finally, we release ItoVision, a modular PyTorch library that implements the unified framework and enables rapid prototyping and fair comparison of stochastic image enhancement methods.
Authors: Tianxiao Li, Zhenglin Huang, Haiquan Wen, Yiwei He, Xinze Li, Bingyu Zhu, Wuhui Duan, Congang Chen, Zeyu Fu, Yi Dong, Baoyuan Wu, Jason Li, Guangliang Cheng
Abstract: Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic distributions, which limit their ability to assess real-world robustness. To address these limitations, we present Omni-Fake, a unified omni-dataset for comprehensive multimodal deepfake detection in social-media settings. It comprises Omni-Fake-Set, a large-scale, high-quality dataset with 1M+ samples, and Omni-Fake-OOD, an out-of-distribution benchmark with 200k+ samples intentionally excluded from training to evaluate generalization. Omni-Fake spans four modalities (image, audio, video, and audio-video talking head) and supports a joint detection-localization-explanation protocol. On top of Omni-Fake, we further propose Omni-Fake-R1, a reinforcement-learning-driven multimodal detector that adaptively integrates visual and auditory cues and outputs structured decisions, localization, and natural-language explanations. Extensive experiments show significant gains in detection accuracy, cross-modal generalization, and explainability over state-of-the-art baselines. Project page: https://tianxiao1201.github.io/omni-fake-project-page/
URLs: https://tianxiao1201.github.io/omni-fake-project-page/
Authors: Fangzheng Wu, Brian Summa
Abstract: We introduce SteeringDiffusion, a bottlenecked activation-level control interface for diffusion models that exposes a smooth, monotonic, and runtime-adjustable control surface over the content--style trade-off. Our method keeps the U-Net backbone frozen and learns a small, prompt-conditioned latent code projected to FiLM/AdaGN-style modulation parameters. A zero-initialized design guarantees exact equivalence to the base model at zero scale, while timestep-aware gating restricts modulation to later denoising stages. A single scalar at inference continuously traverses the control surface without retraining. Across experiments on Stable Diffusion~1.5 and SDXL covering multiple artistic styles, we show that SteeringDiffusion produces smooth and monotonic content--style trade-offs. Under matched parameter budgets, it outperforms LoRA in controllability and stability, while ControlNet and rank-1 adapters do not expose a comparable control surface. We further introduce an inversion-stability diagnostic based on DDIM inversion, used as a post-hoc trajectory probe, which reveals strong correlations with intervention magnitude. These results position \emph{Steering Bottlenecked Explicit Control (S-BEC)} as a practical, general-purpose control interface for frozen diffusion backbones.
Authors: Martin Q. Ma, Yuxiao Qu, Aditya Agrawal, Willis Guo, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic information as the reasoning process evolves. Existing methods that augment Chain-of-Thought (CoT) with additional frame information often exhibit suboptimal CoT quality and lack the crucial ability to synthesize visual information for hypothetical or counterfactual scenarios. We introduce Act-to-See (Act2See), a novel framework that enables active visual perception by empowering VLMs to actively interleave video frames within text CoTs. Act2See is developed via Supervised Fine-Tuning (SFT) on a high-quality dataset of reasoning traces generated by a frontier VLM. These traces integrate active calls to either retrieve existing frames or generate new ones, and are rigorously verified against human-annotated CoTs to ensure quality. This approach cultivates an emergent capability: at inference time, the model actively determines when to search for or synthesize the necessary visual evidence. Act2See establishes new state-of-the-art results on challenging benchmarks, including VideoEspresso and ViTIB, and outperforms comparable or larger models on Video-MME, EgoNormia, and VCR-Bench, demonstrating an advancement in enabling VLMs with active visual perception for video reasoning.
Authors: Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
Abstract: The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarization addresses this challenge by generating concise yet semantically meaningful representations, but existing approaches often rely on expensive manual annotations, struggle to generalize across domains, and incur significant computational costs due to complex architectures. Moreover, unsupervised and weakly supervised methods typically underperform compared to supervised counterparts in capturing long-range temporal dependencies and semantic structure. In this work, we propose TRIMMER (Temporal Relative Information Maximization for Multi-objective Efficient Reinforcement), a novel self-supervised reinforcement learning framework for video summarization. TRIMMER operates in two stages: it first learns robust representations via self-supervised learning and then performs spatio-temporal decision making through reinforcement learning guided by information-theoretic reward functions. Unlike prior approaches that rely on similarity-based objectives, our method introduces entropy-based metrics to capture higher-order temporal dynamics and semantic diversity, while computing rewards directly over selected frame indices to improve computational efficiency. Extensive experiments on standard benchmarks demonstrate that TRIMMER achieves state-of-the-art performance among unsupervised and self-supervised methods, while remaining competitive with leading supervised approaches, highlighting its effectiveness for scalable and generalizable video summarization.
Authors: Martin Q. Ma, Willis Guo, Aditya Agrawal, Ankit Gupta, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
Abstract: Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and performance may plateau. Inspired by active perception theory, which posits that models gain information by acquiring data that differs from their expectations, we introduce Video Active Perception (VAP), a training-free method to enhance long-form video QA using VLMs. Our approach treats keyframe selection as data acquisition in active perception and leverages a lightweight text-conditioned video generation model to represent prior world knowledge. Empirically, VAP achieves state-of-the-art zero-shot results on long-form or reasoning video QA datasets such as EgoSchema, NExT-QA, ActivityNet-QA, IntentQA, and CLEVRER, achieving an increase of up to 5.6 x frame efficiency by frames per question over standard GPT-4o, Gemini 1.5 Pro, and LLaVA-OV. Moreover, VAP shows stronger reasoning abilities than previous methods and effectively selects keyframes relevant to questions. These findings highlight the potential of leveraging active perception to improve the frame effectiveness and efficiency of long-form video QA.
Authors: Haoshen Zhang, Di Wen, Kunyu Peng, David Schneider, Zeyun Zhong, Alexander Jaus, Zdravko Marinov, Jiale Wei, Ruiping Liu, Junwei Zheng, Yufan Chen, Yufeng Zhang, Yuanhao Luo, Lei Qi, Rainer Stiefelhagen
Abstract: We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivated by the need for high-quality structured supervision for learning robot manipulation from human demonstration. IMPACT-HOI frames this task as the incremental resolution of a partially specified, onset-anchored event state. A trust-calibrated controller selects among direct queries, human-confirmed suggestions, and conservative completions based on empirical annotator behavior and evidence quality. A risk-bounded execution protocol, utilizing atomic rollback, ensures that human-confirmed decisions are preserved against conflicting automated updates. A user study with 9 participants shows a 13.5% reduction in manual annotation actions, a 46.67% event match rate, and zero confirmed-field violations under the studied protocol. The code will be made publicly available at https://github.com/541741106/IMPACT_HOI.
Authors: Lucas O. Lyra, Antonio E. Fabris, Joao B. Florindo
Abstract: Orderless encoding methods have shown to improve Convolutional Neural Networks (CNNs) for image classification in the context of limited availability of data. Additionally, hybrid CNN + Vision Transformers (ViT) models have been recently proposed to address CNN locality bias issues. These models outperformed CNN-only approaches. Despite that, the integration of such hybrid models with more elaborated feature representation can be highly beneficial and remains large unexplored in the literature. In this context, we propose the introduction of an orderless encoding method, Fisher Vectors, to hybrid CNN + ViT architectures, aiming at achieving a model suitable for both small and large datasets. Such enconding method relies on estimating a Gaussian Mixture Model (GMM) on image features. In large datasets, computational costs of the GMM estimation is a limiting factor for the application of Fisher Vectors. Thus, we propose a method to limit the growth of GMM estimation costs as we increase the size of the dataset. We explore the feasibility of our method in the context of medical image classification by appling it to MedMNIST (v2), Clean-CC-CCII and ISIC2018. This collection of datasets contains a wide variety of data scales and modalities. We outperform benchmark results in all MedMNIST (v2) datasets and obtain literature-competitive results in Clean-CC-CCII and ISIC2018.
Authors: Qian Yin, Di Wen, Kunyu Peng, David Schneider, Zeyun Zhong, Alexander Jaus, Zdravko Marinov, Jiale Wei, Ruiping Liu, Junwei Zheng, Yufan Chen, Chen Zhang, Lei Qi, Rainer Stiefelhagen
Abstract: Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of information on annotator uncertainty and model reliability. We introduce IMPACT-Scribe, a correction-driven framework for dense labeling that uses each correction to improve future human-machine collaboration. IMPACT-Scribe combines uncertainty-aware boundary scribble supervision, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation. Experiments and a human study show that this closed-loop design improves labeling quality per effort, enhances boundary accuracy, and fosters better human-machine interaction over time. The code will be made publicly available at https://github.com/BanzQians/IMPACT_AS.
Authors: Yiyao Wang, Sixian Zhang, Keming Zhang, Xinhang Song, Songjie Du, Shuqiang Jiang
Abstract: Existing zero-shot Object Goal Navigation (ObjectNav) methods often exploit commonsense knowledge from large language or vision-language models to guide navigation. However, such knowledge arises from internet-scale text rather than embodied 3D experience, and episodic observations collected during navigation are typically discarded, preventing the accumulation of lifelong experience. To this end, we propose Trajectory RAG (TrajRAG), a retrieval-augmented generation framework that enhances large-model reasoning by retrieving geometric-semantic experiences. TrajRAG incrementally accumulates episodic observations from past navigation episodes. To structure these observations, we propose a topological-polar (topo-polar) trajectory representation that compactly encodes spatial layouts and semantic contexts, effectively removing redundancies in raw episodic observations. A hierarchical chunking structure further organizes similar topo-polar trajectories into unified summaries, enabling coarse-to-fine retrieval. During navigation, candidate frontiers generate multiple trajectory hypotheses that query TrajRAG for similar past trajectories, guiding large-model reasoning for waypoint selection. New experiences are continually consolidated into TrajRAG, enabling the accumulation of lifelong navigation experience. Experiments on MP3D, HM3D-v1, and HM3D-v2 show that TrajRAG effectively retrieves relevant geometric-semantic experiences and improves zero-shot ObjectNav performance.
Authors: Ghazal Danaee, M\'elanie Gaillochet, Christian Desrosiers, Herve Lombaert, Sylvain Bouix
Abstract: Active learning (AL) has emerged as a crucial strategy for reducing the prohibitive costs associated with medical image segmentation. However, standard uncertainty-based AL methods typically focus on maximizing performance metrics, ignoring performance disparities or fairness across groups with sensitive attributes. While fair active learning has been explored in classification tasks, its intersection with medical image segmentation remains unaddressed. In this work, we introduced a fairness-aware active learning framework with a Weighted Entropy selection strategy that modulates uncertainty based on current group-specific performance estimates on the labeled set. To decouple true epistemic uncertainty from anatomical volume variances, we further utilized a masked, scaled entropy restricted to the region of interest. The framework was evaluated on synthetic T1-weighted brain MRIs with controlled left caudate bias in both strong and weak bias settings. A 3D U-Net was trained to segment the left caudate under several AL strategies, starting from both demographically balanced and strongly imbalanced initial labeled sets. Experiments demonstrated that our method markedly reduces performance disparities between groups compared to random sampling and standard uncertainty sampling. By prioritizing poorly segmented subgroups during the AL cycles, our method consistently achieved the highest equity-scaled performance and reduced the disparity metric by 75% (strong bias) and 86% (weak bias) relative to standard entropy at the final budget. Overall, this work is among the first studies on fair AL for medical image segmentation, offering an efficient strategy to train more equitable models in resource-constrained environments.
Authors: Ruize He, Dongchen Han, Gao Huang
Abstract: Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we demonstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters. Through this lens, we explain attention's global modeling power not as explicit token-wise aggregation, but as an implicit process where dynamically generated parameters act as a compressed representation of the global context. Inspired by this insight, we investigate a fundamental question: can we achieve Transformer-level sequence global modeling entirely through dynamic parameterization while maintaining linear complexity, effectively replacing explicit attention? To explore this, we design various dynamic parameter prediction strategies and integrate them into standard network layers. Extensive empirical studies on vision models demonstrate that dynamic parameterization can indeed serve as a highly effective, linear-complexity alternative to explicit attention, opening new pathways for efficient sequence modeling. Code is available at https://github.com/LeapLabTHU/WeightFormer.
Authors: Xianlong Wang, Hangtao Zhang, Wenbo Pan, Ziqi Zhou, Changsong Jiang, Li Zeng, Xiaohua Jia
Abstract: Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, existing UE schemes exhibit limited robustness against advanced defenses due to their heuristic design or narrowly scoped domain perturbations. To address this, we propose \texttt{DUNE}, a \underline{\textbf{D}}ual-branch \underline{\textbf{UN}}learnable \underline{\textbf{E}}nsemble perturbation optimization approach. Specifically, \texttt{DUNE} separately optimizes perturbations in the spatial and color domains to establish the mapping between perturbations and shift-induced labels. This design extends the perturbation domain to increase noise intensity for improving robustness and drives the models to learn perturbation-oriented features with degraded generalization, thereby achieving unlearnability. To strengthen \texttt{DUNE}'s performance, we further propose an unlearnability-enhancing ensemble strategy that aggregates diverse pre-trained models during the dual-branch optimization. Extensive experiments on benchmark datasets CIFAR-10 and ImageNet verify that \texttt{DUNE}'s robustness outperforms 12 SOTA UE schemes under 7 mainstream defenses, yielding a lower average test accuracy of 14.95\% to 50.82\%.
Authors: Sen Fang, Hongbin Zhong, Yanxin Zhang, Dimitris N. Metaxas
Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings. While such resources are important for semantic understanding, they do not directly provide a unified interface for open-world recognition and translation, or for modern pose-driven sign language video generation frameworks: 1. RGB-based pretrained recognition models depend heavily on fixed backgrounds or clothing conditions during recording, and are less robust in open-world settings than style-agnostic pose-processing models. 2. Recent pose-guided image/video generation models mostly use a unified keypoint representation such as DWPose as their control interface. At present, the sign language field still lacks a data resource that can directly interface with this modern pose-native paradigm while also targeting real-world open scenarios. We present SignVerse-2M, a large-scale multilingual pose-native dataset for sign language pose modeling and evaluation. Built from publicly available multilingual sign language video resources, it applies DWPose in a unified preprocessing pipeline to convert raw videos into 2D pose sequences that can be used directly for modeling, resulting in a consolidated corpus of about two million clips covering more than 25 sign languages. Unlike many laboratory datasets, this resource preserves the recording conditions and speaker diversity of real-world videos while reducing appearance variation through a unified pose representation. Toward this goal, we further provide the data construction pipeline, task definitions, and a simple SignDW Transformer baseline, demonstrating the feasibility of this resource for multilingual pose-space modeling and its compatibility with modern pose-driven pipelines, while discussing the evaluation claims it can support as well as its current limitations.
Authors: Jing Xu, Yuexiao Ma, Songwei Liu, Xuzhe Zheng, Shiwei Liu, Chenqian Yan, Xiawu Zheng, Rongrong Ji, Fei Chao, Xing Wang
Abstract: Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of $\textbf{6.28}\times$ and $\textbf{1.64}\times$ respectively, while effectively preserving generation quality (VBench: $1\%\downarrow$ and $0.01\%\downarrow$ respectively). The code is available at https://github.com/ywlq/MotionCache.
Authors: Zeshang Li, Shuoyang Zhang, Jiashen Ding
Abstract: Vision-Language Models (VLMs) excel at grounded reasoning but remain prone to object hallucination. Recent work treats self-generated captions as a uniformly positive resource, yet we find that naively embedding one can degrade rather than help--dropping Qwen2.5-VL-3B accuracy on HallusionBench by nearly 10 points. Two structural properties explain this. First, captions anchor not only the model's final answer but also its reasoning trajectory and lexical choices. Second, caption errors are asymmetric: omissions vastly outnumber fabrications, yet each fabrication carries a much larger per-instance impact. A caption's usefulness is therefore a per-query property, not a per-corpus one. We propose GEASS (Gated Evidence-Aware Selective Steering), a training-free module that decides on each query how much of the caption the model consumes: it gates the caption by the clean path's confidence, weights it by the entropy reduction it produces, and raises the evidence bar when the two pathways disagree. Experiments on POPE and HallusionBench across four VLMs show that GEASS consistently improves over vanilla inference and contrastive decoding, with only two extra forward passes per query.
Authors: Sixian Zhang, Yiyao Wang, Xinhang Song, Keming Zhang, Zijian Xu, Shuqiang Jiang
Abstract: Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native interface for large models, thus requiring additional training of feature projection for semantic alignment. To this end, we propose the multi-scale Gaussian-Language Map (GLMap), which introduces three key designs: (1) explicit geometry, (2) multi-scale semantics covering both instance and region concepts, and (3) a dual-modality interface where each semantic unit jointly stores a natural language description and a 3D Gaussian representation. The 3D Gaussians enable compact storage and fast rendering of task-relevant images via Gaussian splatting. To enable efficient incremental construction, we further propose a Gaussian Estimator that analytically derives Gaussian parameters from dense point clouds without gradient-based optimization. Experiments on ObjectNav, InstNav, and SQA tasks show that GLMap effectively enhances target navigation and contextual reasoning, while remaining compatible with large-model-based methods in a zero-shot manner. The code is available at https://github.com/sx-zhang/GLMap.
Authors: Xinquan Yang, Jianfeng Ren, Xuguang Li, Kian Ming Lim, He Meng, Linlin Shen, Yongqiang Deng
Abstract: Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry. However, the development of robust AI models for volumetric analysis is often constrained by the scarcity of large, annotated datasets. Self-supervised learning (SSL), particularly Masked Image Modeling (MIM), offers a promising pathway to leverage unlabeled data. A limitation of standard MIM is its reliance on random masking, which fails to prioritize diagnostically critical regions in dental CBCT volumes, such as subtle pathological changes and intricate anatomical boundaries. To address this, we propose ATMask, a novel adaptive masking strategy. Instead of applying random masks or employing computationally intensive attention modules, ATMask computes an inter-slice texture variation map to identify regions with high structural or textural complexity. These high-variation areas are then selectively masked during pre-training, compelling the model to learn richer contextual representations essential for inferring complex 3D morphological transitions. Furthermore, we contribute the first large-scale CBCT dataset, curated from both public and private sources, comprising 6,314 scans, for the dental AI model pretraining. Extensive experiments on three downstream dental CBCT tasks demonstrate that our ATMask enables more data-efficient and powerful representation learning than standard random masking and other advanced SSL baselines. The dataset and code will be released.
Authors: Phat Nguyen, Xue Geng, Kaixin Xu, Wang Zhe, Xulei Yang, Ngai-Man Cheung
Abstract: Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory requirement, and energy consumption. While individual efficiency techniques such as neural architecture search (NAS), token compression, and low-precision inference have been extensively studied, most prior work targets only a single optimization axis, limiting overall deployment gains while preserving accuracy. In this paper, we present one of the first holistic frameworks that jointly optimizes three complementary axes: architecture, token, and bit-width. Specifically, the framework identifies compact backbones via Neural Architecture Search (AutoFormer), reduces information processing via token merging (ToMe), and accelerates per-operation execution via fp16 mixed-precision inference. Starting from a DeiT-B/16 baseline, we first analyze accuracy-efficiency trade-offs on ImageNet-1K under aggressive compression. Then, we apply the selected configurations to a real-world in-house 3D X-ray semiconductor defect classification dataset for IC chip packaging inspection. Results show that the proposed multi-axis framework achieves more than 10 times improvement in throughput along with over 10 times reductions in parameter count, FLOPs, and energy consumption, while maintaining the required accuracy on the downstream industrial task. To the best of our knowledge, this is among the earliest works to jointly optimize architecture, token, and bit-width dimensions in ViTs and the first such resource-efficient, deployment-focused study tailored to semiconductor manufacturing.
Authors: Chenyang Fan, Junshi Cheng, Wen Yang, Zihong Li, Wenfeng Zhang, Wei Hu, Yi Zhang, Pan Zeng
Abstract: With the burgeoning development of fields such as the Metaverse, Virtual Reality (VR), and Digital Twins, text-to-3D generation has emerged as a research hotspot in both academia and industry. Currently, optimization methods based on Score Distillation Sampling (SDS) utilizing 2D diffusion priors have become the mainstream technological paradigm in this field. However, due to the view bias of 2D priors and the mode-seeking ambiguity combined with gradient noise induced by high Classifier-Free Guidance (CFG), these methods still suffer from macro-topological inconsistency (e.g., the Janus problem) and micro-geometric discontinuity. To address these challenges, we propose MOC-3D, a text-to-3D generation method based on geometric manifold and semantic view-order consistency. Built upon the ScaleDreamer framework, our method incorporates a Semantic View-Order Constraint Module and a Manifold-based Feature Continuity Module. The former aims to rectify macro-topological inconsistency, while the latter focuses on eliminating micro-geometric discontinuity. Specifically, the Semantic View-Order Constraint Module leverages the prior knowledge of CLIP to impose a Monotonicity Rank Constraint on semantic score representations across different views, thereby providing effective guidance for the global topological structure of 3D objects. Meanwhile, the Manifold-based Feature Continuity Module employs the Riemannian Metric on the Symmetric Positive Definite (SPD) manifold. By measuring the distance of feature statistical distributions in the Riemannian space, it promotes the smooth evolution and continuity of micro-textures across multi-views in a statistical sense. Under the macro-micro synergistic optimization of these two modules, our model can simultaneously improve macro-structural consistency and micro-detail continuity.
Authors: Taiki Kanaya, Hideo Saito
Abstract: Single-image 3D face reconstruction is a core problem in computer vision, with important clinical applications such as cephalometric landmark analysis in orthodontics. Traditionally, this analysis relies on lateral X-ray imaging; however, frequent X-ray exposure is impractical due to radiation concerns. While recent research has explored detecting landmarks from lateral RGB images as an alternative, existing methods typically rely on 2D features such as the eyes, mouth, ears, and boundary silhouettes, failing to fully exploit the underlying 3D facial geometry spanning the facial profile and jawline, which is essential for accurate diagnosis. Meanwhile, although 3D face reconstruction from frontal views has seen significant progress, most learning-based 3D morphable model (3DMM) regressors are developed and benchmarked on near-frontal images, where appearance cues are abundant. In extreme profile views (yaw $\approx 90^\circ$), much of the face is occluded, and the available signal is dominated by boundary cues, making accurate 3D reconstruction challenging. In this paper, we bridge this gap with geometry-conditioned synthetic data and a simple profile-specific FLAME regression baseline for single lateral images. We introduce ProfileSynth, a dataset created by sampling FLAME shape and pose parameters in extreme yaw ranges and generating photorealistic profile images using a diffusion model conditioned on depth and normal maps. We further study a profile-specific baseline with visibility-aware jawline regularization. Our framework provides a practical baseline for "profile $\times$ 3DMM" reconstruction and a promising foundation for more accurate, non-invasive cephalometric analysis from lateral RGB images.
Authors: Xinxing Yu, Ajian Liu, Sunyuan Qiang, Hui Ma, Liying Yang, Yuzhong Wang, Zhi Rao, Yanyan Liang
Abstract: Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling paradigm still poses significant limitations in terms of maintaining consistent semantic representations across scenes. This challenge hinders the construction of a unified and transferable semantic space. To address this issue, we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation. This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment. Since serialization-based pretraining requires batch-level input organization, we further introduce an asymmetric semantic preservation distillation (SPD) during finetuning to achieve structural alignment of semantic transfer and eliminate inconsistencies caused by batch dependency. The proposed SPD ensures stable transfer of pretrained semantics through a heterogeneous input mechanism and a semantic feature alignment constraint. This enables the model to maintain structured semantic consistency and robustness under single-scene testing conditions. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art methods in both performance and semantic consistency.
Authors: Quanchen Zou, Nizhang Li, Wenxin Zhang, Jiaye Lin, Yangchen Zeng, Xiangzheng Zhang, Zonghao Ying
Abstract: Text-to-Video (T2V) models have demonstrated remarkable capability in generating temporally coherent videos from natural language prompts, yet they also risk producing unsafe content such as violence or explicit material. Existing prompt-level defenses are largely inherited from text-to-image safety and operate on the lexical surface of the input, making them vulnerable to jailbreak attacks that disguise harmful intent through rephrasing or adversarial prompting. Moreover, T2V generation introduces a distinctive challenge overlooked by prior work: temporally emergent risk, where a seemingly benign prompt leads to unsafe content through the generator's temporal extrapolation toward narrative coherence. We propose \method{}, a training-free, inference-time defense framework that reformulates T2V safety as a causal intervention in a temporally structured semantic space. TrajShield handles explicit unsafe prompts, jailbreak attacks, and temporally emergent risks in a unified manner by simulating the implied trajectory of a prompt, localizing the causal origin of potential risk, and applying a minimally invasive rewrite that neutralizes the risk while preserving safety-irrelevant semantics. Experiments on T2VSafetyBench across 14 safety categories and multiple T2V backends demonstrate that TrajShield achieves state-of-the-art defenseive performance while maintaining high semantic fidelity, substantially outperforming existing defenses, with an average ASR reduction of 52.44\%.
Authors: Giuseppe A. Orlando, Paolo Papotti, Maria A. Zuluaga, Olivier Humbert, Marco Lorenzi
Abstract: Vision-language models (VLMs) have shown potential for automated radiology report generation, yet existing approaches rely on global embedding compression of volumetric data, often leading to hallucinated findings and limited anatomical grounding in 3D CT imaging. We introduce MedScribe, a hypothesis-driven framework that reformulates report generation as an iterative evidence acquisition process rather than a single-pass encoding task. MedScribe models reporting as a sequential decision process in which a large language model dynamically invokes pathology-specific diagnostic tools to extract localized volumetric features. These structured features are used to query a multidimensional retrieval space aligned with pathology-specific textual evidence. By explicitly accumulating quantitative evidence prior to synthesis, the framework enforces fine-grained grounding and reduces unsupported claims. Without task-specific fine-tuning, MedScribe improves clinical accuracy, factual consistency, and interpretability on CT-RATE and RadChestCT compared to state-of-the-art 2D and 3D VLMs, demonstrating the value of hypothesis-driven reasoning for reliable medical image reporting.
Authors: Peiyan Tu, Hanxin Zhu, Jingwen Sun, Shaojie Ren, Cong Wang, Jiayi Luo, Xiaoqian Cheng, Zhibo Chen
Abstract: World models have made significant progress in modeling dynamic environments; however, most embodied world models are still restricted to 2D representations, lacking the comprehensive multi-view information essential for embodied spatial reasoning. Bridging this gap is non-trivial, primarily due to challenges from severe scarcity of paired multi-view data, the difficulty of maintaining spatiotemporal consistency in generated 3D geometries, and the tendency to hallucinate manipulation details. To address these challenges, we propose Embody4D, a dedicated video-to-video world model for embodied scenarios, capable of synthesizing arbitrary novel views from a monocular video. First, to tackle data scarcity, we introduce a 3D-aware compositional synthesis pipeline to curate a heterogeneous dataset compositing cross-embodiment robotic arms with diverse backgrounds, guaranteeing broad generalization. Second, to enforce geometric stability, we devise an adaptive noise injection strategy; by leveraging confidence disparities across image regions, this method selectively regularizes the diffusion process to ensure strict spatiotemporal consistency. Finally, to guarantee manipulation fidelity, we incorporate an interaction-aware attention mechanism that explicitly attends to the robotic interaction regions. Extensive experiments demonstrate that Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning.
Authors: Md. Sohanuzzaman Soad, Mahady Al Hady, S M Rafiuddin Rifat, Sudip Ghose
Abstract: Generative Adversarial Networks (GANs) offer a pragmatic route to mitigate data scarcity in vision tasks. We study generative augmentation across two low-resource domains: Bangla handwritten characters and chest X-ray imaging using DCGAN-style models trained at 64x64 resolution. We evaluate fidelity and diversity via Inception Score (IS), Fr'echet Inception Distance (FID), and embedding visualizations (t-SNE/UMAP), and assess downstream utility by training classifiers on real versus real synthetic data. Our experiments show that generative augmentation improves sample diversity and yields consistent gains in classifier performance under limited-data regimes. We analyze stability enhancements (e.g., gradient-penalized objectives and spectral normalization) and report ablations on synthetic-to-real ratios and sample filtering. We discuss evaluation caveats for medical images, dataset licensing, and privacy risks associated with synthetic data. The resulting protocol is simple to reproduce and provides a strong baseline for applying generative augmentation to resource-constrained imaging tasks.
Authors: Natalia Trukhina, Vadim Vashkelis
Abstract: Bandwidth-constrained robotic and surveillance systems often rely on a single compressed video stream to support both continuous scene awareness and downstream machine perception. In practice, this creates a mismatch: low-bitrate video can preserve motion and coarse context, but often loses the fine local detail needed for reliable object recognition and decision-making. Motivated by a hybrid architecture in which low-resolution video supports dynamic scene understanding while eventdriven high-detail regions of interest (ROIs) support close-up identification and analytics, this paper formalizes a two-channel visual telemetry scheme in which a continuous low-bitrate video stream is augmented by selectively transmitted high-detail still ROIs. This first paper does not attempt to prove the superiority of a new still-image codec. Instead, it establishes the hybrid transmission paradigm itself using a practical and reproducible codec stack: x265/HEVC for the base video stream and JPEG stills for ROI refinement. We formulate the problem as bitrate-constrained information selection for robotic vision and define an experimental protocol in which video-only and hybrid schemes are compared under matched total communication budgets. The study is designed around UAV-oriented datasets, two practical bitrate regimes, several ROI triggering policies, and object-level classification refinement on selectively transmitted ROI stills. The resulting paper lays the methodological foundation for a second-stage investigation of JPEG AI as the semantic still-image channel within the same hybrid architecture.
Authors: Yun Xing, Hanyuan Liu, Jiahao Nie, Shijian Lu
Abstract: Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle region-level perception guided by visual prompts, especially for cases where multiple regions are referred simultaneously, or scenarios where global contexts are necessary for precise visual referring. We introduce Contextual Latent Steering (CSteer), a training-free approach for guiding general LMMs to refer multiple regions contextually, without expensive fine-tuning or architectural modifications. CSteer starts with pre-computing contextual vectors that implicitly represent visual referring behaviors, such as differentiation among regions and attention to global contexts, followed by representation editing during inference time. Experimental results on multiple datasets indicate that general LMMs with CSteer outperform tailored referring LMMs in most cases, suggesting a promising solution in training-free, and setting new state-of-the-art for this field. Code is available at https://github.com/xing0047/csteer.git.
Authors: Favour Nerrise (Stanford University), Lucy Yin (Stanford University), Mohammad H. Abbasi (Stanford University), Kilian M. Pohl (Stanford University), Ehsan Adeli (Stanford University)
Abstract: Brain MRI foundation models learn rich representations of anatomy, but interpreting what clinical information they encode remains an open problem. Standard sparse autoencoders (SAEs) suffer from severe feature collapse in deep transformer layers, and in Alzheimer's disease (AD) research, aging confounds nearly every clinical variable, making naive annotation unreliable. We propose GeoSAE, a geometry-guided SAE framework that uses the foundation model's learned manifold structure to prevent feature collapse and annotates each surviving feature via age-deconfounded partial correlations. Applied to ~14k T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging biomarkers and Lifestyle (AIBL) datasets, GeoSAE identifies a compact, fully interpretable feature set that predicts mild cognitive impairment (MCI)-to-AD conversion (AUC 0.746) using only 2% of the embedding dimensions, while comorbidity-annotated features achieve only chance-level performance. The identified features replicate across cohorts without retraining (r=0.97) and localize to neuroanatomically distinct regions consistent with Braak staging. This shows that geometry-guided SAEs can extract interpretable, biomarkers from frozen brain MRI foundation models.
Authors: Umut Dundar, Alptekin Temizel
Abstract: Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pathological textures and structural features. We address this challenge for ulcerative colitis (UC) endoscopy, where severity follows a continuous ordinal progression along the Mayo Endoscopic Score (MES). Our framework, Disentangled Anatomy-Disease Diffusion (DADD), conditions a latent diffusion model on two complementary embeddings: a pretrained image encoder for patient anatomy and a separately trained ordinal embedder for cumulative disease severity. Since image embeddings inevitably capture disease information, we introduce a Feature Purifier, a cross-attention-based erasure mechanism that identifies and suppresses disease-correlated channels, yielding purified anatomical representations. These cleaned anatomy tokens and target disease tokens are injected into the denoising network via a Triple-Pathway Cross-Attention mechanism with resolution-dependent routing gates. This architecture leverages the U-Net hierarchy, in which different network depths encode global structure versus fine-grained pathological texture. Furthermore, we introduce Delta Steering, a training-free directional signal derived from the ordinal embeddings that enables explicit, single-pass control over disease transitions at inference without requiring additional forward passes. Validated on the LIMUC dataset, our approach produces high-fidelity images across all severity levels and effectively rebalances skewed class distributions, enhancing performance for downstream classification tasks. The dataset is available at zenodo.org/records/5827695 and the code base at github.com/umutdundar99/progressive-stable-diffusion
Authors: Lilika Makabe, Kohei Ashida, Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita
Abstract: Multi-view 3D reconstruction, namely, structure-from-motion followed by multi-view stereo, is a fundamental component of 3D computer vision. In general, multi-view 3D reconstruction suffers from an unknown scale ambiguity unless a reference object of known size is present in the scene. In this article, we show that multi-view images captured using a dual-pixel (DP) sensor can automatically resolve the scale ambiguity, without requiring a reference object or prior calibration. Specifically, the defocus blur observed in DP images provides sufficient information to determine the absolute scale when paired with depth maps (up to scale) recovered from multi-view 3D reconstruction. Based on this observation, we develop a simple yet effective linear method to estimate the absolute scale, followed by the intensity-based optimization stage that aligns the left and right DP images by shifting them back toward each other using cross-view blur kernels. Experiments demonstrate the effectiveness of the proposed approach across diverse scenes captured with different cameras and lenses. Code and data are available at https://github.com/lilika-makabe/dp-sfm-tpami.git
Authors: Youyi Zhan, He Wang, Tianjia Shao, Kun Zhou
Abstract: We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avatars from multi-view video. However, these methods require heavy computation to obtain pose-dependent appearance, making deployment on mobile devices very difficult. Recent methods distill from pretrained models and model pose-dependent nonlinear Gaussian attributes by linearly combining global pose features with blendshapes. Although they can run on mobile devices, they suffer some loss of detail. We observe that nearby Gaussians are often highly correlated within a local region of the body, and can be linearly modeled with less error. Therefore, we use local linear blendshapes in small body parts to capture global nonlinear changes of Gaussian attributes. To further reduce computation and model size, we propose to remove blendshapes for Gaussians whose attributes change little, yielding a minimal blendshape representation. Our method is an end-to-end training method without a pretrained model. To make it run on multiple devices, we implement our method using WebGPU. Experiments show that our method can render high-quality human avatars with better details, and can reach 120 FPS at 2K resolution on mobile devices.
Authors: Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener, Angela Yao
Abstract: Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded streams. Secondly, due to the high cost of collecting and training on unbounded streams, models must learn from short sequences while generalizing to long streams. Existing streaming VideoVLLMs fail to scale to unbounded video streams or focus on cache reuse strategies, leaving the impact of cache construction underexplored. In this paper, we propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings. DSCache maintains a cumulative past KV cache while constructing a separate instant cache on-demand, decoupled from past caches to preserve the informativeness of recent inputs. To enable position extrapolation beyond the training length, DSCache further incorporates a position-agnostic encoding strategy, ensuring KV caches to support unseen positions and preventing position overflow. Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.
Authors: Kuoye Niu, Jianwei Li, Shengze Cai, Yong Ma, Mengyao Jia, Lishun Shen, Zhenheng Zhang, Yuxin Peng, Xian Song
Abstract: Multimodal resources for non-periodic court sports with laboratory-grade sensing remain scarce: few publicly pair instrumented ground reaction force (GRF) with high-frame-rate multi-view video, limiting markerless load estimation in realistic training settings. BadmintonGRF records eight synchronized RGB views at ~120 FPS, four Kistler force plates, and Vicon motion capture (C3D) without hardware genlock across modalities; alignment combines human-verified events, automated quality assurance, and per-camera time offsets with uncertainty metadata. Tier 1 distributes pose, time-aligned GRF, metadata, and splits under CC BY-NC 4.0, enabling the primary benchmark without raw RGB or C3D; we report a Tier 1 task that maps 2D pose to GRF. Tier 2 provides raw RGB and C3D under controlled access for studies that require appearance or full kinematics. The public release contains 17,425 impact-segment archives in the 10-subject benchmark tree (156 instrumented trials; raw multi-view RGB alone exceeds 1 TB); benchmark loader gates retain 12,867 view-specific instances and 1,732 unique impacts after multi-view deduplication. We are not aware of prior public badminton corpora that combine this sensing layout with audited video--GRF alignment for impact-centric GRF estimation. We distribute preprocessing code, leave-one-subject-out splits, ten reference baselines, and optional late fusion (one deterministic test-time pass per instance; no test-time augmentation), with a within-trial diagnostic in the supplementary material.
Authors: Hongkun Pan, Yuwei Wu, Wanyi Hong, Shenghui Hu, Qitong Yan, Yi Yang, Rufei Han, Changju Zhou, Minfeng Zhu, Dongming Han, Wei Chen
Abstract: Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and dense annotations due to three major challenges: (1) limited fine-grained perception results in the omission of critical visual cues; (2) redundant or noisy visual information undermines the performance of multimodal reasoning; (3) lack of adaptive deep reasoning relative to the amount of visual information. To tackle these challenges, we present a novel focus-driven fine-grained chart reasoning model, Chart-FR1, to improve perception, focusing efficiency, and adaptive deep reasoning on HID charts. Specifically, we propose Focus-CoT, a visual focusing chain-of-thought that enhances fine-grained perception by explicitly linking reasoning steps to key visual cues, such as local image regions and OCR signals. Building on this, we introduce Focus-GRPO, a focus-driven reinforcement learning algorithm with an information-efficiency reward that compresses redundant visual information for efficient focusing, and an adaptive KL penalty mechanism that enables flexible control over reasoning depth as more visual cues are discovered. Furthermore, to fill the gap in benchmarks for HID charts, we build HID-Chart, a challenging benchmark with an information-density metric designed to evaluate fine-grained chart reasoning capabilities. Extensive experiments on multiple chart benchmarks demonstrate that Chart-FR1 outperforms state-of-the-art MLLMs in chart understanding and reasoning. Code is available at https://github.com/phkhub/Chart-FR1.
Authors: Xi Zhou, Tao Huang, Qing-Long Han, Rana Abbas, Mostafa Rahimi Azghadi
Abstract: Accurate 3D object detection is essential for ensuring the safety of autonomous vehicles. Cooperative perception, which leverages vehicle-to-everything (V2X) communication to share perceptual data, enhances detection but is vulnerable to channel impairments, such as noise, fading, and interference. To strengthen the reliability of intelligent transportation systems, this work improves the robustness of V2X cooperative perception under communication conditions that reflect common channel impairments. This paper proposes an Adaptive Feature Fusion Transformer (AFFormer), a Transformer-based framework that mitigates the adverse effects of corrupted features by modeling temporal, inter-agent, and spatial correlations. AFFormer introduces three key modules: Multi-Agent and Temporal Aggregation for context-aware fusion across agents and over time, Dual Spatial Attention for efficient modeling of spatial dependencies, and Uncertainty-Guided Fusion for entropy-driven refinement of fused features. A teacher-student knowledge distillation strategy further enhances robustness by aligning fused features with reliable early-collaboration supervision. AFFormer is validated on the V2XSet and DAIR-V2X datasets, where it consistently outperforms existing methods under both ideal and impaired communication conditions, demonstrating improved robustness to communication-induced feature degradation while maintaining a competitive efficiency-accuracy trade-off.
Authors: Junyuan Xiao, Dingkang Liang, Xin Zhou, Yixuan Ye, Tongtong Su, Guangmo Yi, Bin Xia, Qiang Lyu, Shurui Shi, Jun Huang, Jianlou Si, Wenming Yang
Abstract: Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose $M^2$-REPA, the first representation alignment method tailored for multi-modal video generation. Our key insight is that foundation models trained on different modality spaces naturally capture distinct domain-specific priors, acting as complementary "experts." Specifically, we first decouple modality-specific features from the diffusion model's intermediate representations, then align each with its corresponding expert foundation model. To this end, we design two synergistic objectives: a multi-modal representation alignment loss that enforces feature-to-expert matching, and a modality-specific decoupling regularization that encourages complementarity across different modalities. This design enables joint optimization, fully exploiting priors from multiple foundation models. Extensive experiments demonstrate that our method significantly outperforms baselines in visual quality and long-term consistency.
Authors: Rei Tamaru, Pei Li, Bin Ran
Abstract: Traffic digital twins are powerful tools for advanced traffic management, and most systems are built on static geometric representations. However, these representations fail to capture the dynamic functional semantics required for behavior-aware reasoning, such as how a lane operates under complex traffic conditions. To address this gap, we introduce GeoLaneRep, a behavior-grounded lane representation learning framework for traffic digital twins. GeoLaneRep jointly encodes static lane geometry, observed vehicle trajectories, and operational descriptors into a shared, cross-camera semantic embedding. The encoder is trained with a joint objective combining contrastive cross-camera alignment, auxiliary role supervision, and temporal anomaly detection. Across 16 roadside cameras and 132 lanes, the learned embeddings achieve a $0.004$ lateral-rank error and an edge-role F1 of $1.000$ in zero-shot cross-camera matching, and an AUROC of $0.991$ for window-level anomaly detection. We further show that the same behavioral embeddings can condition a diffusion-based generator to synthesize lane geometries that satisfy targeted operational specifications, with $87.9\%$ overall specification accuracy across 38 lane groups. GeoLaneRep thus provides a semantic interface between roadside observations and downstream digital twin tasks, supporting cross-camera transfer, behavior-aware monitoring, and goal-directed lane synthesis. The framework is openly available at https://github.com/raynbowy23/GeoLaneRep.
Authors: Jongmin Shin, Ka Young Kim, Eunki Cho, Seong Tae Kim, Namkee Oh
Abstract: Purpose: Vision-language models (VLMs) have shown promising performance in surgical visual question answering (VQA). However, existing surgical VQA datasets often contain linguistic shortcuts, where question phrasing implicitly constrains the answer space. It remains unclear whether reported performance reflects visual understanding or reliance on such linguistic shortcuts. Methods: We introduce SurgCheck, a diagnostic benchmark for quantifying linguistic shortcut reliance in surgical VQA. SurgCheck employs a paired-question design in which each surgical frame is associated with an original question containing entity names and a less-biased counterpart that removes these names while preserving identical visual content and ground-truth answers. The resulting performance gap provides a diagnostic signal of shortcut reliance. To ensure that the less-biased question remains well-defined even without entity names, four grounding cues are incorporated: bounding box, arrow, spatial position, and periphrasis. We evaluate both general-purpose and surgical-specific VLMs under zero-shot and fine-tuned settings on SurgCheck. To evaluate open-ended zero-shot responses, we introduce an LLM-as-a-judge evaluation protocol. Results: Using SurgCheck, we observe consistent performance degradation on less-biased questions across five VLMs, despite identical visual inputs. Text-only ablation reveals minimal performance drops for action and target prediction, indicating that action and target prediction is largely driven by linguistic shortcuts rather than visual reasoning. Conclusion: SurgCheck provides a controlled diagnostic framework that exposes failure modes masked by linguistic bias in existing surgical VQA benchmarks. Our findings demonstrate that strong benchmark performance does not necessarily imply faithful visual understanding, underscoring the need for bias-aware evaluation in surgical VQA.
Authors: Zhenyu Sun, Luobin Zhang, Axi Niu, Haishen Wang, Qingsen Yan
Abstract: Infrared-visible image fusion aims to create an information-rich fused image by integrating the complementary thermal saliency from infrared sensing and fine textures from visible imaging. Such accurate fusion is essential for real-world perception applications in complex scenes, including nighttime autonomous driving, search and rescue, and surveillance, and can further benefit downstream tasks such as semantic segmentation. However, most existing fusion methods rely upon static trained weights that cannot adapt to scene-specific content at inference time, and often suffer from a granularity mismatch when coarse auxiliary semantics are injected, which makes it difficult to simultaneously highlight targets and preserve details. In this work, we propose EAPFusion to address these issues by using self-evolving intrinsic priors instead of relying on external auxiliary models. Concretely, EAPFusion maintains a compact set of intrinsic priors and progressively updates them across scales. These evolved priors are utilized to dynamically generate convolutional kernels, shifting the paradigm from fixed, pre-trained filters to instance-adaptive parameters via prior-conditioned dynamic convolution. Furthermore, we design a channel-level fusion module that shuffles and interleaves infrared and visible channels, applying local channel mixing to boost cross-modal complementarity. Experiments on different datasets, including cross-dataset evaluation and semantic segmentation, show that the proposed method achieves state-of-the-art quantitative and qualitative fusion results, and consistently boosts downstream performance. Code is coming soon.
Authors: Yingqi Tang, Zhaotie Meng, Erkang Cheng, Haibin Ling
Abstract: Simultaneous perception of 2D objects in perspective view and 3D objects in Bird's Eye View (BEV) is challenging for multi-camera autonomous driving. Existing two-stage pipelines use 2D results only as a one-time cue for 3D detection. We propose SimPB++, which simultaneously detects 2D objects in perspective and 3D objects in BEV from multiple cameras. It unifies both tasks into an end-to-end model with a hybrid decoder architecture, coupling multi-view 2D and 3D decoders interactively. Two novel modules enable deep interaction: Dynamic Query Allocation adaptively assigns 2D queries to 3D candidates, and Adaptive Query Aggregation refines 3D representations using multi-view 2D features, forming a cyclic 3D-2D-3D refinement. For multi-view 2D detection, we use Query-group Attention for intra-group communication. We also design a Crop-and-Scale strategy for long-range perception and a Propagating Denoising strategy with an auxiliary RoI detector. SimPB++ supports mixed supervision with 2D-only and fully annotated data, reducing reliance on expensive 3D labels. Experiments show state-of-the-art performance on nuScenes for both tasks and strong long-range detection (up to 150m) on Argoverse2.
Authors: Vladislav Pyatov, Gleb Bobrovskikh, Saveliy Galochkin, Nikita Boldyrev, Oleg Voynov, Alexander Filippov, Gonzalo Ferrer, Peter Wonka, Evgeny Burnaev
Abstract: We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to sketch-extrude operations due to simplified representations and limited datasets. We address this by introducing a FeatureScript-based representation and constructing a dataset of 450k real-world CAD models spanning 15 modeling operations. We obtain the dataset via a new pipeline that reconstructs clean, executable FeatureScript programs and provides multimodal annotations. Fine-tuning a VLM on this representation yields state-of-the-art results in text-conditioned CAD generation and image-based reconstruction, producing more accurate, diverse, and feature-rich designs than prior frameworks. Ablations show that each individual component of our framework, i.e., the FeatureScript representation, the extended operation set, and representation-aligned textual descriptions, significantly improves performance. Our framework substantially broadens the complexity and realism achievable in generative CAD. The CADFS framework and the new dataset are available at https://voyleg.github.io/cadfs/.
Authors: Yuchen Wang, Wenliang Zhong, Lichen Bai, Zikai Zhou, Shitong Shao, Bojun Cheng, Shuo Chen, Shuo Yang, Zeke Xie
Abstract: Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to these variants remains a critical challenge due to weight space mismatches. We observe that direct application leads to style degradation and structural collapse, yet the underlying mechanisms remain poorly understood. To fill this gap, we delve into the weight space and identify that the incompatibility stems from spectral interference within shared functional clusters defined over singular subspaces. Specifically, our analysis reveals that while both paradigms respect spectral rigidity, they establish conflicting routing pathways that clash through constructive overload or destructive cancellation. To address this issue, we propose Cluster-Aware Spectral Arbitration (CASA), a data-free framework that dynamically arbitrates between safeguarding the target's manifold and restoring LoRA alignment based on spectral density. Extensive experiments demonstrate that CASA effectively mitigates artifacts and revives LoRA functionality. Our code is available at https://github.com/Noahwangyuchen/CASA
Authors: Marah Halawa, Olaf Hellwich
Abstract: Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware methods address this by redesigning the self-supervised objective itself, limiting portability across the rapidly evolving landscape of self-supervised learning (SSL) frameworks. We propose ProtoFair, a fairness-aware contrastive loss designed to work alongside existing SSL objectives without modifying them. ProtoFair leverages unsupervised prototype clustering to identify pseudo-counterfactual pairs: samples sharing the same cluster assignment but belonging to different sensitive groups. By pulling these content-matched, cross-group samples together in the embedding space, ProtoFair encourages the encoder to learn representations that are invariant to the sensitive attribute. The method requires only sensitive attribute annotations, no target labels, and integrates seamlessly with both SimCLR and SupCon. Experiments on CelebA and UTKFace demonstrate consistent fairness improvements while maintaining competitive accuracy.
Authors: Ali Nouri, Yifei Zhang, Yifan Zhang, Tayssir Bouraffa, Zhennan Fei, Zijian Han, H{\aa}kan Sivencrona, Anders Heyden
Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect to the list of rare but still possible safety-related scenarios needed for the development, verification, and validation of the ADS. 3D Gaussian Splatting (3DGS) has shown promising capabilities for the reconstruction and editing of scenes based on data collected by cameras and LiDAR sensors. However, the industrial fidelity evaluation of reconstructions is underexplored, which is crucial when employing such methods in safety-related systems, especially for ADS. This becomes more challenging as ADS operates in a dynamic, uncontrolled environment with limited viewpoints and often partially occluded objects. This paper addresses this gap by proposing and implementing a framework (Fig. 1) to systematically analyze the capabilities and limitations of 3DGS for use in the reconstruction of safety-related scenes. It focuses on the quality of reconstruction for vehicles and pedestrians, which are the two most critical object classes for ADS. Our findings provide industry insights into the fidelity degradation of reconstructions from multiple novel viewpoints, both lateral and longitudinal, enabling the integration of these methods into real-world industrial AD software development and testing pipelines.
Authors: Sana Al-azzawi, Elisa Barney, Marcus Liwicki
Abstract: Handwritten Text Recognition (HTR) under limited labeled data remains a challenging problem, particularly for Arabic-script languages. Although modern sequence-based recognizers perform well in high-resource settings, their accuracy degrades sharply as training data becomes scarce. Arabic-script languages share a common writing system with substantial character overlap, motivating cross-script training as a strategy to mitigate data scarcity. We performed experiments on Arabic, Urdu, and Persian scripts and achieved improvements over single-script baselines (new SotA especially for low-resource settings). A key finding of our experiments is that cross-script transfer is largely driven by script-level overlap rather than uniform accuracy improvements. Through a statistical character-level analysis we show that gains are structurally concentrated on characters shared across scripts, while language-specific characters exhibit limited or negative transfer. These findings provide insight into transfer dynamics in low-resource script families. Detailed results include: We conduct a controlled line-level study of cross-script joint training for Arabic-script HTR under low-resource regimes (number of samples K \in 100, 500, 1000 labeled lines) on Arabic (KHATT), Urdu (NUST-UHWR), and Persian (PHTD). A CRNN model is trained on the union of multiple related Arabic-script datasets and evaluated on individual target languages. On Persian (PHTD), joint training achieves a Character Error Rate (CER) of 9.99, surpassing previously reported results despite not using the full available training data. On an Urdu dataset (UNHD), joint training reduces CER from 17.20 to 14.45. Code and data splits are released to ensure reproducibility.1
Authors: Kunyuan Xie, Zhixi Cai, Kalin Stefanov
Abstract: Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method for sign language recognition that uses segmentation-based masking to adapt to the presence and motion of key body parts, rather than treating hand poses as static visual tokens. The resulting mask-and-reconstruct objective improves fine-grained sign representation learning. On WLASL, NMFs-CSL, and Slovo, our encoder achieves state-of-the-art performance, improving per-instance and per-class Top-1 accuracy while using fewer input frames and modalities than comparable encoders.
Authors: Maximilian Kellner, Dominik Merkle, Michael Brunklaus, Alexander Reiterer
Abstract: Large-scale 3D point clouds can consist of billions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks. In order to develop a semantic understanding of the scene, the point clouds are divided into smaller subclouds that can be processed. Typically, this division is done using spherical crops, resulting in a loss of surrounding geometric context. To address this issue, we propose alternative methods that produce subclouds with larger crop sizes while maintaining a similar number of points. Specifically, we compare exponential, Gaussian, and linear cropping methods with the spherical method. We evaluated two 3D deep learning model architectures using multiple indoor and outdoor environment datasets. Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results. Code is available at https://github.com/mvg-inatech/point_cloud_cropping
Authors: Zhuoyang Lyu, Yiyang Zhang, Tongxin Wang, Ruirui Lan
Abstract: Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and few-shot transfer to novel tasks where task-specific annotation is scarce. We address this gap with EchoCare-CLIP, a CLIP-style dual-encoder contrastive framework that aligns ultrasound images with clinical text in a shared embedding space. We curate a multi-organ corpus of over 16K image-text pairs spanning breast, liver, lung, and thyroid, with over 78% of captions derived from expert-annotated reports, and complement the remainder with a three-tier template-based and LLM-based caption generation pipeline. We evaluate model configurations spanning two text encoder families (CLIP, BioClinicalBERT) and two caption strategies (template-based, LLM-generated) against OpenAI CLIP and BiomedCLIP baselines. Our trained models consistently improve cross-modal alignment over baselines, with the best configuration achieving a paired alignment score of 0.682. However, stronger alignment does not guarantee better downstream performance: CLIP-based variants with partial fine-tuning achieve the strongest zero-shot classification on external held-out datasets (0.709 on BUSI; 0.626 on AULI), while full end-to-end fine-tuning degrades transfer due to overfitting. On linear probing and few-shot adaptation, model rankings are dataset-dependent, reflecting a trade-off between domain adaptation and representational generalizability. We further show that template-based captions match or outperform LLM-generated captions, suggesting lexical diversity is not a proxy for caption quality. Taken together, our results demonstrate that ultrasound vision-language alignment is achievable from public data alone, but robust clinical transfer requires careful balancing of domain adaptation, encoder capacity, and caption supervision quality.
Authors: Le Zhang, Jihan Yang, Soundarya Krishnan, Jimit Majmudar, Xiou Ge, Prasoon Puri, Prathamesh Nandkishor Saraf, Shruti Bhargava, Dhivya Piraviperumal, Yinan Ling, Cindy Pan, Hong Yu, Aishwarya Agrawal, Bo-Hsiang Tseng
Abstract: Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they are for. While existing benchmarks effectively evaluate the geometric perception capabilities of multimodal large language models (MLLMs), they fall short of probing the higher-order cognitive abilities required for grounded intelligence. To address this gap, we introduce the Spatial-Functional Intelligence Benchmark (SFI-Bench), a video-based benchmark with over 1,500 expert-annotated questions derived from diverse egocentric indoor video scans. SFI-Bench systematically evaluates two complementary dimensions of advanced reasoning: (1) Structured Spatial Reasoning, which requires understanding complex layouts and forming coherent spatial representations, and (2) Functional Reasoning, which involves inferring object affordances and their context-dependent utility. The benchmark includes tasks such as conditional counting, multi-hop relational reasoning, functional pairing, and knowledge-grounded troubleshooting, directly challenging models to integrate perception, memory, and inference. Our experiments reveal that current MLLMs consistently struggle to combine spatial memory with functional reasoning and external knowledge, highlighting a critical bottleneck in achieving grounded intelligence. SFI-Bench therefore provides a diagnostic tool for measuring progress toward more cognitively capable and truly grounded multimodal agents.
Authors: Yian Zhao, Feng Wang, Qiushan Guo, Chang Liu, Xiangyang Ji, Jian Zhang, Jie Chen
Abstract: Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable reconstruction quality, continued optimization of reconstruction does not necessarily translate into improved generative performance. How to enhance the diffusability of video latents remains a critical and unresolved challenge. In this work, inspired by principles of predictive world modeling, we investigate the potential of predictive learning to improve the video generative modeling. To this end, we introduce a simple and effective predictive reconstruction objective that unifies predictive learning with video reconstruction. Specifically, we randomly discard future frames and encode only partial past observations, while training the decoder to reconstruct the observed frames and predict future ones simultaneously. This design encourages the latent space to encode temporally predictive structures and build a more coherent understanding of video dynamics, thereby improving generation quality. Our model, termed Predictive Video VAE (PV-VAE), achieves superior performance on video generation, with 52% faster convergence and a 34.42 FVD improvement over the Wan2.2 VAE on UCF101. Furthermore, comprehensive analyses demonstrate that PV-VAE not only exhibits favorable scalability, with generative performance improving alongside VAE training, but also yields consistent gains in downstream video understanding, underscoring a latent space that effectively captures temporal coherence and motion priors.
Authors: Jagrati Talreja, Tewodros Syum Gebre, Leila Hashemi-Beni
Abstract: Accurate flood water mapping is critical for disaster management, yet current methods struggle to fully exploit the potential of spaceborne imagery. Optical data offers high interpretability but is limited by environmental conditions, whereas SAR provides reliable all-weather coverage with reduced visual interpretability. FLoRA (Fusion Latent for Optical Reconstruction and Area Segmentation) is a cross-modal multi-task framework that jointly reconstructs high-fidelity optical imagery and segments flood water regions from Sentinel 1 SAR by fusing the complementary strengths of optical and SAR data. During training, a lightweight optical teacher (driven by RGB and NDVI priors) provides pyramidal features that guide SAR representations into a fusion latent space via multiscale windowed cross attention and FiLM conditioning, with gated residuals preventing overcorrection. This design enables multi-task learning across two complementary objectives: (a) SAR-to-optical translation for fine-grained RGB reconstruction and (b) flood water region segmentation for hydrologic interpretation. The dual decoders are optimized using Charbonnier SSIM for structural fidelity, edge FFT magnitude losses for spectral realism, and Dice BCE hydrology-aware edge alignment for precise flood water delineation. A feature distillation constraint further aligns fused SAR features with the optical teacher's manifold. Evaluations on SEN1FLOODS11, DEEPFLOOD, and SEN12MS demonstrate that FLoRA surpasses fusion baselines in PSNR, SSIM, and LPIPS, demonstrating that multi-modal fusion within a teacher-guided latent space yields semantically faithful and physically consistent flood-water intelligence from spaceborne observations.
Authors: Zhengan Yan, Shikang Zheng, Haoran Qin, Xiaobing Tu, Yinggui Wang, Jiacheng Liu, Jiaxuan Ren, Yuqi Lin, Peiliang Cai, Jinkui Ren, Xiantao Zhang, Linfeng Zhang
Abstract: Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing early steps at reduced resolution. However, existing approaches prioritize upsampling using low-level heuristics such as edge detection or channel variance, which are weakly aligned with editing semantics and may lead to structural inconsistency. Moreover, spatial regions are often upsampled without verifying whether semantic modification is actually required, resulting in redundant high-resolution computation and accumulated errors. Therefore, we propose SpecEdit, a training-free dynamic-resolution framework tailored for diffusion-based image editing. SpecEdit follows a draft-and-verify scheme: a low-resolution draft first estimates the semantic outcome, after which token-level discrepancies are used to identify edit-relevant tokens for high-resolution denoising, while the remaining tokens stay at a coarse resolution. Experiments on Qwen-Image-Edit and FLUX.1-Kontext-dev demonstrate up to 10x and 7x acceleration, while maintaining strong quality. SpecEdit is complementary to step distillation and other acceleration techniques, achieving up to 13x speedup when combined with existing methods. Our code is in supplementary material and will be released on GitHub.
Authors: Jagrati Talreja, Tewodros Syum Gebre, Leila Hashemi Beni
Abstract: Synthetic Aperture Radar (SAR) imagery is widely used for flood monitoring due to its all-weather and day-night imaging capability. However, flood mapping using single-polarization SAR data remains challenging in complex environments where surface and volume scattering coexist. In this paper, we investigate the effectiveness of cross-polarization fusion of VV and VH SAR observations for improved flood mapping. A deep learning-based segmentation framework is employed to jointly exploit complementary information from VV and VH polarizations. To ensure a fair evaluation, three configurations are compared under identical training conditions: VV only, VH only, and fused VV-VH input. Performance is assessed using standard flood mapping metrics, including Intersection over Union (IoU) and F1-score, along with qualitative visual analysis. Experimental results demonstrate that VV-VH fusion consistently outperforms single-polarization models, particularly in vegetated and heterogeneous flood regions, leading to more accurate flood boundary delineation. The findings highlight the importance of cross-polarization SAR fusion for enhancing the reliability of SAR-based flood mapping in disaster monitoring applications.
Authors: Peggy Joy Lu, Wei-Yu Chen, Yao-Tsung Huang, Vincent Shin-Mu Tseng
Abstract: We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data privacy, class imbalance, and heterogeneous architectures. Our framework consists of three key stages. In the Generated Stage, we introduce a one-shot, target-aware diffusion-based generation module that learns visual style from a single target-domain image while leveraging prompt-based control to synthesize specific object instances. Unlike conventional style transfer-based methods that require large target datasets and ignore semantic-level discrepancies, our approach enables privacy-preserving augmentation to reduce ethical concerns, and introduces controllable rare object generation to mitigate long-tailed category degradation. In the Federated Stage, we employ probabilistic Faster R-CNN on the client side to improve localization accuracy, and a dynamic model contrastive strategy to suppress domain-specific bias. The server side performs model fusion across heterogeneous architectures without accessing raw data. Finally, in the Distilled Stage, we propose an inconsistent categories integration algorithm to resolve label inconsistency and architecture heterogeneity across clients. Extensive experiments on multiple cross-domain detection benchmarks demonstrate that our method outperforms existing multi-source domain adaptation and federated learning baselines under multi-class, privacy-preserving settings. Our method improves mAP by +2.1% over prior privacy-preserving approaches and achieves a new state-of-the-art mAP of 33.4%, highlighting the effectiveness of HeroCrystal in enabling practical multi-camera AI surveillance systems.
Authors: Jianing Zhang, Zijian Zhou, Kai Sun
Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images. Although deep learning has advanced this field, mainstream frequency-based methods relying on standard scaled dot-product attention suffer from quadratic computational complexity and fail to exploit the inherent regional sparsity of remote sensing imagery. Furthermore, existing spatial enhancement strategies typically employ static convolution kernels, which struggle to adapt to the complex frequency and regional variations of PAN and MS images. To address these bottlenecks, we propose a Region-Aware Fusion (RAFNet) Network that synergistically models spatial and frequency information. Specifically, we design a Spatial Adaptive Refinement (SAR) module that leverages the discrete wavelet transform (DWT) for directional frequency separation and K-means clustering for regional partitioning, which enables the dynamic construction of region-specific adaptive convolution kernels, achieving spatially and frequency-adaptive feature enhancement. Moreover, we introduce a Clustered Frequency Aggregation (CFA) module based on a sparse attention mechanism guided by the semantic clusters, which executes a region-aware sparse attention strategy that drastically reduces computational redundancy while ensuring high-quality frequency feature extraction. In addition we integrated these modules into a progressive, multi-level spatial-frequency network architecture to facilitate robust interaction and accurate image reconstruction. Extensive experiments on multiple benchmark datasets demonstrate that the proposed RAFNet significantly outperforms state-of-the-art pansharpening methods in both reduced- and full-resolution assessments. The code is available at https://github.com/PatrickNod/RAFNet.
Authors: Ce Wang, Zhenyu Hu, Wanjie Sun
Abstract: Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution. Unlike existing single-step diffusion methods that rely on fixed timesteps, we first introduce an uncertainty-guided timestep assignment strategy to construct a stronger single-step teacher model, where reconstruction difficulty is explicitly linked to diffusion timesteps, enabling adaptive generative strength. Building upon this teacher, we further present a structured pruning strategy tailored to remote sensing imagery, which systematically removes redundant semantic modules and replaces standard operations with lightweight designs, including frequency-separable convolution, direction-separable convolution, and a query-driven global aggregation module. These components explicitly exploit the unique characteristics of remote sensing data, such as sparse high-frequency details, strong directional patterns, and long-range spatial dependencies. To enhance knowledge transfer, we incorporate Maximum Mean Discrepancy (MMD) into the distillation process to align feature distributions between the teacher and student models. Extensive experiments on multiple remote sensing benchmarks demonstrate that SlimDiffSR achieves a favorable balance between efficiency and reconstruction quality. In particular, it attains up to $200\times$ inference acceleration and a $20\times$ reduction in model parameters compared with multi-step diffusion models, while achieving competitive perceptual quality and clearly outperforming existing lightweight diffusion baselines in efficiency. The code is available at: https://github.com/wwangcece/SlimDiffSR.
Authors: Jinyuan Shao, Sangyoong Park, Chunxi Zhao, Ayman Habib, Songlin Fei
Abstract: Airborne Laser Scanning (ALS) can collect point clouds across large areas, enabling large-scale forest inventory. However, ALS point clouds are sparse and noisy, resulting in inaccurate individual-tree-level forest inventory, such as stem localization and tree size estimation. To overcome this problem, we propose a deep learning model, 3D Forest Super Resolution (3DFSR), to simultaneously improve point density and reduce noise for ALS forest point cloud. 3DFSR is a voxel-based CNN with a U-Net architecture. The proposed 3DFSR is evaluated on ALS point clouds collected in both temperate forests in the U.S. and boreal forests in Germany. Experimental results demonstrate that 3DFSR can generate finer point clouds of tree structure than other state-of-the-art point cloud super-resolution algorithms, achieving 0.249 m Chamfer Distance and 2.711 m Hausdorff Distance. Furthermore, to verify the effectiveness of 3DFSR point clouds in forest inventory, we conduct stem detection, DBH measurements, and stem reconstruction on both original ALS point clouds and 3DFSR enhanced point clouds. We find that stem detection and reconstruction algorithms developed for TLS/MLS point clouds can directly work on our 3DFSR point clouds, and DBH can be derived with circle-fitting method. F1 score of stem detection is improved from 0.71 on original ALS point clouds to 0.97 on 3DFSR point clouds; DBH estimation improves from 13.45 cm RMSE using allometric equations to 6.43 cm using circle fitting; comparing to stems reconstruction from MLS point clouds, stem reconstructed from 3DFSR point clouds has 0.170 m of Chamfer Distance and 0.377 m of Hausdorff Distance, and 0.95 R2 volume estimation. Finally, we find that the proposed 3DFSR is applicable to process point densities from 10 to 1700 points/m2; it also can be generalized across data collected from different LiDAR platforms without transfer learning.
Authors: Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel
Abstract: Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluation practices are inconsistent. We present the first systematic study of metric reliability in multimodal unlearning. Five standard metrics, Forget Accuracy (FA), Retain Accuracy (RA), Membership Inference Attack (MIA), Activation Distance (AD), and JS divergence (JS), yield conflicting method rankings across three VQA benchmarks (MLLMU-Bench, UnLOK-VQA, MMUBench). Kendall tau analysis over 36 unlearned LLaVA-1.5-7B models reveals two opposing clusters, {FA, RA, MIA} and {AD, JS}, with tau_FA_AD = -0.26, reproduced on BLIP-2 OPT-2.7B. Agreement is lower in multimodal VQA (average tau = 0.086) than in unimodal classification (average tau = 0.158; difference = 0.072), indicating that dual image-and-text pathways amplify inconsistency. We introduce the Unified Quality Score (UQS), a composite metric with weights derived from each metric's Spearman correlation with the oracle distance d(M_hat, M_star), where M_star is the oracle model retrained only on the retain set. RA shows the strongest reliability (rho = 0.484, p = 0.003), while FA is negatively correlated (rho = -0.418, p = 0.011). UQS yields stable rankings under 100 random weight perturbations (tau = 0.647 +- 0.262). We release the benchmark, 36 checkpoints, and an interactive leaderboard. Code and pre-computed results are available at https://github.com/neurips26/UnifiedUnl.
Authors: Dineth Jayakody, Pasindu Thenahandi, Chameli Dommanige
Abstract: Pneumonia remains a leading global cause of morbidity and mortality, particularly in low resource settings where access to imaging, laboratory testing, and specialist care is limited. Clinical assessment relies on heterogeneous evidence, including symptoms, respiratory patterns, and chest imaging, making screening inherently multimodal. However, many existing computational approaches remain unimodal and focus primarily on radiographs. In this work, we present MultiSense-Pneumo, a multimodal framework for pneumonia oriented screening and triage support that integrates structured symptom descriptors, cough audio, spoken language, and chest radiographs. The system combines deterministic symptom triage, LightGBM based acoustic classification, domain adversarial radiograph analysis using ResNet 18, transformer based speech recognition, and an interpretable multimodal fusion operator. Each modality is transformed into a normalized risk signal and aggregated into a unified screening estimate, enabling transparent and modular decision support. MultiSense-Pneumo is designed for real world deployment under modest computational constraints and can operate fully offline on standard laptop class hardware, making it suitable for community health workers, rural clinics, and emergency response settings. Experimental results demonstrate robustness of the radiograph pathway under domain shifts, while highlighting limitations in minority class recall for acoustic signals. MultiSense-Pneumo is intended as a research prototype for screening and triage support rather than a clinically validated diagnostic system.
Authors: Jiebin Yan, Chenyu Tu, Weixia Zhang, Zhihua Wang, Peibei Cao, Qinghua Lin, Yuming Fang, Xiaoning Liu, Zongwei Wu, Zhuyun Zhou, Radu Timofte
Abstract: This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This challenge focuses on mobile image enhancement under low-light conditions, aiming to design lightweight networks that improve enhancement quality while ensuring practical deployability under limited computational resources. A total of 207 participants registered, 27 teams submitted valid entries, and 17 teams ultimately provided valid factsheet. Based on these submissions, this paper provides a systematic evaluation of recent methods for E-LLIE, offering a comprehensive overview of state-of-the-art progress and demonstrating significant improvements in both performance and efficiency.
Authors: S M Asif Hossain, Shruti Kshirsagar
Abstract: Gliomas are aggressive brain tumors that infiltrate surrounding tissue beyond the visible tumor margins observed on Magnetic Resonance Imaging (MRI). Predicting the spatial extent of this infiltration is essential for surgical planning and radiation therapy, yet existing deep learning approaches focus on segmenting the visible tumor rather than estimating infiltration risk in the surrounding tissue. This paper presents InfiltrNet, a novel dual-branch architecture that combines a convolutional neural network (CNN) encoder with a Swin Transformer encoder through cross-attention fusion modules to predict three-zone infiltration risk maps from multimodal MRI. A label generation strategy based on distance transforms is proposed to derive reproducible infiltration risk zones from standard Brain Tumor Segmentation (BraTS) annotations. InfiltrNet is trained with a combined Dice-CrossEntropy and boundary-aware loss augmented by auxiliary supervision heads at intermediate decoder levels. Extensive experiments on BraTS 2020 and BraTS 2025 demonstrate that InfiltrNet outperforms five established baselines. Explainability analysis using GradCAM++ and Occlusion sensitivity confirms that the model attends to clinically relevant peritumoral regions.
Authors: Shihao Hou, Chikai Shang, Zhiheng Yang, Jiacheng Yang, Xinyi Shang, Junlong Gao, Yiqun Zhang, Yang Lu
Abstract: Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges that remain underexplored in PFL. In this paper, we investigate this long-tailed personalized federated learning and observe that current methods suffer from two limitations: (i) fine-tuning degrades performance below zero-shot baselines due to the erosion of inherent class balance in foundation models; (ii) conventional personalization techniques further transfer this bias to local models through parameter or feature-level fusion. To address these challenges, we propose Federated Learning via Gradient Purification and Residual Learning (FedPuReL), which preserves balanced knowledge in the global model while enabling unbiased personalization. Specifically, we purify local gradients using zero-shot predictions to maintain a class-balanced global model, and model personalization as residual correction atop the frozen global model. Extensive experiments demonstrate that FedPuReL consistently outperforms state-of-the-art methods, achieving superior performance on both global and personalized models across diverse long-tailed scenarios. The code is available at https://github.com/shihaohou/FedPuReL.
Authors: Yagiz Nalcakan, Hyeongjin Ju, Incheol Park, Sanghyeop Yeo, Youngwan Jin, Shiho Kim
Abstract: Vision Foundation Models (VFMs) pretrained on large-scale RGB data have demonstrated remarkable representation quality, yet their applicability to multispectral imaging spanning Near-Infrared (NIR), Short-Wave Infrared (SWIR), and Long-Wave Infrared (LWIR) remains largely unexplored. These spectral modalities offer complementary sensing capabilities critical for robust perception in adverse conditions, but present a fundamental domain gap relative to RGB-centric pretrained models. We present SpectraDINO, a multispectral VFM that bridges this spectral gap by extending DINOv2 ViT backbones to beyond-visible modalities through lightweight, per-modality bottleneck adapters, while preserving the rich representations of the frozen RGB backbone. We introduce a multi-stage teacher-student training protocol in which a frozen DINOv2 teacher guides a spectral student via cosine distillation, symmetric contrastive loss, patch-level alignment, and a novel neighborhood-structure-preservation loss. This staged curriculum enables strong cross-modal alignment without catastrophic forgetting of RGB priors. We evaluate SpectraDINO on multispectral object detection and semantic segmentation across challenging NIR, SWIR, and LWIR benchmarks using widely adopted fusion strategies. SpectraDINO achieves state-of-the-art performance across most benchmarks, validating its effectiveness as a general-purpose backbone for spectral generalization. The code and weights for model variants are available at https://github.com/Yonsei-STL/SpectraDINO.
Authors: Wei Tao, Xiaoyang Qu, Peiqiang Wang, Guokuan Li, Jiguang Wan, Kai Lu, Jianzong Wang
Abstract: Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in VLMs based on token granularity, which is time-consuming in the search process and hardware inefficient during computation. This paper introduces a novel approach called WindowQuant, which employs window-adaptive mixed-precision quantization to optimize the KV cache. WindowQuant consists of two modules: window-level quantization search and window-level KV cache computation. Window-level quantization search quickly determines the optimal bit-width configuration of the KV cache windows based on the similarity scores between the corresponding visual token windows and the text prompt, maintaining the model accuracy. Furthermore, window-level KV cache computation reorders the KV cache windows before quantization, avoiding the hardware inefficiency caused by mixed-precision quantization in inference computation. Extensive experiments demonstrate that WindowQuant outperforms state-of-the-art VLM models and KV cache quantization methods on various datasets.
Authors: Pierpaolo Serio, Hetian Wang, Zixiang Wei, Vincenzo Infantino, Lorenzo Gentilini, Lorenzo Pollini, Valentina Donzella
Abstract: Place recognition is essential for long-term autonomous navigation, enabling loop closure and consistent mapping. Although deep learning has improved performance, deploying such models on resource-constrained platforms remains challenging. This work explores efficient LiDAR-based place recognition for EdgeAI by leveraging Bird's Eye View representations to enable lightweight image-based networks. We benchmark representative architectures without aggregation heads using a unified descriptor scheme based on global pooling and linear projection, and evaluate performance under FP32, FP16, and INT8 quantization. Experiments reveal trade-offs between accuracy, robustness, and efficiency: FP16 matches FP32 with lower cost, while INT8 introduces architecture-dependent degradation. Overall, the presented results are a strong basis for future research on 'use-case'-aware quantisation of Neural Networks for Edge deployment.
Authors: Hyobin Park, Minseok Seo, Dong-Geol Choi
Abstract: Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often requires expert knowledge. Recent electro-optical vision foundation models aim to learn domain-specific representations from remote sensing imagery, but it remains unclear whether they are more effective than strong generalist vision foundation models under retrieval-based evaluation. In this study, we conduct a controlled comparison between representative EO-specific and generalist vision foundation models for remote sensing image retrieval. Using the same datasets, retrieval protocol, and evaluation metric, we evaluate both in-domain performance and cross-scene generalization. Our results show that strong generalist vision foundation models are competitive with, and in some cases outperform, existing EO-specific models. Moreover, EO-specific models often suffer from substantial degradation under cross-scene evaluation, while generalist models show more stable transfer. These findings suggest that EO pretraining alone does not guarantee stronger retrieval-oriented remote sensing representations. We discuss the limitations of current EO-specific pretraining strategies and highlight the need for future EO vision foundation models to better exploit the physical, spatial, spectral, and geographic characteristics of remote sensing imagery.
Authors: Yuchen Zhang, Yao Lu, Johannes Betz
Abstract: Open-Set Object Detection (OSOD) is crucial for autonomous driving, where perception systems must recognize and localize both known and previously unseen objects in complex, dynamic environments. While recent approaches deliver promising results, they often require retraining the detector extensively to learn objectness, which describes the likelihood that a bounding box tightly encloses a valid object, regardless of whether its category was learned during training. Deviating from existing work, we hypothesize that standard off-the-shelf detectors may already contain helpful cues for objectness, owing to their training on numerous and diverse known categories. Building on this idea, we propose NAN-SPOT, a training-light framework that does not require to retrain the base object detector and estimates objectness by leveraging a hidden layer metric called Negative-Aware Norm (NAN), requiring only minutes of training on just hundreds of images. To support comprehensive evaluation, we introduce COCO-Open, an expanded version of the existing COCO-Mixed dataset, increasing unknown object annotations from 433 to 1853, making it the most exhaustively labeled dataset for OSOD to the best of our knowledge. Experimental results demonstrate that NAN-SPOT achieves even better performance on unknown object detection than methods requiring heavy training, without compromising performance on known objects. This efficiency and robustness make NAN-SPOT a promising step towards open-world perception in autonomous driving.
Authors: Jianbao Cao, Zhangrui Zhao, Bohan Feng, Zixuan Hu, Rui Li, Haiyuan Wan, Chenxi Li, Jingyuan Li, Wenzhe Cai, Lei Bai, Wanli Ouyang, Lingyu Duan, Di Huang, Mingting Pan, Sha Zhang, Xinzhu Ma, Shixiang Tang, Dongzhan Zhou
Abstract: Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the rigorous functional semantics and safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are not only realistic but also functionally valid and safe for complex experimental workflows.
Authors: Stefanos Pasios
Abstract: Video game engines have been an important source for generating large volumes of visual synthetic datasets for training and evaluating computer vision algorithms that are to be deployed in the real world. While the visual fidelity of modern game engines has been significantly improved with technologies such as ray-tracing, a notable sim2real appearance gap between the synthetic and the real-world images still remains, which limits the utilization of synthetic datasets in real-world applications. In this letter, we investigate the ability of a state-of-the-art image generation and editing diffusion model (FLUX.2-4B Klein) to enhance the photorealism of synthetic datasets and compare its performance against a traditional image-to-image translation model (REGEN). Furthermore, we propose a hybrid approach that combines the strong geometry and material transformations of diffusion-based methods with the distribution-matching capabilities of image-to-image translation techniques. Through experiments, it is demonstrated that REGEN outperforms FLUX.2-4B Klein and that by combining both FLUX.2-4B Klein and REGEN models, better visual realism can be achieved compared to using each model individually, while maintaining semantic consistency. The code is available at: https://github.com/stefanos50/Hybrid-Sim2Real
Authors: Duy Hoang Khuong, Duy Nguyen Huu, Ngu Huynh Cong Viet
Abstract: Chest X-ray classification suffers from severe class imbalance where gradient updates bias toward majority classes, causing feature drift and poor performance on rare but critical pathologies. We propose a Momentum-Anchored Multi-Scale Fusion Network that uses exponential moving averages (EMA) as a temporal anchoring mechanism to stabilize feature representations under long-tailed distributions. Our approach applies selective momentum updates to the final expansion block of an EfficientNet backbone, creating a slowly-evolving reference branch that resists gradient-induced drift while preserving discriminative patterns for minority classes. Combined with multi-scale spatial fusion ($1\times 1$, $3 \times 3$, $5 \times 5$ convolutions), this anchoring strategy maintains representational stability throughout training. On ChestX-ray14, our method achieves 0.8682 average AUC, outperforming state-of-the-art approaches and showing particular improvements on rare pathologies like Hernia (0.9470) and Pneumonia (0.8165). The results demonstrate that momentum anchoring effectively counters feature instability in long-tailed medical image classification.
Authors: Steffen Knoblauch, Ram Kumar Muthusamy, Luis M. A. Bettencourt, Costas Velis, Pierre Chrzanowski, Edward Charles Anderson, Pete Masters, Innocent Maholi, Antonio Inguane, Levi Szamek, Alexander Zipf
Abstract: Managing municipal solid waste in rapidly urbanizing Sub-Saharan Africa remains challenging due to dispersed informal dumping and limited high-resolution datasets for spatial monitoring. We present an open-access deep learning model for automated detection of openly dumped dispersed solid waste via crowdsourced UAV imagery, trained and evaluated across 29 regions in 10 countries, encompassing diverse environmental contexts. A deep learning model trained on manually annotated image tiles achieved excellent performance in detecting openly dumped dispersed solid waste across all study regions. Predicted distributions reveal heterogeneous accumulation patterns, ranging from localized hotspots - often along waterways, where waste can exacerbate flood and public health risks - to more dispersed litter across urban areas. Waste accumulation is most strongly associated with population density and indicators of lack of local infrastructure access, whereas its relationship with broader measures of regional development is weaker, highlighting the importance of fine-scale data for understanding localized waste dynamics. By releasing the model, this study provides a ready-to-use tool for UAV imagery collected by municipalities and local mapping communities, enabling openly dumped dispersed solid waste monitoring without extensive technical expertise. This approach empowers local practitioners to convert UAV imagery into actionable insights, supporting targeted interventions and improved municipal solid waste management across Sub-Saharan Africa.
Authors: Duy Nguyen Huu, Duy Hoang Khuong, Ngu Huynh Cong Viet
Abstract: Chest radiography is a widely used imaging modality for thoracic disease diagnosis, yet its conventional interpretation remains time-consuming and heavily dependent on expert knowledge. While deep learning has improved diagnostic efficiency through automated feature extraction, challenges such as class imbalance and the localization of multiple co-existing pathologies remain unsolved. In this paper, inspired by the strength of Convolutional Block Attention Module (CBAM) in feature refinement and the capability of CNN blocks in feature extraction, we propose a strategy to integrate CBAM into traditional CNN blocks to enhance performance in multi-label classification tasks. Our method achieves a mean AUC of 0.8695 on ChestXray14 dataset, outperforming several state-of-the-art baselines.Our source code is available at: https://github.com/NNNguyenDuyyy/FETC_CBAM_Enhanced_CNN.git
URLs: https://github.com/NNNguyenDuyyy/FETC_CBAM_Enhanced_CNN.git
Authors: Jiaqi Shi, Jin Xiao, Xiaoguang Hu, Wenxuan Ji, Zichong Jia, Zifan Long, Tianyou Chen
Abstract: In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods, which directly affects the execution precision of downstream tasks such as embodied AI and autonomous driving. Existing methods explore feature correlation discrimination but are limited to point-level spatial distribution or channel responses, enabling only coarse-grained level evaluation. For modern multi-scale point cloud networks, such coarse-grained metrics inevitably incur significant information loss in deeper layers. To address this issue, we propose a novel network equipped with a channel-level metric-based enhancement mechanism, termed the PointCRA network. Our core idea is to introduce temporal trend variation as a new evaluation dimension to avoid the information loss caused by weight dimension collapse in existing spatial and channel attention mechanisms. On this basis, we construct a multi-level calibration framework guided by neighborhood homogeneity for weight calibration, and design a dedicated loss function to enhance channel discriminability. The module effectively leverages the intrinsic feature priors of deep networks to adaptively correct the feature aggregation process, offering strong interpretability with low parameter overhead. Furthermore, our proposed method exhibits strong transferability, interpretability, and parameter efficiency. We validate the proposed method effectiveness on diverse datasets and benchmark models, and further demonstrate its rationality through extensive analytical experiments. Our PointCRA achieves 77.5% mIoU on the S3DIS dataset, 90.4% OA on the ScanObjectNN dataset, and 87.4% instance mIoU on the ShapeNetPart dataset. The code and pretrained weights are publicly available on GitHub:
Authors: Moyu Tang, Chupei Tang, Junxiao Kong, Di Wang, Tianchi Lu
Abstract: Automated medical report generation, MRG, holds substantial value for alleviating radiologist workload and enhancing diagnostic efficiency. However, mainstream approaches typically treat diverse chest abnormalities as isolated classification targets. This paradigm often overlooks inherent disease co-occurrences and struggles to translate medical topological structures into explicit data correlations, constraining the model's reasoning capacity on complex or subtle lesions. To address this, we propose a Graph-Augmented Dual-Stream Medical Report Generation with Topological Internalization, GDMRG. Our framework introduces a Topological Knowledge Internalization module, TKI, which leverages a Graph Convolutional Network, GCN, to generate an explicit parameterized weight matrix based on global disease co-occurrence priors. This facilitates efficient topological knowledge injection without relying on external retrieval mechanisms. Building upon this, we construct a dual-stream classification system: the main branch generates discrete diagnostic prompts under topological constraints, while the auxiliary branch employs an asymmetric optimization strategy to dynamically calibrate decision boundaries for highly imbalanced samples. Concurrently, to establish a logical closed loop between diagnosis and visual grounding, we design a diagnostic-driven Diagnosis-Guided Spatial Attention, DGSA, that utilizes high-dimensional clinical semantics to recalibrate the visual encoder, mitigating feature hallucinations. Comprehensive experiments on the MIMIC-CXR dataset demonstrate that GDMRG achieves competitive clinical efficacy, CE, while maintaining natural language fluency. Furthermore, our model exhibits robust zero-shot generalization on the IU X-Ray dataset. In summary, this work presents an integrated and interpretable paradigm for medical report generation.
Authors: Haoyu Wang, Haonan Wang, Yuyan Chen, Jun Chen, Gang Liu, Qian Wang, Jiahong Yan, Yanghua Xiao
Abstract: In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models often produce correct answers from flawed reasoning, while struggling to extract consistent rules across demonstrations. This gap is further exacerbated by two visual-level obstacles: an overwhelming proportion of redundant visual tokens that obscure textual cues, and a skewed attention distribution that favors the initial image at the expense of subsequent context. To address these issues, we introduce a framework that restructures multimodal ICL as a principled inductive-deductive process. The framework incorporates a similarity-based visual token compression module to filter out redundant patches, a dynamic attention rebalancing mechanism to distribute focus equitably across all images, and a chain-of-thought paradigm that explicitly guides the model to analyze individual examples, derive a generalizable rule, and then apply it to the query. An auxiliary learning pipeline combines supervised fine-tuning with reinforcement learning using verifiable rewards to reinforce faithful citation and noise filtering. Evaluations across eight benchmarks covering visual perception, logical reasoning, STEM problems, and sarcasm detection demonstrate consistent and significant improvements over standard ICL baselines for multiple open-source VLMs, highlighting the potential of equipping models with genuine inductive capabilities in multimodal settings.
Authors: Conghui Li, Huanyu He, Xin Wang, Weiyao Lin, Chern Hong Lim
Abstract: Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty estimation as a passive endpoint for post-hoc analysis, failing to close the loop by feeding this information back to refine feature representations. We contend that independent pixel-wise heteroscedastic modeling is uniquely suited for crack segmentation, as cracks are defined by fine-grained local gradients rather than the global semantic coherence relied upon in general object segmentation. However, this approach suffers from a structural optimization pathology: high predicted variance attenuates loss gradients, effectively causing the model to ignore difficult samples and under-fit complex boundaries. To address these challenges, we propose UnGAP, a novel framework that establishes a closed-loop mechanism between uncertainty estimation and feature learning. Central to our approach is the Uncertainty-Prompted Feature Modulator (UPFM), which treats aleatoric uncertainty as an active visual prompt rather than a mere output. UPFM dynamically calibrates feature distributions through pixel-wise affine transformations. Crucially, this mechanism mitigates the heteroscedastic pathology by transforming high variance, which would otherwise indicate gradient suppression, into a constructive signal for stronger feature rectification in ambiguous regions. Additionally, a boundary-aware detection head is introduced to further constrain prediction precision. Extensive experiments demonstrate that UnGAP balances superior segmentation accuracy with real-time inference speed, effectively validating the benefit of transforming uncertainty from a passive metric into an active calibration tool.
Authors: Soye Kwon, Keonyoung Lee, Dahuin Jung, Jaekoo Lee
Abstract: Fashion design aims to express a designer's creative intent and to depict how garments interact with the human body. Recent methods condition on multimodal inputs to support garment editing and virtual try-on. However, existing methods still (i) confine design to garment-related images, excluding creative design sources such as artwork, abstract imagery, and natural photographs, and (ii) cannot support complete outfits, including accessories. We present FEAT (Fashion Editing And Try-On from Any Design), a method that enables editing and try-on across garments and accessories using diverse design sources. To achieve this, we introduce Disentangled Dual Injection (DDI). It takes both apparel and non-apparel design sources and selectively injects design cues via content and style disentanglement. Furthermore, we propose Orthogonal-Guided Noise Fusion (OGNF), a training-free mechanism that removes residual garments via orthogonal projection and applies region-specific noise strategies to enable virtual try-on for both garments and accessories. Extensive experiments demonstrate that FEAT achieves state-of-the-art performance in design flexibility, prompt consistency, and visual realism.
Authors: Desong Yang, Mang Ye
Abstract: With recent advancements in large-scale pre-trained text-to-image (T2I) models, training-free image editing methods have demonstrated remarkable success. Typically, these methods involve adding noise to a clean image via an inversion process, followed by separate denoising steps for the reconstruction and editing paths during the forward process. However, since the reconstruction path is approximated using noisy latents from mismatched timesteps, existing methods inevitably suffer from accumulated drift, which fundamentally limits reconstruction fidelity. To address this challenge, we systematically analyze the inversion process within the flow transformer and propose DirectEdit, a simple yet effective editing method that eliminates the inherent reconstruction error without introducing additional neural function evaluations (NFEs). Unlike most prior works that attempt to rectify the inversion path, DirectEdit focuses on directly aligning the forward paths, enabling precise reconstruction and reliable feature sharing. Furthermore, we introduce a preservation mechanism based on attention feature injection and multi-branch mask-guided noise blending, which effectively balances fidelity and editability. Extensive experiments across diverse scenarios demonstrate that DirectEdit achieves efficient and accurate image editing, delivering superior performance that outperforms state-of-the-art methods. Code and examples are available at https://desongyang.github.io/Directedit.
Authors: Meritxell Riera-Mar\'in, Javier Garc\'ia L\'opez, J\'ulia Rodr\'iguez-Comas, Miguel A. Gonz\'alez Ballester, Adrian Galdran
Abstract: Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated when multiple expert annotations exhibit substantial disagreement. While inter-rater variability is typically treated as noise, it provides valuable information about intrinsic annotation ambiguity that must be reflected in model confidence. Methods: We improve the probabilistic calibration of medical image segmentation models by reformulating multi-rater supervision as an ordinal learning problem. Voxel-wise annotator agreement is treated as an ordered target, linking predictive confidence to the empirical variability in training data. This formulation allows the use of ordinal-aware scoring rules, such as the Ranked Probability Score ordinal loss, combined with a standard binary objective to preserve discriminative performance. Results: We evaluated the proposed approach across four public segmentation benchmarks spanning ophthalmology, histopathology, and thoracic imaging. Calibration was assessed using a multi-rater extension of expected calibration error. Results consistently show that ordinal-aware training yields substantially improved calibration with respect to inter-rater agreement without degrading segmentation accuracy. Conclusions: Treating multi-rater annotations as ordered information provides a principled and architecture-agnostic route to more reliable probabilistic segmentation models.
Authors: Fuyun Wang, Yuanzhi Wang, Xu Guo, Sujia Huang, Tong Zhang, Dan Wang, Hui Yan, Xin Liu, Zhen Cui
Abstract: Open-set supervised anomaly detection (OSAD) aims to identify unseen anomalies using limited anomalous supervision. However, existing prototype-based methods typically model normal data via a unimodal Gaussian prior, failing to capture inherent multi-modality and resulting in blurred decision boundaries. To address this, we propose Mixture Prototype Flow Matching (MPFM), a framework that learns a continuous transformation from normal feature distributions to a structured Gaussian mixture prototype space. Departing from traditional flow-based approaches that rely on a single velocity vector, MPFM explicitly models the velocity field as a Gaussian mixture prior where each component corresponds to a distinct normal class. This design facilitates mode-aware and semantically coherent distribution transport. Furthermore, we introduce a Mutual Information Maximization Regularizer (MIMR) to prevent prototype collapse and maximize normal-anomaly separability. Extensive experiments demonstrate that MPFM achieves state-of-the-art performance across diverse benchmarks under both single- and multi-anomaly settings.
Authors: Fuyun Wang, Yuanzhi Wang, Xu Guo, Sujia Huang, Tong Zhang, Dan Wang, Hui Yan, Xin Liu, Zhen Cui
Abstract: Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and overfitting, respectively.To mitigate this, we introduce Anomaly Preference Optimization,a novel paradigm that reformulates anomaly generation as a preference learning problem.Central to our approach is an implicit preference alignment mechanism that leverages real anomalies as positive references, deriving optimization signals directly from denoising trajectory deviations without requiring costly human annotation. Furthermore, we propose a Time-Aware Capacity Allocation module that dynamically distributes model capacity along the diffusion timeline,prioritizing structural diversity during highnoise phases while enhancing fine-grained fidelity in low-noise stages. During inference, a hierarchical sampling strategy modulates the coherencealignment trade-off, enabling precise control over generation. Extensive experiments demonstrate that significantly outperforms existing baselines,achieving state-of-the-art performance in both realism and diversity.
Authors: Meihua Zhou, Xinyu Tong, Li Yang
Abstract: Encoder-decoder imbalance and the reliance on large input volumes make many 3D brain tumor segmentation models both compute-heavy and brittle. We present M\textsuperscript{4}Fuse, a lightweight network that prioritizes discriminative brain tumor cues over exhaustive appearance reconstruction. Our method balances encoder and decoder capacity and replaces depth expansion with a synergistic design: it propagates long-range context with linear complexity via a grouped state space mixer, denoises and aligns skip features using a cross-scale dual-stage gating bridge, and absorbs cross-site acquisition shifts with a sample-level mixture-of-experts. On the BraTS2019 and BraTS2021 benchmarks, M\textsuperscript{4}Fuse outperforms other lightweight excellent methods in both parameter count and performance. Even at a challenging input resolution of \(64\times128\times128\) (half that of existing excellent models), M\textsuperscript{4}Fuse reduces parameters by 62.63\% and improves average performance by 0.09\%. Ablations of key components validate the method's exceptional parameter-to-accuracy efficiency and robustness across diverse data centers.
Authors: Aoyu Liu, Zhen Liu, Ziyi Wang, Dian Chen, Bing Zeng, Shuaicheng Liu
Abstract: Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas. While recent diffusion-based approaches offer powerful generative priors, they often overlook the exposure-dependent nature of the degradation and incur substantial computational costs from iterative sampling. To address these challenges, we propose ExpoCM, a novel one-step generative HDR reconstruction framework that reformulates HDR reconstruction as a Probability Flow ODE (PF-ODE) and constructs exposure-aware consistency trajectories via exposure-dependent perturbations. Specifically, a soft exposure mask is first constructed to separate the LDR image into over-, under-, and well-exposed regions. Based on this partition, region-conditioned consistency trajectories are designed to hallucinate saturated details, suppress noise in dark regions, and preserve reliable structures within a single, distillation-free inference step. To further enhance perceptual quality, we introduce an Exposure-guided Luminance-Chromaticity Loss in the CIE~$\text{L}^*\text{a}^*\text{b}^*$ space, which assigns exposure-aware weights to luminance and chromaticity components, effectively mitigating brightness bias and color drift. Extensive experiments on the HDR-REAL, HDR-EYE, and AIM2025 benchmarks demonstrate that ExpoCM achieves state-of-the-art fidelity and perceptual accuracy, while enabling over 400$\times$ and 20$\times$ faster inference compared to DDPM (1000 steps) and DDIM (50 steps), respectively.
Authors: Mete Ahishali, Anis Ur Rahman, Einari Heinaro, Aysen Degerli, Samuli Junttila
Abstract: Mapping standing dead trees is crucial for acquiring information on the effects of climate change on forests and forest biodiversity. However, leveraging high-quality aerial imagery for dead tree segmentation poses challenges due to limitations in sensor availability and the scarcity of annotated data. In this study, we propose a generic blind super-resolution framework that incorporates Attention-Guided Domain Adaptation Networks (ADA-Nets) to learn the mapping from low-resolution to high-resolution multispectral image domains. Our approach operates solely on unpaired samples, mimicking real-world conditions, i.e., low-resolution images are not synthetically obtained by downsampling the high-resolution images. Moreover, the proposed method serves as a general-purpose restorer addressing several image degradation types, including saturation, noise, and low contrast that typically occur in low-resolution images acquired by low-end sensors. To the best of our knowledge, this is the first study to perform real-world and generic super-resolution for multispectral data in the scope of standing dead tree segmentation. Experimental evaluations demonstrate segmentation performances of 54% and 64% in Dice scores. Notably, the first result is obtained without using any high-resolution annotations; the segmentation network is trained on super-resolved low-resolution images, while evaluation is performed on the high-resolution data. We publicly share the aerial multispectral dataset with manually annotated labels at https://www.kaggle.com/datasets/meteahishali/aerial-imagery-for-dead-tree-segmentation-poland.
URLs: https://www.kaggle.com/datasets/meteahishali/aerial-imagery-for-dead-tree-segmentation-poland.
Authors: Xinyi Yin, Yiduo Wang, Tingqi Hu, Meicong Si, Yunyun Shi, Shi Chen, Hao Wang, Junxiao Xue, Xuecheng Wu
Abstract: Affective image editing (AIE) aims to edit visual content to evoke target emotions. However, existing methods often overlook inference efficiency and predominantly depend on discrete emotion representations, which to some extent limits their practical applicability and makes it challenging to capture complex and subtle human emotions. To tackle these gaps, we propose MooD, the first framework that directly leverages continuous Valence-Arousal (VA) values for fine-grained and efficient AIE. Specifically, we first introduce a VA-Aware retrieval strategy to bridge vague affective values and concrete visual semantics. Building upon this, MooD integrates visual transfer and semantic guidance to achieve controllable AIE. Furthermore, we construct AffectSet, a VA-annotated dataset to support model optimization and evaluation. Extensive qualitative and quantitative experimental results demonstrate that our MooD achieves superior performance in both affective controllability and visual fidelity while maintaining high efficiency. A series of ablation studies further reveal the crucial factors of our design. Our code and data will be made publicly open soon.
Authors: Tzu-Yu Liu, Duan-Shin Lee
Abstract: Accurate badminton stroke prediction is crucial for fine-grained sports analysis and tactical decision support. However, existing methods struggle to model rich temporal context. This paper introduces \emph{TemPose-TF-ASF (Adjacent-Stroke Fusion)}, a context-aware extension of \emph{TemPose}. It enhances stroke recognition by incorporating stroke-type information from both preceding and subsequent strokes. A two-stage training and inference strategy is adopted. Preliminary predictions from the baseline model are reused as estimated temporal context. These predictions guide the joint optimization of the \emph{ASF} module and the classifier. By explicitly modeling bidirectional temporal stroke dependencies, the proposed method can be seamlessly integrated into existing state-of-the-art models. Experiments on a large-scale badminton match dataset show consistent improvements over the baseline and its variants in terms of Accuracy and Macro-F1. Moreover, integrating \emph{ASF} into other advanced methods yields notable performance gains. These results demonstrate strong transferability and generalization capability.
Authors: Carmelo Scribano, Giovanni Cappelletti, Elia Giacobazzi, Giorgia Franchini, Paolo Burgio, Marko Bertogna
Abstract: Road traffic accidents remain a significant global concern, with the majority attributed to human factors such as driver distraction and fatigue. This study proposes a camera-based approach to derive useful indicators to assess driver attentiveness and alertness. The proposed pipeline jointly satisfies the stringent real-time requirements imposed by the critical application and minimizes the computational requirements to allow for deployment on a tight computational budget. To this end, we develop a lightweight multi-task neural network that predicts multiple indicators for the face region in a single forward pass. The developed model is integrated into a complete execution workflow to produce a real-time estimate of attentiveness, fatigue, and engagement in distracting activities.
Authors: Thanasis Pantsios, Dimitrios Karageorgiou, Christos Koutlis, George Karantaidis, Olga Papadopoulou, Symeon Papadopoulos
Abstract: The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and when encountering newly emerging generative models. In this work, we propose a data-centric continual adaptation framework for updating detectors in evolving environments. We show that both in-the-wild data and generator-driven data are essential for adapting detectors. We introduce an automated, weakly supervised pipeline for constructing in-the-wild datasets through fact-check article retrieval. Additionally, we demonstrate that incorporating even a small amount of generator-driven data during training enables effective adaptation to newly emerging models, while combining it with in-the-wild data within a continual learning framework enables robust adaptation and mitigates catastrophic forgetting. Extensive experiments on two state-of-the-art detectors show significant improvements of +9.14% and +8% in average accuracy, respectively.
Authors: Yinzhe Wu, Hongyu Rui, Fanwen Wang, Jiahao Huang, Zi Wang, Guang Yang
Abstract: Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction, representing a massive acceleration. Our model, an MLP conditioned on a b=0 structural prior and the b-direction via FiLM, is trained end-to-end on the anisotropic input. The framework not only accurately reconstructs the trained b-directions (spatial SR) but also learns a continuous q-space representation, enabling high-fidelity "zero-shot" synthesis of unseen b-directions (angular SR). On simulated data, our method achieved high fidelity for both trained (34.82 dB) and unseen (33.08 dB) directions. Most importantly, the synthesized angular data also improved the quantitative accuracy of downstream DTI model fitting. Our SA-INR framework breaks the classical sampling limits, paving the way for fast, quantitative high-resolution dMRI.
Authors: Yao Lu, Rohit Mohan, Florian Drews, Yakov Miron, Abhinav Valada
Abstract: Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) aims to segment known thing and stuff classes while identifying valid unknown objects as separate instances. Prior OPS approaches largely treat known categories as a flat label set, ignoring the semantic hierarchy that provides valuable structural priors for distinguishing unknown objects from in-distribution classes. In this work, we propose Hyp2Former, an end-to-end framework for OPS that does not require explicit modeling of unknowns during training, and instead learns hierarchical semantic similarities continuously in hyperbolic space. By explicitly encoding hierarchical relationships among known categories, the model learns a structured embedding space that captures multiple levels of semantic abstraction. As a result, unknown objects that cannot be confidently classified as known categories still remain in close proximity to higher-level concepts (e.g., an unknown animal remains closer to "animal" or "object" than to unrelated concepts such as "electronics" or "stuff") and can therefore be reliably detected, even if their fine-grained category was not represented during training. Empirical evaluations across multiple public datasets such as MS COCO, Cityscapes, and Lost&Found demonstrate that Hyp2Former outperforms existing methods on OPS, achieving the best balance between unknown object discovery and in-distribution robustness.
Authors: Max Reimann, Benito Buchheim, J\"urgen D\"ollner
Abstract: Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained parametric control of stylistic attributes in latent diffusion models by learning disentangled editing directions from synthetic datasets. We use guidance composition to close the domain gap between stylistically finetuned and foundation models, preserving the original image semantics while applying stylistic adjustments. To ensure consistent edits, we introduce a training regularization loss and enhance DDIM inversion with optimized null-conditional embeddings for real image editing. We validate our approach by learning from stylistically filtered synthetic datasets varying a range of stylistic attributes, including outlines, local contrast, watercolorization effects, and geometric patterns. Our evaluations demonstrate that compared to current text-based editing techniques, our method offers well-integrated, more precise and continuously adjustable stylistic modifications.
Authors: Jintao Guo, Lin Wang, Shumeng Li, Jian Zhang, Yulin Zhou, Luyang Cao, Hairong Zheng, Yinghuan Shi
Abstract: Existing cross-subject fMRI decoding methods typically train a model on multiple scanned subjects and then adapt it to a new subject using substantial paired fMRI-image data. However, in realistic scenarios, new-subject fMRI data are often limited due to costly data acquisition, and raw data from previous subjects may be inaccessible, leading existing methods to suffer performance degradation during new-subject adaptation. In this paper, we identify that this degradation stems from two key issues: brain-side instability caused by large subject differences in fMRI responses, and image-side supervision unreliability caused by fine-grained visual details that are not reliably supported by limited fMRI signals. To address these challenges, we propose StableMind, a regularized adaptation framework designed to improve brain-side representation stability and image-side supervision reliability. (1) To stabilize brain representations, StableMind reuses ridge projections from the pretrained model as adaptation priors to constrain limited-data new-subject adaptation, and applies Fourier-based feature-level brain augmentation to improve robustness to individual variability. (2) To improve image supervision reliability, StableMind introduces difficulty-aware image blur for brain-image alignment, reducing the influence of fine-grained visual details that are weakly supported by limited fMRI signals while preserving stable visual structure. Experiments on the Natural Scenes Dataset under a unified 1-hour adaptation protocol demonstrate that StableMind achieves 84.02% image retrieval accuracy and 81.66% brain retrieval accuracy averaged over four subjects, surpassing the state-of-the-art method by 5.71% brain retrieval accuracy with fewer trainable adaptation parameters. Our code is available at https://github.com/lingeringlight/StableMind.
Authors: Hedi Tabia, D\'esir\'e Sidib\'e, Nawres Khlifa, Ahmed Tabia, Ines Rahmany, Noura Aboudi, Zainab Haddad, Hajer Khachnaoui, Hsouna Zgolli
Abstract: Optical Coherence Tomography (OCT) has become one of the most used imaging modality in ophthalmology. It provides high-resolution, non-invasive visualization of retinal microarchitecture. The automated analysis of OCT images through representation learning has emerged as a central research frontier. This has mainly been driven by the clinical need to process large acquisition volumes. The objective is to reduce the reliance on expert annotation, and improve diagnostic consistency across devices and populations. This survey provides a comprehensive and structured review of representation learning methods for retinal OCT image analysis. It covers the period from early deep learning approaches to the most recent developments in foundation models and vision-language systems. We organize the literature along a principled taxonomy of learning paradigms, encompassing supervised learning with CNN-based and transformer-based architectures, self-supervised and semi-supervised methods, generative approaches, as well as 3D volumetric modeling, multimodal representation learning, and large-scale pretrained foundation models. For each paradigm, we analyze the core methodological contributions, identify persistent limitations, and trace the connections between successive approaches. We further provide a structured overview of publicly available OCT datasets, discuss evaluation protocol considerations, and present a unified problem formulation that situates each learning paradigm within a common mathematical framework. Building on this analysis, we identify and discuss the most pressing open research directions emerging in the literature. This includes volumetric foundation model pretraining, uncertainty-aware representation learning, federated and privacy-preserving training, fairness and bias mitigation, concept-based interpretability,...
Authors: Zhou Bingtao, Xiang Mian, Ning Qian
Abstract: Source-Free Domain Adaptation (SFDA) adapts source models to target domains without accessing source data, addressing privacy and transmission issues. However, existing methods still initialize from a source pre-trained model and thus are not truly source-free. Recent works have introduced Vision-Language (ViL) models to guide the adaptation process, in these methods, we observe that for the same target domain, different source models yield minimal variation in final results, indicating the source model itself has limited impact. Motivated by this, we propose ViL-Only Domain Adaptation (VODA) , a stricter setting that eliminates all dependencies on source domain, relying solely on a randomly initialized model, a ViL model, and unlabeled target data. We analyze the adaptation dynamics of VODA and introduce Two-Stage Denoised-Region Distillation (TS-DRD) , a two-stage framework that first warms up the model with ViL guidance, then seek a Denoised-Region inherent in both the ViL and adapting model, yielding cleaner supervision for distillation. Experiments on Office-Home, VisDA, and DomainNet-126 show that under VODA, TS-DRD achieves competitive or superior performance to existing SFDA methods that still use source models, demonstrating its effectiveness and the potential of the VODA setting.
Authors: Xiaoyi Ji, Renata Zelic, Oskar Aspegren, Nita Mulliqi, Michelangelo Fiorentino, Francesca Giunchi, Luca Molinaro, Sol Erika Boman, Lorenzo Richiardi, Andreas Pettersson, Per Henrik Vincent, Martin Eklund, Olof Akre, Kimmo Kartasalo
Abstract: Artificial intelligence (AI) is becoming a clinical tool for prostate pathology, but generalization across variations in sample preparation and preservation over prolonged time periods remains poorly understood. We evaluated GleasonAI, an end-to-end attention-based multiple instance learning model, on an independent validation cohort comprising 10,366 biopsy cores from 1,028 patients across 14 Swedish regions, using archival diagnostic specimens from the ProMort cohorts collected between 1998-2015. The model achieved an overall quadratic-weighted kappa of 0.86 for core-level ISUP grading, comparable to several experienced pathologists and consistent across geographic regions. Notably, performance remained stable across the 17-year collection period, demonstrating robustness to time-related variation in archival material, a property not consistently observed with foundation model-based approaches, with exploratory analysis demonstrating a significant prognostic gradient across AI-assigned grade groups for prostate cancer-specific mortality. These findings support the generalizability of the AI grading model and demonstrate the potential of pathology archives as a large-scale resource for AI development, validation, and retrospective prognostic research.
Authors: Morteza Moradi, Mohammad Moradi, Simone Palazzo, Ali Borji, Concetto Spampinato
Abstract: Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM exhibit strong generalization, their potential for SOD is not fully realized, and training or fully fine-tuning them is computationally expensive and prone to overfitting under limited data. To overcome these challenges, we introduce GLASSNet, a Global-Local feature decoding framework that uses SAMv2 as a frozen encoder paired with a lightweight, spatially aware convolutional adapter-reducing learnable encoder parameters by over 97%. To enhance saliency quality, GLASSNet employs a dual-decoder architecture: one decoder captures global, long-range semantics with an expanded receptive field, while the other captures fine local details such as edges and textures. Fusing these complementary cues yields saliency maps that combine global coherence with local precision, producing accurate final masks. Extensive experiments on standard SOD and camouflaged object detection benchmarks show that GLASSNet surpasses state-of-the-art methods, demonstrating the power of frozen foundation models combined with targeted adaptation and global-local decoding.
Authors: Yiming Ding, Siyu Cao, Luyuan Jiao, Yixuan Li, Zitong Wang, Zhiyong Liu, Lu Zhang
Abstract: Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each query. This assumption does not always hold in real-world scenarios, where queries may correspond to multiple or no moments. Thus, we formulate Generalized Moment Retrieval (GMR), a unified setting that requires retrieving the complete set of relevant moments or predicting an empty set. To enable systematic study of GMR, we introduce Soccer-GMR, a large-scale benchmark built on challenging soccer videos that reflect general GMR scenarios, with realistic negative and positive queries. The benchmark is constructed via a duration-flexible semi-automated pipeline with human verification, enabling scalable data generation while maintaining high annotation quality. We further design a unified evaluation protocol with complementary metrics tailored for null-set rejection, positive-query localization, and end-to-end GMR performance. Finally, we establish strong baselines across two modeling paradigms: a lightweight plug-and-play GMR adapter for discriminative VMR models, and a GMR-tailored GRPO reward for fine-tuning multimodal large language models (MLLMs). Extensive experiments show consistent gains across all metrics and expose key limitations of current methods, positioning GMR as a more realistic and challenging benchmark for video-language understanding.
Authors: Guangrui Bai, Yifan Mei, Yahui Deng, Yuhan Chen, Yuze Qiu, Wenhai Liu, Erbao Dong
Abstract: Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the proposed method achieves competitive or superior quantitative and visual performance, reaching 29.71 dB PSNR and 0.89 SSIM on LOLv2-Real. DarkFace experiments further indicate improved downstream face detection under low-light conditions. Code and pretrained models are available at: https://github.com/mubaisam/ICD.
Authors: Ruilin Yao, Shegnwu Xiong, Tianyu Zou, Shili Xiong, Yi Rong
Abstract: Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and small interactive elements expose a resolution gap between modern displays and model input constraints. Existing zoom-in strategies rely on fixed anchors, heuristic grids, or reinforcement learning, lacking a principled mechanism to adaptively determine where refinement is needed and how much spatial uncertainty should be explored. We propose AutoFocus, a training-free, uncertainty-aware active visual search framework for GUI grounding. Our key insight is that token-level perplexity in coordinate generation naturally reflects spatial uncertainty. Rather than committing to a single prediction, AutoFocus samples multiple coordinate hypotheses and converts their axial perplexities into an anisotropic gaussian spatial probability field, explicitly modeling directional uncertainty. Based on this field, we generate global and local region proposals and introduce Shape-Aware Zooming to balance tight localization with contextual preservation. A visual prompt-based aggregation step then selects the most consistent prediction via structured comparison. Extensive experiments on ScreenSpot-Pro and ScreenSpot-V2 demonstrate consistent improvements across both general-purpose and GUI-specialized VLMs.
Authors: Jiawei Ge, Xintian Zhang, Jiuxin Cao, Bo Liu, Fabian Deuser, Chang Liu, Gong Wenkang, Siyou Li, Juexi Shao, Wenqing Wu, Chen Feng, Ioannis Patras
Abstract: Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. Despite recent progress, existing methods rely heavily on costly frame-level spatial annotations and cross-view identity supervision. To reduce such reliance, we explore CRMOT under weak supervision by leveraging the capabilities of foundation models. However, our empirical study shows that directly applying foundation models such as SAM2 and SAM3, even with task-specific modifications, fails to accurately understand referring expressions and maintain consistent identities across views. Yet, they remain effective at producing reliable object tracklets that can serve as pseudo supervision. We therefore repurpose foundation models as pseudo-label generators and propose a two-stage framework for weakly supervised CRMOT, using only object category labels as coarse-grained supervision. In the first stage, we design an Affinity-guided Cross-view Re-prompting strategy to refine and associate SAM3-generated tracklets across cameras, producing reliable cross-view pseudo labels for subsequent training. In the second stage, we introduce ViewSAM, a CRMOT model built upon SAM2 that explicitly models view-aware cross-modal semantics. By formulating view-induced variations as learnable conditions, ViewSAM bridges the gap between view-variant visual observations and view-invariant textual expressions, enabling robust cross-view referring tracking with only approximately 10% additional parameters. Extensive experiments demonstrate that ViewSAM achieves SOTA performance under weak supervision and remains competitive with fully supervised methods.
Authors: Yangming Shi, Shixiang Zhu, Tao Shen, Zhimiao Yu, Dengsheng Chen, Taicai Chen, Yunfei Yang, Juan Zhou, Chen Cheng, Liang Ma, Xibin Wu, Benxuan Yan, Ge Li, Tuoyu Zhang, Dan Li, Chang Liu, Zhenbang Sun
Abstract: We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the model's generation capability, we equip the Diffusion Transformer backbone with a fine-grained Mixture-of-Experts (MoE) design (128 experts, Top-8 routing), yielding a 25B-parameter model that activates only 3B parameters, significantly reducing training costs while scaling up the model capacity. Mamoda2.5 achieves top-tier generation performance on VBench 2.0 and sets a new record in video editing quality, surpassing evaluated open-source models and matching the performance of current top-tier proprietary models, including the Kling O1 on OpenVE-Bench. Furthermore, we introduce a joint few-step distillation and reinforcement learning framework that compresses the 30-step editing model into a 4-step model and greatly accelerates model inference. Compared to open-source baselines, Mamoda2.5 achieves up to $95.9\times$ faster video editing inference. In real-world applications, Mamoda2.5 has been successfully deployed for content moderation and creative restoration tasks in advertising scenarios, achieving a 98% success rate in internal advertising video editing scenario.
Authors: Luis Angel Aparicio Borjas, Victor Elias Nieto, Juan Irving Vasquez, Alfonso Fernandez-Vazquez, Gerardo Antonio Alvarez Hernandez
Abstract: Physical violence in public spaces is a significant public health concern, with minor incidents such as pushing often serving as precursors to more severe escalations. This research develops an automated system for the real-time detection of moderate physical violence, specifically pushing, in surveillance camera footage. The proposed solution integrates state-of-the-art computer vision models, utilizing YOLO11 and YOLO11-Pose for human detection and skeletal keypoint extraction. By calculating body inclination and joint angles between shoulders and hips, a Random Forest classifier was trained to distinguish between normal behavior and aggressive physical contact. The system's performance was evaluated through three progressive case studies representing increasing levels of difficulty. In controlled environments with frontal views, the model achieved a precision of 0.98. In the most challenging scenario, featuring high-altitude, steep-angle recordings from real-world surveillance infrastructure, the system maintained a precision of 0.72 despite significant perspective distortion and visual noise. These results demonstrate the feasibility of using skeletal analysis for early violence intervention in urban security contexts.
Authors: Tienyu Chang, Tianhao Li, Ruogu Fang, Jiang Bian, Yu Huang
Abstract: Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolution visualization of retinal layers. While deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, its "black box" nature poses challenges for clinical adoption, where explainability is essential for clinical trust and regulatory approval. Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise, limiting the trustworthiness of their explanations. To bridge these gaps, we propose a Structure-Aware Interpretable Learning (SAIL) framework that integrates retinal anatomical priors at the representation level and couples them with semantic features via a fusion design. Without modifying standard post-hoc explainability methods, this representation yields sharper and more anatomically aligned attribution maps. Comprehensive experiments on diverse OCT datasets demonstrate that our structure-aware method consistently enhances interpretability, producing clinically meaningful and anatomy-aware explanations. Ablation studies further show that strong interpretability requires both structural priors and semantic features, and that properly fusing the two is critical to achieve the best explanation quality. Together, these results highlight structure-aware representations as a key step toward reliable explainability in OCT.
Authors: Tienyu Chang, Zhen Chen, Renjie Liang, Jinyu Ding, Jie Xu, Sunu Mathew, Amir Reza Hajrasouliha, Andrew J. Saykin, Ruogu Fang, Yu Huang, Jiang Bian, Qingyu Chen
Abstract: The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations from large-scale unlabeled datasets. However, current ophthalmic AI paradigms are predominantly constrained to single-modality inference, thereby creating a dissonance with clinical practice where diagnosis relies on the synthesis of complementary imaging modalities. Furthermore, the deployment of high-performance AI in resource-limited settings is frequently impeded by the unavailability of advanced three-dimensional imaging hardware. Here, we present the Ophthalmic multimodal Masked Autoencoder (OphMAE), a multi-imaging foundation model engineered to synergize the volumetric depth of 3D Optical Coherence Tomography (OCT) with the planar context of 2D en face OCT. By implementing a novel cross-modal fusion architecture and a unique adaptive inference mechanism, OphMAE was pre-trained on a massive dataset with of 183,875 paired OCT images derived from 32,765 patients. In a rigorous benchmark encompassing 17 diverse diagnostic tasks with 48,340 paired OCT images from 8,191 patients, the model demonstrated state-of-the-art performance, achieving an Area Under the Curve (AUC) of 96.9% for Age-related Macular Degeneration (AMD) and 97.2% for Diabetic Macular Edema (DME), consistently surpassing existing single-modal and multimodal foundation models. Crucially, OphMAE exhibits robust engineering adaptability: it maintains high diagnostic accuracy, such as 93.7\% AUC for AMD, even when restricted to single-modality 2D inputs, and demonstrates exceptional data efficiency by retaining 95.7% AUC with as few as 500 labeled samples. This work establishes a scalable and adaptable framework for ophthalmic AI, ensuring robust performance across different tasks.
Authors: Verena Jasmin Hallitschke, Carsten Eickhoff, Philipp Berens
Abstract: Vision-language models hold considerable promise for ophthalmology, but their development depends on large-scale, high-quality image-text datasets that remain scarce. We present PubMed-Ophtha, a hierarchical dataset of 102,023 ophthalmological image-caption pairs extracted from 15,842 open-access articles in PubMed Central. Unlike existing datasets, figures are extracted directly from article PDFs at full resolution and decomposed into their constituent panels, panel identifiers, and individual images. Each image is annotated with its imaging modality -- color fundus photography, optical coherence tomography, retinal imaging, or other -- and a mark status indicating the presence of annotation marks such as arrows. Figure captions are split into panel-level subcaptions using a two-step LLM approach, achieving a mean average sentence BLEU score of 0.913 on human-annotated data. Panel and image detection models reach a mAP@0.50 of 0.909 and 0.892, respectively, and figure extraction achieves a median IoU of 0.997. To support reproducibility, we additionally release the human-annotated ground-truth data, all trained models, and the full dataset generation pipeline.
Authors: Yangfu Li, Yuning Gong, Hongjian Zhan, Teng Li, Yuanhuiyi Lyu, Tianyi Chen, Qi Liu, Ziyuan Huang, Zhihang Zhong, Dandan Zheng, Yue Lu
Abstract: Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that such supervision is typically suboptimal: it is biased toward geometric precision and offers limited reasoning utility. To bridge this gap, we propose Perceptual Flow Network (PFlowNet), which eschews rigid alignment with the expert priors and achieves interpretable yet more effective visual reasoning. Specifically, PFlowNet decouples perception from reasoning to establish a self-conditioned generation process. Based on this, it integrates multi-dimensional rewards with vicinal geometric shaping via variational reinforcement learning, thereby facilitating reasoning-oriented perceptual behaviors while preserving visual reliability. PFlowNet delivers a provable performance guarantee and competitive empirical results, particularly setting new SOTA records on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).
Authors: Romain Valabregue, Ines Khemir, Eric Badinet, Fran\c{c}ois Rousseau, Guillaume Auzias, Reuben Dorent
Abstract: Synthetic training has recently advanced brain MRI segmentation by enabling contrast-agnostic models trained entirely on generated data. However, most existing approaches rely on hundreds of automatically labeled templates, introducing systematic biases and limiting their flexibility to incorporate new anatomical structures. We present the Segment It All Model (SIAM), a 3D whole-head segmentation framework for 16 anatomical structures, trained using only six high-quality, manually annotated templates. SIAM extends domain randomization to both intensity and shape domains: synthetic image generation ensures contrast variability, while high-resolution spatial transformations model anatomical differences in cortical thickness and deep nuclei morphology. Unlike prior synthetic models, SIAM simultaneously segments brain as well as extra-cerebral tissues, including cerebrospinal fluid, vessels, dura mater, skull, and skin, enabling fully automated, preprocessing-free analysis. Evaluation across eight heterogeneous datasets (N=301), that include multiple contrasts (T1-weighted, T2-weighted, CT) and span a wide range of ages, demonstrates that SIAM matches or outperforms state-of-the-art methods for brain structures, in addition to extending automated segmentation to non-brain structures. The model also exhibits superior consistency across contrasts and repeated acquisitions, together with improved sensitivity to subtle gray matter atrophy. We openly release the model and the label templates at https://github.com/romainVala/SIAM.
Authors: Fatih Aksu, Laura Ciuffetti, Francesco Di Feola, Filippo Ruffini, Giulia Romoli, Fabrizia Gelardi, Arturo Chiti, Valerio Guarrasi, Paolo Soda
Abstract: Accurate histological differentiation between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) is critical for personalized treatment in non-small cell lung cancer (NSCLC). While [$^{18}$F]FDG PET/CT is a standard tool for the clinical evaluation of lung cancer, its utility is often limited by high costs and radiation exposure. In this paper, we investigate the feasibility of "virtual scanning" as a feature-enhancement strategy by evaluating whether synthetic PET data can provide complementary feature representations to supplement anatomical CT scans in histological subtype classification. We propose a framework that leverages a 3D Pix2Pix Generative Adversarial Network (GAN), pretrained on the FDG-PET/CT Lesions dataset, to synthesize pseudo-PET volumes from anatomical CT scans. These synthetic volumes are integrated with structural CT data within the MINT framework, a multi-stage intermediate fusion architecture. Our experiments, conducted on a multi-center dataset of 714 subjects, demonstrate that the inclusion of synthetic metabolic features significantly improves classification performance over a CT-only baseline. The multimodal approach achieved a statistically significant increase in the Area Under the Curve (AUC) from 0.489 to 0.591 and improved the Geometric Mean (GMean) from 0.305 to 0.524. These results suggest that synthetic PET scans provide discriminatory metabolic cues that enable deep learning models to exploit complementary cross-modal information, offering a potential feature-enhancement strategy for clinical scenarios where physical PET scans are unavailable.
Authors: Giacomo Pacini, Luca Ciampi, Nicola Messina, Nicola Tonellotto, Giuseppe Amato, Fabrizio Falchi
Abstract: Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language prompts. However, current evaluation protocols primarily focus on standard counting errors within single-category images, overlooking a fundamental requirement: the ability to correctly ground the textual prompt in the visual scene. In this paper, we show that several state-of-the-art CAC models often struggle to determine which object class should be counted based on the given prompt, revealing a misalignment between textual semantics and visual object representations. This limitation leads to spurious counting responses and reduced reliability in real-world scenarios. To systematically address these limitations, we propose a new evaluation framework focused on model robustness and trustworthiness. Our contribution is two-fold: (i) we introduce PrACo++ (Prompt-Aware Counting++), a novel test suite featuring two dedicated evaluation protocols -- the negative-label test and the distractor test -- paired with new specialized metrics; and (ii) we present the MUCCA (MUlti-Category Class-Agnostic counting) evaluation dataset, a new collection of real-world images featuring multiple annotated object categories per scene, unlike existing CAC benchmarks that typically include a single category per image. Our extensive experimental evaluation of 10 state-of-the-art methods shows that, despite strong performance under standard counting metrics, current models exhibit significant weaknesses in understanding and grounding object class descriptions. Finally, we provide a quantitative analysis of how semantic similarity between prompts influences these failures. Overall, our results underscore the need for more semantically grounded architectures and offer a reliable framework for future assessment in open-world text-guided CAC methods.
Authors: Chenyu Hui, Xiaodi Huang, Siyu Xu, Yunke Wang, Shan You, Fei Wang, Tao Huang, Chang Xu
Abstract: Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited environmental diversity, resulting in weak real-world generalization. We present an efficient video augmentation framework that converts simulated VLA videos into realistic training videos while preserving task semantics and action trajectories. Our pipeline extracts structured conditions from simulation via video semantic segmentation and video captioning, rewrites captions to diversify environments, and uses a conditional video transfer model to synthesize realistic videos. To make augmentation practical at scale, we introduce a diffusion feature-reuse mechanism that reuses video tokens across adjacent timesteps to accelerate generation, and a coreset sampling strategy that identifies a compact, non-redundant subset for augmentation under limited computation. Extensive experiments on Robotwin 2.0, LIBERO, LIBERO-Plus, and a real robotic platform demonstrate consistent improvements. For example, our method improves RDT-1B by 8% on Robotwin 2.0, and boosts $\pi_0$ by 5.1% on the more challenging LIBERO-Plus benchmark. Code is available at: https://github.com/nanfangxiansheng/Seeing-Realism-from-Simulation.
URLs: https://github.com/nanfangxiansheng/Seeing-Realism-from-Simulation.
Authors: Zongzheng Zhang, Sizhe Zou, Guantian Zheng, Zhenxin Zhu, Yu Gao, Guoxuan Chi, Shuo Wang, Yuwen Heng, Zhigang Sun, Yiru Wang, Hao Sun, Chao Ma, Zhen Li, Anqing Jiang, Hao Zhao
Abstract: Online mapping and end-to-end (E2E) planning in autonomous driving remain largely sensor-centric, leaving rich map priors, including HD/SD vector maps, rasterized SD maps, and satellite imagery, underused because of heterogeneity, pose drift, and inconsistent availability at test time. We present UMPE, a Unified Map Prior Encoder that can ingest any subset of four priors and fuse them with BEV features for both mapping and planning. UMPE has two branches. The vector encoder pre-aligns HD/SD polylines with a frame-wise SE(2) correction, encodes points via multi-frequency sinusoidal features, and produces polyline tokens with confidence scores. BEV queries then apply cross-attention with confidence bias, followed by normalized channel-wise gating to avoid length imbalance and softly down-weight uncertain sources. The raster encoder shares a ResNet-18 backbone conditioned by FiLM with scaling and shift at every stage, performs SE(2) micro-alignment, and injects priors through zero-initialized residual fusion, so the network starts from a do-no-harm baseline and learns to add only useful prior evidence. A vector-then-raster fusion order reflects the inductive bias of geometry first, appearance second. On nuScenes mapping, UMPE lifts MapTRv2 from 61.5 to 67.4 mAP (+5.9) and MapQR from 66.4 to 71.7 mAP (+5.3). On Argoverse2, UMPE adds +4.1 mAP over strong baselines. UMPE is compositional: when trained with all priors, it outperforms single-prior models even when only one prior is available at test time, demonstrating powerset robustness. For E2E planning with the VAD backbone on nuScenes, UMPE reduces trajectory error from 0.72 to 0.42 m L2 on average (-0.30 m) and collision rate from 0.22% to 0.12% (-0.10%), surpassing recent prior-injection methods. These results show that a unified, alignment-aware treatment of heterogeneous map priors yields better mapping and better planning.
Authors: Hsin-Jui Pan, Sheng-Wei Chan, Meng-Qian Li, Chun-Po Shen
Abstract: We present FoR-Net, a lightweight architecture for semantic segmentation that focuses on identifying and enhancing hard regions. Instead of relying on heavy global modeling, FoR-Net adopts an efficient strategy that selectively emphasizes informative regions through a learned importance map and a Top-K activation mechanism. Specifically, a selector module predicts region-wise importance, enabling the model to focus on challenging areas such as thin structures and object boundaries. Multi-scale reasoning is achieved using convolutional branches with different receptive fields, allowing diverse spatial context aggregation. We evaluate FoR-Net on the Cityscapes benchmark under limited computational resources. Despite its lightweight design and standard training configuration, FoR-Net achieves competitive performance and demonstrates improved consistency in challenging regions. These results suggest that region-focused reasoning provides a simple yet effective inductive bias for efficient semantic segmentation.
Authors: Sowmya Vajrala, Akshay Bankar, Manjunath Arveti, Shreyas Pandith, Sravanth Kodavanti, Subhajit Sanyal, Amit Unde, Srinivas Soumitri Miriyala
Abstract: Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensive for practical deployment. In this work, we present TOC-SR, a framework for building efficient one-step super-resolution models by first discovering a compact diffusion backbone. Starting from a sixteen-channel latent diffusion model, we construct parameter-efficient surrogate blocks using feature-wise generative distillation and perform architecture discovery using epsilon-constrained Bayesian Optimization to minimize model complexity while preserving generative fidelity. The resulting compact diffusion backbone achieves a 6.6x reduction in parameters and a 2.8x reduction in GMACs compared to the expanded diffusion model. We then adapt this backbone for super-resolution and distill the diffusion process into a single-step generator. Experiments demonstrate that the proposed approach enables efficient super-resolution while maintaining strong reconstruction quality.
Authors: Yining Li, Dongchen Han, Zeyu Liu, Hanyi Wang, Yulin Wang, Gao Huang
Abstract: While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We identify Test-Time Training (TTT) as a linear-complexity architecture whose two-layer dynamic formulation is structurally aligned with Softmax attention, enabling direct inheritance of pretrained attention weights. To further align representational properties, including key shift-invariance and locality, we introduce key instance normalization and a lightweight locality enhancement module. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T$^5$ (Transformer To Test Time Training). With only 1 hour of fine-tuning on 4$\times$H20 GPUs, SD3.5-T$^5$ achieves comparable text-to-image quality to the fine-tuned Softmax model, while accelerating inference by 1.32$\times$ and 1.47$\times$ at 1K and 2K resolutions.
Authors: Yeheng Zong, Pou-Chun Kung, Yike Pan, Seth Isaacson, Yizhou Chen, Ram Vasudevan, Katherine A. Skinner
Abstract: Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interest in building realistic human avatars from video, this paper demonstrates that existing methods do not accurately recover the 3D geometry of humans. ViT-based approaches are not consistently reliable and can overfit to 2D views, while NeRF- and Gaussian Splatting-based avatars treat pose and appearance separately, limiting rendering generalization to new poses. To resolve these shortcomings, this paper proposes HumanSplatHMR, a joint optimization framework that refines 3D human poses while simultaneously learning a high-fidelity avatar for novel-view and novel-pose synthesis. Our key insight is to close the loop between geometric pose estimation and differentiable rendering. Unlike prior human avatar methods that rely on accurate human pose obtained through motion capture systems or offline refinement, which are impractical in in-the-wild scenarios, our approach uses only human mesh estimates from a state-of-the-art human pose estimator to better reflect real-world conditions. Therefore, instead of using the human pose only as a deformation prior, HumanSplatHMR backpropagates photometric, segmentation, and depth losses through a differentiable renderer to the pose parameters and global position. This coupling refines the global 3D pose over time, improving accuracy and alignment while producing better renderings from novel views. Experiments show consistent improvements over pose recovery baselines that omit image-level refinement and avatar baselines that decouple pose estimation from avatar reconstruction.
Authors: Srinivas Soumitri Miriyala, Sowmya Vajrala, Sravanth Kodavanti, Vikram Nelvoy Rajendiran, Sharan Kumar Allur
Abstract: We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving runtime efficiency on edge hardware. While transformers provide strong global modeling through self-attention, their attention kernels incur substantial latency on mobile devices, especially for high-resolution inputs. In contrast, SSMs such as Mamba offer lineartime sequence modeling with lower runtime overhead but may underperform on fine grained restoration tasks. To balance accuracy and efficiency, we train lightweight SSM blocks as feature-distilled surrogates of transformer blocks and use them to construct hybrid U-Net-style architectures. To automatically discover effective block combinations, we introduce Efficient Network Search (ENS), a multi-objective search strategy that selects task-specific hybrid configurations from pre-aligned components. ENS optimizes restoration quality while penalizing transformer usage, serving as a lightweight proxy for latency and enabling architecture discovery without repeated hardware profiling. On a Snapdragon 8 Elite CPU, the Restormer baseline requires 10119.52 ms for inference. In contrast, ENS-discovered hybrids significantly reduce runtime: ENS-Deblurring runs in 2973 ms (3.4x faster), ENS-Deraining in 5816 ms (1.74x faster), and ENS-Denoising in 8666 ms (1.17x faster), while maintaining competitive restoration quality.
Authors: Axi Niu, Jinyang Zhang, Senyan Qing
Abstract: Blind face restoration is highly ill-posed under severe degradation, where identity-critical details may be missing from the degraded input. Same-identity references reduce this ambiguity, but mismatched pose, expression, illumination, age, makeup, or local facial states can lead to overuse of reference appearance. We propose \textbf{IConFace}, a unified reference-aware and no-reference framework with identity--structure asymmetric conditioning. References are distilled into a norm-weighted global AdaFace identity anchor for image-only modulation, while the degraded image is reinforced as the spatial structure anchor through low-rank residuals and block-wise degraded cross-attention with two-route memory. The resulting single checkpoint exploits references when available and falls back to no-reference restoration when absent, improving identity consistency, fine-detail recovery, and degraded-only restoration quality in a unified model.
Authors: Tanush Yadav, Mohammadreza Salehi, Jae Sung Park, Vivek Ramanujan, Hannaneh Hajishirzi, Yejin Choi, Ali Farhadi, Rohun Tripathi, Ranjay Krishna
Abstract: Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding. Unfortunately, due to a lack of sufficiently diverse and challenging data, modern vision-language models (VLMs) are no longer evaluated on their action recognition capabilities. To revitalize action recognition in the era of VLMs, we advocate for a returned focus on domain-specific actions. To this end, we introduce VideoNet, a domain-specific action recognition benchmark covering 1,000 distinct actions from 37 domains. We begin with a multiple-choice evaluation setting, where the difference between closed and open models is stark: Gemini 3.1 Pro attains 69.9% accuracy while Qwen3-VL-8B gets a mere 45.0%. To understand why VLMs struggle on VideoNet, we relax the questions into a binary setting, where random chance is 50%. Still, Qwen achieves only 59.2% accuracy. Further relaxing the evaluation setup, we provide $k\in\{1,2,3\}$ in-context examples of the action. Some models excel in the few-shot setting, while others falter; Qwen improves $+7.0\%$, while Gemini declines $-4.8\%$. Notably, these gains fall short of the $+13.6\%$ improvement in non-expert humans when given few-shot examples. Finding that VLMs struggle to fully exploit in-context examples, we shift from test-time improvements to the training side. We collect the first large-scale training dataset for domain-specific actions, totaling nearly 500k video question-answer pairs. Fine-tuning a Molmo2-4B model on our data, we surpass all open-weight 8B models on the VideoNet benchmark.
Authors: Amirhosein Javadi, Shirin Saeedi Bidokhti, Tara Javidi
Abstract: Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work, we present ActDiff-VC, a diffusion-based video compression framework for the ultra-low-bitrate regime. Our method partitions videos into variable-length segments, transmits keyframes only when needed, and summarizes temporal dynamics using a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder synthesizes the remaining frames, enabling perceptually realistic reconstruction under severe rate constraints. To support this design, we introduce two mechanisms: content-adaptive keyframe selection and budget-aware sparse trajectory selection, which together enable compact yet effective conditioning for generative reconstruction. Experiments on the UVG and MCL-JCV benchmarks show that ActDiff-VC achieves up to 64.6\% bitrate reduction at matched NIQE, improves KID by up to 64.6\% and FID by up to 37.7\% at comparable bitrates against strong learned codecs, and delivers favorable perceptual rate--distortion trade-offs relative to learned and diffusion-based baselines in the ultra-low-bitrate regime.
Authors: Fadeel Sher Khan, Long N. Le, Abhinau K. Venkataramanan, Seok-Jun Lee, Hamid R. Sheikh
Abstract: Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores.
Authors: Baiyan Chen, Weixin Zhai
Abstract: Rural thematic road network construction aims to extract topological road structures from movement trajectory images of agricultural machinery. However, this task faces challenges where downsampling methods commonly used in existing studies tend to blur the sparse high-frequency road structures, and the heavy noise from dense field operations often leads to fragmented or redundant topologies in the extracted networks. To address these challenges, we propose LFINet, a Laplacian Frequency Interaction Network. The network begins with a Laplacian Multi-scale Separator (LMS) to decouple the image into low-frequency semantic contexts and high-frequency structural details. These components are then processed by the Cross-Frequency Interaction Block (CFIB) through a dual-pathway architecture in which a High-Frequency Block (HFB) refines local structures while a Spatial Transformer (ST) captures global semantics. Subsequently, a Frequency Gated Modulation (FGM) mechanism integrates the features from pathways by leveraging semantic contexts to calibrate the structural details. Finally, a Progressive Reconstruction Decoder iteratively fuses multi-scale features to ensure topological consistency. Experiments conducted on a real-world agricultural trajectories dataset from Henan Province, China, show that LFINet establishes a new state-of-the-art. Specifically, it achieves an F1-score of 92.54% and an IoU of 86.12%, surpassing the second-ranked method by 0.64% and 1.1%, respectively. This confirms its capability to effectively construct topological road networks from noisy and sparse field data.
Authors: Yu-Ju Tsai, Brian Price, Qing Liu, Luis Figueroa, Daniil Pakhomov, Zhihong Ding, Scott Cohen, Ming-Hsuan Yang
Abstract: Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely on generic inpainting models that often fail to maintain identity consistency, or assume that suitable reference images are explicitly provided. In practice, suitable references are often not explicitly provided, requiring the system to search for identity-consistent images within personal photo collections. We present AlbumFill, a training-free framework that retrieves identity-consistent references from personal albums for personalized completion. Given an occluded image and a personal album, a vision-language model infers missing semantic cues to guide composed image retrieval, and the retrieved references are used by reference-based completion models. To facilitate this task, we introduce a dataset containing 54K human-centric samples with associated album images. Experiments across multiple baselines demonstrate the difficulty of personalized completion and highlight the importance of identity-consistent reference retrieval. Project Page: https://liagm.github.io/AlbumFill/
Authors: Maria-Eirini Pegia, Dimitrios Stefanopoulos, Bj\"orn {\TH}\'or J\'onsson, Anastasia Moumtzidou, Ilias Gialampoukidis, Stefanos Vrochidis, Ioannis Kompatsiaris
Abstract: Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid expansion of online video. Over the past six years, research has produced numerous methods, such as dual encoders, attention-driven models, and multimodal fusion approaches; however, fundamental questions remain about model behavior, dataset influence, and query difficulty. In this work, we evaluate 14 state-of-the-art retrieval methods across 3 widely used datasets under a unified preprocessing and evaluation framework. We analyze caption characteristics, including length, clarity, semantic category, and Action vs. Scene balance, and link these to model performance. Our results show that short, clear, and simple captions, such as those describing single actions or color attributes, achieve higher recall, while complex events, multi-step activities, or fine-grained scene descriptions remain challenging for all existing models. Attention-driven architectures better handle temporally dependent or multi-step queries, whereas dual-encoder and multimodal fusion models perform well primarily on simpler or single-category captions. Cross-dataset generalization improves with larger, more diverse caption sets, but generative captions do not consistently enhance retrieval accuracy. Overall, our findings highlight key dataset factors, benchmark challenges, and the interplay between query content and model architecture, providing guidance for developing more effective text-to-video retrieval systems.
Authors: Xiaoyang Li
Abstract: EEG based phoneme decoding is promising for brain computer interfaces, but many prior studies rely on within subject evaluation, small cohorts, or weak leakage control. We present a reproducible cross subject benchmark for five class vowel decoding (a, e, i, o, u) from auditory EEG using OpenNeuro ds006104 (16 subjects, 61 channels, 256 Hz). Under strict leave one subject out evaluation with training only normalization and explicit anti leakage checks, we compare 14 pipelines from classical machine learning, deep learning, and Riemannian methods. The best full feature model (XGBoost) reaches 24.5 percent accuracy (chance 20 percent), while differential entropy features with LightGBM reach 25.5 percent in feature specific analysis. After multiple comparison correction, strong pairwise model advantages are limited. Classical methods are competitive with deep models in this low signal regime. Additional analyses (ablation, pairwise vowels, within subject CV, ERP, temporal generalization, and electrode importance) indicate that vowel information is real but weak and mainly carried by early transient auditory responses. We release code and evaluation scripts for full reproducibility.
Authors: Yingzhe Wang, Cunhua Pan, Ruijing Liu, Shaokai Li, Hong Ren, Kezhi Wang, Jiangzhou Wang
Abstract: Device-free fall detection utilizing WiFi Channel State Information (CSI) has emerged as a promising, privacy-preserving solution for elderly health monitoring in the Internet of Things (IoT) era. However, existing deep learning approaches suffer from severe performance degradation when deployed in unseen environments due to static background overfitting and Non-Line-of-Sight (NLoS) signal attenuation. To address these critical bottlenecks, we propose a robust, domain-generalizable framework featuring a novel Attention-Enhanced CNN-Transformer hybrid architecture. First, we design a physics-driven \textbf{Dynamic Variance Gate (DVG)} to dynamically calculate local temporal variance, acting as a soft-attention mask that eliminates static environmental DC components while amplifying dynamic human motion. Second, we introduce a Physics-Aware Data Augmentation strategy to force the network to learn invariant morphological signatures rather than environment-specific noise. Furthermore, a Convolutional Block Attention Module (CBAM) is integrated to refine spatiotemporal features prior to Transformer-based sequence modeling. Extensive cross-domain evaluations across four distinct indoor environments demonstrate that our method achieves 97.6\% accuracy in NLoS scenarios and 98.8\% in completely unseen environments without target-domain fine-tuning. Finally, we deploy the proposed framework on an edge computing system equipped with commercial WiFi NICs. Real-world live inference field tests confirm the system's robustness against unseen environmental layouts and its capability for continuous, low-latency whole-home safety monitoring.
Authors: Badri N. Patro, Vijay S. Agneeswaran
Abstract: State space models (SSMs) achieve linear-time complexity but struggle with multi-channel physiological signals due to three limitations: fixed kernels cannot capture multi-scale temporal dynamics (motor preparation over hundreds of milliseconds vs. execution transients in tens of milliseconds), Markovian state updates restrict global context for periodic oscillations, and channel-independent processing ignores spatial electrode topology. We introduce NAKUL, extending SSMs for medical signal analysis through three contributions: (1) Dynamic Kernel Generation-parallel SSM branches with varying kernel sizes (3, 5, 7, 11 timesteps) are weighted by a meta-network that analyzes input statistics, enabling adaptive temporal scale selection; (2) Spectral Context Modeling-FFT-based operations with learnable Gaussian frequency band filters capture global periodic patterns in $O(N \log N)$ complexity; (3) Graph-Guided Spatial Attention-fixed electrode topology provides spatial biases to multi-head attention for principled cross-channel interaction. On BCI Competition IV-2a motor imagery (our primary benchmark), NAKUL achieves 91.7$\pm$0.6\% accuracy, matching EEG-Conformer (92.1$\pm$0.7\%) while using 28\% fewer parameters (2.5M vs 3.5M) and 2.0$\times$ faster inference (4.3ms vs 8.7ms). The model generalizes to EEG emotion recognition (83.6\%), multimodal EEG-fMRI (91.4\%), and medical imaging (92.8\% on ultrasound), demonstrating architectural versatility. Ablations show dynamic kernels contribute +2.6\% and exhibit interpretable scale selection patterns correlated with known neural dynamics.
Authors: Alireza Rafiei, Anah\'i Venzor Strader, Esteban Castro Arag\'on, Victoriana Rosibely Sut Serech, Enma Carolina Coyote Ixen, Reza Sameni, Peter Rohloff, Gari D. Clifford, Nasim Katebi
Abstract: Hypertensive disorders of pregnancy remain a leading cause of maternal and fetal morbidity worldwide, yet diagnosis relies on intermittent cuff-based blood pressure measurements that are prone to bias and fail to capture continuous physiological dynamics. Growing evidence suggests that fetal cardiovascular activity is associated with maternal-placental hemodynamics and may encode markers of maternal hypertension. To analyze this, we collected a large-scale dataset of fetal one-dimensional Doppler ultrasound recordings paired with maternal blood pressure from 3,255 pregnant women across 8,170 antenatal visits in rural Guatemala. We developed AutoHyPE, a hierarchical attention network that models short- and long-term signal structure, incorporating a novel prototype-based contrastive learning and multi-view strategy to enhance representation robustness under long-tailed class distribution and biological variability. AutoHyPE achieved an AUROC of 0.80 for maternal hypertension detection, outperforming baseline approaches while maintaining balanced performance across classes, with no performance degradation in an edge deployment scenario. Our findings demonstrated that fetal cardiac mechanical activity contains hemodynamic features indicative of maternal hypertension status. This supports a promising paradigm shift toward continuous, objective monitoring of maternal health using existing, low-cost ultrasound technology and introduces a complementary approach to traditional methods based on blood pressure measurements, advancing scalable prenatal care.
Authors: Advait Tilak, Jiwon Choi, Nazifa Mouli, Wei Le
Abstract: The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods. Existing benchmarks largely overlooked implausible scenarios and do not measure audio-visual alignment. We introduce BRITE, the first framework that unifies (1) implausible prompting, (2) fine-grained assessment of audio-visual consistency, and (3) QA-based interpretable evaluation into a comprehensive T2V benchmark. Unlike fully automated Multimodal LLM-based pipelines, which are prone to hallucination and prompt ambiguity, BRITE guarantees reliability through a rigorous human-in-the-loop protocol for benchmark creation. Evaluating five state-of-the-art models (Sora 2, Veo 3.1, Runway Gen4.5, Pixverse V5.5, and Qwen3Max), we reveal a critical performance gap: while models excel at static object composition, they exhibit significant degradation in object-action binding and audio-visual synchronization. Our framework offers the community a reliable, interpretable benchmark and evaluation framework that can detect and locate limitations in the next generation of T2V models, especially for off-manifold prompts
Authors: Duaa Alim, Mogtaba Alim, Liam Chalcroft
Abstract: Vision-language models (VLMs) read an image and produce text in a single forward pass, whereas radiologists typically inspect an image several times and consult the literature before writing a report. We introduce GAZE (Grounded Agentic Zero-shot Evaluation), a framework that lets a medical VLM work in this iterative way by calling viewer-level tools (zoom, windowing, contrast, edge detection) and two retrieval tools backed by the U.S. National Library of Medicine (PubMed for medical literature, Open-i for radiological images), with structured outputs validated against a schema and full tool-call traces recorded for auditability. On NOVA, a benchmark of 906 brain MRI cases covering 281 rare neurological conditions, GAZE reaches 58.2 mean average precision (mAP) at intersection-over-union (IoU) 0.3 for lesion localisation and 34.9% Top-1 diagnostic accuracy under a joint protocol that scores captioning, diagnosis, and localisation from the image alone, without task-specific fine-tuning. Before any tool is used, structured prompting and schema-validated outputs already improve over the published Gemini 2.0 Flash baseline (20.2 to 29.4 mAP@0.3), so framework design is itself an experimental variable. Tool use helps rare pathologies disproportionately: the fraction of cases with IoU > 0.3 rises from 17% to 58% for diagnoses with three or fewer examples versus 25% to 68% for common conditions ($\geq$10 cases), with gains tracking engagement (Gemini 3 Flash: Cohen's d = 0.79, 11.8 tool calls per case; Gemini 2.0 Flash: tools used in 8.2% of cases, no significant benefit). Retrieval ablations additionally reveal a model-dependent trade-off in which gains in diagnosis can coincide with losses in localisation, reinforcing the case for joint evaluation of diagnosis, localisation, and captioning in medical VLMs.
Authors: Yida Xue, Ningyu Zhang, Tingwei Wu, Zhe Ma, Daxiong Ji, Zhao Wang, Guozhou Zheng, Huajun Chen
Abstract: The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.
Authors: Manish Kumar, Rajendra K. Ray
Abstract: Speckle noise severely limits the quality of images acquired from coherent imaging systems such as Synthetic Aperture Radar (SAR) and medical ultrasound. Traditional second-order PDE-based despeckling approaches, although popular, often introduce staircase artifacts and blur fine details. To overcome these limitations, we present a nonlinear, fourth-order coupled hyperbolic-parabolic PDE model that effectively reduces noise while preserving the structure. The framework consists of two evolution equations: one governing fourth-order diffusion for effective speckle reduction and smooth intensity transitions, and another refining an edge indicator to protect textures and structural features. The diffusion coefficient is adaptively constructed using both the image intensity variable u and a grayscale-based indicator function, ensuring structure-aware denoising while avoiding blocky artifacts and preserving fine details. We also prove the existence of a weak solution to the proposed model by applying Schauder fixed-point theorem. A finite-difference scheme with Gauss Seidel iteration is employed for efficient implementation. We compare the proposed model with the existing coupled second-order PDE model (HPCPDE) and the fourth-order telegraph diffusion model (TDFM). The results show that our model consistently outperforms these approaches. Experiments on standard grayscale images, real SAR and ultrasound data, as well as speckle-corrupted color images, demonstrate that the proposed method achieves superior performance over conventional PDE-based techniques in terms of PSNR, MSSIM, and Speckle Index.
Authors: Yunhao Wang, Shuai Ma, Bin Shen, Shouhan Shi, Youlong Wu, Guangming Shi, Xiang Cheng
Abstract: With the evolution of 6G, semantic communication has emerged as a promising paradigm by prioritizing the delivery of task-relevant meaning over strict bit-level correctness. However, existing transport mechanisms still rely on explicit port headers and bit-level validation, making them vulnerable to header corruption and the resulting packet loss. To address this issue, this paper proposes a Semantic Port-Aware Adaptive-Rate Transmission Protocol (SPAT) for semantic communication. The proposed framework jointly embeds source and destination port information into semantic representations, thereby reducing dependence on explicit port headers while enabling robust port-aware transmission. Furthermore, a differentiated semantic processing mechanism is developed for uplink and downlink scenarios, where port identification is introduced for uplink service recognition and destination-aware conditional gating is designed for downlink selective decoding. In addition, an adaptive-rate controller is incorporated to dynamically adjust the number of transmitted semantic channels according to channel conditions and feature importance, thereby improving both robustness and transmission efficiency. Experimental results on the AFHQ and ImageNet-10 datasets, together with real-world experimental measurements, demonstrate that SPAT consistently outperforms TCP, UDP, and SITP in reconstruction quality across different SNRs while maintaining low-latency transmission.
Authors: Anirudh Iyengar Kaniyar Narayana Iyengar, Tampu Ravi Kumar, Manan Suri, Raviteja Bommireddy, Dinesh Manocha, Puneet Mathur, Vivek Gupta
Abstract: Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such structured evidence across diagrams, charts, maps, circuits, and infographics is time-consuming, and existing annotation tools tightly couple their interfaces to dataset-specific formats. We present DIAGRAMS, a lightweight, schema-driven review framework that decouples interface logic from dataset-specific JSON structures through an internal meta-schema and dataset adapters. Given an image and QA pair with optional candidate regions, the system performs QA-conditioned evidence selection and proposes the regions required for reasoning. When QA pairs or candidate regions are missing, it generates them and supports human verification and refinement. Across six Diagram QA datasets, model-suggested evidence achieves 85.39% precision and 75.30% recall against reviewer-final selections (micro-averaged). These results indicate that the review-first framework reduces manual region creation while maintaining high agreement with final reasoning-level attributions. We release a public demo and installable package to support dataset auditing, grounded supervision creation, and grounded evaluation.
Authors: Zhuoyao Xin, Yiren Zhang, Christopher Wu, Dong Liu, Chunming Gu, Elena Greco, Erik H. Middlebrooks, Jun Hua, Jia Guo
Abstract: Accurate synthesis of computed tomography (CT) images from magnetic resonance imaging (MRI) is clinically valuable for cranial applications such as attenuation correction, radiotherapy planning, and image-guided interventions. However, heterogeneity across MRI field strengths and acquisition protocols limits the generalizability of existing methods. In this study, we formulate cranial CT synthesis as a modular, structurally coupled problem and propose a deep learning framework to improve robustness across heterogeneous MRI conditions. The model is designed to adapt to variations in field strength and imaging protocols while preserving anatomical consistency. Experiments on multi-site datasets demonstrate improved performance and generalization compared with conventional approaches. The proposed method enables reliable CT synthesis across heterogeneous MRI settings, supporting broader clinical translation.
Authors: Yan Cui, Jacob S. Leiby, Wenhui Lei, Dokyoon Kim, Yanxiang Deng, Aaron T. Mayer, Zhenqin Wu, Alexandro E. Trevino, Zhi Huang
Abstract: Integrating molecular, morphological, and clinical data is essential for basic and translational biomedical research, yet systematic frameworks for jointly modeling these modalities remain limited. Here we present Haiku, a tri-modal contrastive learning model trained on multiplexed immunofluorescence (mIF). It comprises 26.7 million spatial proteomics patches from 3,218 tissue sections across 1,606 patients spanning 11 organ types, with matched hematoxylin and eosin (H&E) histology and clinical metadata aligned in a shared embedding space. Haiku enables three-way cross-modal retrieval, improves downstream classification and clinical prediction tasks over unimodal baselines, and supports zero-shot biomarker inference through fusion retrieval conditioned on clinical metadata-only text descriptions. Across tasks, Haiku outperforms competing approaches, achieving cross-modal retrieval (Recall@50 up to 0.611 versus near-zero baseline), survival prediction (C-index 0.737, +7.91% relative improvement), and zero-shot biomarker inference (mean Pearson correlation 0.718 across 52 biomarkers). Furthermore, we introduce a counterfactual prediction framework in which modifying only clinical metadata while fixing tissue morphology surfaces niche-specific molecular shifts associated with breast cancer stage progression and lung cancer survival outcomes. In a lung adenocarcinoma case study, the counterfactual analysis recovers niche-specific shifts characterized by increased CD8 and granzyme B, reduced PD-L1, and decreased Ki67, broadly consistent with patterns reported for favorable outcomes. We present these counterfactual results as exploratory, hypothesis-generating signals rather than mechanistic claims. These capabilities demonstrate that tri-modal alignment via Haiku enables integrative analysis of spatial biology, bridging molecular measurements with clinical context for biological exploration.
Authors: An Huang, Junggab Son, Zuobin Xiong
Abstract: Diffusion models have become the foundation of modern generative systems, with most research focusing primarily on improving generation efficiency and output quality. The timestep embedding component is a crucial part of the diffusion pipeline, which provides a temporal conditioning signal to the denoising network, enabling it to adapt its predictions across different noise levels throughout the process. Despite their potential to contain substantial information, timestep embeddings remain underexplored in current research, especially for security risks and reliable provenance. To fill this gap, we introduce Shadow Timestep Embedding (STE), a novel mechanism that investigates the underutilized temporal space for malicious information injection into diffusion models. In particular, when zooming in on the timestep embedding space, we find that different timesteps exhibit distinct representational capabilities that can encode side-channel information. Moreover, such encoded information can be utilized for attack and defense purposes through the scheduler interface. We present a theoretical analysis of timestep embeddings as position-encoding mappings and derive a mutual coherence evaluation that explains the separability of disjoint timestep intervals. Our findings reveal the diffusion model's timestep as a powerful side channel for carrying dedicated information, motivating new directions for adversarial generative modeling by understanding the temporal dimension.
Authors: Jiarui Xing, Song Wang, Jian Wang
Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem. Existing approaches retrain the model with auxiliary variance heads, maintain costly ensembles, or propagate approximate covariance through many integration steps, trading off training cost, inference cost, or accuracy. We show that none of these trade-offs is necessary. We prove that, for any pre-trained flow matching velocity field, the trace of the posterior covariance over the clean data given the current state equals, in closed form, the divergence of the velocity field, up to a known time-dependent prefactor and an additive constant. We call this the \emph{divergence-uncertainty identity} for flow matching. The matrix-level form of the identity is similarly closed-form, depending solely on the velocity Jacobian. Because the identity is exact and post-hoc, it is computable on any pre-trained flow matching model, with no retraining and no architectural modification. For one-step generators such as MeanFlow, the same identity yields the exact end-to-end generation uncertainty in a single forward pass, eliminating the multi-step variance propagation required by all prior methods. Experiments on MNIST confirm that the resulting per-pixel uncertainty maps are semantically meaningful, concentrating on digit boundaries where inter-sample variation is highest, and that the scalar uncertainty score tracks actual prediction error, all at roughly 10,000$\times$ less total compute than ensembling or Monte Carlo dropout.
Authors: Dan Soliman
Abstract: Background: Sensitivity of AI-assisted lung nodule detection systems is known to vary with CT acquisition parameters including radiation dose, reconstruction kernel, and slice thickness. However, the dependence of detection probability on nodule position within the reconstruction cycle -- the z-phase -- has not, to the author's knowledge, been characterized for deep learning-based detection systems. Methods: A retrospective analysis was performed using the LIDC-IDRI dataset. Detection results from a previously validated 154-case perturbation study were re-analyzed. For each consensus nodule (>=4-reader agreement), z-phase was defined as the fractional position of the nodule center within the reconstruction cycle, folded to [0, 0.5]. Detection sensitivity was stratified by z-phase bin, reconstruction interval (1mm, 3mm, 5mm), and by the ratio of reconstruction interval to nodule diameter (d/D). Results: At 5mm reconstruction interval, sensitivity was 71.6% vs 84.8% at 1mm baseline. Within the 5mm condition, sensitivity varied by 17.6 percentage points across z-phase bins. Stratified by d/D ratio, sensitivity was 92.4% for d/D < 0.5, 78.0% for 0.5 <= d/D < 1.0, and 61.4% for d/D >= 1.0, with a systematic z-phase effect present only in the d/D >= 1.0 stratum. Conclusions: AI detection sensitivity depends on the ratio of reconstruction interval to nodule diameter. When this ratio approaches or exceeds 1.0 -- as occurs for 3-6mm nodules at 5mm reconstruction -- z-phase becomes the dominant source of per-study detection variance. This stochastic effect is invisible to protocol-level quality metrics and not reflected in AI confidence scores.
Authors: Nihanth W. Cherukuru, Matt Rehme, Kirsten J. Mayer, David John Gagne, John Schreck, John Clyne, Charlie Becker
Abstract: Earth system science is producing increasingly large, high-dimensional datasets from physics based Earth system models to AI-based weather and climate models. Embedding-based representations can make these data searchable through similarity search and analog retrieval, but nearest neighbors in latent space are not automatically scientifically meaningful: it may reflect real weather structure, or preprocessing, geography, or model bias. Researchers therefore need ways to inspect how embeddings organize meteorological data, compare representation models, develop retrieval strategies, and verify results against physical evidence. We present an open-source visual analytics workbench for each of these steps. The system links embedding experiments to source data, metadata, spatial context, and model configurations, so latent-space results can be traced back to the physics. Users can explore latent spaces for different models, issue global or localized queries, and inspect analogs through familiar meteorological views. This enables a discovery workflow in which scientists characterize a phenomenon of interest in a well-understood dataset, identifying its signature in latent space, and then use that signature to probe larger, less-labeled archives or ensembles for similar events. We demonstrate the workbench through tropical-cyclone retrieval using ERA5-derived embeddings and IBTrACS metadata, and evaluate its out-of-core retrieval backend to show that large embedding collections can be searched beyond in-memory limits on commodity workstation hardware.
Authors: Bruno Abrahao
Abstract: Outlier Exposure (OE) is among the strongest training-based OOD detectors on standard benchmarks but exhibits scorer-dependent tradeoffs (e.g., strong on MSP, weak on KNN) and requires curated auxiliary data. We show why OE works: its features sit at the same geometric locus as real near-OOD data, with the boundary-adjacent quartile driving nearly all of OE's gain. OE is boundary calibration, not OOD coverage. GEODE (GEOmetry-preserving DEtection) replicates this calibration synthetically through an angle-adaptive norm loss in which targets scale per-sample with cosine similarity to the nearest class mean, preserving feature geometry where boundary structure matters. Four theorems grounded in neural collapse justify the design. GEODE works across all seven standard scorers on CIFAR-10 (near-OOD AUROC 89.0-92.3, far-OOD reaching 93.05; no catastrophic failure on any scorer). Since the OOD regime is unknown at deployment, this is the test that matters. GEODE outperforms vanilla CE at matched epoch counts. Combined with OE, GEODE reaches 95.0 MSP / 94.8 KNN on CIFAR-10 and beats OE on every scorer on CIFAR-100. The gains hold on WRN-28-10 (+4.5 Energy, 3 seeds). Unlike methods that push OOD into the classifier null space (e.g., PFS, 14.38 KNN AUROC, worse than random), GEODE's adaptive target preserves the geometry that distance-based scorers depend on.
Authors: Alexander Warnecke, Konrad Rieck
Abstract: Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft adversarial examples, drawing inspiration from insights of explainable machine learning. In particular, we design \emph{adversarial image filters} that are based on classic edge detection algorithms but optimized to deceive learning models. The resulting untargeted attacks are transferable and require only a single pass over the input. Empirically, we find that 3x3 filters already enable success rates between 30% and 80% on different neural networks. Compared to related approaches using generative models for crafting adversarial examples, we reduce the number of parameters by five orders of magnitude, resulting in a very efficient attack. When investigating the parameters of the learned filters, we observe interesting properties such as a high transferability between models and structures common to classic image filters. Our results provide further insights into the vulnerability of neural networks and their fragility to malicious noise.
Authors: Mayesha Maliha R. Mithila, Mylene C. Q. Farias
Abstract: Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortions are often asymmetric, where one modality may be severely degraded while the other remains clean. Still, most contemporary AVQA metrics treat audio and video as equally reliable, causing confidence-unaware fusion to emphasize unreliable signals. This paper proposes MCM-AVQA, a multimodal confidence-aware AVQA framework that explicitly estimates modality-specific confidence and injects it into a dedicated audio-visual mixer for cross-modal attention. The Audio-Visual Mixer utilizes frame-level, confidence-guided channel attention to gate fusion, modulating feature interaction between modalities so that high-confidence streams dominate while unreliable inputs are suppressed, preserving temporal degradation patterns. A multi-head visual confidence estimator turns frame-level artifact probabilities into temporally smoothed, clip-level visual confidence scores, while an audio confidence module derives confidence from speech-quality cues without requiring a clean reference. Experiments on multiple AVQA benchmarks show that MCM-AVQA, and specifically its confidence-guided Audio-Visual Mixer, improve correlation with human mean opinion scores and yield more interpretable behavior under real-world asymmetric audio-visual distortions.
Authors: Zikang Leng, Edan Eyal, Yingtian Shi, Jiaman He, Yaqi Liu, Thomas Pl\"otz
Abstract: Engagement, which links to attentional, emotional, and cognitive dimensions, plays an important role in learning. In online and video-based learning environments, learners often need to regulate their own interactions with instructional materials. Measuring and reflecting on engagement can therefore support both learners and adaptive learning systems. In this study, we use wearable and camera-based sensing devices to collect physiological and motion signals, including PPG, ECG, EDA, EEG, IMU, heart rate, temperature, and eye-tracking data, to estimate learner engagement. We conducted a user study with 16 participants in a video-based learning scenario, where participants completed learning tasks and provided repeated in-situ self-reports of engagement through brief probes. We develop and evaluate a system for engagement estimation, compare different sensing modalities, and further analyze the feasibility and effectiveness of multimodal modeling for characterizing learner engagement. Across participant-based cross-validation, our model achieves an MAE of 0.81, 83.75% within-1 accuracy, 73.93% binary accuracy, and 68.45% binary Macro-F1, outperforming sensor-free, statistical, deep temporal, foundation-model, and LLM-based baselines. Our results suggest that fine-grained engagement estimation is feasible but inherently noisy, and that practical systems should prioritize lightweight combinations of behavioral and physiological signals over full multimodal instrumentation. We release the EduGage dataset, including synchronized multimodal sensor signals, probe-aligned momentary engagement labels, video metadata, quizzes, and study materials, to support reproducible research on fine-grained sensor-based engagement modeling in self-guided learning.
Authors: Yi Yang, Jinyang Huang, Binbin Liu, Feng-Qi Cui, Xiaokang Zhou, Zhi Liu, Jie Zhang, Meng Li
Abstract: Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class. Clean-label backdoor attacks are especially dangerous because poisoned samples remain label-consistent and are therefore harder to detect. Yet existing clean-label attacks typically rely on expensive optimization, surrogate-model training, or nontrivial data access. We present Checkerboard, a theoretically grounded, learning-free clean-label backdoor attack that is effective, efficient, and simple to implement. From a linear separability formulation, we derive a checkerboard trigger in closed form, removing the need for surrogate-model training and trigger optimization. For texture-rich datasets, we introduce Complexity-driven Sample Selection, which uses only target-class data to improve trigger-to-background contrast by selecting low-complexity images for poisoning. Across four benchmark datasets, Checkerboard outperforms 8 baseline attacks and achieves state-of-the-art performance under low poisoning budgets. For example, on CIFAR-10, under a trigger perturbation budget of $10/255$, poisoning 20 training samples achieves $99.99\%$ Attack Success Rate (ASR). On ImageNet-100, a poisoning rate of only $0.46\%$ yields over $94\%$ ASR without degrading clean accuracy. The proposed attack also remains effective against state-of-the-art backdoor defenses and shows strong resistance to adaptive defenses.
Authors: Yao Du, Shanshan Li, Xiaomeng Li
Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. We identify the lack of cross-sample relational supervision as a key limitation of existing MLLM training paradigms. To address it, we propose a distribution-aware reinforcement learning framework based on Group Relative Policy Optimization, which introduces batch-level comparison-based supervision via the Concordance Correlation Coefficient-based reward to align predicted and ground-truth distributions in terms of correlation, scale, and mean. The framework is plug-and-play, requiring no architectural modification. Experiments on a unified suite of long-tailed regression benchmarks show consistent improvements over SFT and existing MLLM regression methods, with particularly strong gains in medium- and few-shot regimes.
Authors: Chengzheng Wu, Ke Qiu, Baoming Zhang, Ruiyu Mao, Xulong Tang, Kaixing Yang
Abstract: The growing availability of health-related instructional videos creates new opportunities for clinical training, patient rehabilitation, and health education, yet existing retrieval systems remain largely single-turn: a user submits one query and receives one ranked list. This interaction is brittle in health scenarios, where information needs are often vague at first and become clinically meaningful only after follow-up constraints such as posture, hand placement, contraindications, equipment, or patient condition are specified. We introduce interactive multi-turn semantic retrieval for health videos and construct MHVRC, a Multi-Turn Health Video Retrieval Corpus, by combining video-grounded descriptions from VideoChat-Flash with query refinements generated by DeepSeek. We further propose DATR, a Dialogue-Aware Two-Stage Retrieval framework. DATR first performs efficient coarse retrieval with a CLIP-style dual encoder and sparse frame sampling, then re-ranks the top candidates through multi-turn query fusion and a lightweight cross-encoder scoring module. Experiments on MHVRC show consistent gains over strong text-video retrieval baselines, while user studies indicate that refined multi-turn queries better capture fine-grained procedural semantics than single-turn annotations. The work establishes a benchmark and a scalable technical recipe for interactive health video retrieval.
Authors: Xitie Zhang, Aming Wu, Yahong Han
Abstract: Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-context learning approaches leverage seen task demonstrations to generate actions for unseen tasks without parameter updates. However, existing methods provide only low-level continuous action sequences as context, failing to capture composable skill knowledge and causing models to degenerate into superficial trajectory imitation. We propose Decompose and Recompose, a skill reasoning framework using atomic skill-action pairs as intermediate representations. Our approach decomposes seen demonstrations into interpretable skill--action alignments, enabling the model to recompose these skills for unseen tasks through compositional reasoning. Specifically, we construct a task-adaptive dynamic demonstration library via visual-semantic retrieval combined with skill sequences from a planning agent, complemented by a coverage-aware static library to fill missing skill patterns. Together, these yield skill-comprehensive demonstrations that explicitly elicit compositional reasoning for skill composition and execution ordering. Experiments on the AGNOSTOS benchmark and real-world environments validate our method's zero-shot cross-task generalization capability.
Authors: Biswarup Karmakar, Ratikanta Behera
Abstract: Tensor completion has emerged as a powerful framework for recovering missing data in multidimensional signals by exploiting low-rank tensor structures. Among existing approaches, linear transform-based tensor nuclear norm (TNN) methods have achieved considerable success by enforcing low-rankness on transformed frontal slices. However, the low-rank structure revealed by linear transforms remains inherently limited. To better capture intrinsic correlations, nonlinear transform-based TNN (NTTNN) models have been proposed, significantly enhancing low-rank representation through composite transforms. Despite their effectiveness, existing NTTNN methods are restricted to real-valued tensors and fail to model quaternion-valued data, which are essential for preserving inter-channel dependencies in color images and videos. Extending nonlinear TNN models to the quaternion domain is challenging due to the non-commutativity of quaternion multiplication and the complexity of quaternion singular value decomposition. To address the limitations encountered in prior works, we propose a quaternion nonlinear transform-induced tensor nuclear norm (QNTTNN) via a real embedding of quaternions, enabling tractable nuclear norm definitions and efficient optimization. Building upon QNTTNN, we formulate a quaternion tensor completion model and develop a proximal alternating minimization algorithm with rigorous convergence guarantees. Extensive experiments on benchmark color video inpainting datasets validate the superior performance of the proposed method over existing approaches.
Authors: Milad Parvan
Abstract: Electrocardiogram (ECG) biometrics have emerged as a promising modality for continuous, liveness-aware authentication in wearable systems. However, many prior studies report overly optimistic results due to data leakage (e.g., random splits within the same session). To address this issue, we introduce ECG-biometrics-bench, a modular, reproducible benchmarking framework that standardizes preprocessing, segmentation, and evaluation across seven widely used public ECG datasets spanning clinical, ambulatory, and large-scale cohort settings. The framework supports both closed-set and open-set (i.e., subject-disjoint generalization in this work) evaluation, as well as progressively realistic protocols including cross-session and long-term temporal separation. To facilitate reproducible research in the community, the ECG-biometrics-bench repository will be made publicly accessible on GitHub upon the acceptance of this manuscript. Through a comprehensive multi-dataset analysis, we expose the Random Split Fallacy, demonstrating that intra-session evaluation protocols artificially inflate performance while masking severe degradation caused by temporal drift and unseen identities. Furthermore, by evaluating multiple architectures, including DeepECG, ResNet1D, and CNN-LSTM, we show that these failures are not model-specific but are likely inherent to current supervised feature-learning paradigms. Finally, we demonstrate that performance degradation due to temporal aging can be partially mitigated through a heavy enrollment, lightweight authentication strategy based on dynamic multi-session template fusion. These findings establish a more realistic baseline for ECG biometrics and highlight critical challenges that must be addressed for reliable real-world deployment.
Authors: Merve Eryilmaz, Yuzhu Li, Xiao Wang, Max Zhang, Alp Inegol, Zixiang Ji, Lucas Thai, Guangdong Ma, Akihiko Fujisawa, Kazunori Yamaguchi, Aydogan Ozcan
Abstract: The plaque reduction assay (PRA) remains the gold standard for antiviral susceptibility testing, evaluating drug potency by measuring reductions in plaque-forming units (PFUs). However, the traditional PRA is time-consuming, labor-intensive, prone to manual counting errors, and offers limited scalability. Moreover, its reliance on destructive fixation and chemical staining reduces the assay to a static, endpoint observation, obscuring the dynamic, time-resolved kinetics of dose-dependent viral inhibition. Here, we introduce a label-free, time-resolved PRA platform that transforms the conventional assay into a continuous, high-dimensional measurement of viral infection dynamics. Our system integrates a compact lens-free imaging setup with a custom-designed ultra-large-area (100 cm^2) thin-film transistor (TFT) image sensor and deep learning-based algorithms to autonomously quantify PFU dynamics within an incubator. Validated using herpes simplex virus type-1 (HSV-1) treated with acyclovir, the platform matched chemically-stained ground truth measurements with zero false positives while accelerating readout by ~26 hours. Crucially, our system revealed that increasing drug concentrations induce temporally distinct delays and suppress new PFU formation, enabling conclusive drug efficacy evaluations within ~60 hours post-infection. This scalable, label-free framework redefines antiviral susceptibility testing as a rapid, time-resolved and information-rich measurement framework, providing a generalizable platform for virology research, high-throughput drug screening, and clinical diagnostics.
Authors: Itai Allouche, Joseph Keshet
Abstract: Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However, a critical challenge remains: these models often suffer from hallucinations, generating outputs that diverge from the provided perceptual inputs. This tendency stems from an inherent imbalance in modality utilization during inference, where the dominance of textual tokens undermines the potential of perceptual inputs. As a result, the model frequently resorts to textual language priors at the expense of grounded evidence. To tackle this issue, we propose Learning Inference-time Modality Enhancement (LIME), a training-free framework designed to bolster multimodal grounding by explicitly enhancing modality usage during decoding. LIME leverages Layer-wise Relevance Propagation (LRP) to quantify token-level contributions and defines a relevance-based objective that promotes increased reliance on perceptual inputs. This objective is enforced through inference-time updates to the model's key-value representations, without modifying model parameters or requiring additional training data. We evaluate LIME across multiple multimodal benchmarks in both vision and audio domains, demonstrating consistent reductions in hallucinations and enhanced grounding while preserving generation quality. Further analysis shows that LIME increases modality contribution and produces more localized and semantically aligned relevance patterns.
Authors: Weixuan Chen, Qianqian Yang
Abstract: Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication overhead. In this paper, we propose an evolving semantic token communication system with a parametric memory network over MIMO fading channels. Specifically, only an equal-length prefix of each semantic token is transmitted, which reduces transmission cost while preserving a consistent token structure for receiver-side recovery. At the receiver, a parametric memory network is introduced to reconstruct the missing suffix information from the received token prefixes, where semantic memory is stored implicitly in the network parameters. To realize this design, full semantic tokens are first organized into a codebook, and truncated tokens are paired with the codeword labels of their corresponding full tokens. Based on these token-label pairs, kNN-based teacher distributions are constructed to fine-tune a pretrained GPT-2-based recovery module, which learns to infer the codeword distribution of each incomplete token and recover the corresponding complete semantic token. In addition, an online evolution strategy is developed to periodically update the parametric memory network and the entire system using newly observed test samples, thereby improving adaptability under distribution shifts. Experimental results demonstrate that the proposed method consistently outperforms the existing evolving memory benchmark under different channel conditions and channel bandwidth ratios, with up to 1.09 dB PSNR improvement.
Authors: Shengzhe Lyu, Yuhan She, Patrick S. Y. Hung, Ray C. C. Cheung, Weitao Xu
Abstract: Vision Mamba (ViM) models offer a compelling efficiency advantage over Transformers by leveraging the linear complexity of State Space Models (SSMs), yet efficiently deploying them on FPGAs remains challenging. Linear layers struggle with dynamic activation outliers that render static quantization ineffective, while uniform quantization fails to capture the weight distribution at low bit-widths. Furthermore, while associative scan accelerates SSMs on GPUs, its memory access patterns are misaligned with the streaming dataflow required by FPGAs. To address these challenges, we present ViM-Q, a scalable algorithm-hardware co-design for end-to-end ViM inference on the edge. We introduce a hardware-aware quantization scheme combining dynamic per-token activation quantization and per-channel smoothing to mitigate outliers, alongside a custom 4-bit per-block Additive Power-of-Two (APoT) weight quantization. The models are deployed on a runtime-parameterizable FPGA accelerator featuring a linear engine employing a Lookup-Table (LUT) unit to replace multiplications with shift-add operations, and a fine-grained pipelined SSM engine that parallelizes the state dimension while preserving sequential recurrence. Crucially, the hardware supports runtime configuration, adapting to diverse dimensions and input resolutions across the ViM family. Implemented on an AMD ZCU102 FPGA, ViM-Q achieves an average 4.96x speedup and 59.8x energy efficiency gain over a quantized NVIDIA RTX 3090 GPU baseline for low-batch inference on ViM-tiny. This co-design shows a viable path for deploying ViM models on resource-constrained edge devices.
Authors: Yisheng Zhang, Michael Xu, Alan Williams, Matthew Gray, Nare Karapetyan, Miao Yu
Abstract: Accurate seabed mapping is essential for habitat monitoring and infrastructure inspection. In turbid, shallow coastal waters, such as shellfish aquaculture farms, the effectiveness of traditional optical methods is limited. Autonomous surface vehicles (ASVs) equipped with forward-looking sonar (FLS) offer a promising alternative. However, existing sonar-based systems face challenges in achieving fine resolution mapping over long trajectories due to low-resolution positioning measurements and accumulated drift over long trajectories. In this paper, we present a drift-resilient seabed mapping framework that integrates local FLS frame alignment using the Fourier-Mellin transform (FMT) with global trajectory optimization based on an extended Kalman filter (EKF) that fuses global positioning system (GPS), inertial measurement unit (IMU), and compass data. A variance-based image blending strategy is used to further reduce visual artifacts in overlapping regions. Field trials on a structured oyster farm site show that our framework helps reduce drift in RMSE by 9.5% relative to the FMT-only baseline. This framework also enables sub-meter reconstruction accuracy and preservation of high-resolution textures needed for oyster inventory estimation within the mapped areas.
Authors: Yavuz Yarici, Ghassan AlRegib
Abstract: Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ separate encoders for each modality and a fusion module, training the system end-to-end by optimizing on the fused features. In this paper, we identify that such joint optimization causes encoders to exploit cross-modal co-occurrences, statistical relationships between modalities that arise from source-specific recording conditions, rather than learning domain-invariant features. We term this failure mode Fusion Overfitting. To address this, we propose Modality-Entropy Regularization for Domain Generalization (MER-DG), which maximizes the entropy of each encoder's feature distribution to preserve feature diversity. MER-DG is architecture-agnostic and integrates into existing multimodal frameworks as an additive loss term. Extensive experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of approximately 5% over standard fusion and approximately 2% over state-of-the-art methods.
Authors: Daniel da Silva Costa, Pedro Nuno de Souza Moura, Adriana C. F. Alvim
Abstract: In recent years, several advances have been observed in Deep Learning with surprising results. Models in this area have been increasingly used in numerous applications, including those sensitive to human life, which require clear explanations and justifications. Various explainability methods have been proposed, but not many metrics to evaluate these methods. The most commonly used metric is the Intersection over Union (IoU). However, due to the characteristics of the results of the explainability methods, called saliency maps, which do not have a known shape, we hypothesise that there must be a better metric that allows one to find an explainability method that produces results that best resemble the human perception. We propose using different metrics to assess the similarity between human perception and the explanation saliency maps to find a better metric. An investigation was conducted employing a subset of the Chihuahuas images from ImageNet dataset. Several CAM-based explainability methods were used to generate saliency maps for each chihuahua image. Alignment was measured by applying distance metrics between the bounding box of human annotations and the saliency maps produced by each explainability method. Rankings of the best saliency maps were created using the results of the distance metrics and compared to the ranking obtained using people's choice, collected through crowdsourcing, of the best explanation saliency maps for each selected image. Comparison between rankings was performed using the Rank-Biased Overlap (RBO) metric. The results indicate the feasibility of our method to find the explainability method that best resembles human perception. In our experiments, the two metrics that best resemble human perception corresponded to Manhattan and Correlation. Besides, the best explainability methods regarding human perception were LayerCAM, Score-CAM, and IS-CAM.
Authors: Nicholas B. Andrews, Kristi A. Morgansen
Abstract: This paper presents a dual quaternion framework for 6-DOF visual target tracking that addresses key limitations of perspective-n-point (P$n$P) solvers: sensitivity to noise and outliers, and inability to propagate estimates through measurement dropouts. A nonlinear observability analysis is performed using a Lie algebraic approach, deriving sufficient conditions for local observability under two sensing modalities: relative position vector and unit vector measurements. For the unit vector case, the classical collinear feature point degeneracy of the perspective-three-point problem is recovered through rank analysis of the observability codistribution matrix, providing a control-theoretic interpretation of a previously geometric result. A dual quaternion Lie group unscented Kalman filter is then developed, directly modeling relative dynamics without assumptions about cooperative measurements or slowly-varying motion. Simulations demonstrate improved pose estimation accuracy and robustness to occlusions compared to an off-the-shelf P$n$P solver. Results are broadly applicable to visual-inertial navigation, simultaneous localization and mapping, and P$n$P solver development.
Authors: Soyeon Kim, Seongwoo Lim, Kyowoon Lee, Jaesik Choi
Abstract: Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield unreliable explanations when the integration path between a baseline and the input passes through regions with noisy gradients. While Guided Integrated Gradients reduces this sensitivity by adaptively updating low-gradient-magnitude features, input-space guidance still produces intermediate inputs that deviate from the data manifold. To address this limitation, we propose \emph{Manifold-Aligned Guided Integrated Gradients} (MA-GIG), which constructs attribution paths in the latent space of a pre-trained variational autoencoder. By decoding intermediate latent states, MA-GIG biases the path toward the learned generative manifold and reduces exposure to implausible input-space regions. Through qualitative and quantitative evaluations, we demonstrate that MA-GIG produces faithful explanations by aggregating gradients on path features proximal to the input. Consequently, our method reduces off-manifold noise and outperforms prior path-based attribution methods across multiple datasets and classifiers. Our code is available at https://github.com/leekwoon/ma-gig/.
Authors: Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk, Bo Zhu
Abstract: We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to permutation symmetries, so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; and (ii) particles live in physical space, so the flow terminal velocity has physical meaning and can encode geometric attributes, e.g., surface normals. OGPP instantiates three key components: (1) orbit-space canonicalization of the probability-path terminal endpoint, (2) particle index embeddings for role specialization, and (3) geometric probability paths with arc-length-aware terminal velocities that generate normals as a byproduct of the flow. We evaluate OGPP on minimal-surface benchmarks, where it reduces metric error by up to two orders of magnitude in a single inference step; on ShapeNet, where it matches the state of the art with 5x fewer steps and reaches airplane EMD comparable to DiT-3D with 26x fewer parameters and 5x fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D.
Authors: Tung Vu, Yen Nguyen, Hai Nguyen, Cuong Pham, Cong Tran
Abstract: Recent advances in voice cloning and text-to-speech synthesis have made partial speech manipulation - where an adversary replaces a few words within an utterance to alter its meaning while preserving the speaker's identity - an increasingly realistic threat. Existing audio deepfake detection benchmarks focus on utterance-level binary classification or single-region tampering, leaving a critical gap in detecting and localizing multiple inpainted segments whose count is unknown a priori. We address this gap with three contributions. First, we introduce MIST (Multiregion Inpainting Speech Tampering), a large-scale multilingual dataset spanning 6 languages with 1-3 independently inpainted word-level segments per utterance, generated via LLM-guided semantic replacement and neural voice cloning, with fake content constituting only 2-7% of each utterance. Second, we propose ISA (Iterative Segment Analysis), a backbone-agnostic framework that performs coarse-to-fine sliding-window classification with gap-tolerant region proposal and boundary refinement to recover all tampered regions without prior knowledge of their count. Third, we define SF1@tau, a segment-level F1 metric based on temporal IoU matching that jointly evaluates region count accuracy and localization precision. Zero-shot evaluation reveals that partial inpainting at word granularity remains unsolved by existing deepfake detectors: utterance-level classifiers trained on fully synthesized speech assign near zero fake probability to MIST utterances where only 2-7% of content is manipulated. ISA consistently outperforms non-iterative baselines in this challenging setting, and the dataset, code, and evaluation toolkit are publicly released.
Authors: Abolfazl Mohammadi-Seif, Ricardo Baeza-Yates
Abstract: The widespread adoption of machine learning in critical applications demands techniques to mitigate high-consequence errors. Our method utilizes a dual-classifier GBDT pipeline to distinguish routine human-like errors from high-risk non-human misclassifications. Evaluated across three domains, animal breed classification, skin lesion diagnosis (ISIC 2018), and prostate histopathology (SICAPv2), our framework demonstrates robust safety improvements. To address real-world deployment concerns, our results confirm the pipeline introduces negligible inference latency (1.60% overhead for the animal dataset, 1.84% for ISIC, and 1.70% for SICAPv2) while outperforming traditional Maximum Class Probability (MCP) baselines in correction precision. Our conservative correction strategy successfully reduced dangerous non-human errors by 34.1% in ISIC and 12.57% in SICAPv2, improving super-class diagnostic safety to 90.41% and 92.13% respectively. This proves that safety-critical reliability can be substantially enhanced post-hoc without expensive model retraining. keywords: Error Analysis, Post-hoc Correction, Trustworthy AI.
Authors: Dasari Naga Raju
Abstract: Predicting microsatellite instability (MSI) status from routine hematoxylin and eosin (H&E) whole slide images (WSIs) offers a practical alternative to molecular testing, but models trained at one institution tend to generalize poorly to slides acquired at a different site. Foundation model representations, despite their generality, still encode site-specific texture alongside the conserved biological morphology underlying MSI. We investigate whether tile-level spatial priors derived from known MSI histology can guide these representations toward more site-invariant features. We introduce a biologically motivated spatial prior based on peripheral distance encoding, reflecting the Crohn's-like peripheral lymphocytic reaction at the tumor invasive margin, and evaluate a secondary local immune neighborhood encoding reflecting the lymphocyte-to-tumor ratio in each tile's immediate spatial neighborhood. Both priors are injected into a TransMIL aggregator before self-attention, allowing the transformer to integrate spatial biological context with UNI2-h or Virchow2 features across all attention layers. We evaluate six foundation model and MIL aggregator combinations as a reference, then assess the effect of each spatial prior. Training on TCGA-COAD (137 slides) and evaluating externally on TCGA-READ (50 slides) without retraining, peripheral distance encoding achieves MSI AUC 0.959 +/- 0.012 on COAD and MSS specificity 1.000 on READ, compared to 0.957 and 0.939 for the strongest reference configuration. Local immune neighborhood encoding achieves comparable internal AUC but lower cross-site specificity, suggesting margin proximity encodes a more site-invariant biological signal than local immune density. Results suggest biologically grounded spatial priors act as regularizers that reduce reliance on site-specific imaging patterns.
Authors: Simon Dorer, Martin B\"uchner, Nick Heppert, Abhinav Valada
Abstract: Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces. To mitigate these errors, large-scale monocular depth estimation approaches provide strong structural priors, but their predictions can be potentially skewed or mis-scaled in metric units, limiting their direct use in robotics. Thus, in this work, we propose a training-free depth grounding framework that anchors monocular depth estimation priors from a depth foundation model in raw sensor depth through factor graph optimization. Our method performs a patch-wise affine alignment, locally grounding monocular predictions in metric real-world depth while preserving fine-grained geometric structure and discontinuities. To facilitate evaluation in challenging real-world conditions, we introduce a benchmark dataset with dense scene-wide ground truth depth in the presence of non-Lambertian objects. Ground truth is obtained via matte reflection spray and multi-camera fusion, overcoming the reliance on object-only CAD-based annotations used in prior datasets. Extensive evaluations across diverse sensors and domains demonstrate consistent improvements in depth performance without any (re-)training. We make our implementation publicly available at https://anchord.cs.uni-freiburg.de.
Authors: Sergio Orozco, Tushar Kusnur, Brandon May, George Konidaris, Laura Herlant
Abstract: Learning data-efficient object dynamics models for robotic manipulation remains challenging, especially for deformable objects. A popular approach is to model objects as sets of 3D particles and learn their motion using graph neural networks. In practice, this is not enough to maintain physical feasibility over long horizons and may require large amounts of interaction data to learn. We introduce PIEGraph, a novel approach to combining analytical physics and data-driven models to capture object dynamics for both rigid and deformable bodies using limited real-world interaction data. PIEGraph consists of two components: (1) a \textbf{P}hysically \textbf{I}nformed particle-based analytical model (implemented as a spring--mass system) to enforce physically feasible motion, and (2) an \textbf{E}quivariant \textbf{Graph} Neural Network with a novel action representation that exploits symmetries in particle interactions to guide the analytical model. We evaluate PIEGraph in simulation and on robot hardware for reorientation and repositioning tasks with ropes, cloth, stuffed animals and rigid objects. We show that our method enables accurate dynamics prediction and reliable downstream robotic manipulation planning, which outperforms state of the art baselines.
Authors: Kateryna Zorina, Vojtech Priban, Mederic Fourmy, Josef Sivic, Vladimir Petrik
Abstract: Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control. However, off-the-shelf methods lack temporal consistency and robustness that are mandatory for a stable feedback control. In this work, we develop a factor graph approach to enforce temporal consistency of the object pose estimates. In particular, the proposed approach: (i) incorporates object motion models, (ii) explicitly estimates the object pose measurement uncertainty, and (iii) integrates the above two components in an online optimization-based estimator. We demonstrate that with appropriate outlier rejection and smoothing using the proposed factor graph approach, we can significantly improve the results on standardized pose estimation benchmarks. We experimentally validate the stability of the proposed approach for a feedback-based robot control task in which the object is tracked by the camera attached to a torque controlled manipulator.
Authors: Ye Zhang, Longguang Wang, Qing Gao, Chaocan Xiang, Mohammed Bennamoun, Yulan Guo
Abstract: The field of sensor-based human activity recognition (HAR) mainly uses posture, motion and context data of Inertial Measurement Units (IMUs) to identify daily activities. Despite the advancements in learning-based methods, it is challenging to perform information fusion from the temporal perspective due to the complexities in fusing heterogeneous sensor data and establishing long-term context correlations. This paper proposes a novel triple spectral fusion framework tailored for HAR. First, we develop an adaptive complementary filtering technique for noise suppression and organize each IMU's sensors into posture and motion modality nodes. Given that IMU nodes form a dynamic heterogeneous graph, we then apply adaptive filtering within the graph Fourier domain to merge both homogeneous and heterogeneous node information. Furthermore, an adaptive wavelet frequency selection approach is implemented to suppress context redundancy and shorten the length of features. This approach enhances both timestamp-based graph aggregation and the correlation of long-term contexts. Our framework uses adaptive filtering in the Fourier, graph Fourier, and wavelet domains, enabling effective multi-sensor fusion and context correlation. Extensive experiments on ten benchmark datasets demonstrate the superior performance of our framework. Project page: https://github.com/crocodilegogogo/TSF-TPAMI2026.
Authors: Danil Tokhchukov, Veronika Morozova, Gonzalo Ferrer
Abstract: Traditional Simultaneous Localization and Mapping (SLAM) algorithms rely heavily on the static environment assumption, which severely limits their applicability in real-world spaces populated by moving entities, such as pedestrians. In this work, we propose DynoSLAM, a tightly-coupled Dynamic GraphSLAM architecture that integrates socially-aware Graph Neural Networks (GNNs) directly into the factor graph optimization. Unlike conventional approaches that use rigid constant-velocity heuristics or deterministic single-agent neural priors, our framework formulates pedestrian motion forecasting as a stochastic World Model. By utilizing Monte Carlo rollouts from a trained GNN, we capture the multimodal epistemic uncertainty of human interactions and embed it into the SLAM graph via a dynamic Mahalanobis distance factor. We demonstrate through extensive simulated experiments that this stochastic formulation not only maintains highly accurate retrospective tracking but also prevents the optimization failures caused by the deterministic "argmax problem". Ultimately, extracting the empirical mean and covariance matrices of future pedestrian states provides a mathematically rigorous, probabilistic safety envelope for downstream local planners, enabling anticipatory and collision-free robot navigation in densely crowded environments.
Authors: Dongliang Cao, Florian Bernard
Abstract: The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser scanners), meshes encode rich and expressive topological information, but their creation typically requires some form of (often manual) curation. In turn, methods that purely rely on point clouds are unable to meet the matching quality of mesh-based methods that utilise the additional topological structure. In this work we close this gap by introducing a self-supervised multimodal learning strategy that combines mesh-based functional map regularisation with a contrastive loss that couples mesh and point cloud data. Our shape matching approach allows to obtain intramodal correspondences for triangle meshes, complete point clouds, and partially observed point clouds, as well as correspondences across these data modalities. We demonstrate that our method achieves state-of-the-art results on several challenging benchmark datasets even in comparison to recent supervised methods, and that our method reaches previously unseen cross-dataset generalisation ability.
Authors: Dongliang Cao, Paul Roetzer, Florian Bernard
Abstract: We propose a novel learning-based approach for robust 3D shape matching. Our method builds upon deep functional maps and can be trained in a fully unsupervised manner. Previous deep functional map methods mainly focus on predicting optimised functional maps alone, and then rely on off-the-shelf post-processing to obtain accurate point-wise maps during inference. However, this two-stage procedure for obtaining point-wise maps often yields sub-optimal performance. In contrast, building upon recent insights about the relation between functional maps and point-wise maps, we propose a novel unsupervised loss to couple the functional maps and point-wise maps, and thereby directly obtain point-wise maps without any post-processing. Our approach obtains accurate correspondences not only for near-isometric shapes, but also for more challenging non-isometric shapes and partial shapes, as well as shapes with different discretisation or topological noise. Using a total of nine diverse datasets, we extensively evaluate the performance and demonstrate that our method substantially outperforms previous state-of-the-art methods, even compared to recent supervised methods. Our code is available at https://github.com/dongliangcao/Unsupervised-Learning-of-Robust-Spectral-Shape-Matching.
URLs: https://github.com/dongliangcao/Unsupervised-Learning-of-Robust-Spectral-Shape-Matching.
Authors: Dongliang Cao, Paul Roetzer, Florian Bernard
Abstract: We propose a novel unsupervised learning approach for non-rigid 3D shape matching. Our approach improves upon recent state-of-the art deep functional map methods and can be applied to a broad range of different challenging scenarios. Previous deep functional map methods mainly focus on feature extraction and aim exclusively at obtaining more expressive features for functional map computation. However, the importance of the functional map computation itself is often neglected and the relationship between the functional map and point-wise map is underexplored. In this paper, we systematically investigate the coupling relationship between the functional map from the functional map solver and the point-wise map based on feature similarity. To this end, we propose a self-adaptive functional map solver to adjust the functional map regularisation for different shape matching scenarios, together with a vertex-wise contrastive loss to obtain more discriminative features. Using different challenging datasets (including non-isometry, topological noise and partiality), we demonstrate that our method substantially outperforms previous state-of-the-art methods.
Authors: Jiaqi Yang, Bo Du, Rong Liu, Zhu Mao, Liangpei Zhang
Abstract: Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation. Therefore, a natural idea is to combine multimodal images for refined and accurate land-cover interpretation. Although many efforts have been attempted to achieve multi-source remote sensing image classification, there are still three issues as follows: 1) indiscriminate feature representation without sufficiently considering modal heterogeneity, 2) abundant features and complex computations associated with modeling long-range dependencies, and 3) overfitting phenomenon caused by sparsely labeled samples. To overcome the above barriers, a transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. Then, a self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling. Finally, a mean forward strategy is developed in order to avoid overfitting. Based on the above structures, the proposed model is able to break through modal gaps to obtain differentiated graph representation with competitive time cost, even for a small fraction of training samples. Experiments and analyses in three benchmark datasets with various state-of-the-art (SOTA) approaches show the performance of the proposed THSGR. The code will be available in https://github.com/jqyang22.
Authors: Yonghao Yu, Shunan Zhu, Huai Qin, Haorui Li
Abstract: Witnessing the evolution of text-to-image diffusion models, significant strides have been made in text-to-3D generation. Currently, two primary paradigms dominate the field of text-to-3D: the feed-forward generation solutions, capable of swiftly producing 3D assets but often yielding coarse results, and the Score Distillation Sampling (SDS) based solutions, known for generating high-fidelity 3D assets albeit at a slower pace. The synergistic integration of these methods holds substantial promise for advancing 3D generation techniques. In this paper, we present BoostDream, a highly efficient plug-and-play 3D refining method designed to transform coarse 3D assets into high-quality. The BoostDream framework comprises three distinct processes: (1) We introduce 3D model distillation that fits differentiable representations from the 3D assets obtained through feed-forward generation. (2) A novel multi-view SDS loss is designed, which utilizes a multi-view aware 2D diffusion model to refine the 3D assets. (3) We propose to use prompt and multi-view consistent normal maps as guidance in refinement. Our extensive experiment is conducted on different differentiable 3D representations, revealing that BoostDream excels in generating high-quality 3D assets rapidly, overcoming the Janus problem compared to conventional SDS-based methods. This breakthrough signifies a substantial advancement in both the efficiency and quality of 3D generation processes.
Authors: Jiawen Xu, Margret Keuper
Abstract: Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural classifiers trained on a closed set of data typically struggle to identify novel classes, leading to erroneous predictions. To address this issue, various heuristic methods have been proposed, allowing models to express uncertainty by stating "I don't know." However, a gap in the literature remains, as there has been limited exploration of the underlying mechanisms of these methods. In this paper, we conduct an analysis of open set recognition methods, focusing on the aspect of feature diversity. Our research reveals a significant correlation between learning diverse discriminative features and enhancing OSR performance. Building on this insight, we propose a novel OSR approach that leverages the advantages of feature diversity. The efficacy of our method is substantiated through rigorous evaluation on a standard OSR testbench, demonstrating a substantial improvement over state-of-the-art methods.
Authors: Jiajun Huang, Shuolin Xu, Hongchuan Yu, Tong-Yee Lee
Abstract: We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS). Our approach bridges cage-based deformation and 3DGS by using a proxy point-cloud representation. This point cloud is generated from 3D Gaussians, and deformations applied to the point cloud are translated into transformations on the 3D Gaussians. To handle potential bending caused by deformation, we incorporate a splitting process to approximate it. Our method does not modify or extend the core architecture of 3D Gaussian Splatting, making it compatible with any trained vanilla 3DGS or its variants. Additionally, we automate cage construction for 3DGS and its variants using a render-and-reconstruct approach. Experiments demonstrate that GSDeformer delivers superior deformation results compared to existing methods, is robust under extreme deformations, requires no retraining for editing, runs in real-time, and can be extended to other 3DGS variants. Project Page: https://jhuangbu.github.io/gsdeformer/
Authors: Mohammad Reza Karimi Dastjerdi, Dominique Tanguay-Gaudreau, Fr\'ed\'eric Fortier-Chouinard, Yannick Hold-Geoffroy, Nima Kalantari, Jean-Fran\c{c}ois Lalonde
Abstract: Most novel view synthesis methods -- including Neural Radiance Fields (NeRF) -- struggle to capture the high dynamic range (HDR) radiance required for realistic image-based lighting (IBL). This limitation stems from a reliance on low dynamic range (LDR) imagery, which fails to capture the intensity of light sources found in indoor environments. While exposure bracketing can recover this range, it is often too slow for practical, large-scale acquisition. In this work, we introduce PanDORA: PANoramic Dual-Observer Radiance Acquisition, a system specifically designed for the fast and affordable capture of high-quality HDR radiance maps for IBL. Our approach utilizes two 360{\deg} cameras mounted on a portable monopod to simultaneously record videos at different exposures. These videos are processed by our proposed two-stage NeRF-based algorithm featuring a novel self-calibrating pipeline to estimate camera parameters. This pipeline produces non-saturated HDR radiance fields that accurately capture the radiance of a scene. When evaluated on a new dataset of real indoor environments featuring HDR ground truth lighting, PanDORA demonstrates superior fidelity in reconstructing the peak intensities necessary for downstream rendering tasks, providing a scalable and efficient solution for capturing real-world IBLs.
Authors: Mulugeta Weldezgina Asres, Lei Jiao, Christian Walter Omlin
Abstract: Recent advancements in artificial intelligence hold ample potential for monitoring applications using surveillance cameras. However, concerns about privacy and model bias have made it challenging to utilize them in public. Although de-identification approaches have been proposed in the literature, aiming to achieve a certain level of anonymization (AN), most of them employ deep learning models that are computationally demanding for real-time edge deployment. This study revisits conventional AN solutions for privacy protection and real-time video anomaly detection (VAD) applications. We propose a lightweight adaptive AN for VAD (LA3D) that employs dynamic adjustment to enhance full-body privacy protection. We have evaluated privacy protection and VAD utility retention efficacy using several publicly available datasets to examine the strengths and weaknesses of different AN methods and highlight the promising leverage of our approach. Our experiment demonstrates that the LA3D enables substantial improvement in privacy AN without severely degrading VAD efficacy, outperforming conventional and deep learning approaches. Code is available at https://github.com/muleina/LA3D .
Authors: Tao Liu, Dapeng Man, Jiguang Lv, Chen Xu, Weiye Xi, Huanran Wang, Yuhang Zhang, Tianming Zhao, Wu Yang
Abstract: Federated learning (FL) is widely used in Internet-of-Things (IoT) systems, but its distributed training process also exposes it to backdoor attacks. Existing studies mainly consider single-target or centralized multi-target settings, while coordinated distributed multi-target attacks remain underexplored. In practical IoT scenarios, one adversarial entity may control multiple distributed malicious clients and assign each client distinct triggers and target labels. Under this setting, existing distributed backdoor methods often fail to preserve the effectiveness of all backdoors because malicious updates conflict during aggregation. To address this issue, we propose a Distributed Multi-Target Backdoor Attack (DMBA) for FL. DMBA introduces a Backdoor Replay (BR) mechanism to reduce discrepancies among malicious gradients and a Channel-Frequency Composite Trigger (CFCT) strategy to improve trigger distinguishability and alleviate local interference. Experiments on multiple datasets show that DMBA ensures attack success rates above 80% for all implanted backdoors, whereas some baseline backdoors fall below 50% and may even approach 0.
Authors: Jian Shi, Qian Wang, Zhenyu Li, Wenqing Cui, Ramzi Idoughi, Peter Wonka
Abstract: Generating high-quality stereo videos requires consistent depth perception and temporal coherence across frames. Despite advances in image and video synthesis using diffusion models, producing high-quality stereo videos remains a challenging task due to the difficulty of maintaining consistent temporal and spatial coherence between left and right views. We introduce DissolveStereo, a novel framework for zero-shot stereo video generation that leverages video diffusion priors without requiring paired training data. Our key innovations include a noisy restart strategy to initialize stereo-aware latent representations and an iterative refinement process that progressively harmonizes the latent space, addressing issues like temporal flickering and view inconsistencies. Importantly, we propose the use of dissolved depth maps to streamline latent space operations by reducing high-frequency depth information. Our comprehensive evaluations, including quantitative metrics and user studies, demonstrate that DissolveStereo produces high-quality stereo videos with enhanced depth consistency and temporal smoothness. In terms of epipolar consistency, our method achieves an 11.7% improvement in MEt3R score over the current state-of-the-art. Furthermore, user studies indicate strong perceptual gains over the previous arts, with an 8.0% higher perceived frame quality and 10.9% higher perceived temporal coherence. Our code is in https://github.com/shijianjian/DissolveStereo.
Authors: Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura
Abstract: Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html
Authors: Priyanto Hidayatullah, Nurjannah Syakrani, Muhammad Rizqi Sholahuddin, Trisna Gelar, Refdinal Tubagus
Abstract: Note: This is a preliminary version of the manuscript. The final, peer-reviewed, and substantially revised version has been published in Jurnal RESTI. Readers are encouraged to access and cite the published version: DOI: https://doi.org/10.29207/resti.v10i2.6598 In the field of deep learning-based computer vision, YOLO is revolutionary. With respect to deep learning models, YOLO is also the one that is evolving the most rapidly. Unfortunately, not every YOLO model possesses scholarly publications. Moreover, there exists a YOLO model that lacks a publicly accessible official architectural diagram. Naturally, this engenders challenges, such as complicating the understanding of how the model operates in practice. Furthermore, the review articles that are presently available do not investigate the specifics of each model. The objective of this study is to present a comprehensive and in-depth architecture comparison of the four most recent YOLO models, specifically YOLOv8 through YOLO11, thereby enabling readers to quickly grasp not only how each model functions, but also the distinctions between them. To analyze each YOLO version's architecture, we meticulously examined the relevant academic papers, documentation, and scrutinized the source code. The analysis reveals that while each version of YOLO has improvements in architecture and feature extraction, certain blocks remain unchanged. The lack of scholarly publications and official diagrams presents challenges for understanding the model's functionality and future enhancement. Future developers are encouraged to provide these resources.
Authors: Shulong Zhang, Daoliang Li, Jiayin Zhao, Mingyuan Yao, Yingyi Chen, Haihua Wang
Abstract: Fish feeding behavior analysis is a key foundation for intelligent feeding and precision aquaculture management, and plays an important role in improving feed utilization efficiency, reducing production costs, and mitigating environmental burden. Existing reviews mainly focus on specific technical modalities or related applications in smart aquaculture, which makes it difficult to present the overall development of fish feeding behavior analysis in a comprehensive manner. To address these issues, this paper provides a thematic review of fish feeding behavior analysis in aquaculture, and systematically examines its task definition, technical support, and application status. First, from the task perspective, two core subtasks of fish feeding behavior analysis are clearly distinguished, and relevant behavioral characteristics and evaluation metrics are summarized. Second, from the technical perspective, the development trajectories of computer vision, acoustics, sensors, and multimodal fusion technologies are examined, and their advantages, limitations, and applicable scenarios are analyzed. On this basis, the application value of fish feeding behavior analysis in intelligent feeding and aquaculture management is further summarized. Finally, this paper discusses the challenges in robust perception under complex environments, generalization across fish species and farming scenarios, collaborative multimodal modeling and lightweight deployment, closed loop intelligent feeding, coordinated optimization of multiple tasks, and long-term production validation, and outlines future research directions. This review provides a reference for task standardization, technical selection, and engineering application in fish feeding behavior analysis, and offers insights into the development of smart aquaculture and sustainable aquaculture management.
Authors: Jen-Tse Huang, Dasen Dai, Jen-Yuan Huang, Youliang Yuan, Xiaoyuan Liu, Wenxuan Wang, Wenxiang Jiao, Pinjia He, Zhaopeng Tu, Haodong Duan
Abstract: Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models (MLLMs) are trained directly on complex downstream tasks, often bypassing these foundational visual capabilities. To systematically investigate this gap, we introduce VisFactor, a benchmark that digitizes 20 vision-centric subtests from FRCT, a well-established cognitive psychology assessment spanning four domains of human visual cognition. Furthermore, we design algorithms to automatically construct and validate unlimited test cases with controllable difficulty. Using VisFactor, we evaluate 39 frontier MLLMs, including both proprietary (e.g., GPT, Gemini) and open-source (e.g., LLaMA, Qwen) models. The best model achieves a score of only 54.0%. Analysis reveals good internal consistency (Cronbach's alpha = 0.94) and construct validity (compared to existing vision benchmarks). Models consistently fail on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination, regardless of model size or prompting strategy. These findings suggest that performance improvements on existing general benchmarks might represent castles in the air instead of a genuine mastery of human-like visual cognition.
Authors: Peizhen Zheng, Dongjing Jiang, Qingchong Jiao, Redouane EL Bouchtaoui, Flynnwell Jianfei Zhang
Abstract: The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving objects, occlusions, and real-time processing constraints, limiting their effectiveness in complex urban environments. While multi-view stereo and neural radiance fields have advanced 3D reconstruction, they face challenges in computational efficiency and handling scene dynamics. This paper proposes a novel 3D Gaussian point distribution method for dynamic street scene reconstruction. Our approach introduces an adaptive transparency mechanism that eliminates moving objects while preserving high-fidelity static scene details. Additionally, iterative refinement of Gaussian point distribution enhances geometric accuracy and texture representation. We integrate directional encoding with spatial position optimization to optimize storage and rendering efficiency, reducing redundancy while maintaining scene integrity. Experimental results demonstrate that our method achieves high reconstruction quality, improved rendering performance, and adaptability in large-scale dynamic environments. These contributions establish a robust framework for real-time, high-precision 3D reconstruction, advancing the practicality of dynamic scene modeling across multiple applications. The source code for this work is available to the public at https://github.com/okic-ca/3dgs
Authors: Susung Hong, Ira Kemelmacher-Shlizerman, Brian Curless, Steven M. Seitz
Abstract: We introduce MusicInfuser, an approach that aligns pre-trained text-to-video diffusion models to generate high-quality dance videos synchronized with specified music tracks. Rather than training a multimodal audio-video or audio-motion model from scratch, our method demonstrates how existing video diffusion models can be efficiently adapted to align with musical inputs. We propose a novel layer-wise adaptability criterion based on a guidance-inspired constructive influence function to select adaptable layers, significantly reducing training costs while preserving rich prior knowledge, even with limited, specialized datasets. Experiments show that MusicInfuser effectively bridges the gap between music and video, generating novel and diverse dance movements that respond dynamically to music. Furthermore, our framework generalizes well to unseen music tracks, longer video sequences, and unconventional subjects, outperforming baseline models in consistency and synchronization. All of this is achieved without requiring motion data, with training completed on a single GPU within a day.
Authors: Suraj Singh, Anastasia Batsheva, Oleg Y. Rogov, Ahmed Bouridane
Abstract: Modern image restoration and super-resolution methods utilize deep learning due to its superior performance compared to traditional algorithms. However, deep learning typically requires large labeled training datasets, which are rarely available in astrophotography. Deep Image Prior (DIP) bypasses this constraint by performing unsupervised optimization on a single image without training data; however, DIP often suffers from overfitting, artifact generation, and instability. This work proposes DIPLI - a framework designed specifically for resolved, high-contrast astronomical targets that shifts from single-frame to multi-frame processing using the Back Projection technique, combined with dense optical flow estimation via the TVNet model, and replaces deterministic predictions with Monte Carlo estimation obtained through Stochastic Gradient Langevin Dynamics (SGLD). A comprehensive evaluation compares the method against the original DIP, the transformer-based model RVRT, and the diffusion-based model DiffIR2VR-Zero on synthetic data with ground truth, while comparing qualitatively against Lucky Imaging on real astronomical data. On synthetic datasets, DIPLI achieves the best perceptual fidelity scores (LPIPS in 12/12 and DISTS in 10/12 scenarios), while the diffusion-based DiffIR2VR-Zero achieves the best pixel-level distortion scores (PSNR in 9/12 and SSIM in 8/12 scenarios), consistent with the well-known perceptual-distortion trade-off in image restoration. Compared to classical Lucky Imaging, the model requires far fewer input frames (7-13 versus thousands) and avoids the need for early stopping that limits standard DIP. Qualitative evaluation on real-world data of resolved solar-system objects, where ground truth is unavailable and domain shifts typically hinder generalization, suggests that the method appears to preserve fine detail while suppressing noise and artifacts.
Authors: Qian Wang, Zhihao Zhan, Jialei He, Zhituo Tu, Jie Yuan
Abstract: Highly accurate geometric precision and dense image features characterize True Digital Orthophoto Maps (TDOMs), which are in great demand for applications such as urban planning, infrastructure management, and environmental monitoring. Traditional TDOM generation methods need sophisticated processes, such as Digital Surface Models (DSM) and occlusion detection, which are computationally expensive and prone to errors. This work presents an alternative technique rooted in 2D Gaussian Splatting (2DGS), free of explicit DSM and occlusion detection. With depth map generation, spatial information for every pixel within the TDOM is retrieved and can reconstruct the scene with high precision. Divide-and-conquer strategy achieves excellent GS training and rendering with high-resolution TDOMs at a lower resource cost, which preserves higher quality of rendering on complex terrain and thin structure without a decrease in efficiency. Experimental results demonstrate the efficiency of large-scale scene reconstruction and high-precision terrain modeling. This approach provides accurate spatial data, which assists users in better planning and decision-making based on maps.
Authors: Xu Wang, Jialang Xu, Shuai Zhang, Baoru Huang, Danail Stoyanov, Evangelos B. Mazomenos
Abstract: Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep learning methods have made significant advancements, challenges remain in achieving an optimal balance between accuracy, robustness, and inference speed. To address these challenges, we propose the StereoMamba architecture, which is specifically designed for stereo disparity estimation in RAMIS. Our approach is based on a novel Feature Extraction Mamba (FE-Mamba) module, which enhances long-range spatial dependencies both within and across stereo images. To effectively integrate multi-scale features from FE-Mamba, we then introduce a novel Multidimensional Feature Fusion (MFF) module. Experiments against the state-of-the-art on the ex-vivo SCARED benchmark demonstrate that StereoMamba achieves superior performance on EPE of 2.64 px and depth MAE of 2.55 mm, the second-best performance on Bad2 of 41.49% and Bad3 of 26.99%, while maintaining an inference speed of 21.28 FPS for a pair of high-resolution images (1280*1024), striking the optimum balance between accuracy, robustness, and efficiency. Furthermore, by comparing synthesized right images, generated from warping left images using the generated disparity maps, with the actual right image, StereoMamba achieves the best average SSIM (0.8970) and PSNR (16.0761), exhibiting strong zero-shot generalization on the in-vivo RIS2017 and StereoMIS datasets.
Authors: Miaoyun Zhao, Qiang Zhang
Abstract: Achieving group-robust generalization in the presence of spurious correlations remains a significant challenge, particularly when bias annotations are unavailable. Recent studies on Class-Conditional Distribution Balancing (CCDB) reveal that spurious correlations often stem from mismatches between the class-conditional and marginal distributions of bias attributes. They achieve promising results by addressing this issue through simple distribution matching in a bias-agnostic manner. However, CCDB approximates each distribution using a single Gaussian, which is overly simplistic and rarely holds in real-world applications. To address this limitation, we propose a novel Multi-stage data-Selective reTraining strategy (MST), which describes each distribution in greater detail using the hard confusion matrix. Building on these finer descriptions, we propose a fine-grained variant of CCDB, termed FG-CCDB, which enhances distribution matching through more precise confusion-cell-wise reweighting. FG-CCDB learns sample weights from a global perspective, effectively mitigating spurious correlations without incurring substantial storage or computational overhead. Extensive experiments demonstrate that MST serves as a reliable proxy for ground-truth bias annotations and can be seamlessly integrated with bias-supervised methods. Moreover, when combined with FG-CCDB, our method performs on par with bias-supervised approaches on binary classification tasks and significantly outperforms them in highly biased multi-class and multi-shortcut scenarios.
Authors: Bo Li, Haoke Xiao, Lv Tang
Abstract: Vision Mamba offers linear complexity for long visual sequences, yet its performance depends critically on how a two-dimensional patch grid is serialized into a one-dimensional state-space recurrence. Raster-style scans disrupt spatial continuity, and the mismatch between 2D locality and 1D state propagation becomes increasingly severe when the inference resolution grows beyond the training grid. This paper presents FractalMamba++, a resolution-scalable vision backbone organized around a single geometric principle: the recursive self-similar structure of the Hilbert curve determines how patches are serialized, where long-range state shortcuts are inserted, and how positional relations are encoded. First, Hilbert-curve-based Fractal Serialization preserves local 2D neighborhoods more faithfully than linear scans and provides consistent neighborhood statistics across resolutions. Second, the Fractal Hierarchy Skip Connection (FHSC) derives a compact set of deterministic state-injection routes from Hilbert recursion levels, mitigating long-sequence information fading without runtime search, hand-derived gradients, or dedicated CUDA kernels. Third, Fractal-Aware 2D Rotary Position Encoding (FA-RoPE) combines normalized 2D coordinates with a fractal hierarchy level so that feature interactions depend on actual spatial proximity and recursive structural role rather than serialized 1D distance. Extensive experiments on ImageNet-1K classification, COCO detection and instance segmentation, ADE20K semantic segmentation, and LEVIR-CD+ remote sensing change detection show that FractalMamba++ improves over existing Mamba-based vision backbones, especially under high-resolution inputs.
Authors: Lei Lei, Jie Gu, Xiaokang Ma, Chu Tang, Jingmin Chen, Tong Xu
Abstract: Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which aligns well with MLLMs ultimate goal of instruction following. Previous works generally assume that visual tokens achieve better vision-language alignment in the shallow layers of LLMs, which have led to task-related token compression being primarily applied in intermediate LLM layers. In contrast, our study reveals that with proper selection, task-related token compression is feasible at the input stage of LLM with negligible performance loss. This new paradigm significantly reduces task-irrelevant visual tokens and its model-agnostic design enables application without modifying the LLM architecture. Specifically, we suggest that explainability methods for transformer-based architechtures can evaluate the global importance of each visual token with respect to the given instruction, which can effectively guide the task-related token compression for MLLMs. Furthermore, we propose to learn a mapping from the attention map of the first LLM layer to the explanation results, thereby avoiding the need for a full inference pass. Interestingly, this mapping can be learned using a simple and lightweight convolutional network, whose training is efficient and independent of MLLMs. Extensive experiments on 13 image and video benchmarks across three leading MLLMs (Qwen2-VL, LLaVA-OneVision, and VILA1.5) demonstrate the remarkable effectiveness and strong generalization of our approach. Additionally, our new compression paradigm achieves faster inference with reductions in both prefilling time and KV cache memory.
Authors: Dongjie Fu, Tengjiao Sun, Pengcheng Fang, Xiaohao Cai, Hansung Kim
Abstract: Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Nevertheless, jointly achieving high fidelity, streaming capability, real-time responsiveness, and scalability remains a fundamental challenge. In this paper, we propose MOGO (Motion Generation with One-pass), a novel autoregressive framework tailored for efficient and real-time 3D motion generation. MOGO comprises two key components: (1) MoSA-VQ, a motion scale-adaptive residual vector quantization module that hierarchically discretizes motion sequences with learnable scaling to produce compact yet expressive representations; and (2) RQHC-Transformer, a residual quantized hierarchical causal transformer that generates multi-layer motion tokens in a single forward pass, significantly reducing inference latency. To enhance semantic fidelity, we further introduce a text condition alignment mechanism that improves motion decoding under textual control. Extensive experiments on benchmark datasets including HumanML3D, KIT-ML, and CMP demonstrate that MOGO achieves competitive or superior generation quality compared to state-of-the-art transformer-based methods, while offering substantial improvements in real-time performance, streaming generation, and generalization under zero-shot settings.
Authors: Jingguo Qu, Xinyang Han, Jia Ai, Juan Wu, Tong Zhao, Tonghuan Xiao, Sheng Ning, Yuqi Yang, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying
Abstract: Vision-Language Foundation Models (VLFMs) exhibit remarkable generalization, yet their direct application to medical ultrasound is severely hindered by a profound modality gap. The unique acoustic physics of ultrasound, characterized by speckle noise, shadowing, and heterogeneous textures, often degrades the performance of off-the-shelf VLFMs. To bridge this gap, we propose a novel Hybrid Tuning (HT) strategy for the parameter-efficient adaptation of CLIP-based models to ultrasound analysis. Instead of updating the pre-trained weights, HT freezes the visual backbone and integrates a specialized lightweight adapter. This adapter features a Frequency Filtering module to suppress domain-specific periodic artifacts and a Noise Estimation module to dynamically calibrate feature representations. Extensive evaluations across six multi-center datasets demonstrate that our HT-enhanced models significantly outperform existing state-of-the-art adapters and medical VLFMs in both segmentation and classification tasks. Notably, HT exhibits exceptional data efficiency in few-shot scenarios and robust cross-dataset generalization. Our findings prove that preserving pre-trained semantic priors while explicitly modeling ultrasound-specific noise is key to unlocking foundational intelligence in automated ultrasound diagnosis. The source code is available at https://github.com/jinggqu/NextGen-UIA.
Authors: Zheda Mai, Arpita Chowdhury, Zihe Wang, Sooyoung Jeon, Lemeng Wang, Jiacheng Hou, Jihyung Kil, Wei-Lun Chao
Abstract: The rise of vision foundation models (VFMs) calls for systematic evaluation. A common approach pairs VFMs with large language models (LLMs) as general-purpose heads, followed by evaluation on broad Visual Question Answering (VQA) benchmarks. However, this protocol has two key blind spots: (i) the instruction tuning data may not align with VQA test distributions, meaning a wrong prediction can stem from such data mismatch rather than a VFM' visual shortcomings; (ii) VQA benchmarks often require multiple visual abilities, making it hard to tell whether errors stem from lacking all required abilities or just a single critical one. To address these gaps, we introduce AVA-Bench, the first benchmark that explicitly disentangles 14 Atomic Visual Abilities (AVAs) -- foundational skills like localization, depth estimation, and spatial understanding that collectively support complex visual reasoning tasks. By decoupling AVAs and matching training and test distributions within each, AVA-Bench pinpoints exactly where a VFM excels or falters. Applying AVA-Bench to leading VFMs thus reveals distinctive "ability fingerprints," turning VFM selection from educated guesswork into principled engineering. Notably, we find that a 0.5B LLM yields similar VFM rankings as a 7B LLM while cutting GPU hours by 8x, enabling more efficient evaluation. By offering a comprehensive and transparent benchmark, we hope AVA-Bench lays the foundation for the next generation of VFMs.
Authors: Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
Abstract: The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods depend heavily either on supervised annotations or on attention-based models, which are computationally expensive and brittle in the face of distribution shifts that hinder cross-domain applicability across datasets. We introduce a pioneering self-supervised video summarization model that captures both spatial and temporal dependencies without the overhead of attention, RNNs, or transformers. Our framework integrates a novel set of Markov process-driven loss metrics and a two-stage self supervised learning paradigm that ensures both performance and efficiency. Our approach achieves state-of-the-art performance on the SUMME and TVSUM datasets, outperforming all existing unsupervised methods. It also rivals the best supervised models, demonstrating the potential for efficient, annotation-free architectures. This paves the way for more generalizable video summarization techniques and challenges the prevailing reliance on complex architectures.
Authors: Ehsan Pajouheshgar, Yitao Xu, Ali Abbasi, Alexander Mordvintsev, Wenzel Jakob, Sabine S\"usstrunk
Abstract: Neural Cellular Automata (NCAs) are bio-inspired dynamical systems in which identical cells iteratively apply a learned local update rule to self-organize into complex patterns, exhibiting regeneration, robustness, and spontaneous dynamics. Despite their success in texture synthesis and morphogenesis, NCAs remain largely confined to low-resolution outputs. This limitation stems from (1) training time and memory requirements that grow quadratically with grid size, (2) the strictly local propagation of information that impedes long-range cell communication, and (3) the heavy compute demands of real-time inference at high resolution. In this work, we overcome this limitation by pairing an NCA that evolves on a coarse grid with a lightweight implicit decoder that maps cell states and local coordinates to appearance attributes, enabling the same model to render outputs at arbitrary resolution. Moreover, because both the decoder and NCA updates are local, inference remains highly parallelizable. To supervise high-resolution outputs efficiently, we introduce task-specific losses for morphogenesis (growth from a seed) and texture synthesis with minimal additional memory and computation overhead. Our experiments across 2D/3D grids and mesh domains demonstrate that our hybrid models produce high-resolution outputs in real-time, and preserve the characteristic self-organizing behavior of NCAs.
Authors: Guangrui Bai, Hailong Yan, Wenhai Liu, Yahui Deng, Erbao Dong
Abstract: Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, limiting their deployment on resource-constrained platforms. In this paper, we propose LiteIE, an ultra-lightweight unsupervised enhancement framework that eliminates dependence on large-scale supervision and generalizes well across diverse conditions. We design a backbone-agnostic feature extractor with only two convolutional layers to produce compact image features enhancement tensors. In addition, we develop a parameter-free Iterative Restoration Module, which reuses the extracted features to progressively recover fine details lost in earlier enhancement steps, without introducing any additional learnable parameters. We further propose an unsupervised training objective that integrates exposure control, edge-aware smoothness, and multi-scale color consistency losses. Experiments on the LOL dataset, LiteIE achieves 19.04 dB PSNR, surpassing SOTA by 1.4 dB while using only 0.07\% of its parameters. On a Snapdragon 8 Gen 3 mobile processor, LiteIE runs at 30 FPS for 4K images with just 58 parameters, enabling real-time deployment on edge devices. These results establish LiteIE as an efficient and practical solution for low-light enhancement on resource-limited platforms.
Authors: Yun Chen, Matthew Haines, Jingkang Wang, Sahil Jain, Krzysztof Baron-Lis, Sivabalan Manivasagam, Ze Yang, Raquel Urtasun
Abstract: High-fidelity sensor simulation of light-based sensors such as cameras and LiDARs is critical for safe and accurate autonomy testing. Neural radiance field (NeRF)-based methods that reconstruct sensor observations via ray-casting of implicit representations have demonstrated accurate simulation of driving scenes, but are slow to train and render, hampering scalability. 3D Gaussian Splatting (3DGS) has demonstrated faster training and rendering times through rasterization, but is primarily restricted to pinhole camera sensors, preventing usage for realistic multi-sensor autonomy evaluation. Moreover, both NeRF and 3DGS couple the representation with the rendering procedure (implicit networks for ray-based evaluation, particles for rasterization), preventing interoperability, which is key for general usage. In this work, we present Sparse Local Fields (SaLF), a novel volumetric representation that supports rasterization and raytracing for unified multi-sensor simulation. SaLF represents volumes as a sparse set of 3D voxel primitives, where each voxel is a local implicit field. SaLF has fast training ($<$30 min) and rendering capabilities (50+ FPS for camera and 600+ FPS for LiDAR), has adaptive pruning and densification to easily handle large scenes, and can support non-pinhole cameras and spinning LiDARs. We demonstrate that SaLF has similar realism as existing self-driving sensor simulation methods while improving efficiency and enhancing capabilities, enabling more scalable simulation.
Authors: Babak Taati, Muhammad Muzammil, Yasamin Zarghami, Abhishek Moturu, Amirhossein Kazerouni, Hailey Reimer, Alex Mihailidis, Thomas Hadjistavropoulos
Abstract: Accurate pain assessment in patients with limited ability to communicate, such as older adults with severe dementia, represents a critical healthcare challenge. Robust automated systems of pain behavior detection may facilitate such assessments. Existing pain detection datasets, however, suffer from limited ethnic/racial diversity, privacy constraints, and underrepresentation of older adults who are the primary target population for clinical deployment. We present SynPAIN, a large-scale synthetic dataset containing 10,710 facial expression images across five ethnicities/races, representing two age groups, and two genders. Using commercial generative AI tools, we created demographically balanced synthetic identities with clinically meaningful pain expressions. Our validation demonstrates that synthetic pain expressions exhibit expected pain patterns, scoring significantly higher than neutral and non-pain expressions using clinically validated pain assessment tools based on facial action unit analysis. We experimentally demonstrate SynPAIN's utility in identifying algorithmic bias in existing pain detection models. Through comprehensive bias evaluation, we reveal substantial performance disparities across demographics characteristics. These performance disparities were previously undetectable with smaller, less diverse datasets. Furthermore, we demonstrate that age-matched synthetic data augmentation improves pain detection performance on real clinical data, achieving a 2.4 percentage point improvement in average precision. SynPAIN addresses critical gaps in pain assessment research by providing the first publicly available, demographically diverse synthetic dataset specifically designed for older adult pain detection, while establishing a framework for measuring and mitigating algorithmic bias. The dataset, code, and trained models is available at https://mmzml.github.io/SynPAIN
Authors: Ece Takmaz, Albert Gatt, Jakub Dotlacil
Abstract: Images vary in how memorable they are to humans. Inspired by findings from cognitive science and computer vision, we explore correlates of image memorability in pretrained transformer-based vision encoders for the first time. Focusing initially on activations, attention distributions, and the uniformity of image patches, we find that these features correlate with memorability to some extent. Additionally, we explore sparse autoencoder loss over the representations of vision encoders as a proxy for memorability, which yields results outperforming past methods using convolutional neural network representations. Our results shed light on the relationship between model-internal features and memorability. They show that some features are informative predictors of what makes images memorable to humans; revealing that, in particular, the reconstruction loss from our autoencoders is a strong correlate of image memorability.
Authors: Aymen Bouguerra, Daniel Montoya, Alexandra Gomez-Villa, Chokri Mraidha, Fabio Arnez
Abstract: Vision-Language Models (VLMs) such as CLIP have revolutionized zero-shot classification and safety-critical tasks, including Out-of-Distribution (OOD) detection. However, their high computational cost hinders efficient real-world deployment. While quantization is a standard solution for efficiency, its broader impact on reliability metrics beyond simple Top-1 accuracy remains critically under-explored. In this study, we conduct a large-scale evaluation of VLM quantization across a comprehensive experimental suite of over 700k evaluation runs with varying configurations. We find that, contrary to the assumption that quantization's noise degrades performance, it can simultaneously improve accuracy, calibration, OOD detection, and robustness to noise, though not to covariate shift or spurious correlations. We leverage these counterintuitive findings to characterize the mechanics of quantization beyond simple regularization: we show that quantization dampens high-rank spectral components, compelling the model to rely more heavily on robust, low-rank features. Ultimately, this spectral filtering effect drives the observed improvements in generalization and noise tolerance, establishing a pathway to deploy faster, more reliable VLMs by utilizing quantization beyond its conventional role.
Authors: Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi
Abstract: Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense captioning and region-set captioning. We also introduce a new trace captioning task that further demonstrates the effectiveness of patch-wise semantic representations for flexible caption generation. Project page at https://paciosoft.com/Patch-ioner/ .
Authors: Xiaoyu Yang, En Yu, Wei Duan, Jie Lu
Abstract: This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory. We propose Autonomous Preference Optimization (APO), a novel framework that treats inter-model divergences not as noise, but as dynamic negative constraints. APO operates via a two-stage protocol: first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative Plackett-Luce objective. Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark comprising 170,982 reasoning trajectories from seven large-scale MLLMs to facilitate research on reasoning alignment under drift. Code and data are available at: https://github.com/XiaoyuYoung/APO.
Authors: Shikun Liu, Kam Woh Ng, Wonbong Jang, Jiadong Guo, Junlin Han, Haozhe Liu, Yiannis Douratsos, Juan C. P\'erez, Zijian Zhou, Chi Phung, Tao Xiang, Juan-Manuel P\'erez-R\'ua
Abstract: We present Kaleido, a family of generative models designed for photorealistic, unified object- and scene-level neural rendering. Kaleido operates on the principle that 3D can be regarded as a specialised sub-domain of video, expressed purely as a sequence-to-sequence image synthesis task. Through a systemic study of scaling sequence-to-sequence generative neural rendering, we introduce key architectural innovations that enable our model to: i) perform generative view synthesis without explicit 3D representations; ii) generate any number of 6-DoF target views conditioned on any number of reference views via a masked autoregressive framework; and iii) seamlessly unify 3D and video modelling within a single decoder-only rectified flow transformer. Within this unified framework, Kaleido leverages large-scale video data for pre-training, which significantly improves spatial consistency and reduces reliance on scarce, camera-labelled 3D datasets -- all without any architectural modifications. Kaleido sets a new state-of-the-art on a range of view synthesis benchmarks. Its zero-shot performance substantially outperforms other generative methods in few-view settings, and, for the first time, matches the quality of per-scene optimisation methods in many-view settings.
Authors: Zhantao Deng, M\'eriem Er-Rafik, Anna Sushko, C\'ecile H\'ebert, Pascal Fua
Abstract: Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles, but it suffers from the missing-wedge problem that causes severe reconstruction artifacts. Deep learning approaches have shown promising results in alleviating these artifacts, yet they typically require large high-quality training datasets with known 3D ground truth which are difficult to obtain in electron microscopy. To address these challenges, we propose TEMDiff, a novel 3D diffusion-based iterative reconstruction framework. Our method is trained on readily available volumetric FIB-SEM data using a simulator that maps them to TEM tilt series, enabling the model to learn realistic structural priors without requiring clean TEM ground truth. By operating directly on 3D volumes, TEMDiff implicitly enforces consistency across slices without the need for additional regularization. On simulated electron tomography datasets with limited angular coverage, TEMDiff outperforms state-of-the-art methods in reconstruction quality. We further demonstrate that a trained TEMDiff model generalizes well to real-world TEM tilts obtained under different conditions and can recover accurate structures from tilt ranges as narrow as 8 degrees, with 2-degree increments, without any retraining or fine-tuning.
Authors: Minkwan Kim, Changwoon Choi, Young Min Kim
Abstract: We propose scene-adaptive strategies to efficiently allocate representation capacity for generating immersive experiences of indoor environments from incomplete observations. Indoor scenes with multiple rooms often exhibit irregular layouts with varying complexity, containing clutter, occlusion, and flat walls. We maximize the utilization of limited resources with guidance from geometric priors, which are often readily available after pre-processing stages. We record observation statistics on the estimated geometric scaffold and guide the optimal placement of bases, which greatly improves upon the uniform basis arrangements adopted by previous scalable Neural Radiance Field (NeRF) representations. We also suggest scene-adaptive virtual viewpoints to compensate for geometric deficiencies inherent in view configurations in the input trajectory and impose the necessary regularization. We present a comprehensive analysis and discussion regarding rendering quality and memory requirements in several large-scale indoor scenes, demonstrating significant enhancements compared to baselines that employ regular placements. Project page is available at: https://mkjjang3598.github.io/Geo-Scene-Config.
Authors: Connor Lane, Mihir Tripathy, Leema Krishna Murali, Ratna Sagari Grandhi, Shamus Sim Zi Yang, Sam Gijsen, Debojyoti Das, Manish Ram, Utkarsh Kumar Singh, Cesar Kadir Torrico Villanueva, Yuxiang Wei, Will Beddow, Gianfranco Cort\'es, Suin Cho, Daniel Z. Kaplan, Benjamin Warner, Tanishq Mathew Abraham, Paul S. Scotti
Abstract: We study the problem of training self-supervised foundation models for functional MRI. Our main contributions are: (1) we introduce a new model family (CortexMAE) trained using the masked autoencoder framework on 2.1K hours of open fMRI data, and (2) we release the first open evaluation suite (Brainmarks) for fMRI foundation models. Our core innovation is simple: we adapt the Vision Transformer to fMRI by first converting each 3D fMRI volume to a 2D map using a cortical flat map projection. We directly compare flat maps to both parcellation and volume-based representations. While each has its advantages, flat maps generally perform best. We perform the first systematic scaling analysis for fMRI and observe strict power law scaling, albeit with limits. Finally, we use Brainmarks to do controlled benchmark comparisons. On subject-level trait prediction, we report a challenging null result: no single model achieves clear state-of-the-art performance. Moreover, all models struggle to outperform a simple functional connectivity baseline. On cognitive state decoding, we observe more robust performance, and in this setting our CortexMAE family outperforms prior models by a large margin. Code, models, and datasets are available at https://github.com/MedARC-AI/CortexMAE and https://github.com/MedARC-AI/Brainmarks.
URLs: https://github.com/MedARC-AI/CortexMAE, https://github.com/MedARC-AI/Brainmarks.
Authors: Kenneth Yang, Wen-Li Wei, Jen-Chun Lin
Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key strategy for adapting large-scale pre-trained models to downstream tasks, but existing approaches face notable limitations. Addition-based methods, such as Adapters, introduce inference latency and engineering complexity, whereas selection-based methods like Gradient-based Parameter Selection (GPS) require a full backward pass. The reliance on gradients not only incurs massive memory usage and substantial computational latency, but also leaves the selection vulnerable to the randomness of stochastic batch sampling. To resolve this, we propose Growth-Driven Feedforward Parameter Selection (GD-FPS). Operating entirely via forward passes, this strictly gradient-free method identifies the optimal parameter subset by scaling intrinsic weight magnitudes by their relative activation growth against a pre-training anchor. Evaluated on $26$ visual tasks spanning image classification and semantic segmentation, GD-FPS achieves competitive or superior performance over state-of-the-art PEFT baselines. Crucially, compared to GPS, it reduces peak memory usage by nearly $18\times$ and accelerates execution by over $2.7\times$ during the parameter selection stage. By guaranteeing deterministic selection, GD-FPS offers a memory-efficient, fast, and robust solution for fine-tuning.
Authors: Kai Luo, Hao Shi, Kunyu Peng, Fei Teng, Sheng Wu, Kaiwei Wang, Kailun Yang
Abstract: To address panoramic distortion, large search space, and identity ambiguity under a 360{\deg} FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception with trajectory cues. A DynamicSSM block first stabilizes panoramic features, implicitly alleviating geometric distortion. On top of normalized representations, FlexiTrack Instances use trajectory-informed feedback for flexible localization and reliable short-term association. To ensure long-term robustness, an ExpertTrack Memory consolidates appearance cues via a Mixture-of-Experts design, enabling recovery from fragmented tracks and reducing identity drift. Finally, a Tracklet Management module adaptively switches between end-to-end and tracking-by-detection modes according to scene dynamics, offering a balanced and scalable solution for panoramic MOT. To support rigorous evaluation, we establish the EmboTrack benchmark, a comprehensive dataset for panoramic MOT that includes QuadTrack, captured with a quadruped robot, and BipTrack, collected with a bipedal wheel-legged robot. Together, these datasets span wide-angle environments and diverse motion patterns, providing a challenging testbed for real-world panoramic perception. Extensive experiments on JRDB and EmboTrack demonstrate that OmniTrack++ achieves state-of-the-art performance, yielding substantial HOTA improvements of +3.94 on JRDB and +15.03 on QuadTrack over the original OmniTrack. These results highlight the effectiveness of trajectory-informed feedback, adaptive paradigm switching, and robust long-term memory in advancing panoramic multi-object tracking. Datasets and code will be made available at https://github.com/xifen523/OmniTrack.
Authors: Song Yan, Wei Zhai, Chenfeng Wang, Xinliang Bi, Jian Yang, Yancheng Cai, Yusen Zhang, Yunwei Lan, Tao Zhang, GuanYe Xiong, Min Li, Zheng-Jun Zha
Abstract: Diffusion models start generation from an isotropic Gaussian latent, yet changing only the random seed can lead to large differences in prompt faithfulness, composition, and visual quality. We study this seed sensitivity through the semantic map from initial noise to generated meaning. Although the sampling flow is locally invertible, the subsequent semantic projection is many-to-one, inducing a degenerate pullback semi-metric on the latent space: most local directions are nearly semantic-invariant, while semantic-sensitive variation is concentrated in a much smaller horizontal subspace. This provides an explanatory geometric view of the seed lottery. Motivated by this view, we introduce a training-free prompt-residual seed-shaping procedure. Rather than claiming to recover the exact horizontal space, the method uses a single high-noise cold-start prompt residual as a model-coupled proxy, injects only its tangential component, and retracts the seed to the original Gaussian radius shell. This keeps the initialization prior-compatible while adding only one conditional/unconditional probe before standard sampling. Across multiple generation benchmarks, the method improves alignment and quality metrics over standard sampling, supporting both the practical value of the proxy and the explanatory relevance of semantic anisotropy.
Authors: Jiazhen Yan, Ziqiang Li, Fan Wang, Boyu Wang, Ziwen He, Zhangjie Fu
Abstract: The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, privacy violations, and trust erosion in digital media. Although large-scale multimodal models like CLIP offer strong transferable representations for detecting synthetic content, fine-tuning them often induces catastrophic forgetting, which degrades pre-trained priors and limits cross-domain generalization. To address this issue, we propose the Distillation-guided Gradient Surgery Network (DGS-Net), a novel framework that preserves transferable pre-trained priors while suppressing task-irrelevant components. Specifically, we introduce a gradient-space decomposition that separates harmful and beneficial descent directions during optimization. By projecting task gradients onto the orthogonal complement of harmful directions and aligning with beneficial ones distilled from a frozen CLIP encoder, DGS-Net achieves unified optimization of prior preservation and irrelevant suppression. Extensive experiments on 50 generative models demonstrate that our method outperforms state-of-the-art approaches by an average margin of 6.6%, achieving superior detection performance and generalization across diverse generation techniques.
Authors: Yue Yin, Enze Tao, Dylan Campbell
Abstract: Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which they perform notably poorly is in the synthesis of transparent objects, which exhibit refraction, reflection, absorption and scattering. Refraction is a particular challenge, because refracted pixel rays often intersect with surfaces observed in other parts of the image, providing a constraint on the color. It is clear from inspection that generative models have not distilled the laws of optics sufficiently well to accurately render refractive objects. In this work, we consider the problem of generating images with accurate refraction, given a text prompt. We synchronize the pixels within the object's boundary with those outside by warping and merging the pixels using Snell's Law of Refraction, at each step of the generation trajectory. For those surfaces that are not directly observed in the image, but are visible via refraction or reflection, we recover their appearance by synchronizing the image with a second generated image -- a panorama centered at the object -- using the same warping and merging procedure. We demonstrate that our approach generates much more optically-plausible images that respect the physical constraints.
Authors: Jie Li, Hongyi Cai, Mingkang Dong, Muxin Pu, Shan You, Fei Wang, Tao Huang
Abstract: Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced anomaly coverage, and temporal complexity needed to reliably assess real-world performance. Meanwhile, the community is increasingly moving toward Video Anomaly Understanding (VAU), which requires deeper semantic and causal reasoning but remains difficult to benchmark due to the heavy manual annotation effort it demands. In this paper, we introduce Pistachio, a new VAD/VAU benchmark constructed entirely through a controlled, generation-based pipeline. By leveraging recent advances in video generation models, Pistachio provides precise control over scenes, anomaly types, and temporal narratives, effectively eliminating the biases and limitations of Internet-collected datasets. Our pipeline integrates scene-conditioned anomaly assignment, multi-step storyline generation, and a temporally consistent long-form synthesis strategy that produces coherent 41-second videos with minimal human intervention. Extensive experiments demonstrate the scale, diversity, and complexity of Pistachio, revealing new challenges for existing methods and motivating future research on dynamic and multi-event anomaly understanding.
Authors: Hongyu Lyu, Thomas Monninger, Julie Stephany Berrio Perez, Mao Shan, Zhenxing Ming, Stewart Worrall
Abstract: Autonomous driving systems benefit from high-definition (HD) maps that provide critical information about road infrastructure. The online construction of HD maps offers a scalable approach to generate local maps from on-board sensors. However, existing methods typically rely on costly 3D map annotations for training, which limits their generalization and scalability across diverse driving environments. In this work, we propose MapRF, a weakly supervised framework that learns to construct 3D maps using only 2D image labels. To generate high-quality pseudo labels, we introduce a novel Neural Radiance Fields (NeRF) module conditioned on map predictions, which reconstructs view-consistent 3D geometry and semantics. These pseudo labels are then iteratively used to refine the map network in a self-training manner, enabling progressive improvement without additional supervision. Furthermore, to mitigate error accumulation during self-training, we propose a Map-to-Ray Matching strategy that aligns map predictions with camera rays derived from 2D labels. Extensive experiments on the Argoverse 2 and nuScenes datasets demonstrate that MapRF achieves performance comparable to fully supervised methods, attaining around 75% of the baseline while surpassing several approaches using only 2D labels. This highlights the potential of MapRF to enable scalable and cost-effective online HD map construction for autonomous driving.
Authors: Ke Liu, Shangde Gao, Yichao Fu, Shuaike Shen, Shangqi Gao, Chunhua Shen
Abstract: Lesion segmentation is inherently influenced by imaging uncertainty, arising from ill-defined lesion boundaries and inter-observer variability in diagnosis. To address this challenge, previous works formulated the multi-rater medical image segmentation task, where multiple experts provide separate annotations for each image. However, existing models are typically constrained to either generate diverse segmentation that lacks expert specificity or to produce personalized outputs that merely replicate individual annotators. We propose \textbf{Pro}babilistic modeling of multi-rater lesion \textbf{Seg}mentation (\textbf{ProSeg}) that simultaneously enables both diversification and personalization. Specifically, we introduce two latent variables to model expert annotation preferences and lesion boundary ambiguity. Their conditional probabilistic distributions are then obtained through variational inference, allowing segmentation outputs to be generated by sampling from these distributions. Extensive experiments on both the nasopharyngeal carcinoma dataset (NPC) and the lung nodule dataset (LIDC-IDRI) demonstrate that our ProSeg achieves a new state-of-the-art performance, providing segmentation results that are both diverse and expert-personalized.
Authors: Jingkang Wang, Henry Che, Yun Chen, Ze Yang, Lily Goli, Sivabalan Manivasagam, Raquel Urtasun
Abstract: Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have achieved impressive photorealistic reconstruction, they suffer from scalability limitations and require annotations to decouple actor motion. Existing self-supervised methods attempt to eliminate explicit annotations by leveraging motion cues and geometric priors, yet they remain constrained by per-scene optimization and sensitivity to hyperparameter tuning. In this paper, we introduce Flux4D, a simple and scalable framework for 4D reconstruction of large-scale dynamic scenes. Flux4D directly predicts 3D Gaussians and their motion dynamics to reconstruct sensor observations in a fully unsupervised manner. By adopting only photometric losses and enforcing an "as static as possible" regularization, Flux4D learns to decompose dynamic elements directly from raw data without requiring pre-trained supervised models or foundational priors simply by training across many scenes. Our approach enables efficient reconstruction of dynamic scenes within seconds, scales effectively to large datasets, and generalizes well to unseen environments, including rare and unknown objects. Experiments on outdoor driving datasets show Flux4D significantly outperforms existing methods in scalability, generalization, and reconstruction quality.
Authors: Alexander Goslin
Abstract: For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. Conversely, diffusion models offer unprecedented fidelity but remain generally confined to bounded canvases. We introduce InfiniteDiffusion, a training-free algorithm that reformulates diffusion sampling for lazy and unbounded generation, bridging the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. To demonstrate the utility of this approach, we present Terrain Diffusion, a framework for learned procedural terrain generation with a procedural noise-like interface. Our framework outpaces orbital velocity by 9 times on a consumer GPU, enabling realistic terrain generation at interactive rates. We integrate a hierarchical stack of diffusion models to couple planetary context with local detail, a compact Laplacian encoding to stabilize outputs across Earth-scale dynamic ranges, and an open-source infinite-tensor framework for constant-memory manipulation of unbounded tensors. Together, these components position diffusion models as a practical foundation for the next generation of infinite virtual worlds.
Authors: Jian Xu, Wei Chen, Shigui Li, Delu Zeng, John Paisley, Qibin Zhao
Abstract: Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely on iterative sampling and are difficult to deploy under strict latency budgets. Consistency models offer a natural route to one-step restoration, but direct adaptation to Retinex-factorized enhancement is unstable: one-step inference is evaluated at the high-noise endpoint, whereas standard training schedules provide little supervision there, and temporal self-consistency alone does not determine the correct conditional target. We propose Consist-Retinex, which first uses a Retinex Transformer Decomposition Network (TDN) to obtain paired reflectance and illumination maps, then trains two conditional consistency models with a Retinex-aware dual objective and adaptive noise-emphasized fixed-point sampling. The dual objective combines trajectory consistency with paired ground-truth component alignment, while the sampling rule concentrates supervision near the inference endpoint without discarding full-range noise coverage. We further provide an endpoint error bound, an anchoring-propagation result, and a high-noise sample-allocation analysis that explain why endpoint supervision and temporal consistency are complementary for one-step Retinex enhancement. Experiments on paired and unpaired low-light benchmarks show that Consist-Retinex obtains the best VE-LOL-L scores among the compared methods under one-step inference and remains competitive on LOL, with substantially reduced sampling and consistency-stage training cost in the reported setup.
Authors: Hongsin Lee, Hye Won Chung
Abstract: Adversarial distillation in the standard min-max adversarial training framework aims to transfer adversarial robustness from a large, robust teacher network to a compact student. However, existing work often neglects to incorporate state-of-the-art robust teachers. Through extensive analysis, we find that stronger teachers do not necessarily yield more robust students-a phenomenon known as robust saturation. While typically attributed to capacity gaps, we show that such explanations are incomplete. Instead, we identify adversarial transferability-the fraction of student-crafted adversarial examples that remain effective against the teacher-as a key factor in successful robustness transfer. Based on this insight, we propose Sample-wise Adaptive Adversarial Distillation (SAAD), which reweights training examples by their measured transferability without incurring additional computational cost. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that SAAD consistently improves AutoAttack robustness over prior methods. Our code is available at https://github.com/HongsinLee/saad.
Authors: Haojie Zheng, Shuchen Weng, Jingqi Liu, Siqi Yang, Boxin Shi, Xinlong Wang
Abstract: Recent advancements in video generation highlight that realistic audio-visual synchronization is crucial for engaging content creation. However, existing video editing methods largely overlook audio-visual synchronization and lack the fine-grained spatial and temporal controllability required for precise instance-level edits. In this paper, we propose AVI-Edit, a framework for audio-sync video instance editing. We propose a granularity-aware mask refiner that iteratively refines coarse user-provided masks into precise instance-level regions. We further design a self-feedback audio agent to curate high-quality audio guidance, providing fine-grained temporal control. To facilitate this task, we additionally construct a large-scale dataset with instance-centric correspondence and comprehensive annotations. Extensive experiments demonstrate that AVI-Edit outperforms state-of-the-art methods in visual quality, condition following, and audio-visual synchronization. Project page: https://hjzheng.net/projects/AVI-Edit/.
Authors: Jinqi Xiao, Qing Yan, Liming Jiang, Zichuan Liu, Hao Kang, Shen Sang, Tiancheng Zhi, Jing Liu, Cheng Yang, Xin Lu, Bo Yuan
Abstract: Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA. The Mixture of Low-rank Experts (MoLE) architecture offers a modular solution, but its potential is usually limited by routing policies that operate at a token level. Such local routing can conflict with the global nature of user instructions, leading to artifacts like spatial fragmentation and semantic drift in complex image generation tasks. To address these limitations, we introduce InstructMoLE, a novel framework that employs an Instruction-Guided Mixture of Low-Rank Experts. Instead of per-token routing, InstructMoLE utilizes a global routing signal, Instruction-Guided Routing (IGR), derived from the user's comprehensive instruction. This ensures that a single, coherently chosen expert council is applied uniformly across all input tokens, preserving the global semantics and structural integrity of the generation process. To complement this, we introduce an output-space orthogonality loss, which promotes expert functional diversity and mitigates representational collapse. Extensive experiments demonstrate that InstructMoLE significantly outperforms existing LoRA adapters and MoLE variants across challenging multi-conditional generation benchmarks. Our work presents a robust and generalizable framework for instruction-driven fine-tuning of generative models, enabling superior compositional control and fidelity to user intent.
Authors: Alexander Koebler, Lukas Kuhn, Ingo Thon, Florian Buettner
Abstract: In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do not align well with human domain knowledge, relying instead on spurious correlations. This might result in brittle behavior once deployed in the real-world. To address this issue, we introduce a novel and efficient method for aligning small task-specific vision models with human domain knowledge by leveraging the generalization capabilities of a Large Vision Language Model (LVLM). Our LVLM-Aided Visual Alignment (LVLM-VA) method provides a bidirectional interface that translates model behavior into natural language and maps human class-level specifications to image-level critiques, enabling effective interaction between domain experts and the model. Our method demonstrates substantial improvement in aligning model behavior with human specifications, as validated on both synthetic and real-world datasets. We show that it effectively reduces the model's dependence on spurious features and on group-specific biases, without requiring fine-grained feedback.
Authors: Mariya Miteva, Maria Nisheva-Pavlova
Abstract: Non-invasive inference of molecular tumor characteristics from medical imaging is a central goal of radiogenomics, particularly in glioblastoma (GBM), where O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation carries important prognostic and therapeutic significance. Although radiomics-based machine learning methods have shown promise for this task, conventional unimodal and early-fusion approaches are often limited by high feature redundancy and incomplete modeling of modality-specific information. In this work, we introduce a multi-view latent representation learning framework based on variational autoencoders (VAE) that preserves modality-specific radiomic structure while enabling late fusion in a compact probabilistic latent space. The approach is evaluated on radiomic features extracted from the necrotic tumor core in post-contrast T1-weighted (T1Gd) and Fluid-Attenuated Inversion Recovery (FLAIR) MRI. Experimental results demonstrate that the proposed multi-view VAE combined with a random forest classifier achieves a test AUC of 0.77 (95% CI: 0.71-0.83), substantially outperforming both a baseline radiomics model (AUC = 0.54) and a hyperparameter-tuned model (AUC = 0.64). These findings indicate that multi-view probabilistic encoding enables more effective integration of complementary MRI information and significantly improves predictive performance for MGMT promoter methylation status.
Authors: Chao Yang, Haoyuan Zheng, Yue Ma
Abstract: This paper addresses the critical bottleneck of infrared (IR) data scarcity in Printed Circuit Board (PCB) defect detection by proposing a cross-modal data augmentation framework integrating CycleGAN and YOLOv8. Unlike conventional methods relying on paired supervision, we leverage CycleGAN to perform unpaired image-to-image translation, mapping abundant visible-light PCB images into the infrared domain. This generative process synthesizes high-fidelity pseudo-IR samples that preserve the structural semantics of defects while accurately simulating thermal distribution patterns. Subsequently, we construct a heterogeneous training strategy that fuses generated pseudo-IR data with limited real IR samples to train a lightweight YOLOv8 detector. Experimental results demonstrate that this method effectively enhances feature learning under low-data conditions. The augmented detector significantly outperforms models trained on limited real data alone and approaches the performance benchmarks of fully supervised training, proving the efficacy of pseudo-IR synthesis as a robust augmentation strategy for industrial inspection.
Authors: Melonie de Almeida, Daniela Ivanova, Tong Shi, John H. Williamson, Paul Henderson
Abstract: Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, and preserving geometric integrity. Leveraging explicit intermediate 3D representations offers a promising solution by enabling coherent video generation aligned with a given camera trajectory. Although these methods often use 3D point clouds to render scenes and introduce object motion in a later stage, this two-step process still falls short in achieving full temporal consistency, despite allowing precise control over camera movement. We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames. Extensive experiments on the KITTI, Waymo, RealEstate10K and DL3DV-10K datasets demonstrate that our method achieves state-of-the-art video quality and inference efficiency. The project page is available at https://melonienimasha.github.io/Pixel-to-4D-Website.
Authors: Hongjie Wang, Niraj K. Jha
Abstract: Modern Vision-Language Models (VLMs) achieve impressive performance but are limited by the quadratic complexity of self-attention, which prevents their deployment on edge devices and makes their understanding of high-resolution images and long-context videos prohibitively expensive. To address this challenge, we introduce LinMU (Linear-complexity Multimodal Understanding), a VLM design that achieves linear complexity for the language model decoder without using any quadratic-complexity modules while maintaining the performance of global-attention-based VLMs. LinMU replaces every self-attention layer in the language model decoder with an M-MATE block: a dual-branch module that combines a bidirectional state-space model for global context (Flex-MA branch) with localized Swin-style window attention (Local-Swin branch) for adjacent correlations. To transform a pre-trained VLM into the LinMU architecture, we propose a three-stage distillation framework that (i) initializes both branches with self-attention weights and trains the Flex-MA branch alone, (ii) unfreezes the Local-Swin branch and fine-tunes it jointly with the Flex-MA branch, and (iii) unfreezes the remaining blocks and fine-tunes them using LoRA adapters, while regressing on hidden states and token-level logits of the frozen VLM teacher. On MMMU, TextVQA, LongVideoBench, Video-MME, and other benchmarks, LinMU matches the performance of teacher models, yet reduces Time-To-First-Token (TTFT) by up to 2.7$\times$ and improves token throughput by up to 9.0$\times$ on minute-length videos. Ablations confirm the importance of each distillation stage and the necessity of the two branches of the M-MATE block. The proposed framework demonstrates that state-of-the-art multimodal reasoning can be achieved without quadratic attention, thus opening up avenues for long-context VLMs that can deal with high-resolution images and long videos.
Authors: Paraskevi Valergaki, Vassilis C. Nicodemou, Iason Oikonomidis, Antonis Argyros, Anastasios Roussos
Abstract: Reliable stress recognition is critical in applications such as medical monitoring and safety-critical systems, including real-world driving. While stress is commonly detected using physiological signals such as perinasal perspiration and heart rate, facial activity provides complementary cues that can be captured unobtrusively from video. We propose a multimodal stress estimation framework that combines facial videos and physiological signals, remaining effective even when biosignal acquisition is challenging. Facial behavior is represented using a dense 3D Morphable Model, yielding a 56-dimensional descriptor that captures subtle expression and head-pose dynamics over time. To study how stress modulates facial motion, we perform extensive experiments alongside established physiological markers. Paired hypothesis tests between baseline and stressor phases show that 38 of 56 facial components exhibit consistent, phase-specific stress responses comparable to physiological markers. Building on these findings, we introduce a Transformer-based temporal modeling framework and evaluate unimodal, early-fusion, and cross-modal attention strategies. Cross-modal attention fusion of 3D-derived facial features with physiological signals substantially improves performance over physiological signals alone, increasing AUROC from 52.7% and accuracy from 51.0% to 92.0% and 86.7%, respectively. Although evaluated on driving data, the proposed framework and protocol may generalize to other stress estimation settings.
Authors: Tolgay Atinc Uzun, Dmitry Ignatov, Radu Timofte
Abstract: Channel-configuration search, the optimization of layer specifications such as channel widths in deep neural networks, presents a combinatorial challenge constrained by tensor-shape compatibility and computational budgets. We investigate whether large language models (LLMs) can support neural architecture search (NAS) by reasoning over architectural code structures in ways that complement traditional search heuristics. We apply an LLM-driven NAS framework to channel-configuration search, formulating the task as conditional code generation in which the LLM refines architectural specifications using performance feedback. To address data scarcity, we generate a corpus of valid, shape-consistent architectures through abstract syntax tree (AST) mutations. Although these mutated networks are not necessarily optimized for performance, they provide structural examples that help the LLM learn executable architectural patterns and relate channel configurations to model performance. Experimental results on CIFAR-100 show that the closed-loop LLM improves upon the initial AST-generated architecture population under the same proxy-evaluation protocol. Our analysis further shows that the generated architectures reflect domain-specific design patterns, including non-standard channel widths and late-stage expansion, highlighting the potential of language-driven design for code-level NAS. The code and prompts are publicly available at https://github.com/ABrain-One/NN-GPT, and the generated deep neural networks are published at https://github.com/ABrain-One/NN-Dataset under model names with the prefix ast-dimension-.
URLs: https://github.com/ABrain-One/NN-GPT,, https://github.com/ABrain-One/NN-Dataset
Authors: John Waithaka, Gustave Bwirayesu, Moise Busogi
Abstract: Self-supervised pretraining in remote sensing is mostly done using mid-spatial resolution (MR) image datasets due to their high availability. Given the release of high-resolution (HR) datasets, we ask how HR datasets can be included in self-supervised pretraining to enhance MR image representation learning and downstream segmentation performance on MR tasks. We design a spatial affinity component that can be added to existing self-supervised learning frameworks and that uses HR imagery to learn better representations of MR imagery. We test the spatial affinity component on two self-supervised learning frameworks and show that it outperforms models pretrained on HR or MR images alone.
Authors: Cuong Tran Van, Trong-Thang Pham, Ngoc-Son Nguyen, Duy Minh Ho Nguyen, Ngan Le
Abstract: Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-grained anatomical details, which correspond to high-frequency components. Conventional CNN-based methods often struggle to recover these fine structures, as they are typically biased toward learning low-frequency information. To address this challenge, this paper presents DuFal (Dual-Frequency-Aware Learning), a novel framework that integrates frequency-domain and spatial-domain processing via a dual-path architecture. The core innovation lies in our High-Local Factorized Fourier Neural Operator, which comprises two complementary branches: a Global High-Frequency Enhanced Fourier Neural Operator that captures global frequency patterns and a Local High-Frequency Enhanced Fourier Neural Operator that processes spatially partitioned patches to preserve spatial locality that might be lost in global frequency analysis. To improve efficiency, we design a Spectral-Channel Factorization scheme that reduces the Fourier Neural Operator parameter count. We also design a Cross-Attention Frequency Fusion module to integrate spatial and frequency features effectively. The fused features are then decoded through a Feature Decoder to produce projection representations, which are subsequently processed through an Intensity Field Decoding pipeline to reconstruct a final Computed Tomography volume. Experimental results on the LUNA16 and ToothFairy datasets demonstrate that DuFal significantly outperforms existing state-of-the-art methods in preserving high-frequency anatomical features, particularly under extremely sparse-view settings.
Authors: Xinjue Hu, Chi Wang, Boyu Wang, Xiang Zhang, Zhenshan Tan, Zhangjie Fu
Abstract: Deep image steganography (DIS) has achieved significant results in capacity and invisibility. However, current paradigms enforce the secret image to maintain the same resolution as the cover image during hiding and revealing. This leads to two challenges: secret images with inconsistent resolutions must undergo resampling beforehand which results in detail loss during recovery, and the secret image cannot be recovered to its original resolution when the resolution value is unknown. To address these, we propose ARDIS, the first Arbitrary Resolution DIS framework, which shifts the paradigm from discrete mapping to reference-guided continuous signal reconstruction. Specifically, to minimize the detail loss caused by resolution mismatch, we first design a Frequency Decoupling Architecture in hiding stage. It disentangles the secret into a resolution-aligned global basis and a resolution-agnostic high-frequency latent to hide in a fixed-resolution cover. Second, for recovery, we propose a Latent-Guided Implicit Reconstructor to perform deterministic restoration. The recovered detail latent code modulates a continuous implicit function to accurately query and render high-frequency residuals onto the recovered global basis, ensuring faithful restoration of original details. Furthermore, to achieve blind recovery, we introduce an Implicit Resolution Coding strategy. By transforming discrete resolution values into dense feature maps and hiding them in the redundant space of the feature domain, the reconstructor can correctly decode the secret's resolution directly from the steganographic representation. Experimental results demonstrate that ARDIS significantly outperforms state-of-the-art methods in both invisibility and cross-resolution recovery fidelity.
Authors: Steffen Knoblauch, Ram Kumar Muthusamy, Pedram Ghamisi, Alexander Zipf
Abstract: Highway networks are crucial for economic prosperity. Climate change-induced temperature fluctuations are exacerbating stress on road pavements, resulting in elevated maintenance costs. This underscores the need for targeted and efficient maintenance strategies. This study investigates the potential of open-source data to guide highway infrastructure maintenance. The proposed framework integrates airborne imagery and OpenStreetMap (OSM) to fine-tune YOLOv11 for highway crack localization. To demonstrate the framework's real-world applicability, a Swiss Relative Highway Crack Density (RHCD) index was calculated to inform nationwide highway maintenance. The crack classification model achieved an F1-score of $0.84$ for the positive class (crack) and $0.97$ for the negative class (no crack). The Swiss RHCD index exhibited weak correlations with Long-term Land Surface Temperature Amplitudes (LT-LST-A) (Pearson's $r\ = -0.05$) and Traffic Volume (TV) (Pearson's $r\ = 0.17$), underlining the added value of this novel index for guiding maintenance over other data. Significantly high RHCD values were observed near urban centers and intersections, providing contextual validation for the predictions. These findings highlight the value of open-source data sharing to drive innovation, ultimately enabling more efficient solutions in the public sector.
Authors: Shima Salehi, Atharva Agashe, Andrew J. McFarland, Joshua Peeples
Abstract: We propose a new method for few-shot 3D reconstruction that integrates global and local frequency regularization to stabilize geometry and preserve fine details under sparse-view conditions, addressing a key limitation of existing 3D Gaussian Splatting (3DGS) models. We also introduce a new multispectral greenhouse dataset containing four spectral bands captured from diverse plant species under controlled conditions. Alongside the dataset, we release an open-source benchmarking package that defines standardized few-shot reconstruction protocols for evaluating 3DGS-based methods. Experiments on our multispectral dataset, as well as standard benchmarks, demonstrate that the proposed method achieves sharper, more stable, and spectrally consistent reconstructions than existing baselines. The dataset and code for this work are publicly available
Authors: Tayyab Nasir, Daochang Liu, Ajmal Mian
Abstract: Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the effects of different training recipes, such as scaling laws, objective design, and optimization strategies. A rigorous empirical analysis is essential not only for benchmarking performance and revealing true gains but also for establishing the current state of ASSR, identifying saturation limits, and highlighting promising directions. We fill this gap by comparing existing techniques across diverse settings and presenting aggregated performance results on multiple image quality metrics. We contribute a unified framework for more reliable interpretation of performance comparisons and model evaluation claims. To facilitate reproducible comparisons, a unified codebase is also provided. Furthermore, we investigate the impact of carefully controlled training configurations on perceptual image quality and analyze the role of auxiliary objectives in preserving edges, textures, and fine details during training. We conclude the following key insights that have been previously overlooked: (1) Recent, more complex INR methods provide only marginal improvements over earlier methods. (2) Model performance is strongly correlated to training configurations, a factor overlooked in prior works. (3) Auxiliary objectives consistently enhance texture fidelity across architectures compared to standard L1-Loss, emphasizing the role of objective design for targeted perceptual gains. (4) Scaling laws apply to INR-based ASSR, confirming predictable gains with increased model complexity, training compute, and data diversity.
Authors: Ziyang Song, Xinyu Gong, Bangya Liu, Zelin Zhao
Abstract: Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V pipeline, failing to exploit the full potential of video subject control. In this work, we propose and address the challenging Multi-View S2V (MV-S2V) task, which synthesizes videos from multiple reference views to enforce 3D-level subject consistency. Regarding the scarcity of training data, we first develop a synthetic data curation pipeline to generate highly customized synthetic data, complemented by a small-scale real-world captured dataset to boost the training of MV-S2V. Another key issue lies in the potential confusion between cross-subject and cross-view references in conditional generation. To overcome this, we further introduce Temporally Shifted RoPE (TS-RoPE) to distinguish between different subjects and distinct views of the same subject in reference conditioning. Our framework achieves superior 3D subject consistency w.r.t. multi-view reference images and high-quality visual outputs, establishing a new meaningful direction for subject-driven video generation. Code and data are available at: https://szy-young.github.io/mv-s2v
Authors: Yanlong Chen, Amirhossein Habibian, Luca Benini, Yawei Li
Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its potential, quantization-aware training for VLMs remains underexplored. We propose GRACE, a framework unifying knowledge distillation and QAT under the Information Bottleneck principle: quantization constrains information capacity while distillation guides what to preserve within this budget. Treating the teacher as a proxy for task-relevant information, we introduce confidence-gated decoupled distillation to filter unreliable supervision, relational centered kernel alignment to transfer visual token structures, and an adaptive controller via Lagrangian relaxation to balance fidelity against capacity constraints. Across extensive benchmarks on LLaVA and Qwen families, our INT4 models consistently outperform FP16 baselines (e.g., LLaVA-1.5-7B: 70.1 vs. 66.8 on SQA; Qwen2-VL-2B: 76.9 vs. 72.6 on MMBench), nearly matching teacher performance. Using real INT4 kernel, we achieve 3$\times$ throughput with 54% memory reduction. This principled framework significantly outperforms existing quantization methods, making GRACE a compelling solution for resource-constrained deployment.
Authors: Hongyang Du, Junjie Ye, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we introduce VideoGPA (Video Geometric Preference Alignment), a data-efficient self-supervised framework that leverages a geometry foundation model to automatically derive dense preference signals that guide VDMs via Direct Preference Optimization (DPO). This approach effectively steers the generative distribution toward inherent 3D consistency without requiring human annotations. VideoGPA significantly enhances temporal stability, physical plausibility, and motion coherence using minimal preference pairs, consistently outperforming state-of-the-art baselines in extensive experiments.
Authors: Hail Song, Boram Yoon, Seokhwan Yang, Seoyoung Kang, Hyunjeong Kim, Henning Metzmacher, Woontack Woo
Abstract: We present VRGaussianAvatar, an integrated system that enables real-time full-body 3D Gaussian Splatting (3DGS) avatars in virtual reality using only head-mounted display (HMD) tracking signals. The system adopts a parallel pipeline with a VR Frontend and a GA Backend. The VR Frontend uses inverse kinematics to estimate full-body pose and streams the resulting pose along with stereo camera parameters to the backend. The GA Backend stereoscopically renders a 3DGS avatar reconstructed from a single image. To improve stereo rendering efficiency, we introduce Binocular Batching, which jointly processes left and right eye views in a single batched pass to reduce redundant computation and support high-resolution VR displays. We evaluate VRGaussianAvatar with quantitative performance tests and a within-subject user study against image- and video-based mesh avatar baselines. Results show that VRGaussianAvatar sustains interactive VR performance and yields higher perceived appearance similarity, embodiment, and plausibility. Project page and source code are available at https://vrgaussianavatar.github.io.
Authors: Junbo Jacob Lian, Feng Xiong, Yujun Sun, Kaichen Ouyang, Zong Ke, Mingyang Yu, Shengwei Fu, Zhong Rui, Zhang Yujun, Huiling Chen
Abstract: Second-order feature statistics are central to texture recognition, yet existing mechanisms exhibit a structural tension: bilinear pooling and Gram matrices capture global channel correlations but discard spatial structure, whereas self-attention models capture cross-position relations through weighted sums rather than explicit pairwise products. We propose TwistNet-2D, a lightweight module that computes local pairwise channel products under directional spatial displacement, jointly encoding where features co-occur and how they interact. The core component, Spiral-Twisted Channel Interaction (STCI), shifts one feature map along a prescribed direction before L2-normalized channel multiplication, capturing cross-position co-occurrence patterns that characterize structured and periodic textures. Four directional heads are aggregated through content-adaptive channel reweighting, and the result is injected via a sigmoid-gated residual path with near-zero initialization. TwistNet-2D adds only approximately 3.5% parameters and approximately 2% FLOPs over ResNet-18. To isolate the contribution of architectural inductive bias from that of transfer learning, all models in this study are trained from scratch without ImageNet pretraining. Under this protocol, TwistNet-2D consistently surpasses parameter-matched baselines and substantially larger ConvNeXt and Swin Transformer backbones across four texture and fine-grained recognition benchmarks, while the multi-head structure produces interpretable, orientation-selective representations that align with classical texture analysis.
Authors: Jayawant Bodagala, Balaji Bodagala
Abstract: Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy, and a phase-change decision becomes temporally irreversible once yellow onset is initiated. This paper presents UCATSC, an interpretable uncertainty-aware constrained decision layer for vision-based adaptive signal control. UCATSC maintains a reduced movement-level belief state over queue, arrival, and service-age variables; evaluates admissible phase actions through finite-horizon counterfactual rollouts in belief space; and filters candidate actions using predictive dilemma-zone safety and service-age/starvation constraints before execution. The method is evaluated primarily in SUMO using matched seeds, classical baselines, a trained DQN-RL baseline, a safety-masked DQN variant, targeted safety/liveness/uncertainty stress tests, and a three-intersection corridor extension. In the tested scenarios, UCATSC demonstrates competitive mobility performance, eliminates observed dilemma-zone violations for the constrained variants, bounds service age in starvation stress tests, and maintains millisecond-level online runtime. A controlled physical vision testbed is included as supplementary feasibility evidence for the vision-to-belief interface; it is not presented as field validation of safety, emissions, or deployment readiness.
Authors: Constantino \'Alvarez Casado, Mohammad Rahman, Sasan Sharifipour, Nhi Nguyen, Manuel Lage Ca\~nellas, Xiaoting Wu, Miguel Bordallo L\'opez
Abstract: Human-machine interfaces in industrial automation need sensing modules that monitor operator actions and physiological state. This is important in factories, vehicles, machinery cabins, and human-robot collaboration, where workload, stress, fatigue, or reduced attention can affect safety. RGB monitoring is limited by low light, shadows, and privacy concerns, while thermal infrared imaging captures skin temperature dynamics without visible illumination. This paper studies thermal video as a contactless computer vision modality for estimating electrodermal activity (EDA), heart rate (HR), and breathing rate (BR), with the goal of supporting adaptive human-machine interfaces and operator-state awareness. We propose a signal-processing pipeline that tracks facial regions, aggregates thermal signals, and separates slow sudomotor trends from faster cardiorespiratory components. HR is estimated using orthogonal matrix image transformation (OMIT) across multiple facial regions, while BR is estimated from nasal and cheek thermal signals using spectral peak detection. We characterize 288 ROI-method configurations against contact references with lag-tolerant metrics using 31 sessions from the public SIMULATOR STUDY 1 (SIM1) driver monitoring dataset. The best fixed EDA configuration reaches a mean absolute correlation of $0.40 \pm 0.23$ against palm EDA, with individual sessions reaching $0.89$. BR estimation achieves $3.1 \pm 1.1$\,bpm mean absolute error, while HR estimation yields $13.8 \pm 7.5$\,bpm MAE, limited by the $7.5$\,Hz thermal camera frame rate. The results show that thermal video provides useful respiratory and sudomotor cues, while revealing limitations caused by ROI selection, polarity changes, latency, and subject variability. These findings provide baseline design guidance for thermal computer vision as an auxiliary sensing layer in adaptive industrial HMI systems.
Authors: Seongheon Park, Changdae Oh, Hyeong Kyu Choi, Sean Du, Sharon Li
Abstract: Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on language priors and are therefore ill-suited for evaluating vision-conditioned predictions. We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple datasets.
Authors: Junmyeong Lee, Hoseung Choi, Minsu Cho
Abstract: Forecasting dynamic scenes remains a fundamental challenge in computer vision, as limited observations make it difficult to capture coherent object-level motion and long-term temporal evolution. We present Motion Group-aware Gaussian Forecasting (MoGaF), a framework for long-term scene extrapolation built upon the 4D Gaussian Splatting representation. MoGaF introduces motion-aware Gaussian grouping and group-wise optimization to enforce physically consistent motion across both rigid and non-rigid regions, yielding spatially coherent dynamic representations. Leveraging this structured space-time representation, a lightweight forecasting module predicts future motion, enabling realistic and temporally stable scene evolution. Experiments on synthetic and real-world datasets demonstrate that MoGaF consistently outperforms existing baselines in rendering quality, motion plausibility, and long-term forecasting stability. Our project page is available at https://slime0519.github.io/mogaf
Authors: Yaoqi Huang, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: Maintaining situational awareness in complex driving scenarios is challenging. It requires continuously prioritizing attention among extensive scene entities and understanding how prominent hazards might affect the ego vehicle. While existing studies excel at detecting specific semantic categories and visually salient regions, they lack the ability to assess safety-relevance. Meanwhile, the generic spatial predicates either for foreground objects only or for all scene entities modeled by existing scene graphs are inadequate for driving scenarios. To bridge this gap, we introduce a novel task, Traffic Scene Graph Generation, which captures traffic-specific relations between prominent hazards and the ego vehicle. We propose a novel framework that explicitly uses traffic accident data and depth cues to supplement visual features and semantic information for reasoning. The output traffic scene graphs provide intuitive guidelines that stress prominent hazards by color-coding their severity and notating their effect mechanism and relative location to the ego vehicle. We create relational annotations on Cityscapes dataset and evaluate our model on 10 tasks from 5 perspectives. The results in comparative experiments and ablation studies demonstrate our capacity in ego-centric reasoning for hazard-aware traffic scene understanding.
Authors: Kirill Koltsov, Aleksandr Gushchin, Anastasia Antsiferova, Dmitriy Vatolin
Abstract: Recent text-to-image models have improved global realism, but text rendering remains a persistent failure mode: images may look convincing overall, yet local typography often contains malformed glyphs, broken strokes, irregular spacing, and other artifacts that humans heavily penalize. We formulate Text-in-Image Quality Assessment (TIQA), a no-reference task that estimates a human-aligned perceptual quality score for detected text regions while disentangling visual text quality from semantic correctness. To support this setting, we introduce two datasets. TIQA-Crops contains 120k text crops from 36k AI-generated images produced by 12 generators, with 10k mean-opinion-score (MOS) labels and 110k proxy labels for pretraining. TIQA-Images contains 1,500 text-heavy images from 10 recent generators, including proprietary systems, with paired overall-quality and text-quality subjective scores. We also propose ANTIQA, a lightweight predictor with text-specific inductive biases. Across crop-level and image-level evaluations, ANTIQA achieves the best alignment with human judgments, reaching PLCC/SROCC of 0.942/0.935 on TIQA-Crops and 0.842/0.837 for text-quality MOS on unseen generators in TIQA-Images. In best-of-5 AI-generated image ranking, ANTIQA improves the text quality of the selected image by 0.36 MOS (14%), demonstrating utility for benchmarking, filtering, and generation-time selection. Together, these findings establish perceptual text quality as a distinct evaluation target for modern text-to-image generation.
Authors: \"Umit Mert \c{C}a\u{g}lar, Alptekin Temizel
Abstract: Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature similarity, which is difficult to interpret and does not always correlate with the contribution to downstream tasks. We propose a vision-language grounded framework for interpretable synthetic data augmentation and evaluation in remote sensing. Our approach combines generative models, semantic segmentation and image captioning with vision and language models. Based on this framework, we introduce ARAS400k: A large-scale Remote sensing dataset Augmented with Synthetic data for segmentation and captioning, containing 100k real images and 300k synthetic images, each paired with segmentation maps and descriptions. ARAS400k enables the automated evaluation of synthetic data by analyzing semantic composition, minimizing caption redundancy, and verifying cross-modal consistency between visual structures and language descriptions. Experimental results indicate that while models trained exclusively on synthetic data reach competitive performance levels, those trained with augmented data (a combination of real and synthetic images) consistently outperform real-data baselines. Consequently, this work establishes a scalable benchmark for remote sensing tasks, specifically in semantic segmentation and image captioning. The dataset is available at zenodo.org/records/18890661 and the code base at github.com/caglarmert/ARAS400k.
Authors: Jakub Gregorek, Paraskevas Pegios, Nando Metzger, Konrad Schindler, Theodora Kontogianni, Lazaros Nalpantidis
Abstract: We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based methods. By shifting computational burden from inference to finetuning, our approach enables efficient and robust 3D perception under real-world latency constraints. Marigold-SSD achieves significantly faster inference with a training cost of only 4.5 GPU days. We evaluate our method across four indoor and two outdoor benchmarks, demonstrating strong cross-domain generalization and zero-shot performance compared to existing depth completion approaches. Our approach significantly narrows the efficiency gap between diffusion-based and discriminative models. Finally, we challenge common evaluation protocols by analyzing performance under varying input sparsity levels. Page: https://dtu-pas.github.io/marigold-ssd/
Authors: Joseph Geo Benjamin, Anil K. Jain, Karthik Nandakumar
Abstract: The quality and realism of synthetically generated fingerprint images have increased significantly over the past decade fueled by advancements in generative artificial intelligence (GenAI). This has exacerbated the vulnerability of fingerprint recognition systems to data injection attacks, where synthetic fingerprints are maliciously inserted during enrollment or authentication. Hence, there is an urgent need for methods to detect if a fingerprint image is real or synthetic. While it is straightforward to train deep neural network (DNN) models to classify images as real or synthetic, often such DNN models overfit the training data and fail to generalize well when applied to synthetic fingerprints generated using unseen GenAI models. In this work, we formulate synthetic fingerprint detection as a continual few-shot adaptation problem, where the objective is to rapidly evolve a base detector to identify new types of synthetic data. To enable continual few-shot adaptation, we employ a combination of binary cross-entropy and supervised contrastive (applied to the feature representation) losses and replay a few samples from previously known styles during fine-tuning to mitigate catastrophic forgetting. Experiments based on several DNN backbones (as feature extractors) and a variety of real and synthetic fingerprint datasets indicate that the proposed approach achieves a good trade-off between fast adaptation for detecting unseen synthetic styles and forgetting of known styles.
Authors: Xiaolu Liu, Yicong Li, Song Wang, Junbo Chen, Angela Yao, Jianke Zhu
Abstract: Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically predict future states through appearance generation or deterministic regression, which limits their ability to capture trajectory-conditioned scene evolution and leads to unreliable action planning. To address this, we propose DynFlowDrive, a latent world model that leverages flow-based dynamics to model the transition of world states under different driving actions. By adopting the rectifiedflow formulation, the model learns a velocity field that describes how the scene state changes under different driving actions, enabling progressive prediction of future latent states. Building upon this, we further introduce a stability-aware multi-mode trajectory selection strategy that evaluates candidate trajectories according to the stability of the induced scene transitions. Extensive experiments on the nuScenes and NavSim benchmarks demonstrate consistent improvements across diverse driving frameworks without introducing additional inference overhead. Source code will be abaliable at https://github.com/xiaolul2/DynFlowDrive.
Authors: Hui Zhong, Yichun Gao, Luyan Liu, Xusen Guo, Zhaonian Kuang, Qiming Zhang, Xinhu Zheng
Abstract: Building facade defect inspection is fundamental to structural health monitoring and sustainable urban maintenance, yet it remains a formidable challenge due to extreme geometric variability, low contrast against complex backgrounds, and the inherent complexity of composite defects (e.g., cracks co-occurring with spalling). Such characteristics lead to severe pixel imbalance and feature ambiguity, which, coupled with the critical scarcity of high-quality pixel-level annotations, hinder the generalization of existing detection and segmentation models. To address gaps, we propose \textit{FacadeFixer}, a unified multi-agent framework that treats defect perception as a collaborative reasoning task rather than isolated recognition. Specifically,\textit{FacadeFixer} orchestrates specialized agents for detection and segmentation to handle multi-type defect interference, working in tandem with a generative agent to enable semantic recomposition. This process decouples intricate defects from noisy backgrounds and realistically synthesizes them onto diverse clean textures, generating high-fidelity augmented data with precise expert-level masks. To support this, we introduce a comprehensive multi-task dataset covering six primary facade categories with pixel-level annotations. Extensive experiments demonstrate that \textit{FacadeFixer} significantly outperforms state-of-the-art (SOTA) baselines. Specifically, it excels in capturing pixel-level structural anomalies and highlights generative synthesis as a robust solution to data scarcity in infrastructure inspection. Our code and dataset will be made publicly available.
Authors: Bingxuan Zhao, Qing Zhou, Chuang Yang, Qi Wang
Abstract: Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of training at the large resolutions that RS applications demand. Training-free resolution promotion via Rotary Position Embedding (RoPE) rescaling offers a practical remedy, but every existing method applies a static positional scaling rule throughout the denoising process. This uniform compression is particularly harmful for RS imagery, whose substantially denser medium- and high-frequency energy encodes the fine structures critical for aerial-scene realism, such as vehicles, building contours, and road markings. Addressing both challenges requires a domain-specialized generative prior coupled with a denoising-aware positional adaptation strategy. To this end, we fine-tune FLUX on over 100,000 curated RS images to build a strong domain prior (RS-FLUX), and propose Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion (SHARP), a training-free method that introduces a rational fractional time schedule k_rs(t) into RoPE. SHARP applies strong positional promotion during the early layout-formation stage and progressively relaxes it during detail recovery, aligning extrapolation strength with the frequency-progressive nature of diffusion denoising. Its resolution-agnostic formulation further enables robust multi-scale generation from a single set of hyperparameters. Extensive experiments across six square and rectangular resolutions show that SHARP consistently outperforms all training-free baselines on CLIP Score, Aesthetic Score, and HPSv2, with widening margins at more aggressive extrapolation factors and negligible computational overhead. Code and weights are available at https://github.com/bxuanz/SHARP.
Authors: Yusri Al-Sanaani, Rebecca Thornhill, Sreeraman Rajan
Abstract: Accurate segmentation of the left atrial (LA) wall in 3D late gadolinium-enhanced MRI (LGE-MRI) is essential for wall thickness mapping and fibrosis quantification, yet it remains challenging due to the wall's thin geometry, complex anatomy, and low contrast. We propose C2W-Tune, a two-stage cavity-to-wall transfer framework that leverages a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation. Using a 3D U-Net with a ResNeXt encoder and instance normalization, Stage 1 pre-trains the network to segment the LA cavity, learning robust atrial representations. Stage 2 transfers these weights and adapts the network to LA wall segmentation using a progressive layer-unfreezing schedule to preserve cavity features while enabling wall-specific refinement. On the 2018 LA Segmentation Challenge dataset, C2W-Tune outperformed an architecture-matched baseline trained from scratch. The wall Dice score increased from 0.623 to 0.814, surface Dice at 1 mm increased from 0.553 to 0.731, 95th-percentile Hausdorff distance (HD95) decreased from 2.95 mm to 2.55 mm, and average symmetric surface distance (ASSD) decreased from 0.71 mm to 0.63 mm. Under reduced supervision using 70 training volumes sampled from the same training set, C2W-Tune achieved a Dice of 0.78, remaining competitive with recent multi-class bi-atrial benchmarks, typically 0.6-0.7. These results show that anatomically grounded task transfer with controlled fine-tuning improves accuracy for thin LA wall segmentation in 3D LGE-MRI.
Authors: Seng Nam Chen, Hao Chen, Chenglam Ho, Xinyu Mao, Jinping Wang, Yu Zhang, Chao Li
Abstract: Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. This Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.
Authors: Jian Zhang, Shijie Zhou, Bangya Liu, Achuta Kadambi, Zhiwen Fan
Abstract: Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems.
Authors: Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jiang, Hongyu Li, Dian Zheng, Chenyang Wang, Xiangyu Yue
Abstract: Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.
Authors: Jingqi Xu
Abstract: Vision-Language Models (VLMs) have demonstrated strong capabilities across a wide range of multimodal tasks. However, recent studies have shown that VLMs, such as CLIP, perform poorly in understanding negation expressions, which are common in natural language. In this work, we propose Omni-NegCLIP, a fine-tuned CLIP model that improves CLIP's understanding of two types of negation, namely presence-based negation and absence-based negation, which correspond to negated expressions of objects that are actually present in an image and those that may plausibly exist in an image but are in fact absent, respectively, by modifying CLIP's original InfoNCE contrastive loss. Specifically, we design a presence-based contrastive objective that pulls image embeddings closer to their original caption embeddings while pushing them away from the corresponding presence-based negated caption embeddings, and an absence-based contrastive objective that aligns image embeddings with both original and absence-based negated caption embeddings while maintaining a semantic distinction between the two text embeddings. Based on our observation that the front transformer layers of CLIP text encoder have stronger learning ability for negated text than the later layers, we fine-tune the front transformer layers of the CLIP text encoder at each training step using the combined contrastive objective. Experimental results show that, compared with pretrained CLIP, Omni-NegCLIP improves performance on presence-based negation and absence-based negation tasks by up to 52.65% and 12.50%, respectively, without sacrificing general capability in image-text retrieval and even improving it by up to 19.62%. Compared with prior works, Omni-NegCLIP demonstrates a more comprehensive ability to understand multiple types of negation tasks.
Authors: Shi Li, Vinkle Srivastav, Nicolas Chanel, Saurav Sharma, Nabani Banik, Lorenzo Arboit, Kun Yuan, Pietro Mascagni, Nicolas Padoy
Abstract: Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to navigate evolving intraoperative scenes. Computer-assisted systems such as surgical visual question answering (VQA) offer promises for education and intraoperative support. Current surgical VQA research largely focuses on static frame analysis, overlooking rich temporal semantics. Surgical video question answering is further challenged by low visual contrast, its highly knowledge-driven nature, diverse analytical needs spanning scattered temporal windows, and the hierarchy from basic perception to high-level intraoperative assessment. To address these challenges, we propose SurgTEMP, a multimodal LLM framework featuring (i) a query-guided token selection module that builds hierarchical visual memory (spatial and temporal memory banks) and (ii) a Surgical Competency Progression (SCP) training scheme. Together, they enable effective modeling of variable-length surgical videos while preserving procedure-relevant cues and temporal coherence, and better support diverse downstream assessment tasks. To support model development, we introduce CholeVidQA-32K, a surgical video question answering dataset comprising 32K open-ended QA pairs and 3,855 video segments (approximately 128 h total) from laparoscopic cholecystectomy. The dataset is organized into a three-level hierarchy -- Perception, Assessment, and Reasoning -- spanning 11 tasks from instrument/action/anatomy perception to Critical View of Safety (CVS), intraoperative difficulty, skill proficiency, and adverse event assessment. In comprehensive evaluations against state-of-the-art open-source multimodal and video LLMs (fine-tuned and zero-shot), SurgTEMP achieves substantial performance improvements, advancing the state of video-based surgical VQA. The project page is available at: https://camma-public.github.io/SurgTEMP/
Authors: Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo
Abstract: We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types.
Authors: Zhenyu Wang, Weichen Cheng, Weijia Li, Junjie Mou, Zongyou Zhao, Guoying Zhang
Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have improved MSD through cross-modal interaction and incongruity reasoning, most still treat modalities as equally reliable. In real social media posts, however, text and images often differ in noise level and relevance, making deterministic fusion susceptible to noisy evidence and weakened incongruity cues. To address this issue, we propose Uncertainty-aware Robust Multimodal Fusion (URMF), a unified framework for robust MSD. URMF first injects visual evidence into textual representations through multi-head cross-attention, and then applies self-attention in the fused semantic space to enhance incongruity reasoning. It models textual, visual, and interaction-aware representations as learnable Gaussian posteriors to estimate modality-specific uncertainty. Based on the estimated uncertainty, URMF dynamically adjusts modality contributions during fusion to suppress unreliable evidence. We further optimize the model with a unified objective that combines information bottleneck regularization, modality prior regularization, cross-modal distribution alignment, and uncertainty-driven contrastive learning. Experiments on the public MSD and MMSD2 benchmarks show that URMF outperforms representative unimodal, multimodal, and MLLM-based baselines. The results demonstrate that explicit uncertainty modeling can improve both accuracy and robustness in multimodal sarcasm detection.
Authors: Rui Xu, Dafei Qin, Kaichun Qiao, Qiujie Dong, Huaijin Pi, Qixuan Zhang, Longwen Zhang, Lan Xu, Jingyi Yu, Wenping Wang, Taku Komura
Abstract: Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes. A key advantage of this formulation is its unified representation, enabling the same token sequence to be decoded into either a triangle or quadrilateral mesh. This flexibility facilitates joint training on both data types: large-scale triangle data provides fundamental structural priors, while high-quality quad data enhances the geometric regularity of the outputs. Extensive experiments demonstrate that SATO consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation. Project page: https://ruixu.me/html/SATO/index.html
Authors: Aaditya Baranwal, Vishal Yadav, Abhishek Rajora
Abstract: While Vision-Language Models (VLMs) demonstrate remarkable zero-shot recognition capabilities across a diverse spectrum of multimodal tasks, it yet remains an open question whether these architectures genuinely comprehend geometric structure or merely exploit RGB textures and contextual priors as statistical shortcuts. Existing evaluations fail to isolate this mechanism, conflating semantic reasoning with texture mapping and relying on imprecise annotations that inadvertently leak environmental cues. To address this gap, we introduce $\textbf{BareBones}$, a zero-shot benchmark designed to stress-test pure geometric shape comprehension. We curate pixel-level silhouettes of geometrically distinct classes across six datasets: five established segmentation sources (ImageNet-S, DIS5K, ThinObject5K, PASCAL VOC, CUB-200) and our novel flagship collection, WTP-Bench, establishing a noise-free geometric taxonomy. WTP-Bench is an extreme, fine-grained visual puzzle that forces models to identify inter-class geometric concepts from boundary contours alone. Our evaluation of 26 state-of-the-art proprietary and open-weight VLMs (eg. GPT-4.1, Gemini, Claude Sonnet 4.5, LLaVA) reveals a consistent, severe performance collapse under RGB deprivation, a phenomenon we term the $\textit{Texture Bias Cliff}$. By documenting universal structural blindspots, BareBones establishes a rigorous yardstick for genuine geometric grounding. Project Page: https://eternal-f1ame.github.io/WTP-Bench/
Authors: Shiyin Jiang, Wei Long, Minghao Han, Zhenghao Chen, Ce Zhu, Shuhang Gu
Abstract: The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack a principled mechanism for joint rate-distortion (RD) optimization due to the disconnect between representation learning and entropy modeling. We propose RDVQ, a unified framework that enables end-to-end RD optimization for VQ-based compression via a differentiable relaxation of the codebook distribution, allowing the entropy loss to directly shape the latent prior. We further develop an autoregressive entropy model that supports accurate entropy modeling and test-time rate control. Extensive experiments demonstrate that RDVQ achieves strong performance at extremely low bitrates with a lightweight architecture, attaining competitive or superior perceptual quality with significantly fewer parameters. Compared with RDEIC, RDVQ reduces bitrate by up to 75.71% on DISTS and 37.63% on LPIPS on DIV2K-val. Beyond empirical gains, RDVQ introduces an entropy-constrained formulation of VQ, highlighting the potential for a more unified view of image tokenization and compression. The code will be available at https://github.com/CVL-UESTC/RDVQ.
Authors: Bo Ma, Jinsong Wu, Weiqi Yan
Abstract: Mamba selective state space models (SSMs) provide linear-time sequence modeling but remain sensitive to selective-scan chunk scheduling. We present COREY, a \emph{concept-and-feasibility} runtime scheduler that maps fixed-bin activation entropy to chunk size. We evaluate COREY in three tiers: a prototype cost model, real-checkpoint kernel timing, and routed end-to-end ablations on modern GPUs. At the kernel level, a calibrated rule, \(H_{\mathrm{ref}}=\log K\), recovers the locally optimal chunk and matches a one-time static oracle, yielding \(4.41\times\) lower latency than an unoptimized baseline on a consumer GPU and \(3.90\times\)--\(4.04\times\) lower latency on a data-center accelerator. Routing this choice into a patched live scan kernel closes the engineering loop without improving end-to-end speed: in unified routed ablations, the best static chunk outperforms all entropy-guided and proxy schedulers. Sampled-histogram COREY adds \(+4.6\%\) overhead; a guarded fallback to Static-512 reduces this to \(+1.3\%\); and a lightweight sequence-length-keyed table further reduces it to \(+0.7\%\). However, both remain slower than the static oracle because they retain scheduling cost. On an 80-prompt LongBench subset, passive and routed inference are exactly output-equivalent, with \(100\%\) greedy-token agreement and zero metric deltas. A mixed-regime study shows that a single sequence-length rule matches the per-regime chunk oracle for balanced serving. COREY is therefore validated as a quality-preserving scheduling prototype, but current entropy statistics are not a robust throughput win over static chunk tuning on measured SSM checkpoint workloads. SourceCode: https://github.com/mabo1215/COREY_Transformer/.
Authors: Junwoo Park, Jangho Lee, Sunho Lim
Abstract: Pretrained detectors perform well on benchmarks but often suffer performance degradation in real-world deployments due to distribution gaps between training data and target environments. COCO-like benchmarks emphasize category diversity rather than instance density, causing detectors trained under per-class sparsity to struggle in dense, single- or few-class scenes such as surveillance and traffic monitoring. In fixed-camera environments, the quasi-static background provides a stable, label-free prior that can be exploited at inference to suppress spurious detections. To address the issue, we propose Background Embedding Memory (BEM), a lightweight, training-free, weight-frozen module that can be attached to pretrained detectors during inference. BEM estimates clean background embeddings, maintains a prototype memory, and re-scores detection logits with an inverse-similarity, rank-weighted penalty, effectively reducing false positives while maintaining recall. Empirically, background-frame cosine similarity correlates negatively with object count and positively with Precision-Confidence AUC (P-AUC), motivating its use as a training-free control signal. Across YOLO and RT-DETR families on LLVIP and simulated surveillance streams, BEM consistently reduces false positives while preserving real-time performance. Our code is available at https://github.com/Leo-Park1214/Background-Embedding-Memory.git
URLs: https://github.com/Leo-Park1214/Background-Embedding-Memory.git
Authors: Manuela Gonz\'alez-Gonz\'alez, Soufiane Belharbi, Muhammad Osama Zeeshan, Masoumeh Sharafi, Muhammad Haseeb Aslam, Lorenzo Sia, Nicolas Richet, Marco Pedersoli, Alessandro Lameiras Koerich, Simon L Bacon, Eric Granger
Abstract: Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that improve medical outcomes. In-person interventions are costly and difficult to scale, especially in resource-limited regions. Digital health interventions offer a cost-effective approach, potentially supporting independent living and self-management. Automating such interventions, especially through machine learning, has gained considerable attention recently. Ambivalence and hesitancy (A/H) play a primary role for individuals to delay, avoid, or abandon health interventions. A/H are subtle and conflicting emotions that place a person in a state between positive and negative evaluations of a behaviour, or between acceptance and refusal to engage in it. They manifest as affective inconsistency across modalities or within a modality, such as language, facial, vocal expressions, and body language. While experts can be trained to recognize A/H, integrating them into digital health interventions is costly and less effective. Automatic A/H recognition is therefore critical for the personalization and cost-effectiveness of digital health interventions. Here, we explore the application of deep learning models for A/H recognition in videos, a multi-modal task by nature. In particular, this paper covers three learning setups: supervised learning, unsupervised domain adaptation for personalization, and zero-shot inference via large language models (LLMs). Our experiments are conducted on the unique and recently published BAH video dataset for A/H recognition. Our results show limited performance, suggesting that more adapted multi-modal models are required for accurate A/H recognition. Better methods for modeling spatio-temporal and multimodal fusion are necessary to leverage conflicts within/across modalities.
Authors: Mohammad Saleh, Azadeh Tabatabaei
Abstract: Reliable fall detection in elderly care requires monitoring systems that are not only accurate but also capable of producing stable, interpretable explanations of motion dynamics, a requirement that existing post hoc explainability methods rarely satisfy when applied to sequential biosignals. This study introduces a lightweight framework for skeleton-based fall detection that combines a Long Short-Term Memory (LSTM) model with a temporally stabilized attribution mechanism. We propose Temporal SHAP (T-SHAP), which treats frame-wise SHAP attributions as a temporal signal and applies a linear smoothing operator to reduce high-frequency variance. From a signal processing perspective, this operation is analogous to low-pass filtering, enabling the extraction of consistent temporal patterns while preserving the theoretical properties of Shapley-based attributions. Experiments conducted on the NTU RGB+D dataset demonstrate that the proposed approach achieves 94.3% classification accuracy with an end-to-end latency below 25 ms, supporting real-time applicability. Quantitative evaluation using perturbation-based faithfulness metrics shows that T-SHAP improves attribution reliability compared to standard SHAP (AUP: 0.91 vs. 0.89) and Grad-CAM (0.82), while also reducing temporal variance in the attribution signals. The resulting explanations highlight biomechanically relevant motion patterns, such as lower-limb instability and changes in trunk posture, which are consistent with known characteristics of fall events. The resulting framework is computationally lightweight, requires no additional model training, and produces explanations that are both temporally stable and biomechanically meaningful, properties directly relevant to the reliability demands of AI-assisted clinical monitoring.
Authors: Zhanhao Liang, Tao Yang, Jie Wu, Chengjian Feng, Liang Zheng
Abstract: This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memory costs and gradient explosion. Therefore, direct-gradient methods struggle to update early generation steps, which are crucial for determining the global structure of the final image. To address this issue, we introduce LeapAlign, a fine-tuning method that reduces computational cost and enables direct gradient propagation from reward to early generation steps. Specifically, we shorten the long trajectory into only two steps by designing two consecutive leaps, each skipping multiple ODE sampling steps and predicting future latents in a single step. By randomizing the start and end timesteps of the leaps, LeapAlign leads to efficient and stable model updates at any generation step. To better use such shortened trajectories, we assign higher training weights to those that are more consistent with the long generation path. To further enhance gradient stability, we reduce the weights of gradient terms with large magnitude, instead of completely removing them as done in previous works. When fine-tuning the Flux model, LeapAlign consistently outperforms state-of-the-art GRPO-based and direct-gradient methods across various metrics, achieving superior image quality and image-text alignment.
Authors: Yiwei Zhao, Yi Zheng, Huapeng Su, Jieyu Lin, Stefano Ambrogio, Cijo Jose, Michael Ramamonjisoa, Patrick Labatut, Barbara De Salvo, Chiao Liu, Phillip B. Gibbons, Ziyun Li
Abstract: Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive framework for efficient on-device inference of language-aligned VFMs that dynamically adjusts computation based on scene context and task complexity. Our key insight is that the effect of model size reduction on performance is task-dependent in vision applications, motivating a runtime-adaptive execution strategy. AdaVFM integrates neural architecture search (NAS) into the language-aligned VFM backbone to enable lightweight subnet execution during runtime. A multimodal large language model (LLM) deployed on the cloud enables runtime control with a context-aware agent. This synergy allows efficient model adaptation under diverse conditions while maintaining strong accuracy. Extensive experiments on zero-shot classification and open-vocabulary segmentation demonstrate that AdaVFM achieves state-of-the-art accuracy-efficiency trade-offs, surpassing prior baselines by up to $7.9\%$ in acc@1 on IN1K and $5.2\%$ mIoU on ADE20K over the best models of comparable VFM sizes. For models with similar accuracy, AdaVFM further reduces average FLOPs by up to $77.9\%$.
Authors: Yue Jiang, Mingyu Yang, Liuyuxin Yang, Yang Xu, Bingxin Yun, Yuhe Zhang
Abstract: Recent advances in generative motion synthesis have enabled the production of realistic human motions from diverse input modalities. However, synthesizing compound actions from texts, which integrate multiple concurrent actions into coherent full-body sequences, remains a major challenge. We identify two key limitations in current text-to-motion diffusion models: (i) catastrophic neglect, where earlier actions are overwritten by later ones due to improper handling of temporal information, and (ii) attention collapse, which arises from excessive feature fusion in cross-attention mechanisms. As a result, existing approaches often depend on overly detailed textual descriptions (e.g., raising right hand), explicit body-part specifications (e.g., editing the upper body), or the use of large language models (LLMs) for body-part interpretation. These strategies lead to deficient semantic representations of physical structures and kinematic mechanisms, limiting the ability to incorporate natural behaviors such as greeting while walking. To address these issues, we propose the Motion-Adapter, a plug-and-play module that guides text-to-motion diffusion models in generating compound actions by computing decoupled cross-attention maps, which serve as structural masks during the denoising process. Extensive experiments demonstrate that our method consistently produces more faithful and coherent compound motions across diverse textual prompts, surpassing state-of-the-art approaches.
Authors: Zonghai Yao, Benlu Wang, Yifan Zhang, Junda Wang, Iris Xia, Zhipeng Tang, Shuo Han, Feiyun Ouyang, Zhichao Yang, Arman Cohan, Hong Yu
Abstract: Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, where models must interpret each image, combine cross-view evidence, and answer diagnostic questions with intermediate supervision and step-level evaluation. The dataset contains 8,067 cases, including 720 test cases, with an average of 6.62 images per case, substantially denser than prior work, whose expert-level benchmarks use at most 1.43 images per case. On the test set, the best closed-source models, Claude-4.6-Opus, Gemini-3-Pro, and GPT-5.2-xhigh, reach only 57.2%, 55.3%, and 54.9% accuracy, while GPT-5-mini and GPT-5-nano reach 39.7% and 30.8%. Strong open-source models lag behind, led by Qwen3.5-397B-A17B at 52.2% and Qwen3.5-27B at 50.6%. Further analysis identifies grounded multi-image reasoning as the main bottleneck: models often fail to extract, align, and compose evidence across views before higher-level inference can help. Providing expert single-image cues and cross-image summaries improves performance, whereas replacing them with self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors arise from image reading and cross-view integration. Scaling results further show that additional inference-time computation helps only when visual grounding is already reliable; when early evidence extraction is weak, longer reasoning yields limited or unstable gains and can amplify misread cues. These results suggest that the key challenge is not reasoning length alone, but reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world multimodal clinical inputs.
Authors: Chengan Che, Chao Wang, Jiayuan Huang, Xinyue Chen, Luis C. Garcia-Peraza-Herrera
Abstract: Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extending these visual foundations to multi-modal reasoning tasks is severely bottlenecked by the prohibitive cost of expert textual annotations. To overcome this scalability limitation, we introduce \textbf{LIME}, a large-scale multi-modal dataset derived from open-access surgical videos using human-free, Large Language Model (LLM)-generated narratives. While LIME offers immense scalability, unverified generated texts may contain errors, including hallucinations, that could potentially lead to catastrophically degraded pre-trained medical priors in standard contrastive pipelines. To mitigate this, we propose \textbf{SurgLIME}, a parameter-efficient Vision-Language Pre-training (VLP) framework designed to learn reliable cross-modal alignments using noisy narratives. SurgLIME preserves foundational medical priors using a LoRA-adapted dual-encoder architecture and introduces an automated confidence estimation mechanism that dynamically down-weights uncertain text during contrastive alignment. Evaluations on the AutoLaparo and Cholec80 benchmarks show that SurgLIME achieves competitive zero-shot cross-modal alignment while preserving the robust linear probing performance of the visual foundation model. Dataset, code, and models are publicly available at https://github.com/visurg-ai/SurgLIME.
Authors: Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li, Han Wang, Shaoqing Xu, Yuechen Luo, Fang Li, Chenxu Dang, Junli Wang, Tao Xu, Jing Wu, Jianhua Wu, Xiaoshuai Hao, Wen Zhang, Tianyi Jiang, Lingfeng Zhang, Lei Zhou, Yingbo Tang, Jie Wang, Yinfeng Gao, Xizhou Bu, Haochen Tian, Yihang Qiu, Feiyang Jia, Lin Liu, Yigu Ge, Hanbing Li, Yuannan Shen, Jianwei Cui, Hongwei Xie, Bing Wang, Haiyang Sun, Jingwei Zhao, Jiahui Huang, Pei Liu, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Hanchao Leng, Kun Ma, Naiyan Wang, Guang Chen, Kuiyuan Yang, Hangjun Ye, Long Chen
Abstract: Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. In inference, the auxiliary decoders are discarded, and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering superior accuracy at answer-only latency. These results show that with world model supervision, latent CoT produces more generalizable representations than verbose token-by-token reasoning. Code has been open-sourced to the community. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL
Authors: Aaron Nicolson, Elizabeth J. Cooper, Hwan-Jin Yoon, Claire McCafferty, Ramya Krishnan, Michelle Craigie, Nivene Saad, Jason Dowling, Ian A. Scott, Bevan Koopman
Abstract: Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress on automated metrics, yet their clinical utility remains uncertain due to limited qualitative evaluation by radiologists. We present CXRMate-2, a state-of-the-art CXR RRG model that enables tractable reinforcement learning (RL) through structured multimodal temporal embeddings and high-resolution visual feature compression, for efficient, unified conditioning of an LLM decoder on visual, textual, and temporal context from a study and its prior. This enables group relative policy optimisation (GRPO), where a proposed reward function is used to improve semantic alignment with radiologist reports. Across the MIMIC-CXR, CheXpert Plus, and ReXgradient datasets, CXRMate-2 achieves statistically significant improvements over strong benchmarks, including gains of 11.2% and 24.4% in GREEN and RadGraph-XL, respectively, on MIMIC-CXR relative to MedGemma 1.5 (4B). To directly compare CXRMate-2 against radiologist reporting, we conduct a blinded, randomised qualitative retrospective evaluation. Three consultant radiologists compare generated and radiologist reports across 120 studies from the MIMIC-CXR test set. Generated reports were deemed acceptable (defined as preferred or rated equally to radiologist reports) in 45% of ratings, with no statistically significant difference in preference rates for seven of the eight analysed findings. Preferences for radiologist reports were driven primarily by higher recall, while generated reports were consistently preferred for readability. Together, these results define a clear pathway to clinically acceptable CXR RRG. Improving recall and the detection of subtle findings represents the primary remaining barrier to non-inferiority with radiologist reporting, positioning CXR RRG for prospective evaluation in assistive, radiologist-led workflows.
Authors: Shurui Wang, Yuhe Zhang, Ruizhe Guo, Yaning Zhang, Yifei Xie, Xinyu Zhou
Abstract: The development of 3D scanning technology has enabled the acquisition of massive point cloud models with diverse structures and large scales, thereby presenting significant challenges in point cloud processing. Fast neighboring points search is one of the most common problems, which is frequently used in model reconstruction, classification, retrieval and feature visualization. Hash function is well known for its high-speed and accurate performance in searching high-dimensional data, which is also the core of the proposed 2L-LSH. Specifically, the 2L-LSH algorithm adopts a two-step hash function strategy, in which the popular step divides the bounding box of the point cloud model and the second step constructs a generalized table-based data structure. The proposed 2L-LSH offers a highly efficient and accurate solution for fast neighboring points search in large-scale 3D point cloud models, making it a promising technique for various applications in the field. The proposed algorithm is compared with the well-known methods including Kd-tree and Octree; the obtained results demonstrated that the proposed method outperforms Kd-tree and Octree in terms of speed, i.e. the time consumption of kNN search can be 51.111% and 94.159% lower than Kd-tree and Octree, respectively. And the RN search time can be 54.519% and 41.840% lower than Kd-tree and Octree, respectively.
Authors: Suiyang Guang, Chenyu Liu, Ruohan Zhang, Siyuan Chen
Abstract: Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible and fine-grained relation phrases beyond a fixed predicate vocabulary. While recent vision-language models greatly expand the semantic coverage of SGG, they also introduce a critical reliability issue: predicted relations may be driven by language priors or object co-occurrence rather than grounded visual evidence. In this paper, we propose an evidence-rounded open-vocabulary SGG framework based on counterfactual relation verification. Instead of directly accepting plausible relation proposals, our method verifies whether each candidate relation is supported by relation-pecific visual, geometric, and contextual evidence. Specifically, we first generate open-vocabulary relation candidates with a vision-language proposer, then decompose predicate phrases into soft evidence bases such as support, contact, containment, depth, motion, and state. A relation-conditioned evidence encoder extracts predicate-relevant cues, while a counterfactual verifier tests whether the relation score decreases when necessary vidence is removed and remains stable under irrelevant perturbations. We further introduce contradiction-aware predicate learning and graph-level preference optimization to improve fine-grained discrimination and global graph consistency. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that our method consistently improves standard recall-based metrics, unseen predicate generalization, and counterfactual grounding quality. These results demonstrate that moving from relation generation to relation verification leads to more reliable, interpretable, and evidence-grounded scene graphs.
Authors: Amir Hosseini, Sara Farahani, Xinyi Li, Suiyang Guang
Abstract: Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing methods usually treat annotated triplets as positives and all unannotated object-pair relations as negatives. However, scene graph annotations are inherently incomplete: many valid relations are missing, and the same interaction can be described at different granularities, e.g., \textit{on}, \textit{standing on}, \textit{resting on}, and \textit{supported by}. This issue becomes more severe in open-vocabulary SGG due to the much larger relation space. We propose \textbf{ReLIC-SGG}, a relation-incompleteness-aware framework that treats unannotated relations as latent variables rather than definite negatives. ReLIC-SGG builds a semantic relation lattice to model similarity, entailment, and contradiction among open-vocabulary predicates, and uses it to infer missing positive relations from visual-language compatibility, graph context, and semantic consistency. A positive-unlabeled graph learning objective further reduces false-negative supervision, while lattice-guided decoding produces compact and semantically consistent scene graphs. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that ReLIC-SGG improves rare and unseen predicate recognition and better recovers missing relations.
Authors: Varun Totakura, Shayok Chakraborty
Abstract: Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. Unfortunately, deep learning systems are not perfect and can fail, sometimes abruptly, without prior warning or explanation. While reducing the error rate of deep neural networks has been the primary focus of the multimedia community, the problem of predicting when a deep learning system is going to fail has received significantly less research attention. In this paper, we propose a simple yet effective framework, MetaErr, to address this under-explored problem in deep learning research. We train a meta-model whose goal is to predict whether a base deep neural network will succeed or fail in predicting a particular data sample, by observing the base models performance on a given learning task. The meta-model is completely agnostic of the architecture and training parameters of the base model. Such an error prediction system can be immensely useful in a variety of smart multimedia applications. Our empirical studies corroborate the promise and potential of our framework against competing baselines. We further demonstrate the usefulness of our framework to improve the performance of pseudo-labeling-based semi-supervised learning, and show that MetaErr outperforms several strong baselines on three benchmark computer vision datasets.
Authors: Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen, Chia-Min Lin, Yung-Che Wang, Jen-Shiun Chiang
Abstract: High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational overhead and limit accessibility under constrained hardware settings. In this paper, we propose DGM-Net (Directional Geometric Mamba Network), an efficient architecture that improves modeling capability through structural design rather than increasing model capacity. We introduce Directional Geometric Mamba (G-Mamba), a linear-complexity O(N) operator as an alternative to conventional context modeling modules such as ASPP and PPM. To further enhance structural awareness in state space model (SSM)-based modeling, we design the DGM-Module, which extracts centripetal flow fields and topological skeletons to guide the scanning process and improve boundary preservation. Without relying on large-scale pretraining or heavy backbone scaling, DGM-Net achieves 80.8% mIoU within 28k iterations, 82.3% mIoU on Cityscapes test set, and 45.24% mIoU on ADE20K. In addition, the model maintains stable performance under constrained hardware settings (e.g., batch size of 2 on 8GB VRAM), highlighting its efficiency and practicality. These results demonstrate that incorporating geometric guidance into SSM-based architectures provides an effective and resource-efficient direction for semantic segmentation.
Authors: Lixian Chen, Yanhui Chen, Junyi Lin
Abstract: Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can sharpen the fused posterior while increasing error, because an unreliable modality may still dominate fusion. We study this failure mode through a majorization view of multimodal posteriors and cast adaptation as a constrained de-mixing problem on the fused prediction. Based on this view, we propose MG-MTTA, which keeps the backbone frozen and updates only a lightweight gate or adapter. The objective combines fused-posterior entropy minimization with a reliability-aware gate prior built from anchor-based modality consistency and cross-modal conflict. Our analysis gives conditions under which entropy reduction preserves the correct ranking and a threshold that characterizes modality-dominance failure. On the ImageNet-based benchmark, MG-MTTA improves top-1 accuracy from 57.97 to 66.51 under semantics-preserving textual shift and from 21.68 to 26.27 under joint visual-textual shift, while remaining competitive in the visual-only benchmark. These results show that multimodal test-time adaptation should control modality reliability, not just prediction entropy.
Authors: Fangqiang Fan, Zhicheng Zhao, Xiaoliang Ma, Chenglong Li, Jin Tang
Abstract: Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT image semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and severe semantic confusion among fine-grained ground objects under top-down aerial views. To address these issues, we propose a Graph-based Semantic Calibration Network (GSCNet) for unaligned UAV RGBT image semantic segmentation. Specifically, we design a Feature Decoupling and Alignment Module (FDAM) that decouples each modality into shared structural and private perceptual components and performs deformable alignment in the shared subspace, enabling robust spatial correction with reduced modality appearance interference. Moreover, we propose a Semantic Graph Calibration Module (SGCM) that explicitly encodes the hierarchical taxonomy and co-occurrence regularities among ground-object categories in UAV scenes into a structured category graph, and incorporates these priors into graph-attention reasoning to calibrate predictions of visually similar and rare categories. In addition, we construct the Unaligned RGB-Thermal Fine-grained (URTF) benchmark, to the best of our knowledge, the largest and most fine-grained benchmark for unaligned UAV RGBT image semantic segmentation, containing over 25,000 image pairs across 61 semantic categories with realistic cross-modal misalignment. Extensive experiments on URTF demonstrate that GSCNet significantly outperforms state-of-the-art methods, with notable gains on fine-grained categories. The dataset is available at https://github.com/mmic-lcl/Datasets-and-benchmark-code.
URLs: https://github.com/mmic-lcl/Datasets-and-benchmark-code.
Authors: Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin
Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model's original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, where perception errors and reasoning failures follow distinct drift patterns that compound during subsequent RL. We introduce PRISM, a three-stage pipeline that mitigates this drift by inserting an explicit distribution-alignment stage between SFT and RLVR. Building on the principle of on-policy distillation (OPD), PRISM casts alignment as a black-box, response-level adversarial game between the policy and a Mixture-of-Experts (MoE) discriminator with dedicated perception and reasoning experts, providing disentangled corrective signals that steer the policy toward the supervision distribution without requiring access to teacher logits. While 1.26M public demonstrations suffice for broad SFT initialization, distribution alignment demands higher-fidelity supervision; we therefore curate 113K additional demonstrations from Gemini 3 Flash, featuring dense visual grounding and step-by-step reasoning on the hardest unsolved problems. Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the SFT-to-RLVR baseline on 4B and 8B, respectively. Our code, data, and model checkpoints are publicly available at https://github.com/XIAO4579/PRISM.
Authors: Vincenzo Polizzi, David B. Lindell, Jonathan Kelly
Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a cross-modal framework that learns an RGB and Event Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models. Instead of task-specific training, we leverage low-rank adaptation (LoRA) to bridge the modality gap, effectively unlocking the geometric and semantic priors of frozen RGB backbones for asynchronous event streams. We demonstrate that REALM effectively maps events into the ViT-based foundation latent space. Our method allows us to perform downstream tasks like depth estimation and semantic segmentation by simply transferring linear heads trained on the RGB teacher. Most significantly, REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures. Code and models are available upon acceptance.
Authors: Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo
Abstract: Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.
Authors: Adrian Chang, Kai Wang, Yuanbo Li, Manolis Savva, Angel X. Chang, Daniel Ritchie
Abstract: In this work we study indoor scene object placement. Given a 3D indoor scene and an object, the task is to predict placement locations within the scene. Empirical observations of data-driven approaches to the problem show their tendency to miss placement modes. We introduce a system which helps to address this flaw. We design a Domain Specific Language (DSL) that specifies object relational constraints. Upon execution, programs from our language predict possible placements from a partial scene and object. We design a generative model which writes these programs automatically. Available 3D scene datasets do not contain programs to train on, and naively extracted programs only predict the original placement location of scene objects. Training on these programs results in subpar performance so we introduce a new program bootstrapping algorithm that improves our system's performance compared to the naive approach. To quantify our qualitative observations, we introduce a new evaluation procedure which captures how well a system models per-object location distributions. We ask human annotators to label all the possible places an object can go in a scene and compare this set against locations produced by the system in question. Our system produces per-object location distributions more consistent with human annotators than those produced by existing data-driven approaches and a zero-shot approach using an LLM. While other systems degrade in performance when training data is sparse, our system does not degrade to the same degree.
Authors: Shijie Chen, Yiwei Chen, Amir Aghabiglou, Motahare Torki, Chao Tang, Ruud B. van Heeswijk, Yves Wiaux
Abstract: We introduce interlaced R2D2 (iR2D2), a DNN series paradigm for scalable image reconstruction from accelerated non-Cartesian k-space acquisitions in MRI with sensitivity map self-calibration. While unrolled DNN architectures provide robust image formation, embedding non-uniform fast Fourier transform operators within the backpropagation graph becomes impractical to train at large scale, e.g., in 2D MRI with a large number of coils, or for higher-dimensional imaging. To address this scalability challenge, we leverage the R2D2 paradigm as a learned version of the Matching Pursuit algorithm that was recently introduced in radio astronomy for fast large-scale Fourier imaging. R2D2's reconstruction is formed as a series of residual images iteratively estimated as outputs of DNN modules taking the previous iteration's data residual as input. Specific to MRI, precomputed sensitivity maps derived from undersampled data can yield an inaccurate measurement operator, which may adversely affect the performance of iterative algorithms such as R2D2. Thus, we extend the R2D2 framework to iR2D2 by introducing a bespoke interlaced architecture that alternates between two R2D2 DNN series to jointly self-calibrate sensitivity maps and form the MR image. We further enhance iR2D2 to operate as an adaptive solver governed by an error-controlled update condition that enforces a sufficient residual energy descent, a dynamic capability fundamentally incompatible with the predefined forward passes of unrolled architectures. Extensive experiments in simulation and on real data, targeting undersampled radial k-space sampling, demonstrate that iR2D2 significantly improves upon R2D2 and outperforms state-of-the-art benchmarks, delivering scalable, high-fidelity imaging with corrected sensitivity profiles.
Authors: Tajamul Ashraf, Mohammed Mohsen Peerzada, Moloud Abdar, Yutong Xie, Yuyin Zhou, Xiaofeng Liu, Iqra Altaf Gillani, Janibul Bashir
Abstract: Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows, numerous techniques have been proposed to tackle its practical challenges. However, the lack of standardized evaluation across key dimensions hampers systematic progress and fair comparison of FL methods. In this work, we introduce ATR-Bench, a unified framework for analyzing federated learning through three foundational dimensions: Adaptation, Trust, and Reasoning. We provide an in-depth examination of the conceptual foundations, task formulations, and open research challenges associated with each theme. We have extensively benchmarked representative methods and datasets for adaptation to heterogeneous clients and trustworthiness in adversarial or unreliable environments. Due to the lack of reliable metrics and models for reasoning in FL, we only provide literature-driven insights for this dimension. ATR-Bench lays the groundwork for a systematic and holistic evaluation of federated learning with real-world relevance. We will make our complete codebase publicly accessible and a curated repository that continuously tracks new developments and research in the FL literature.
Authors: Kateryna Lutsai, Pavel Stra\v{n}\'ak
Abstract: Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)
Authors: Hongli Chen, Pengcheng Fang, Yuxia Chen, Yingxuan Ren, Jing Hao, Fangfang Tang, Xiaohao Cai, Shanshan Shan, Feng Liu
Abstract: Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision tasks offer promising long-range modeling capabilities with linear-time complexity, their direct application to MRI reconstruction inherits two key limitations: (1) insensitivity to high-frequency anatomical details; and (2) reliance on redundant multi-directional scanning. To address these limitations, we introduce High-Fidelity Mamba (HiFi-Mamba), a novel dual-stream Mamba-based architecture comprising stacked W-Laplacian (WL) and HiFi-Mamba blocks. Specifically, the WL block performs fidelity-preserving spectral decoupling, producing complementary low- and high-frequency streams. This separation enables the HiFi-Mamba block to focus on low-frequency structures, enhancing global feature modeling. Concurrently, the HiFi-Mamba block selectively integrates high-frequency features through adaptive state-space modulation, preserving comprehensive spectral details. To eliminate the scanning redundancy, the HiFi-Mamba block adopts a streamlined unidirectional traversal strategy that preserves long-range modeling capability with improved computational efficiency. Extensive experiments on standard MRI reconstruction benchmarks demonstrate that HiFi-Mamba consistently outperforms state-of-the-art CNN-based, Transformer-based, and other Mamba-based models in reconstruction accuracy while maintaining a compact and efficient model design.
Authors: Xun Su, Hiroyuki Kasai
Abstract: Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation information into the generation process of the diffusion models. However, this presents an inherent dilemma: excessive integration can disrupt the generative process, while insufficient integration fails to emphasize the constraints imposed by the inverse problem. To address this, we propose \emph{Noise Combination Sampling}, a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score, replacing the noise term in the standard Denoising Diffusion Probabilistic Models process. This enables conditional information to be naturally embedded into the generation process without reliance on step-wise hyperparameter tuning. Our method can be applied to a wide range of inverse problem solvers, including image compression, and, particularly when the number of generation steps $T$ is small, achieves superior performance with negligible computational overhead, significantly improving robustness and stability.
Authors: Jonas Hein, Lazaros Vlachopoulos, Maurits Geert Laurent Olthof, Bastian Sigrist, Philipp F\"urnstahl, Matthias Seibold
Abstract: Purpose: Surgical scene understanding is key to advancing computer-aided and intelligent surgical systems. Current approaches predominantly rely on visual data or end-to-end learning, which limits fine-grained contextual modeling. This work aims to enhance surgical scene representations by integrating 3D acoustic information, enabling temporally and spatially aware multimodal understanding of surgical environments. Methods: We propose a novel framework for generating 4D audio-visual representations of surgical scenes by projecting acoustic localization information from a phased microphone array onto dynamic point clouds from an RGB-D camera. A transformer-based acoustic event detection module identifies relevant temporal segments containing tool-tissue interactions which are spatially localized in the audio-visual scene representation. The system was experimentally evaluated in a realistic operating room setup during simulated surgical procedures performed by experts. Results: The proposed method successfully localizes surgical acoustic events in 3D space and associates them with visual scene elements. Experimental evaluation demonstrates accurate spatial sound localization and robust fusion of multimodal data, providing a comprehensive, dynamic representation of surgical activity. Conclusion: This work introduces the first approach for spatial sound localization in dynamic surgical scenes, marking a significant advancement toward multimodal surgical scene representations. By integrating acoustic and visual data, the proposed framework enables richer contextual understanding and provides a foundation for future intelligent and autonomous surgical systems.
Authors: Andreas Koukounas, Georgios Mastrapas, Florian H\"onicke, Sedigheh Eslami, Guillaume Roncari, Scott Martens, Han Xiao
Abstract: We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language decoder and makes use of image tiling and attention-pooling for token-efficient processing of arbitrary-resolution images. To understand the contribution of different training data categories, we conduct a leave-one-out data mixture ablation study-systematically removing task, domain, modality, and language categories-to diagnose which data types are necessary versus redundant and whether task benefits transfer across domains. Model weights and code are publicly released at https://huggingface.co/jinaai/jina-vlm.
Authors: Aizierjiang Aiersilan, Ruting Cheng, James Hahn
Abstract: The release of SAM 3D Body is a recent development in human mesh recovery, demonstrating improved performance in producing clean, topologically coherent meshes from single images. By leveraging the Momentum Human Rig (MHR), it achieves robustness to occlusion and diverse poses. However, our evaluation reveals a specific and consistent limitation: the model struggles to reconstruct detailed anthropometric deviations, particularly in populations exhibiting distinctive morphological alterations such as geriatric muscle atrophy, scoliosis, or pregnancy, even when these features are prominent in the input image. In this paper, we investigate this phenomenon not as a failure of the model's capacity, but as a byproduct of the "perception-distortion trade-off". We posit that the architectural reliance on the low-dimensional parametric MHR representation, combined with semantic-invariant conditioning (DINOv3) and annotation-based alignment, creates a pervasive "regression to the mean" effect. We analyze these mechanisms to understand why individual biological details are smoothed out. Furthermore, we state our contributions by proposing specific, constructive pathways for future work, such as implicit-explicit hybrid representations and Medical-in-the-Loop alignment, to extend the baseline performance of SAM 3D Body into the high-precision medical domain.
Authors: Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee
Abstract: Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informative about the underlying ground-truth actions. For effective supervision, latent actions should contain information about the underlying actions even though they are inaccessible. We propose Multi-ViewPoint Latent Action Moel (MVP-LAM), which learns latent actions that are highly informative about ground-truth actions from multi-view videos. MVP-LAM trains latent actions with a cross-viewpoint reconstruction objective, so that a latent action from one view must explain the future in another view, reducing reliance on viewpoint-specific cues. On Bridge V2, MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks. The code and trained checkpoints are available at https://jmsnu.github.io.
URLs: https://jmsnu.github.io.
Authors: Lingfeng He, De Cheng, Huaijie Wang, Xi Yang, Nannan Wang, Xinbo Gao
Abstract: Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks. However, they (i) overlook task-shared directions, which suppresses knowledge transfer, and (ii) fail to capture truly effective task-specific directions since these ``null bases" of old tasks can remain nearly inactive for new task under correlated tasks. To address this, we study LoRA learning capability from a projection energy perspective, and propose Low-rank Decomposition and Adaptation (LoDA). It performs a task-driven decomposition to build general and truly task-specific LoRA subspaces by solving two energy-based objectives, decoupling directions for knowledge sharing and isolation. LoDA fixes LoRA down-projections on two subspaces and learns robust up-projections via a Gradient-Aligned Optimization (GAO) approach. After each task, before integrating the LoRA updates into the backbone, LoDA derives a closed-form recalibration for the general update, approximating a feature-level joint optimum along this task-shared direction. Experiments indicate that LoDA outperforms existing CL methods.
Authors: Jan Finke, Wayne Paul Martis, Adrian Schmelter, Lars Erbach, Christian Jestel, Marvin Wiedemann
Abstract: Reliable obstacle avoidance in industrial settings demands 3D scene understanding, but widely used 2D LiDAR sensors perceive only a single horizontal slice of the environment, missing critical obstacles above or below the scan plane. We present a teacher-student framework for vision-based mobile robot navigation that eliminates the need for LiDAR sensors. A teacher policy trained via Proximal Policy Optimization (PPO) in NVIDIA Isaac Lab leverages privileged 2D LiDAR observations that account for the full robot footprint to learn robust navigation. The learned behavior is distilled into a student policy that relies solely on monocular depth maps predicted by a fine-tuned Depth Anything V2 model from four RGB cameras. The complete inference pipeline, comprising monocular depth estimation (MDE), policy execution, and motor control, runs entirely onboard an NVIDIA Jetson Orin AGX mounted on a DJI RoboMaster platform, requiring no external computation for inference. In simulation, the student achieves success rates of 82-96.5%, consistently outperforming the standard 2D LiDAR teacher (50-89%). In real-world experiments, the MDE-based student outperforms the 2D LiDAR teacher when navigating around obstacles with complex 3D geometries, such as overhanging structures and low-profile objects, that fall outside the single scan plane of a 2D LiDAR.
Authors: Jiajun He, Zongyu Guo, Zhaoyang Jia, Xiaoyi Zhang, Jiahao Li, Xiao Li, Bin Li, Jos\'e Miguel Hern\'andez-Lobato, Yan Lu
Abstract: Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for compact storage or reuse. In this work, we introduce a new visual representation framework that encodes a signal as a function, which is parametrized by low-rank adaptations attached to a frozen visual generative model. Such implicit representations of visual signals, e.g., an 81-frame video, can further be hashed into a single compact vector, achieving strong perceptual video compression at extremely low bitrates. Beyond basic compression, the functional nature of this representation enables inference-time scaling and control, allowing additional refinement on the compression performance. More broadly, as the implicit representations directly act as a function of the generation process, this suggests a unified framework bridging visual compression and generation.
Authors: Aizierjiang Aiersilan, Zhangfei Yang
Abstract: Adaptive 360{\deg} video streaming for teleoperation faces two coupled challenges: viewport prediction under uncertain gaze patterns and bitrate adaptation over fluctuating wireless channels. While Deep Reinforcement Learning (DRL) methods achieve high Quality of Experience (QoE), their lack of interpretability and dependence on offline training limit deployment in safety-critical systems. We propose OrbitStream, a training-free framework that formulates viewport prediction as a Gravitational Viewport Prediction (GVP) problem, where semantic objects generate potential fields that attract operator gaze, and employs a Saturation-Based Proportional-Derivative (PD) Controller for buffer regulation. On object-rich teleoperation traces, OrbitStream achieves 94.7% zero-shot viewport prediction accuracy without user-specific profiling, approaching trajectory-extrapolation baselines (~98.5%). Across 3,600 Monte Carlo simulations, it ranks second among 12 algorithms (QoE 2.71 vs. BOLA-E's 2.80), outperforming FastMPC (1.84), with 1.01 ms decision latency and minimal rebuffering.
Authors: Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit
Abstract: Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts.
Authors: Puja Saha, Eranga Ukwatta
Abstract: Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized settings frequently fail to generalize across clinical sites because of heterogeneity in imaging protocols and continuously evolving data distributions arising from differences in scanners, acquisition parameters, and patient populations. Federated learning offers a promising solution by enabling collaborative model training without sharing raw data. However, incorporating differential privacy into federated learning, while essential for privacy guarantees, often leads to degraded accuracy, unstable convergence, and reduced generalization. In this work, we propose an adaptive differentially private federated learning (ADP-FL) framework for medical image segmentation that dynamically adjusts privacy mechanisms to better balance the privacy-utility trade-off. The proposed approach stabilizes training, significantly improves Dice scores and segmentation boundary quality, and maintains rigorous privacy guarantees. We evaluated ADP-FL across diverse imaging modalities and segmentation tasks, including skin lesion segmentation in dermoscopic images, kidney tumor segmentation in 3D CT scans, and brain tumor segmentation in multi-parametric MRI. Compared with conventional federated learning and standard differentially private federated learning, ADP-FL consistently achieves higher accuracy, improved boundary delineation, faster convergence, and greater training stability, with performance approaching that of non-private federated learning under the same privacy budgets. These results demonstrate the practical viability of ADP-FL for high-performance, privacy-preserving medical image segmentation in real-world federated settings.
Authors: Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
Abstract: As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are more faithful but require solving the NP-hard Graph Edit Distance (GED) problem. We propose U-CECE, a unified, model-agnostic multi-resolution framework for conceptual counterfactual explanations that adapts to data regime and compute budget. U-CECE spans three levels of expressivity: atomic concepts for broad explanations, relational sets-of-sets for simple interactions, and structural graphs for full semantic structure. At the structural level, both a precision-oriented transductive mode based on supervised Graph Neural Networks (GNNs) and a scalable inductive mode based on unsupervised graph autoencoders (GAEs) are supported. Experiments on the structurally divergent CUB and Visual Genome datasets characterize the efficiency-expressivity trade-off across levels, while human surveys and LVLM-based evaluation show that the retrieved structural counterfactuals are semantically equivalent to, and often preferred over, exact GED-based ground-truth explanations.
Authors: Romain Hermary, Samet Hicsonmez, Dan Pineau, Abd El Rahman Shabayek, Djamila Aouada
Abstract: Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.