Authors: Tianci Wu, Siqi Cao, Guangming Zhu, Jiang Lu, Siyuan Wang, Longfei Zhang, Jincai Huang, Jun Sheng, Liang Zhang
Abstract: Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are insufficient for capturing subtle interactions and fine-grained semantics. While recent prompt-based approaches introduce disentanglement, they lack explicit semantic guidance, and methods based solely on visual or structured cues remain coarse-grained. In this paper, we propose Knowledge-guided Disentanglement with Atomic Actions (KDA), which leverages fine-grained semantic knowledge to enhance action representations and enable more precise disentanglement. Specifically, we use Large Language Models (LLMs) to decompose action labels into atomic actions, providing explicit spatial-temporal semantics. A Knowledge Injection Module (KIM) first integrates atomic action knowledge into video features. Based on this enhanced representation, a Knowledge Disentanglement Module (KDM) further disentangles atomic action knowledge to produce more precise semantic guidance for action disentanglement. A Knowledge Disentanglement Loss (KD Loss) is introduced to encourage clearer disentanglement of knowledge components within KDM. Extensive experiments demonstrate that KDA improves feature discriminability and achieves state-of-the-art performance on multi-label action recognition benchmarks. Moreover, KIM and KDM can be readily integrated into other methods, demonstrating strong generality.
Authors: Hira Yaseen, Arif Mahmood, Waqas Sultani
Abstract: A person's physical characteristics such as weight and height are important indicators of his physical and mental health, daily life routines and finances. Body Mass Index (BMI) is a well known measure that encodes the characteristics of both the weight and the height. BMI has been used as a self-monitoring tool, and it has long-term implications on one's life. For example, it may help predicting the risk of various diseases and estimating longevity. Automatic BMI estimation using a single person image in the wild is a challenging task due to wide variations in human pose, camera geometry, personal appearance and distracting backgrounds. In this paper, we explore the performance of deep neural networks using single and multi-task learning by employing different modalities including RGB, depth-maps, pose-affinity maps, and edge-maps to predict BMI, weight, and height from daily life images available on social networking websites. Currently, no full body image dataset for BMI estimation is publicly available, therefore we propose a new dataset consisting of 6105 images with ground truth labels of height, weight and BMI. Our proposed dataset is collected in the wild containing images from various ethnicity and distributed over varying age groups and gender. It consists of frontal, back, full and half body, side poses, mirror selfies with varying backgrounds and scale variations and may contain artifacts hiding partial or full face. Extensive experimentation is performed using full body, half body and face images only using different CNN backbones including VGG, Densenet and ResNet. Our experimental results demonstrate that full body images have produced better results than the other half body and facial images in the wild.
Authors: Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong
Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions. CLIP provides a strong foundation for these tasks by learning a shared image-text embedding space from large-scale contrastive pre-training. However, its image-level objective aligns text with a CLS-derived global representation, leaving local vision-language correspondence only indirectly constrained. Existing methods either introduce additional supervision, external models, or task-specific adaptation, while training-free approaches mainly recover dense responses from existing patch features without examining where local semantics become most accessible within CLIP. We introduce TraceCLIP, a training-free framework that recovers latent patch-level semantic evidence by isolating the patch-specific terms written into the CLS attention output. TraceCLIP further converts contribution-derived semantic responses into a semantic-geodesic topology gate that calibrates final-layer patch affinity for dense feature reconstruction. Diagnostic experiments show that these contribution features exhibit strong local semantic discrimination and text-conditioned spatial alignment. On eight zero-shot semantic segmentation benchmarks, TraceCLIP achieves gains of 1.3 to 4.5 points in average mIoU over the strongest prior training-free methods across both backbones and background settings, without additional training, external vision foundation models, or region-level supervision. More broadly, these findings suggest that spatially localized semantics may remain accessible within the internal construction of globally aligned representations.
Authors: Yung-Hsu Yang, Luigi Piccinelli, Siyuan Li, Mattia Segu, Lei Ke, Martin Danelljan, Yuqian Fu, Zuria Bauer, Fisher Yu, Hermann Blum, Marc Pollefeys
Abstract: Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance trajectories. While depth-aware video panoptic segmentation (DVPS) unifies these tasks, existing approaches often rely on computationally expensive, multi-stage pipelines or offline tracking, rendering them unsuitable for real-time decision-making. To address this, we propose DVPSFormer, a unified online architecture designed for efficient 4D scene understanding. Central to our approach is explicit scene discretization (ESD), a novel mechanism that leverages segmentation queries to represent foreground and background regions, enabling a discrete-to-continuous (D2C) depth head to decode metric depth in a single pass. This tightly couples semantic and geometric learning while significantly reducing latency. Furthermore, we propose an online majority voting (OMV) mechanism that exploits temporal consistency to refine classification during instance tracking. DVPSFormer establishes a new state-of-the-art on the Cityscapes-DVPS and SemKITTI-DVPS benchmarks, offering a streamlined solution for online robotic perception. Code and models are available at https://royyang0714.github.io/DVPSFormer.
Authors: Hua Qian, Manisha Kotha, Tuan Tran, Jennifer Shin, Haining Zheng
Abstract: This study developed a hybrid computer vision method to quantify exposed skin from images for dermal exposure assessment. Using 170 indoor-painting images, Mask R-CNN first identified human subjects and removed background interference; a color-based algorithm then segmented exposed skin. The resulting exposed-skin-to-body pixel ratios showed approximately 80% agreement with human estimates. The approach demonstrates a scalable way to extract semi-quantitative exposure information from images, with future extensions to body-part recognition, PPE detection, and video-based exposure analysis.
Authors: Quoc-Huy Trinh, Minh-Van Nguyen, Ulas Bagci
Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet existing volumetric encoders often fail to preserve the coarse spatial and geometric structure that downstream reasoning depends on, limiting their performance on organ disentanglement, abnormality detection, and spatial understanding when paired with language models. We introduce Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations by predicting the latent features of a complete scan from a masked view. At its core is a hybrid H-Mamba encoder that fuses a Mamba state-space branch, which models inter-slice continuity through sequential scanning, with a grouped-query attention branch, which captures cross-plane spatial context, combined through a lightweight per-token router. To improve the quality of intermediate representations, we further propose Hidden States Orthogonal Regularization (HSOR), which aligns student-teacher hidden states and reduces feature redundancy throughout the encoder. This layer-wise regularization produces more consistent and discriminative volumetric representations, leading to improved performance on organ recognition and spatial reasoning tasks. Pretrained on approximately 120,000 CT scans, Rad-JEPA 3D attains state-of-the-art results despite its compact size: with only 4.0B total parameters, it achieves competitive results with state-of-the-art on closed-ended VQA and the best average spatial-reasoning score on the Spatial-Med benchmark. Ablation studies confirm that the hybrid block and HSOR contribute complementary gains, and that the induced spatial structure can substitute for raw language-model scale on volumetric reasoning tasks.
Authors: Jiamin Xu, Cong Wang, Zheng Dong, Chi Wang, Renshu Gu, Weiwei Xu, Gang Xu
Abstract: Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data. Despite its importance to numerous vision and graphics applications, it remains largely unexplored in unconstrained real-world scenarios. To address this gap, we present WildShadowRemover, a framework that adapts a pretrained video diffusion model for robust video shadow removal via LoRA fine-tuning. To preserve fine image details while retaining the model's powerful generative prior, we augment the frozen VAE decoder with a detail injection module and introduce a shadow-mask-guided frequency-decomposed modulation module to selectively restore high-frequency textures while suppressing shadow artifacts. Monocular depth priors from Depth Anything 3 further provide geometry-aware guidance under challenging lighting conditions. We also construct WildShadow, a large-scale paired video shadow removal dataset and benchmark, covering diverse synthetic scenes. Extensive experiments demonstrate that our method outperforms existing approaches in shadow removal quality and temporal consistency, producing temporally coherent shadow-free videos with superior visual quality and strong generalization across challenging in-the-wild scenarios.
Authors: Mahmuda Akter Sristy, Md Al-Mahfuz Chowdhury, Momota Ahsana Meem, Sajid Ahamed, Kazi Irfan Subhan
Abstract: Brain tumors such as glioma, meningioma, and pituitary adenoma alter the mechanical behavior of soft brain tissue, yet common diagnostic methods rely on static imaging that cannot capture tumor growth, tissue displacement, or changes in stiffness over time. Deep learning models for this task typically require pooling patient data at one site, which conflicts with privacy rules such as GDPR and HIPAA and limits generalization across institutions, a challenge that is pronounced in neuro oncology given patient diversity. This study presents a federated physics informed neural network combining federated learning with a physics informed loss built on the equations of linear elasticity. Three simulated clinical sites each train a local network on patient specific MRI data using a physics informed loss, and only model weights are shared with a central server through the FedAvg protocol over one hundred rounds, keeping raw data at its site of origin. The federated model reached an overall accuracy of 91.4%, against 90.0% for a non federated baseline trained on pooled data, an average AUC of 0.985 across tumor classes, and a rise in pituitary tumor accuracy from 85.6 to 94.5%. Training produced smooth, divergence free displacement fields consistent with expected tissue deformation, showing that federated training can be paired with physics based constraints without a meaningful loss in performance.
Authors: Fatemeh Ziaeetabar
Abstract: Dual-hand action segmentation commonly fuses left- and right-hand representations at identical temporal indices, although coordinated hand transitions may occur with nonzero and time-varying delays. We introduce Lag-Aware Cross-Hand Alignment (LACA), a lightweight module that explicitly estimates directional temporal-offset distributions between hand-specific feature streams. LACA retrieves cross-hand information from the estimated offsets and incorporates a learned null state to suppress transfer when no compatible cross-hand transition is supported. Alignment is supervised using compatibility-aware targets derived automatically from frame-level training annotations, without requiring additional labels. Analysis of the HA-ViD and ATTACH training annotations reveals robust nonzero cross-hand matches for 44.7% and 48.9% of transition anchors, respectively, compared with 18.6% and 21.3% under temporally shifted controls. When integrated into Polyphony, LACA improves the two-hand mean F1@50 from 40.4 to 42.5 and boundary F1 from 56.5 to 59.6 on HA-ViD, and from 19.9 to 21.8 and 44.7 to 47.9, respectively, on ATTACH, relative to our reproduced Polyphony baseline. These gains require only approximately 0.0086 million additional trainable parameters. We further introduce LACA-C, a future-free variant that restricts alignment and the complete inference pipeline to current and past observations. On ATTACH, LACA-C achieves 83.6% transition-cue recall, a seed-averaged median availability delay of 233~ms, 0.72 false cues per minute, and segmentation-stage throughput of 224.9 current-position predictions per second. These results demonstrate that explicit cross-hand temporal alignment improves both action segmentation and boundary localization while supporting timely future-free perception.
Authors: Bugra Alperen Uluirmak, Rifat Kurban
Abstract: Background manipulation is a practical but under-specified image-forensics setting: the manipulated evidence can sit outside the salient foreground object, while many evaluations emphasize object-centric copy-move, splicing, or generic synthetic edits. We introduce BG-REAL, a public real-data anchored benchmark package for background manipulation detection and localization. The current release is built from Open Images V7 instance-segmentation sources and contains 7,000 processed samples over 1,200 source groups, including 6,000 public-data anchored samples and 1,000 synthetic control samples. BG-REAL covers six edit families, matched authentic controls, source-group splits, mask and leakage QA, 599 human-assisted quality-control rows, three completed external baselines (TruFor, MVSS-Net, and HiFi-Net), and five-seed model evaluation. Beyond aggregate accuracy, we use matched-authentic-control diagnostics to measure how often baselines misclassify re-encoded authentic images as manipulated at a threshold fixed on held-out validation data; false-positive rates range from 0.57 (TruFor, the lowest) to 1.00 (several weak or mask-informed baselines), indicating that re-encoding artifacts are a shared shortcut risk across baselines rather than a problem specific to any one model. The release provides the construction pipeline, evaluation protocol, paper-ready figures, and reproduction documentation. We frame BG-REAL as a background-manipulation-focused complement to general image-manipulation-localization benchmarks, not as a fully real-only or general-purpose benchmark.
Authors: Davor Dobrota, Vsevolod Skorokhodov, Chenghao Xu, Olga Fink, Malcolm Mielle
Abstract: Image-based reconstruction aims to recover three-dimensional geometry from images. Recent advances have enabled the recovery of visually detailed models, yet their representations are not well-suited for numerical simulation. Simulation frameworks typically require explicit, watertight, and smooth geometries to ensure numerical robustness and accuracy, properties that surfaces extracted from image-based reconstructions lack. We propose FORGE-SIM, a method to directly reconstruct a multi-patch B-spline boundary representation from sparse posed RGB images without manual intervention. By optimizing the spline representation itself, our approach produces compact, smooth, and watertight geometries that are natively compatible with both Computer Aided Design and simulation workflows. Additionally, we introduce a strategy to project observation-derived fields, such as a thermal state and semantic information, onto the reconstructed models in the same spline basis, enabling immediate use in simulation. We demonstrate that the obtained models are of sufficiently high quality to enable thermal simulation and modal analysis. By unifying image-based reconstruction and simulation-ready modeling within a single optimization framework, this work removes a long-standing barrier between computer vision and numerical analysis. We anticipate that it will enable new workflows for simulation-driven design, inspection, and digital twin applications.
Authors: Bowen Chen, Shreshth Saini, Balu Adsumilli, Alan C. Bovik
Abstract: Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to produce high dynamic range (HDR) content. In this work, we introduce LumaGuide, a training-free framework for distribution shaping in diffusion models. Instead of modifying model parameters, LumaGuide steers the sampling process to match target feature distributions via differentiable energy-based guidance. We instantiate this framework for HDR generation by controlling luminance distributions in perceptually uniform PQ space. Our results show that aligning luminance histograms is sufficient to induce HDR-consistent behavior, including coherent highlights and preserved shadow detail, while maintaining semantic fidelity. Beyond HDR, LumaGuide enables flexible specification of target distributions through data-driven presets, reference images, or text-driven predictors, and extends naturally to video generation with temporal consistency constraints. More broadly, our work demonstrates that controllable generation can be achieved by directly shaping output distributions at sampling time, without retraining diffusion models.
Authors: Takeshi Nishikawa
Abstract: We investigate lightweight raptor-species classification for real-time edge deployment in wind-turbine collision mitigation. Using DINOv2-L (304M parameters) as a teacher, we distilled three lightweight students (MobileNetV4, ViT-Small, and EfficientNet-B0). To reduce confusion between closely related species, we expanded the dataset to 12,519 images, including an increase in Steller's Sea Eagle images from 463 to 2,050 via video-frame extraction. Under a group split that separates samples at the video- and source-image level to mitigate source leakage at that granularity, the three-student ensemble achieved a macro recall of 0.935 +/- 0.004 over five distillation seeds (0.955 on a conventional image-level split, retaining 97.5% of the teacher's macro recall) with roughly one-eighth as many parameters. On a subset of 1,258 images disjoint from the former training images, White-tailed Eagle recall improved by up to 38.6 percentage points, while the rate at which it was misclassified as the Steller's Sea Eagle decreased from 61% to 15% of errors. TensorRT FP16 deployment of EfficientNet-B0 on an NVIDIA Jetson Orin Nano achieved 3.19 ms/image including host-device transfer (313 images/s), with 99.95% argmax agreement with FP32. In five-seed controlled comparisons, neither distillation (versus CE-only) nor the change from a DINOv2-L to a DINOv3-L teacher yielded a clear ensemble-level improvement; the primary gains stem from the dataset expansion and teacher re-fine-tuning.
Authors: Erich Schmitz, Meixu Chen, Bowen Jing, Jing Wang
Abstract: Background: Early prediction of distant metastasis (DM) risk in head and neck cancer (HNC) can enable timely interventions that may improve treatment outcomes. Many current machine learning methods rely on prior knowledge of the region of interest such as tumor segmentations, which require expert knowledge, is time-consuming and introduces user-dependent variability. Medical image-based foundation models have recently been developed for specific imaging modalities to streamline down-stream prediction tasks by extracting modality-relevant features. Purpose: In this study, we evaluate the effectiveness of using a foundation model as the feature extractor to predict DM risk in HNC patients and compare its performance with traditional approaches that require prior knowledge on the regions of interest. Methods: Preoperative CT images of 2327 patients from the RADCURE dataset were used. Three features-sets were created including radiomics, deep-learning based features, and CT Foundation derived features. The feature-sets were used individually in a multi-layer perceptron (MLP) to predict DM risk. Results: The model using CT Foundation embeddings outperformed the radiomics and deep learning-based models, achieving a Receiver Operating Characteristic Area Under the Curve (AUC) of 0.791, compared to AUC values of 0.772 and 0.753 for the radiomics and deep learning-based models, respectively. The CT Foundation based model had similar performance to a model that combined the use of radiomics and deep learning-based features that achieved an AUC of 0.794. Conclusions: Features based on foundation models offer a promising alternative to traditional radiomics while reducing the need for domain expertise and extensively annotated datasets. Their minimal preprocessing requirements also make them a more accessible and scalable option.
Authors: Armin Maleki, Hayder Radha
Abstract: Collaborative Perception (CP) improves autonomous systems' awareness of their surroundings by sharing sensor data, intermediate features, and detection results. In real-world deployments, however, collaborating vehicles often use heterogeneous sensors, perception models, datasets, and training domains, creating feature-space shifts that degrade downstream fusion and detection. Existing approaches typically retrain fusion and detection components or introduce modality-specific feature interpreters. These methods scale poorly to newly joining agents and often require access to proprietary metadata, raising privacy concerns. We propose HeteroPROMPT, a real-time and privacy-preserving framework for heterogeneous collaborative perception. HeteroPROMPT rapidly aligns each heterogeneous agent's features with an ego-centric unified feature space through modular prompts and lightweight learning-based tuning, while keeping agent encoders and the collaborative fusion and detection stacks frozen. Its visual prompt-based training and inference modulate Bird's Eye View (BEV) features across channels and spatial locations with low computational overhead. For metadata-free deployment, an autoencoder learns a compact unified representation and extracts modality cues from shared features, enabling real-time modality classification and routing to the appropriate HeteroPROMPT modules without exposing proprietary agent information. Experiments on the OPV2V-H and V2XSet datasets show that HeteroPROMPT improves Average Precision over state-of-the-art heterogeneous CP methods while using orders of magnitude fewer trainable parameters. This offers a scalable and practical CP solution. The proposed modality classifier also predicts the joining agent's modality from compact features with greater than 99.99 percent accuracy during deployment. Code will be available at https://github.com/arminmaleki007/HeteroPROMPT.
Authors: Antoine Legouhy, Ross Callaghan, Yuchuan Qiao, Whitney Stee, Philippe Peigneux, Hojjat Azadbakht, Hui Zhang
Abstract: Diffusion MRI (dMRI) relies on diffusion-weighted echo-planar imaging, which is highly susceptible to eddy-current-induced geometric distortions. These distortions vary across diffusion volumes according to gradient strength and direction, causing between-volume misalignment that can bias downstream microstructural analyses. Current state-of-the-art correction methods, such as FSL Eddy, achieve high-quality correction through iterative prediction-correction schemes but are computationally expensive. We propose Eddeep, a deep-learning framework for fast eddy-current distortion correction in dMRI. Eddeep decomposes the problem into two stages. First, a supervised image translation network standardises the appearance of diffusion-weighted and b=0 images, removing contrast differences that hinder reliable registration. Second, an unsupervised registration network estimates both eddy-current distortion and between-volume head motion parameters under a physics-constrained quadratic distortion model, enabling correction in a single forward pass. The method was trained on UK Biobank data and evaluated on both in-domain (UK Biobank) and out-of-domain (Memodyn) datasets. Across a range of complementary metrics, including between-volume jitter, diffusion kurtosis imaging residuals, signal irregularity, and mutual information, Eddeep achieved correction quality comparable to that of FSL Eddy while substantially reducing inference time. These results demonstrate that deep learning can provide accurate and efficient eddy-current distortion correction without relying on iterative optimisation, supporting the development of faster diffusion MRI processing pipelines for large-scale studies and clinical deployment. The code is available at: https://github.com/CIG-UCL/eddeep.
Authors: Nazanin Amini, Kevin Desai
Abstract: Editing character motion often requires transferring a gesture or gait from one or more reference motions while preserving the source action, timing, root trajectory, and unselected body regions. Existing motion datasets, however, rarely provide paired targets for arbitrary part-local content--reference combinations, and self-reconstruction training may allow a diffusion model to reproduce the content motion while underusing the routed reference. We present MoSAIC, a latent diffusion framework for part-local reference-conditioned motion style transfer. MoSAIC factorizes content and reference features by anatomical region, preserves the root trajectory through a separate conditioning pathway, and routes user-selected references to individual body parts. Its central contribution is aligned intervention supervision, which constructs synchronized references and counterfactual targets through controlled local transformations, making both the requested regional response and the motion to be preserved directly observable during training. In a frozen evaluation comprising 128 motions and 896 routed conditions, part-masked routing reduces preserved-region error from 70.64 to 66.45~mm and matched-noise off-target leakage from 18.08 to 9.88~mm relative to whole-body routing, while retaining a positive selected-region response. A matched-budget continuation study further shows that retaining aligned intervention supervision produces an 8.8\% relative increase in selected-target response and a 2.0-percentage-point increase in requested-route influence concentration. These results demonstrate that MoSAIC improves the response--preservation trade-off required for selective and controllable part-local motion editing.
Authors: Jiaang Li, Chengzu Li, Zhaochong An, Yifei Yuan, Xi Liu, Serge Belongie, V\'esteinn Sn{\ae}bjarnarson
Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge. We explore these failures separately using two diagnostic paradigms: (1) probing whether visual information is available, via image reconstruction, and (2) measuring multimodal context sensitivity, the extent to which the model follows visual context versus the language prior. To support the second, we introduce the WhatIfVis, a benchmark spanning five coarse-grained dimensions (spatial-temporal, color, count, size, and weight) whose questions admit answers from either the image or the prior. Our analysis yields three findings: (i) Coarse-grained visual evidence is preserved, as these attributes can be reconstructed from the final-layer image tokens of frozen MLLMs. Failures on questions about these attributes therefore point to post-perceptual utilization, rather than to degraded visual encoding during perception. (ii) Even when explicitly instructed to use or ignore visual evidence, vanilla models (without supervised fine-tuning on the WhatIfVis) show unstable visual context sensitivity. Supervised fine-tuning (SFT) improves this controllability and generalizes across domains, and activation patching further localizes the vision-versus-prior trade-off at architecture-specific depths across all six models. (iii) The vision-versus-prior trade-off is controllable along a learned vector. Applying this steering vector, even without any intent instruction, improves controllability over the vanilla model. Together, these results relocate the bottleneck, indicating that for the coarse attributes we study, MLLMs encode the visual evidence but cannot reliably control their reliance on it.
Authors: Yitong Shen, Cheng Guo, Peiliang Wang, Jingzhe Zhang, Yi Sheng, Haopeng Zhang, Hongfei Xue, Yili Ren
Abstract: Wi-Fi-based human activity recognition has advanced substantially, but most existing methods assume a closed set of activities and require labeled Wi-Fi samples for every target class, limiting their ability to recognize unseen activities. We present Zero-Fi, a contrastive signal-language alignment framework for zero-shot Wi-Fi-based human activity recognition. Zero-Fi learns unified representations from complementary Wi-Fi signal features and aligns them with the semantic representations of natural-language activity descriptions in a shared embedding space. This cross-modal alignment enables Zero-Fi to recognize new activity classes without requiring labeled Wi-Fi samples or model adaptation for those classes. Experiments on large-scale public benchmark datasets demonstrate effective zero-shot recognition of held-out activity classes, highlighting the potential of signal-language alignment to extend Wi-Fi sensing beyond predefined activity classes.
Authors: Pengyu Jie, Wanquan Liu, Rui He, Pengcheng Li, Weiping Wen, Deyu Meng, Junwei Han, Chenqiang Gao
Abstract: White-light imaging (WLI) and narrow-band imaging (NBI) provide complementary views of endoscopic lesions, but their paired observations are often spatially misaligned due to viewpoint changes, tissue deformation, and sequential handheld acquisition. This makes direct WLI/NBI fusion prone to mixing non-corresponding regions and may even degrade segmentation around lesion boundaries. To address this problem, we propose a reliability-aware complex-domain fusion framework for paired-but-unregistered WLI/NBI lesion segmentation. The framework first establishes topology-regularized feature correspondence and further estimates where the cross-modal correspondence is reliable. Guided by this reliability, the model selectively fuses WLI and NBI features in a learnable complex representation. In this representation, WLI-derived cues mainly provide appearance-related magnitude responses, while NBI-derived cues provide structure-sensitive phase responses. Unlike conventional real-valued or symmetric multimodal fusion, the proposed method explicitly models the different roles of WLI and NBI and suppresses unreliable cross-modal interaction in locally mismatched regions. Experiments on paired WLI/NBI endoscopic datasets show that the proposed reliability-aware registration grounding and complex-domain fusion consistently improve lesion segmentation performance. Role-reversal and module ablation studies further validate the necessity of both the modality-role design and reliability-guided cross-modal interaction.
Authors: Yu Wang, Sharon Li
Abstract: Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture, yet it remains unclear whether these capabilities share a unified and transferable semantic space. This question is fundamentally challenging, as the two branches operate over heterogeneous representations (text tokens vs.\ visual latents) and distinct training objectives, making direct comparison difficult. To address this, we introduce \emph{cross-branch semantic steering}, an intervention-based framework that extracts semantic directions from one branch and applies them to the other. We show that steering vectors learned from the understanding branch can transfer to generation, enabling controllable image synthesis and improved semantic faithfulness. In contrast, the reverse direction consistently shows limited effectiveness. Our analysis suggests that this asymmetry may be related to a practical representational mismatch: understanding-derived vectors capture transferable, object-centric semantics, while generation-derived vectors primarily encode low-level appearance features. Our results reveal that architectural unification does not guarantee semantic alignment, and establish cross-branch steering as a practical tool for probing multimodal representations.
Authors: Vran Lee, Xin Liu, Yijie Wei, Yeqiang Liu, Hwa Liang Leo, Zhenbo Li
Abstract: Tracking dense, homogeneous targets like schooling fish remains a major challenge for multiple object tracking due to extreme inter-individual homogeneity, severe physical clustering, and rapid non-rigid deformations. While heavy-backbone separated detection and embedding trackers like SU-T push accuracy boundaries using complex Re-Identification networks, their computational overhead prohibits edge deployment. Furthermore, these modules often fail when appearance features degrade under severe occlusions. To overcome this, we propose Tracking Identities with Dual-branch Elasticity (TIDE). Bypassing expensive appearance cues, TIDE utilizes the Adaptive Geometric Correspondence IoU, an association mechanism leveraging spatial and structural consistency to robustly handle complex morphological variations. Crucially, TIDE introduces system-level deployment elasticity, decoupling the algorithmic pipeline from strict hardware constraints. Evaluations on the MFT-Edge benchmark demonstrate that our Lightweight L-branch achieves a competitive HOTA of 28.43 using merely 20.47G FLOPs. This represents a 38.7-fold computational reduction compared to upper bounds like SU-T, directly facilitating real-time edge deployment. Concurrently, our Scalable S-branch establishes a 29.98 HOTA, successfully bridging the gap between high-precision cloud analysis and efficient edge tracking. The dataset and codes are released at https://vranlee.github.io/TIDE/.
Authors: Hongyang Wang, Yichen Shi, Hongrui Li, Yiru Huo, Jun Feng, Zitong Yu
Abstract: Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-region localization. FAS-R1 first uses FAS-R1-23K, a high-quality long-CoT dataset, for cold-start supervised fine-tuning, and then performs FAS-specific GRPO post-training. Degradation-Simulated Augmentation (DSA) encourages stable spoof-cue reasoning across visual-quality shifts, while Difficulty-Aware GRPO (DA-GRPO) mitigates easy-sample dominance that may leave difficult task--attack groups under-optimized, especially for subtle or ambiguous attacks such as makeup and mask attacks. The main 3B FAS-R1 model achieves 98.75\% authenticity accuracy, 93.33\% attack-type accuracy, and 96.30/94.73\% AP@40/AP@50 in-domain. It also outperforms the compared systems in cross-domain authenticity generalization and answer-and-rationale quality. Experiments with different base models further show favorable scaling behavior. The code will be released soon.
Authors: Sophie Zeng, Sean Kalaycioglu, Collin Hong, Haipeng Xie
Abstract: Acne vulgaris affects most adolescents and many adults. Accurate severity grading guides treatment, monitoring, and clinical trial endpoints, but manual assessment using the Investigator's Global Assessment or Hayashi criteria is limited by inter-rater variability and inconsistent imaging conditions. We developed a four-class acne severity classifier based on the Hayashi criteria using transfer learning with an ImageNet-pretrained EfficientNet-B0 model. The model was fine-tuned on the public ACNE04 dataset of 2,983 labeled images using AdamW optimization, geometric and photometric augmentation, and checkpoint selection based on validation macro-F1. On a held-out stratified 15 percent test set, the classifier achieved 93.5 percent accuracy and 94.4 percent macro-F1, with per-class F1 scores from 0.92 to 0.97. Eighty-three percent of errors occurred between adjacent grades. Quadratic-weighted Cohen's kappa was 0.956, with a 95 percent confidence interval of 0.935 to 0.973. Bootstrap confidence intervals indicated stable performance. Grad-CAM visualizations from the final convolutional block focused on clinically relevant facial regions, including the forehead, cheeks, and chin. The complete pipeline is provided as functionally equivalent open-source implementations in Python using PyTorch and timm, and in MATLAB R2026a. The software includes a clinician-facing inference interface and a fallback backbone option that supports operation without specialized pretrained-weight packages. These results show that lightweight transfer learning can provide accurate, balanced, and interpretable acne severity grading while offering a reproducible cross-platform reference for future prospective and device-stratified clinical validation.
Authors: Kai Wang, Meixu Chen, Elie Nasr, Ryan Lanning, Moyed Miften
Abstract: We present HERMES (Hybrid Ensemble for Radiotherapy-target segmentation, Malignancy staging, and Event-free Survival), a single containerized algorithm for the three HECKTOR 2026 subtasks: segmentation of the primary tumor (GTVp) and pathological lymph nodes (GTVn), radiological T/N staging, and recurrence-free survival (RFS), computed from a paired FDG-PET/CT scan and an electronic health record. A 10-fold ensemble of STU-Net Small networks produces the segmentation; the predicted mask then drives two downstream tasks. Rather than pass a generic radiomics vector to the staging models, we derive from the predicted masks a compact set of geometry features aligned with the size and number axes of AJCC/UICC 7th-edition radiological N/T staging. On internal cross-validation these features raise N-stage balanced accuracy from 0.691 to 0.720 (+0.030), our largest single design gain, at lower feature dimensionality. For prognosis we combine complementary deep and clinical risk experts in an equal-weight ensemble, and train one deep expert with a concordance-tracking survival loss of our own, whose value approximates the concordance index during training. Every component was selected on honest out-of-fold predictions under a regularization-oriented protocol, with no tuning on the public validation set, and deployed as two decorrelated submissions. On the HECKTOR 2026 validation leaderboard, HERMES achieved a weighted score of 0.6454 (Mean Dice 0.641, T balanced accuracy 0.580, N balanced accuracy 0.642, RFS C-index 0.679) and qualified for the testing phase. Team: AMC_HNC.
Authors: Xiaozhen Qiao, Da Zhang, Yubin Guo, Junyu Gao, Zhiyuan Zhao, Xuelong Li
Abstract: UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It differs from conventional UAV tracking and ground-based Anti-UAV tracking because both the camera platform and the target move simultaneously. This dual-dynamic setting induces rapid viewpoint changes, motion blur, scale variation, and visually similar distractors, making reliable appearance matching difficult. Under such rapidly changing conditions, fixed visual representations are often insufficient because target appearance becomes unreliable and feature distributions may deviate from the training domain. The target language description remains stable across frames and can therefore serve as a semantic anchor for temporal state propagation, while online feature-distribution alignment can reduce video-specific test-time shifts. In this paper, we propose \emph{SATATrack}, a Semantic-Aware Temporal Adaptation framework for UAV Anti-UAV tracking. SATATrack introduces Semantic-Aware Context Propagation (SACP), which uses the target description to guide temporal context propagation across backbone stages and preserve target identity under rapid appearance changes. An auxiliary contrastive regularizer is used during training to discourage responses to semantically similar background regions. During inference, Temporal-Aware Distribution Alignment (TADA) aligns feature distributions online without updating model parameters, combining recent-frame estimates with training-time statistics for stability. SATATrack achieves state-of-the-art performance on the UAV-Anti-UAV benchmark while remaining competitive in Anti-UAV and UAV object tracking tasks. The code will be available at https://github.com/XiaozhenQiao/SATATrack.
Authors: Yuyun Chen, Tianao Li, TianQuan Feng, Cen Chen, Huiping Zhuang, Hao Peng, Ziqian Zeng
Abstract: Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic uncertainty. While Large Vision-Language Models (LVLMs) demonstrate impressive semantic alignment on standard benchmarks, they often struggle to distinguish between superficial correlation and genuine forensic logic when grounded in the dynamic, partially observable nature of first-person experiences. Existing evaluations, dominated by third-person surveillance footage and binary classification metrics, fail to expose this cognitive gap. To address this, we introduce EgoSafe-Bench, a benchmark specifically designed to probe forensic reasoning in egocentric safety scenarios. It comprises 12,000 unique evaluation samples, generated by pairing each of the 3,000 video clips with a QA chain governed by our proposed Hierarchical Reasoning Evaluation (HRE) protocol. Unlike standard benchmarks, HRE mandates a rigorous reasoning trajectory from initial feature anchoring to blind-spot deduction and intent inference, thereby enforcing logical consistency and penalizing shortcut-based predictions. Extensive evaluations of state-of-the-art LVLMs (e.g., Qwen3-VL, Gemini, VideoLLaMA 3) reveal a significant perception-reasoning decoupling: models often achieve high descriptive scores but exhibit notable fragility in causal reasoning and logical closure. Our work provides both a challenging dataset and a systematic evaluation framework to foster the development of logically robust video understanding systems.
Authors: Yuyang Huang, Yabo Chen, Wenrui Dai, Ziyang Zheng, Haibin Huang, Chi Zhang, Junni Zou, Hongkai Xiong, Xuelong Li
Abstract: Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained controllability over characters and scenes, and long-form generation across extended temporal horizons. Existing methods rely on customization and retraining to separately address specific requirements, and cannot simultaneously fulfill all the requirements with a unified framework. In this paper, we shed light on the training-free paradigm with the key insight that the difficulty of multi-shot generation arises from a structural bias toward temporal continuity in pretrained video diffusion models, and consequently, propose a unified framework named CineWeaver to achieve reference-controllable multi-shot long-video generation without retraining. We manipulate positional encoding and attention patterns to break temporal continuity during inference to enable clear shot transitions using pretrained video diffusion models. Furthermore, we extend the proposed framework with a shot-routed reference conditioning mechanism for per-shot fine-grained controllability, and develop an anchor memory mechanism to allow long-form generation with consistent global appearance cues. To our best knowledge, CineWeaver is the first unified framework to simultaneously enable \textbf{long-form}, \textbf{reference-controllable}, and \textbf{multi-shot} video generation in a training-free fashion. Experimental results demonstrate that CineWeaver produces high-quality cinematic videos of long durations with consistent identities, stable global appearance, and clear shot transitions. The project page is available at: https://cineweaver.github.io.
Authors: Jinkun Zhao, Kui Zhang, Wenjun Wu
Abstract: High-pressure prompts can push vision-language models (VLMs) into unsupported commitments, such as reading illegible text, reporting indeterminate times, or affirming absent objects. This paper asks whether the pressure-induced distribution itself can serve as a contrastive-decoding negative branch. Tone-pressure contrastive decoding (TPCD) subtracts logits produced under a high-pressure instruction from logits produced under a safe neutral instruction. On the 800-example tone-matters benchmark, LLaVA-1.5-7B under pressure reaches 66.75% attack success rate (ASR); safe neutralization reduces ASR to 9.88%; full TPCD reaches 0.50% but collapses positives to 15.56%. A benchmark-specific task-prior/disagreement gate preserves measured positive accuracy (54.44%) while lowering ASR to 1.63% on LLaVA. Treating this LLaVA analysis as the design split, full $n=800$ negative and $n=780$ matched-positive held-out runs on GLM-4.6V and Llama-3.2-Vision show that simple gates can improve over safe neutralization, with sensitivity analyses bounding the weak time-positive subtask. A category-prior-free answer-disagreement router reduces held-out aggregate ASR to 6.93%, improving over both safe neutralization (10.98%) and branch disagreement (9.67%) while matching branch disagreement's 79.94% positive accuracy, although it remains post-hoc and surface-form based. We conclude that pressure is a useful probe of commitment bias and a viable mitigation signal, but the current gates are not yet independently validated grounding-aware detectors.
Authors: Shaoxuan Wu, Xiao Zhang, Xiaodi Zhao, Yunzhi Tian, Yilin Tang, Jun Feng
Abstract: Medical image segmentation heavily depends on labor-intensive and time-consuming pixel-level annotations. Eye tracking offers a cost-effective solution that can be naturally integrated into clinical workflows. Recorded by eye trackers, gaze conveys the spatial regions of clinicians' attention through fixations and the temporal context of clinicians' progressive visual perception from trajectories. Nevertheless, effective modeling of temporal trajectories remains challenging, and noise in gaze caused by exploratory fixations greatly limits segmentation performance. To overcome these limitations, we propose the Trajectory-guided Uncertainty-aware Network (TrailNet), which exploits gaze-supervised medical image segmentation from spatial semantics modeling to temporal context by jointly leveraging fixations and trajectories. Specifically, the proposed trajectory-guided spatio-temporal encoder models temporal context and establishes complementary interactions with image spatial semantics to strengthen target perception. Furthermore, the multi-scale uncertainty decoder leverages category mutual-exclusivity constraints to produce deterministic predictions and mitigate supervision uncertainty induced by noise. To enable gaze-free inference, we further introduce a cycle distillation strategy that transfers feature-level knowledge via teacher-student networks. Experimental results on two public datasets demonstrate that TrailNet outperforms state-of-the-art methods, achieving Dice scores of 81.25% and 81.85%, respectively.
Authors: Yitao Zhu, Mengjun Liu, Yingji Fu, Haowen Pang, Anqi Qiu
Abstract: Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.
Authors: Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Hamed Damirchi, Stephen Gould, Damith Ranasinghe
Abstract: Vision models do not form a representation at once; each block revises it. We ask whether the resulting computation path contains evidence that the final representation discards, and whether that evidence improves OOD detection and image classification on clean and shifted data. Unlike approaches that treat intermediate layers as separate snapshots, we retain sample identity across depth and study the transformations connecting successive states. We separate class-coherent transport from input-specific innovation, and coordinate movement from relational reorganization. Across supervised, self-supervised, vision--language, hierarchical, and convolutional encoders, these paths show strong sample-specific continuity and architecture-specific depth profiles that recur across datasets. They are also practically useful. An ID-only transition-surprise score complements strong final-state detectors, reducing FPR95 in 131/152 non-saturated comparisons on a balanced OpenOOD grid; gains are largest for visually disruptive and semantically far shifts, and remain positive on near-OOD for most detectors. Frozen update probes improve 71/72 clean model--dataset cases, while shifted-data gains vary with architecture and corruption type. Computation paths therefore provide a broadly useful reliability signal whose value is determined jointly by model organization and the shift encountered.
Authors: Meng Yang, Shuyin Xia, Dawei Dai, YiWang
Abstract: Three-dimensional Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis through explicit Gaussian primitives and differentiable rasterization. 3DGS and Granular Ball Computing (GBC), proposed in 2019, share a natural compatibility in adaptive representation. The efficiency of 3DGS partly stems from a coarse-to-fine and on-demand refinement process that draws on the generation principle of GBC. This connection motivates us to further introduce adaptive granular ball organization into anchor-based 3DGS. Existing anchor-based methods typically construct anchors from sparse SfM point clouds through fixed voxelization, which cannot adequately adapt to spatially non-uniform point distributions and leads to a trade-off among anchor count, model compactness, and rendering quality. To address this issue, we propose 3DGBGS (3D Granular Ball Gaussian Splatting), a compact anchor-based framework for novel-view synthesis. 3DGBGS adaptively partitions SfM point clouds into 3D granular balls, using larger balls to compactly represent smooth and redundant regions and smaller balls to preserve complex geometry and local details. Based on this representation, Granular Ball Anchor Initialization (GBAI) uses granular ball centers to initialize compact anchor positions, while the Granular Ball Scale Prior (GBSP) exploits granular ball radii to provide local scale priors for Gaussian generation. Experiments on four benchmarks show that 3DGBGS reduces initial and final anchors by 37.1% and 10.0%, respectively, and model storage by 9.8% on average, while maintaining comparable rendering quality.
Authors: Nand Lal Yadav, Rajesh Kumar, Satyendra Singh, Sudhakar Singh
Abstract: With the increase in the number of cases related to respiratory diseases, there is an urgent need to detect them early and diagnose them accurately. Convolutional neural networks have given promising results when used for diagnosing diseases using imaging tests. In this study, we investigate the potential of applying deep learning algorithms such as VGG16, VGG19, and ResNet50 for classification of lung ailments based on X-ray images. A detailed analysis of the aforementioned models' performances was conducted to assess how well they can classify various types of lung ailments, including pneumonia, tuberculosis, lung cancer, and normal lungs. In order to do that, these deep learning models were trained on a vast amount of X-ray images. The results of our study show that while all three models provide good results, ResNet-50 performs best in comparison with other models due to its efficiency and high level of accuracy. We believe that these deep learning models can be successfully implemented in the practice of diagnosing pulmonary diseases in the future. It helps with early disease detection and improves patient outcomes.
Authors: Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Stephen Gould, Damith Ranasinghe
Abstract: Selecting a zero-shot out-of-distribution (OOD) detector for a new deployment is typically based on benchmark rankings, implicitly assuming that the highest-ranked detector will transfer across domains. We show that this assumption does not hold. Through a controlled portability audit across seventeen in-distribution datasets, three vision-language models, and seven representative zero-shot OOD detectors, we find that detector rankings reverse across deployments, every detector exceeds $80\%$ FPR95 on at least one domain, and the preferred detector depends on both the in-distribution data and the underlying VLM. We trace these reversals to complementary evidence channels in vision-language logits. Corpus-free detectors rely on different combinations of absolute match level and relative or spatial sharpness, while WordNet-based methods additionally depend on external semantic coverage. A simple proposition shows that level and sharpness cannot generally be recovered from one another, explaining why no single detector transfers reliably across deployments. Motivated by this diagnosis, we introduce the Complementary Evidence Guard (CEG), a detector-agnostic wrapper that preserves complementary evidence through a non-compensatory fusion of the base detector, level, and sharpness using only empirical in-distribution percentiles. Controls replacing these channels with entropy, logit variance, or random noise do not reproduce the gains. Without OOD samples, auxiliary corpora, or learned fusion, CEG reduces detector sensitivity and improves GL-MCM from $38.1$ to $28.8$ and MCM from $42.6$ to $30.5$ family-balanced FPR95.
Authors: Yusen Wan, Zeyuan Chen, Qianshi Zou, Xu Chen
Abstract: Point-cloud (PC) registration is fundamental to three-dimensional (3D) perception in robotic systems. However, classic registration algorithms falter when aligning a source PC containing limited, incomplete, or ambiguous geometric cues against a reference. This challenge of registering a small, partial PC to a significantly larger global reference is pervasive in real-world deployment yet remains insufficiently addressed by existing learning-based approaches, which typically assume comparable scales and significant overlap. To bridge this gap, we propose the Region-based Small-to-Large Point-cloud Registra- tion framework (R-SLPR), a novel three-stage architecture that fundamentally reformulates the scale-mismatched registration problem into a sequence of region proposal, regional matching, and iterative refinement. Unlike conventional methods that fail to localize specific regions, R-SLPR explicitly identifies candidate regions prior to estimating rigid transformations, ensuring robust alignment even under severe scale mismatch. The framework introduces a Fibonacci Grid Segmentation method coupled with a contrastive learning objective to effectively generate and match local geometric patches. Building on this, a novel Cascade Anchor Selection and Refinement algorithm iteratively aligns the source with the target region to maximize precision. Extensive evaluation on ModelNet40 demonstrates that R-SLPR establishes a new state-of-the-art accuracy standard, outperforming prior approaches and significantly reducing position and rotation Mean Absolute Error (MAE) to 0.009 and 1.104, respectively.
Authors: Jingxuan Su, Shenglin Wang, Tiesong Zhao, Ge Li, Wei Gao
Abstract: 3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing demand for reliable quality assessment. Unlike conventional image quality assessment (IQA), the quality of a 3DGS scene depends not only on the perceptual fidelity of rendered views, but also on scene-level factors such as spatial structure and cross-view consistency. Existing IQA methods are limited by their reliance on 2D perceptual cues, whereas general multimodal large language models (MLLMs) are not designed for stable quality regression and may produce unreliable judgments. To address these limitations, a multimodal quality assessment framework is developed for 3DGS scene understanding. First, a 3D-aware quality representation learning framework is introduced by augmenting a VGGT-based encoder with a dedicated quality head. Multi-view images are encoded into view-specific features and aggregated to capture cross-view consistency, while geometric cues are incorporated through joint modeling of depth and point-cloud-related structural information, enabling the learning of structure-aware quality representations beyond appearance-driven features. Second, a grounded multimodal reasoning mechanism is constructed by jointly feeding original images, depth maps, point cloud renderings, and camera parameters into a Qwen-based MLLM.
Authors: Mingkuan Feng, Zhengqi Wen, Jianhua Tao
Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture. However, fine-tuning all parameters of these models for visual instruction tuning is computationally expensive and often unnecessary, as the representation requirements for visual and textual tokens diverge significantly in the deeper layers of the network. In this paper, we propose Decoupled Visual Processing (DVP), an efficient training framework that replaces the upper decoder layers of a pretrained LLM with a lightweight, independently trainable single transformer block dedicated exclusively to visual token processing. Specifically, after shared processing through the first half of the decoder layers, visual and textual tokens are split: visual tokens are routed through a newly initialized single transformer block while textual tokens continue through the original frozen decoder layers. The two streams are then concatenated before the language modeling head. During training, only the single transformer block is updated, dramatically reducing the number of trainable parameters. Experiments on the LLaVA-1.5 framework demonstrate that DVP achieves competitive performance on MME, POPE, and ChartQA benchmarks while training only a fraction of the total parameters, suggesting that visual representations in MLLMs can be effectively learned through a decoupled, parameter-efficient pathway.
Authors: Ionu\c{t} Grigore, C\u{a}lin-Adrian Popa
Abstract: Self-supervised monocular depth estimation typically relies on photometric reconstruction losses that couple depth, pose, and appearance assumptions. In this paper, we propose JEPADepth, a self-supervised monocular depth framework that incorporates a complementary training objective inspired by Image Joint-Embedding Predictive Architectures (I-JEPA) for self-supervised depth learning. Our method augments a standard photometric pipeline with a masked prediction loss computed in the representation space of a pretrained DINOv3 Vision Transformer encoder. A predictor infers target-region embeddings from visible context-region embeddings under structured masking, and is discarded along with the target encoder at inference time, adding no deployment cost. On KITTI, adding the JEPA objective consistently improves performance over the same DINOv3-based photometric baseline, without changing the inference-time architecture. Compared to prior monocular self-supervised methods, JEPADepth is competitive with state-of-the-art transformer-based approaches and outperforms strong CNN-based baselines on the standard benchmark. In zero-shot transfer (trained on KITTI and evaluated without fine-tuning), JEPADepth achieves the best or near-best performance among the compared methods on both Make3D and Cityscapes across multiple metrics.
Authors: Yinghao Hou, Jiahe Fan, Yuanhao Pu, Zongyuan Chen, Hong Xie
Abstract: Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvements in aggregate performance do not reveal what a smaller model actually inherits. Existing studies are largely designed and evaluated on limited task sets or aggregate metrics; as evaluation expands to broader task collections, whether different capabilities can transfer across scales remains poorly understood. To investigate this question, we introduce Cross-Scale Directional Parameter Injection (CDPI), a simple linear probe to analyze cross-scale knowledge transfer during heterogeneous fusion. A local theoretical analysis indicates that knowledge transfer selectivity is determined at first order by capability-dependent responses to a shared injection direction, while second-order curvature effects constrain the effective transfer regime. Across four Qwen3-VL model pairs and twelve multimodal benchmarks, our experiments reveal a consistent pattern of selectivity: gains concentrate on reasoning, particularly high-level reasoning, whereas perception performance remains close to that of the original target model. Component-wise ablations further show that high-level reasoning gains arise primarily from the language model, while ratio analysis finds that positive selective transfer occurs mainly in the small-ratio regime. These findings recast cross-scale heterogeneous MLLM fusion as selective language-side reasoning transfer within a narrow, low-interference regime, rather than broad capability inheritance.
Authors: Mu\~noz-Haro Javier, Teruel Andres, Tolosana Ruben, DeAlcala Daniel, Vera-Rodriguez Ruben, Morales Aythami, Fierrez Julian
Abstract: Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns. However, advanced Generative AI models can now inject localized, high-fidelity manipulations, creating deceptive attacks that bypass standard verification. Training robust image forensic models to detect these anomalies is hindered by privacy regulations, forcing reliance on synthetic templates lacking the intricate visual patterns of real IDs. To bridge this domain gap, we introduce FakeIDet3-DB, the first comprehensive database of digital manipulations on real, government-issued IDs. FakeIDet3-DB encompasses classical (e.g., copy-move) and Generative AI-driven manipulations (e.g., face-swapping, inpainting) enhanced with advanced image refinement procedures to suppress visual artifacts. In addition, to comply with strict data protection regulations (e.g., GDPR), we adopt a recently-proposed framework based on patches. In order to maximize forensic utility, we formulate privacy-aware patch extraction from a real ID as a geometrically constrained image processing problem. We propose PACE, a Pseudo-Anonymized Contextual patch Extraction algorithm, which leverages Integral Image mapping and distance-driven Non-Maximum Suppression (NMS). PACE efficiently contours anonymization masks that prevent Personally Identifiable Information (PII) leakage while maximizing semantic density in peri-censorship regions, yielding almost 5.2M patches extracted from more than 6.4K images from real/fake IDs. Furthermore, an extensive evaluation of the proposed FakeIDet3-DB is performed using state-of-the-art models, showcasing they all struggle to detect and locate attacks coming from generative and classic techniques (32.45\% EER in detection and 83.48\% AUC-ROC in localization).
Authors: Wenzhe He, Meng Wang, JiaWei Qian, Jinfeng Xu, Ying Liu, Ruihui Li
Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion. During training, noisy point clouds are constructed by perturbing complete ground-truth scenes, whereas during inference, they are initialized by adding noise to duplicated partial scans. This train-inference mismatch inherits the sparsity and visibility bias of partial scans, leading to sparse distant regions and incomplete geometry in occluded areas. Moreover, the reliance on partial scans restricts generation when LiDAR observations are unavailable or replaced by layout cues. We present FPSGen, a flexible framework that constructs point sources independently of partial scans. FPSGen first predicts a bird's-eye-view (BEV) prior with density, height, and mask channels from the active cues. The density map is then sampled to form a BEV-supported point source, enabling both unconditional and conditioned initialization. A teacher-student approximate optimal transport scheme then uses teacher-predicted endpoints to learn a velocity field that induces straighter transport paths. By integrating BEV point source construction with path-straightening transport, FPSGen provides a unified framework for unconditional and flexible cue-conditioned scene generation. Extensive experiments show that FPSGen achieves state-of-the-art JSD and voxel IoU performance on SemanticKITTI completion while maintaining strong performance with a single point transport step. On KITTI-360 unconditional generation, it also achieves the best Coverage (COV) among the compared methods.
Authors: Yongxin Su, Linjie Hou, Feng Wang, Jialin Tang, Zhijun Li, Qian Wang, Maoqing Yao
Abstract: We address the problem of reconstructing a high-fidelity, freely navigable 3D scene from a single $360^\circ$ panorama, without per-scene optimization or multi-view capture. Existing methods either lack metric trajectory control, which hinders reliable downstream 3D reconstruction, or struggle with large disocclusions under long-range camera motion while requiring high-end multi-GPU servers.We present Genie Sim PanoWorld, a two-stage feed-forward pipeline that bridges generation and reconstruction via an explicit, trajectory-controllable panoramic video. A NavMesh-planned $\mathrm{SE}(3)$ roaming trajectory is injected into a latent video diffusion model through dense geometry-warped conditioning; long--short trajectory mixed training and a self-consistency objective based on shortcut models together yield high-fidelity video in four CFG-free denoising steps. A feed-forward panoramic reconstructor then lifts the generated video into a high-fidelity 3D Gaussian scene that supports real-time, free-viewpoint roaming and can be directly used as a simulation-ready asset for embodied AI applications. Experiments show that Genie Sim PanoWorld outperforms geometry-conditioned baselines in both panoramic video generation and downstream 3D reconstruction, while generalizing zero-shot to unseen indoor scenes.
Authors: Xinyi Wang, Yuyang Huang, Yalin Su, Pengcheng Luan, Tao Zhang, Feiming Wei, Wenxian Yu
Abstract: While text-to-image diffusion models achieve impressive visual quality, they frequently struggle to maintain precise alignment with complex compositional prompts. An effective strategy is to improve the inference process of diffusion models, thereby better leveraging their pretrained priors to address misalignment. Existing training-free methods can be divided into two categories. The first category focuses on improving the randomly sampled initial noise, either performing costly search over noise pools or manipulating sampled noise without ensuring reliable semantic injection. The second category focuses on improving the denoising trajectory, lacking explicit mechanisms to timely diagnose and correct semantic errors. we propose \textbf{AnchorSteer}, a training-free framework that exerts fine-grained control over \textbf{both initialization} and \textbf{the denoising trajectory}. AnchorSteer consists of two synergistic components: \textbf{Semantic Anchoring} replaces uninformative Gaussian noise with text-aligned initializations via CLIP-based prior extraction and a novel Latent-Prior Score Distillation Sampling (LP-SDS) objective. Specifically, LP-SDS distills CLIP visual priors into the knowledge distribution of diffusion models, mitigating the domain gap between CLIP-based priors and diffusion-based priors. \textbf{Reflective Steering} transforms passive denoising with an active Think--Erase--Retouch loop that enables mid-generation self-correction. It leverages VLM-based diagnosis to detect semantic deviations and performs targeted latent refinement to suppress erroneous content and recover missing attributes. Extensive experiments on GenEval and T2I-CompBench++ demonstrate that AnchorSteer consistently outperforms existing baselines in text--image alignment while preserving high visual quality.
Authors: Shen You, Wei Jiang, Jiarui Liu, Yijian Ye, Qiuzhen Lin, Xiangtao Li, Ka-Chun Wong
Abstract: With the promising performance of deep neural networks on image-based tasks, different real-world applications such as autonomous driving and motion detection have become increasingly mature and relevant to human lives. In particular, Optical Flow Estimation Networks (OFENs), as upstream models, play a critical role in different domains. Its outputs are heavily assumed and adopted for different downstream tasks, and it is essential to test its robustness to prevent safety accidents. We present an approach for real-time attacks on OFENs in the physical world, leveraging infrared lights for their stealthiness. By generating a large number of Adversarial Examples in advance, our approach computes AEs in real time and dynamically displays them, which allows our method to facilitate precise and targeted attacks without modifying the victim system. Unlike previous digital-to-physical attack techniques, our method directly attacks victim models within the physical world, thereby overcoming the limitations associated with the ineffectiveness of AEs. Experimental results demonstrate the efficacy of our approach in compromising OFENs across diverse lighting conditions, varying object motion velocities, and different object placements, ultimately impairing the network's ability to accurately estimate optical flow.
Authors: Xiangbo Gao, Siyuan Yang, Ping He, Mingyang Wu, Yuheng Wu, Yushen Zuo, Jiongze Yu, Ryan Cui, Hongyuan Hua, Devin Ma, Xiao Jin, Yubo Yuan, Qing Yin, Jie Yang, Zhengzhong Tu
Abstract: We present Visko Orbis 1.0, a Live Model for real-time, interactive long-video generation. Users can change the prompt at any moment during generation, and the update becomes visible in real time. Visko Orbis 1.0 supports long-form text-to-video, image-to-video, and video continuation, with multilingual prompts and prompt switching while generation is in progress. A bounded multi-scale memory preserves subjects, scenes, and style across chunks, sustaining hour-scale rollouts without evident quality or color drift. Built on a distilled chunk-wise streaming generator and a streaming video upscaler, Visko Orbis 1.0 delivers real-time 4K video generation at 24 FPS using an optimized GPU serving engine. In long-form Arena comparisons, Visko Orbis 1.0 obtains the highest overall-preference and temporal-stability ratings among state-of-the-art real-time interactive video-generation systems.
Authors: Katharina Bendig, Ren\'e Schuster, Didier Stricker
Abstract: Event cameras follow a retina-inspired sensing principle, reporting local intensity changes asynchronously with hightemporal resolution and a wide dynamic range. Spiking Neural Networks (SNNs) complement these sparse event streams through brain-inspired dynamics, using sparse spikes and leaky membrane potentials to integrate information over time. However, many SNN object detectors process isolated event intervals with a single label and reset the network state after each prediction, thereby underusing temporal information in continuous event streams. We introduce Sequence-SOD, a sequence-aware SNN object detector that processes extended event sequences containing labels at multiple time points. Events are accumulated into short intervals, discretized into temporal steps, and fed sequentially to an SSD-style Spiking DenseNet while preserving membrane potentials across intervals within a sequence, so that detection is driven by an evolving neural state instead of independently reset input windows. On the Gen1 Automotive Detection Dataset, sequence-aware training improves mAP from 23.38 for single-interval training to 25.30 without augmentation and to 26.88 withevent-data augmentation. The model achieves a theoretical prediction frequency of 40 Hz. Training and evaluating SNN object detectors on extended event sequences improves their ability to exploit temporal cues while preserving the energy-efficiency benefits of sparse spiking computation. The results highlight sequence-aware training as a complementary direction to architectural improvements for event-based SNN detection.
Authors: Taewon Kang, Matthias Zwicker
Abstract: Text-to-video diffusion models generate temporally coherent content from natural language, yet when a prompt describes an early scene that persists while a new event emerges on top of it---such as "a tall sandcastle standing on a beach where a wave rushes in and washes it away"---generation frequently fails to realize the late-segment event in the corresponding frames. We identify this failure as Temporal Prior Suppression (TPS): the dominant prior of the early segment captures the cross-attention trajectory across the temporal axis and suppresses the guidance signal needed for late-segment realization, a competing tendency existing guidance mechanisms do not model. We introduce Temporal Prior Decoupling (TPD), a training-free framework that restores suppressed late-segment signals during diffusion sampling. TPD constructs a temporal counterfactual by conditioning on the early segment alone, and defines the discrepancy between the full-prompt and counterfactual trajectories as a suppressed signal direction. Rather than removing this direction as in prior subtractive projection methods, TPD restores it through a frame-selective lower-bound constraint resolved jointly over diffusion timestep and video frame, realizing the suppressed event in the late frames without disrupting early-segment coherence: where prior work enforces upper-bound feasibility to remove unwanted semantics, TPD enforces lower-bound feasibility to guarantee suppressed-signal contribution. TPD runs entirely within standard diffusion sampling without retraining, and is defined purely in classifier-free guidance space, making it backbone-agnostic by construction. Experiments show that TPD significantly improves late-concept realization while preserving temporal coherence and visual fidelity, and that the targeted suppression recurs across distinct text-to-video backbones.
Authors: Yinan Wang, Yan Huang, Yong Xu, Patrick Le Callet
Abstract: Existing supervised and unsupervised shadow removal methods often suffer from limited generalization due to the insufficient diversity of available training datasets, while zero-shot methods tend to produce artifacts and require time-consuming test-time optimization. To address these issues, we propose FreeShadow, a training-free shadow removal method built upon pretrained diffusion models, which exploits diffusion priors for shadow removal without any training or optimization. For illumination recovery, we propose an illumination transfer attention (ITA), which re-weights the self-attention maps in diffusion model to transfer illumination cues from non-shadow to shadow regions. For content preservation, we analyze the effects of illumination variations on self-attention maps and latent high-frequency features in diffusion model, and selectively preserve illumination-invariant components to maintain content fidelity while suppressing residual shadows. We further propose local texture-preserving relighting (LTPR) to mitigate local texture misalignment caused by VAE compression. Extensive experiments demonstrate that our method achieves strong generalization and produces realistic shadow-free images.
Authors: Yupeng Qiu, Han Fang, Ee-Chien Chang
Abstract: Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding. We argue that achieving geometric robustness requires two essential properties: (1) global spread of the watermark message, ensuring resilience even when large regions are removed, and (2) geometry-invariant representations, enabling decoding to remain synchronized despite spatial transformations. Building on these insights, we propose CASIAL, a geometric distortion-robust watermarking framework with cover image-aware message spreading (CAS) strategy and invariance alignment learning (IAL) module. CAS tightly couples watermark bits with cover image features and distributes them adaptively across the entire image, enhancing per-pixel information capacity and robustness to region removal. IAL leverages spatial attention to capture cross-pixel dependencies and align perturbed features into a shared geometry-invariant representation space, mitigating failures due to desynchronization. Across six challenging geometric transformations, CASIAL achieves substantially stronger robustness than eleven prior baselines while preserving high visual quality. It also maintains competitive performance under six signal distortions and four photometric transformations. Notably, although trained only with white-box distortions, CASIAL also exhibits strong transfer robustness to unseen black-box distortions. Comprehensive experiments demonstrate the broad robustness and superior visual quality of our method.
Authors: Wassim Swaileh, Florent Imbert, Yann Soullard, Romain Tavenard, Eric Anquetil
Abstract: Handwriting with digital pens is a common way to facilitate human-computer interaction through the use of Online Handwriting (OH) trajectory reconstruction. In this work, we focus on a digital pen equipped with sensors from which one wants to reconstruct the OH trajectory. Such a pen allows to write on any surface and to get the digital trace, which can help learning to write, by writing on paper, and can be useful for many other applications such as collaborative meetings, etc. In this paper, we introduce a novel processing pipeline that maps the sensor signals of the pen to the corresponding OH trajectory. Notably, in order to tackle the difference of sampling rates between the pen and the tablet (which provides ground truth information), our preprocessing pipeline relies on Dynamic Time Warping to align the signals. We introduce a dedicated neural network architecture, inspired by a Temporal Convolutional Network, to reconstruct the online trajectory from the pen sensor signals. Finally, we also present a new benchmark dataset on which our method is evaluated both qualitatively and quantitatively, showing a notable improvement over its most notable competitor.
Authors: Xiaolong Liu, Junjian Li, Yuan Xiao, Jiaqi Deng, Dayong Ye, Tianqing Zhu, Huan Huo
Abstract: Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineering. However, existing prompt inversion methods suffer from significant limitations: (1) gradient-based methods are unstable and uninterpretable, often resulting in generated images with severe artifacts; (2) gradient-free methods yield human-readable prompts but still fail to preserve visual fidelity due to the lack of fine-grained detail alignment. We contend that the limitations stem from treating prompt inversion as a sufficient condition for reverse engineering, ignoring the critical role of the latent noise that encodes structural information. Consequently, we propose Dualin (Dual inversion), a two-stage method that jointly recovers both the semantic prompt and latent noise of the target image. In the first stage, we integrate vision-language model, CLIP and large language model to invert a faithful, human-interpretable hard prompt. In the second stage, unconditional DDIM inversion reconstructs the exact latent noise of the target image, guaranteeing the consistency at the structural information level. Theoretically, we prove that the inverted noise enables flexible image editing without re-optimization. Extensive experiments on diverse datasets demonstrate that Dualin simultaneously generates high-quality inverted prompts and achieves state-of-the-art image fidelity. Additionally, Dualin can establish a robust foundation for the precise and controllable image editing.
Authors: Nevio Dubbini, Lisa Yeomans, Marco Pavia, Ramazan Parmaksiz, Ayse Atas Hooglugt, Gabriele Gattiglia, Beatrice Demarchi
Abstract: Artificial intelligence has shown considerable potential for archaeological applications, yet its use in zooarchaeology remains limited, particularly for the identification of avian skeletal remains. This study presents a proof-of-concept multimodal framework that integrates convolutional neural network-based image analysis with osteometric measurements for the classification of bird bones. Using a dataset of more than 10,000 images from multiple museum and research collections, two classification tasks were investigated: skeletal element identification and family-level taxonomic classification. Prior to classification, images were automatically segmented using a two-stage pipeline combining BiRefNet and SAM2. Visual features extracted with a pre-trained EfficientNet_V2_S backbone were fused with standardized morphometric data through a feature-level multimodal architecture. The model achieved 86% accuracy on the test set for bone-type classification, demonstrating reliable recognition of skeletal elements. Family-level classification proved more challenging, reaching 51% top-1 accuracy but 75% top-3 accuracy, indicating that correct taxa were frequently included among the most probable predictions. These results demonstrate the feasibility of combining visual and morphometric information within a unified deep-learning framework and establish a methodological baseline for future AI-assisted zooarchaeological identification. The approach contributes to ongoing efforts to develop scalable, interpretable, and archaeologically meaningful tools for the study of avian remains.
Authors: Zijun Lin, Zeqing Wang, Cheston Tan, Bihan Wen, Yeying Jin
Abstract: Recent game world models can generate visually realistic and interactive environments conditioned on player actions. However, games are not defined by pixels alone; they are governed by explicit mechanics, namely state-dependent rules that control health reduction, skill activation, and game termination. These mechanics depend on precise internal states, such as health points, skill meters, and timers, which are tightly coupled with visual observations and determine how gameplay evolves. Without modeling these state dynamics, existing game world models may generate visually plausible rollouts but violate the underlying game rules. In this paper, we propose StatePlay, a novel state-aware game world model that jointly predicts visual content and game states to promote mechanics-consistent generation. StatePlay adopts a mixture-of-transformers (MoT)-style architecture that preserves specialized visual and state representations while enabling cross-modal interaction, allowing predicted states to guide frame generation. Each branch is further optimized with a distinct objective suited to its modality. Experiments show that StatePlay achieves an average normalized L1 distance below 0.06 for state prediction. Furthermore, compared with models without explicit state modeling, our method improves mechanics fidelity in generated game rollouts by 18.6%. Overall, our work highlights the importance of state-aware game world modeling and advances beyond pixel-level realism toward complete and mechanically faithful game generation.
Authors: Jiahao You, Xu Han, Jinfeng Xu, Xianzhi Li
Abstract: Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving their training utility, enabling efficient 3D point cloud training. Current point cloud dataset distillation methods only tackle geometric and representation challenges while ignoring the distributional imbalance prevalent in point cloud datasets where both training and test splits follow long-tailed class distributions. To our knowledge, we present the first study on long-tailed point cloud dataset distillation. Rather than focusing primarily on geometric and representation properties or simply constructing a class-balanced synthetic set, our framework explicitly accounts for long-tailed class distributions via two core modules. First, we design Adaptive Synthetic Budgeting to allocate class-wise synthetic budgets according to class quantity and the expected benefit of additional synthetic samples. Given the allocated budgets, we further design 3D Long-Tailed Distribution Matching to optimize synthetic point clouds through Global-Local Feature Alignment and Prior-Aware Supervision. The former preserves both global class distributions and diverse intra-class structures, while the latter provides class-dependent expert supervision to keep tail-class samples recognizable while maintaining diverse head-class patterns. Extensive experiments demonstrate the effectiveness of our method, lifting classification accuracy by 7.0 points on ShapeNet55 against state-of-the-art methods.
Authors: Alexander Kozachok, Ilya Latyshev, Evgeny Karpulevich, Elena Kozachok, Egor Ushakov, Oleg Samovarov
Abstract: Background/Objectives: Dermoscopic skin lesion classifiers often lose accuracy under domain shift across imaging devices, illumination, and capture artifacts. We study how data augmentation improves the robustness of a binary malignant-versus-non-malignant classifier, with emphasis on out-of-domain (OOD) generalization. Methods: Single augmentations, photometric combinations, and composite policies were searched on a multi-source ISIC Archive collection with Derm7pt, using a ConvNeXt-Large backbone and ROC-AUC. Splits were made at the lesion-ID level, and HAM10000 and ISIC 2019-2020 were held out as a predominantly source-disjoint OOD test. Results: The largest OOD gain came from the mix policy, and photometric transformations dominated the most useful OOD operations. On an expanded pool from the same held-out sources the gain was +0.053 (95% CI +0.045 to +0.061, p<0.001), consistent across four training seeds (per-seed ROC-AUC: baseline 0.761-0.775, mix 0.806-0.829). On a small independent clinical collection, single-checkpoint sensitivity rose from 0.591 to 0.818, but this rested on 22 malignant cases and did not persist across seeds. Conclusions: Augmentations modelling real sources of domain shift can matter more than maximizing in-domain accuracy. Because the policy was selected on the same sources used to evaluate it, a source-disjoint selection protocol is needed before this effect size can be read as unbiased.
Authors: Siyu Yan, Zhuoran Yan, Haiying Xu, Panhao Zhou, Jingyu Chen, Chenhao Ji, Shuo Cao, Yongheng Zhang, Haoze Liu, Siyu Zhang, Xiwen Gu, Yihao Liu, Alex Jinpeng Wang
Abstract: Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states. Existing benchmarks are limited both by task collections with narrow coverage or partially text-solvable samples and by evaluations that emphasize final answers without diagnosing how intermediate visual states are generated, rendered, and used. We introduce See2Think, a unified evaluation framework comprising See2ThinkBench and Visual Action-of-Thought (VAoT). See2ThinkBench contains 1,200 open-ended, visually dependent problems across 12 task categories spanning 2D structured, 3D scene, and real-world reasoning. VAoT records textual thoughts, visual actions, rendered states, and subsequent reasoning under four controlled inference settings. Evaluating representative proprietary and open-source multimodal models, we find that visual reasoning is strongly model- and environment-dependent, with no single setting consistently dominating across tasks. Process analysis further shows that models usually select relevant visual operations, while faithful rendering remains the clearest bottleneck and high feedback uptake does not necessarily translate into accuracy gains. Under task-relevant corrupted feedback, models exhibit behavioral dependence on visual states, with accuracy dropping by over 10 percentage points in controlled interventions.
Authors: Boya Zhang, Shuaiwen Zhou, Di Kong, Mingxu Wang, Wenbiao Du, Yiman Zhong, Yuexin Duan, Xiawei Yue, Liuquan Cheng, Xiru Li
Abstract: Breast DCE-MRI AI is increasingly being explored for breast-level classification of no-lesion, benign, and malignant findings, beyond conventional lesion-centered diagnosis. Within this broader diagnostic scope, however, patient-specific background variability remains a major source of imaging confounding across classification tasks. Existing approaches predominantly focus on unilateral or lesion-centric analysis, whereas bilateral methods offer limited explicit modeling of spatially adaptive cross-breast correspondence. We propose PRISM-Net, a registration-free bilateral framework that leverages contralateral breast features as patient-specific references for background-aware representation learning. PRISM-Net integrates bilateral feature matching and asymmetry-aware attention to establish adaptive inter-breast correspondence and enhance representations of discriminative asymmetric patterns. On ODELIA, Macro AUC, Micro AUC, and quadratic weighted kappa were $84.11 \pm 2.33$, $90.64 \pm 1.61$, and $60.94 \pm 5.64$ on the in-distribution test set, and $68.51 \pm 4.54$, $80.74 \pm 2.68$, and $43.45 \pm 7.10$ on the held-out institution, respectively, outperforming the evaluated baseline methods across the primary evaluation metrics. PRISM-Net further demonstrated performance on independent institutional and background-complexity evaluations. Ablation experiments revealed that both bilateral relation modeling and asymmetry-aware reweighting contributed to improved classification performance. These findings highlight patient-specific bilateral reference modeling as a clinically grounded strategy for DCE-MRI interpretation, improving asymmetric pattern discrimination through explicit modeling of background complexity.
Authors: Jiaxing Li, Kai Zou, Cindy Zhou, Kaichen Huang, Junyao Gao, Zile Wang, Yang Liu, Bin Liu, Bo An, Yangguang Li
Abstract: Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they typically decouple the initialization and DMD stages -- which then pursue different target distributions -- and judge the intermediate student mainly by visual scores such as VBench. In this paper, we revisit this design from a distributional perspective. Given the mode-seeking nature of the distribution matching loss, a good initialization should match the mode coverage of the target DMD teacher, rather than merely pursuing high quality. To analyze this, we introduce a distributional evaluation protocol that measures precision and coverage between student and teacher distributions in a shared latent space. It exposes differences hidden by visual scores: some initializations reach high precision but low coverage, leading to suboptimal refinement, while mode-covering ones preserve broader support. Furthermore, even when the target distributions are aligned, DMD's reverse-KL objective can still drive the student toward high-probability teacher regions in late training, reducing coverage and diversity. To address this, we propose joint distillation, which combines DMD's mode-seeking objective with a Consistency Distillation-based mode-covering constraint. Experiments show that our method improves generation quality, coverage, and diversity; notably, even with a Wan-1.3B DMD teacher, it outperforms baselines refined with Wan-14B, underscoring the importance of distributional alignment in autoregressive video distillation.
Authors: Yanbo Ding, Zhizhi Guo, Quanyue Song, Yishan He, Zhixiang He, Yongxiang Li, Yali Wang
Abstract: Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose \textbf{Ripple}, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuously summarize audio and video context. Cross-modal memory interaction is further introduced to enhance audio-visual synchronization. To learn this memory-augmented model effectively, we devise a three-stage training recipe: (1) adapting a bidirectional audio-video teacher to block-wise causal attention with simulated memory, (2) optimizing the memory construction and interaction pipeline through end-to-end distillation, and (3) applying online reinforcement post-training tailored for streaming audio-video generation. As a result, Ripple achieves ~28 FPS at 480P resolution, over faster than the teacher, while capable of coherent long-form generation. Extensive experiments on both short-video and long-video benchmarks demonstrate our superior performance over existing offline and online joint audio-video generation methods.
Authors: David Hagerman, Roman Naeem, Fredrik Kahl
Abstract: Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We present BATS (Boundary-Aware Token Selection), a 3D medical image segmentation architecture that concentrates fine-resolution processing near predicted class boundaries. A dense boundary predictor identifies where additional resolution is needed, while a fine-first context cascade constructs an input-dependent mixed-resolution hierarchy. Homogeneous regions are represented coarsely, with finer tokens retained around boundaries, thin structures, and small targets. The sparse hierarchy is refined and rasterised into a dense segmentation. BATS predicts boundary relevance independently at every resolution level, preventing an erroneous coarse-scale decision from suppressing fine-scale evidence. Parent cluster attention further injects hierarchical ancestor tokens into local attention neighbourhoods, providing cross-scale context without dense multi-scale feature maps or cross-scale neighbour search. We evaluate BATS on five public CT and MRI datasets using the standardised nnU-Net Revisited protocol. BATS achieves the highest LiTS Dice among the compared methods and averages within 0.37 Dice points of the strongest dense baseline, MedNeXt-L, across the five datasets. Relative to MedNeXt-L, it reduces peak allocated GPU memory by more than 53% on KiTS, LiTS, and BraTS. Inference is up to 30% faster on KiTS and LiTS, which retain fewer tokens, but slower on the more token-dense BraTS. Mixed-resolution processing therefore provides consistent memory savings, while runtime and accuracy gains depend on dataset boundary density.
Authors: Fahad Ahmed, S\"oren Auer, Jennifer D'Souza
Abstract: Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meaningful knowledge, often not presented in the text of a research publication. The Sci-ImageMiner benchmark dataset, accompanied by a community-driven competition, raises the bar over prior scientific competitions by curating a comprehensive, expert-annotated dataset across four end-to-end complementary tasks. The competition attracted 68 active participants and 1,263 public/private submissions from 9th January 2026 to 8th April 2026. Our results show that state-of-the-art multimodal models perform well on classification and summarization tasks but struggle with data extraction and scientific reasoning, particularly in visual question-answering. These findings reveal key limitations and highlight challenges and opportunities for improving domain-aware multimodal AI systems. Overall, the Sci-ImageMiner benchmark and competition establish a rigorous platform for advancing research in scientific figure comprehension and reasoning and demonstrate the potential of state-of-the-art approaches for a challenging and complex research area.
Authors: Yunzhan Fu, Enyu Bao, Xiangyu Shen, Yihao Wu, Chunbo Jiang, Fangli Guan, Liqi Yan
Abstract: Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibitive memory overhead of joint end-to-end training with large batch sizes, and (iii) the medical hallucinations induced by vanilla contrastive losses that ignore fine-grained anatomical laterality and negation modifiers. To address these challenges, we propose \textbf{SCALPEL}, a \textbf{S}emantic \textbf{C}ross-modal \textbf{A}lignment framework via \textbf{L}LM-\textbf{P}owered \textbf{E}ncoder \textbf{L}earning. First, Clinical Report Contrastive fine-tuning converts a generative LLM into an isotropic encoder via domain-specific clinical text adaptation. Second, an asymmetric alignment strategy leverages offline feature caching to enable efficient training. Critically, we formulate an Anatomy-Negation Aware Objective that explicitly penalizes mismatched image-text pairs involving laterality confusion or false negations. Extensive experiments across MIMIC-CXR, CheXpert, and IU X-Ray benchmarks demonstrate that SCALPEL achieves state-of-the-art performance in cross-modal retrieval, zero-shot disease classification and medical visual question answering.
Authors: Siddharth Vohra
Abstract: When asked to describe a medical image that was never attached, frontier vision-language models do not abstain: they confabulate a diagnosis. We show that this confabulation is not random. It is structured by who the patient is said to be. Across chest X-ray, brain MRI, and dermatology, Claude Opus-4.7, GPT-5.4, and Gemini-3.1-Pro are each queried with only a demographic descriptor and no image, and changing the descriptor systematically shifts the diagnosis returned. Claude concentrates sharply: a 65-year-old white man asking about a skin mole receives Melanoma in nearly every response, and a 32-year-old Black woman asking about her chest X-ray receives a Sarcoidosis diagnosis whose reasoning reads "suspected, based on demographics and classic pattern.'' GPT-5.4's effect is broader, fabricating across every demographic cell we test, most conspicuously naming Sarcoidosis for young Black patients on chest X-ray. Two structural findings sharpen the problem. A hedged regime appears in which the prose acknowledges the missing image while the structured diagnosis field nevertheless names a disease, a dissociation invisible to prose-only audits. And Claude's dermatology effect collapses entirely when 'skin mole' is swapped for 'skin lesion' while GPT-5.4's is preserved, indicating that mirage is a family of distinct failure modes rather than a single phenomenon. Trustworthy VLM deployment in clinical pipelines requires auditing the structured output channel directly, and probe-word sensitivity should be treated as a first-class evaluation dimension
Authors: Qianru Li, Xuyang Chen, Erkin T\"urk\"oz, Lu Liu, Xuqin Wang, Liqiu Meng, Tao Wu, Yanfeng Zhang
Abstract: Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high practical value, with applications ranging from real-estate advertising to virtual tour creation. Existing methods either lack true 3D spatial awareness by relying on 2D image priors, or treat trajectory generation as a geometric path planning problem divorced from cinematographic semantics. We present CinemaTraj, a framework that reframes camera trajectory planning as a language-grounded spatial reasoning problem. Given a set of RGB-D images and a user prompt, CinemaTraj equips an LLM agent with a structured 3D scene graph: the agent decomposes the prompt into a sequence of atomic cinematographic movements (dolly, orbit, crane, pan, tilt, zoom, arc). Each movement is instantiated via a novel parametric trajectory representation that is both cinematographically expressive and optimizable for collision avoidance. The scene graph acts as a structured spatial prior, grounding the agent's reasoning in accurate geometric and semantic knowledge of the environment. CinemaTraj further generates synchronized voiceover and subtitles aligned with camera motion, producing narrated cinematic video outputs. We evaluate CinemaTraj on real-world ScanNet++ environments, and show that it produces prompt-faithful, collision-free trajectories with high cinematographic quality, outperforming existing approaches on prompt alignment, trajectory quality, and safety metrics.
Authors: Weile Gong, Zijian Lu, Mingcai Chen, Yiping Zuo, Xin He, Weibei Fan
Abstract: Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise correct visual judgment toward an outdated answer. We study this failure as visual lock-in in a controlled grounding setting where only the verbalized prior varies. Across models, stronger lock-in accompanies smaller changes in the model representation before the final answer. This reversal suggests that lock-in depends not on how far this representation moves, but on how that movement is organized. In models that are harder to correct, prior-induced changes concentrate along a compact set of directions that repeatedly appear across examples. We call these recurrent axes the Prior Directions. They recur on held-out examples, while a descriptive four-model comparison associates greater concentration with stronger lock-in. Controlled interventions show that removing the component aligned with the Prior Directions restores visual grounding, whereas removing an equally large orthogonal component has little effect. Prior control thus arises when prior-induced changes form a coherent and reusable pattern in the representation used to produce the answer. This account explains why the same prior remains revisable in one model yet becomes dominant in another.
Authors: Alexej Klushyn, Juan Rivero Sesma, Florian Seligmann, Richard Kurle, Kinh Tieu, Jayant Sen Gupta
Abstract: YOLO-Pose models provide efficient keypoint localization, but do not quantify the associated spatial uncertainty. We introduce a lightweight post-hoc probabilistic extension that augments a trained YOLO-Pose model with calibrated bivariate predictive distributions over keypoint locations, centered at the model's original predictions. Concretely, we train additional probabilistic heads with an importance-weighted negative log-likelihood to predict an input-dependent $2\times2$ dispersion matrix for each keypoint, followed by Gaussian calibration for broad downstream compatibility or Student-$t$ calibration for distributional fidelity. Complementing this, we propose an evaluation protocol that combines a suite of distributional calibration diagnostics with average keypoint precision (AKP), a keypoint-level extension of the COCO AP protocol for assessing reliability rankings. Experiments on COCO show that the learned uncertainty estimates enable effective keypoint-level reliability ranking, Student-$t$ calibration best captures the empirical residual distribution, and uncertainty-based pruning removes unreliable keypoints. A central application-level demonstration is vision-based aircraft landing, where calibrated covariances for runway keypoints support uncertainty-aware aircraft position estimation and downstream sensor fusion.
Authors: Duzhen Zhang, Yahan Yu, Qiaoyi Su, Jiahua Dong, Tielin Zhang
Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding. In Multimodal Continual Instruction Tuning (MCIT), however, shifting visual distributions and evolving instruction semantics cause this shared projector to drift, leading to projector-level forgetting, an issue largely overlooked by methods that focus primarily on the LLM backbone. We introduce Progressive Multimodal Alignment (PMA), a framework that enables the projector to adapt continually while preserving previously learned alignment. PMA detects multimodal distribution shifts via a lightweight representation descriptor and progressively expands projector experts only when needed. An expandable router integrates expert outputs based on multimodal features, while the original pretrained projector is retained as a stable alignment anchor. This progressive mechanism balances stability and plasticity with sub-linear parameter growth and serves as a method-agnostic add-on to existing MCIT approaches. Extensive experiments on two recent MCIT benchmarks demonstrate that mitigating projector-level forgetting yields consistent gains over prior state-of-the-art methods when combined with PMA. Moreover, PMA scales across diverse MLLM backbones, demonstrating robust and broadly applicable MCIT performance.
Authors: Roger Mar\'i, El\'ias Masquil, Xavier Bou, Thibaud Ehret, Gabriele Facciolo
Abstract: Accurate refinement of Rational Polynomial Camera (RPC) models is essential for high-quality satellite image geolocation. In ground control point (GCP)-free multi-view pipelines, this refinement is commonly performed through bundle adjustment from automatically extracted image correspondences. However, conventional RPC bundle adjustment pipelines rely on handcrafted feature matching, which becomes unreliable in multi-date collections affected by seasonal, illumination, and land-cover changes. We propose an appearance-aware RPC refinement pipeline that combines learned local feature matching for season-invariant correspondences with global image descriptors for selecting visually compatible image pairs. This reduces redundant and error-prone matching while preserving the connectivity of the matching graph. Experiments on seasonally diverse WorldView-3 images show that our pipeline improves GCP-free relative RPC refinement over open-source baselines, achieving lower geometric consistency errors while substantially reducing matching time on collections with 39-42 views. By making RPC refinement more robust to diachronic appearance variation, our approach enables more effective use of multi-date satellite imagery.
Authors: Taiye Chen, Qi Zhang, Yisen Wang
Abstract: Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation that degrades frame quality over time. Although this phenomenon has been widely observed, the underlying mechanism of compounding error and how to achieve stable long-horizon generation remain largely unresolved. In this paper, we investigate the internal representation dynamics of video world models and discover that compounding error is tightly coupled with dimensional collapse of hidden representations. Specifically, the effective rank of model representations sharply decreases at the onset of generation drift, revealing a strong connection between representational degradation and long-term rollout instability. Furthermore, we find that pure training data scaling fails to boost model resistance to error drift, contradicting mainstream scaling paradigms. To address this problem, we propose video representation regularization, a lightweight training constraint that stabilizes latent representations and suppresses iterative error accumulation. Compared with Diffusion Forcing, our method achieves improvements from 38.65 to 55.56 and from 44.37 to 72.08 on the Aesthetic Quality and Imaging Quality metrics of VBench. Our work establishes the first connection between autoregressive video drifting and model internal representations, adopts erank as a quantitative metric for error accumulation, reveals counterintuitive scaling limitations for video world models, and presents a simple yet effective regularization strategy to improve long video generation robustness.
Authors: Danning Zhu, Ziyan Lin, Jing Wu
Abstract: Currently, autonomous driving object detection models face significant data scarcity and generalization challenges when navigating complex Chinese rural traffic scenarios. To address these limitations, we propose a novel real-synthetic mixed object detection dataset tailored specifically for Chinese rural roads and systematically evaluate the performance of 13 mainstream detectors under different real-to-synthetic data ratios, thereby providing empirical evidence for model selection and data strategy design in rural autonomous driving scenarios. Our dataset combines real-world images captured in Weishi County, Henan Province, with parameterized virtual scenes generated via Unreal Engine. To accurately reflect the unique realities of rural traffic, we define a comprehensive 14-category object system encompassing region-specific elements such as electric tricycles, low-speed vehicles (LSVs), and roadside stalls. Under a unified training protocol, we systematically evaluate 13 mainstream detectors -- spanning the YOLOv5, YOLOv8, YOLO11, and YOLO26 series, as well as RT-DETR-L -- across three data configurations: an all-real baseline, a 1:0.5 real-to-virtual mix, and a 1:1 mix. Experimental results demonstrate that a moderate injection of synthetic data (1:0.5 ratio) effectively enhances detection performance, with YOLO11m achieving the highest mAP@0.5 of 0.758. However, a higher proportion of synthetic data (1:1) introduces domain shifts that offset the benefits of data scaling. While most models reliably identify distinct local vehicles, significant perceptual bottlenecks remain for long-tail, non-standard objects like stalls and railings. This research provides crucial empirical evidence and novel insights for model selection and synthetic data strategies, facilitating the practical deployment of autonomous driving perception systems in rural areas.
Authors: Paul Julius K\"uhn, Saptarshi Neil Sinha, Tiago Kleist, Richard Hoffmann, Arjan kuijper, Michael Weinmann
Abstract: While automated defect detection such as the detection of surface scratched is an important aspect in industrial quality control, the scarcity of annotated defect data make this task challenging. This paper presents a procedural rendering pipeline that generates large-scale annotated synthetic training data using BlenderProc, with configurable material appearance, camera modes, and domain randomization, producing automatic COCO-format annotations. To show the potential of our approach, we evaluate four training strategies, namely synthetic-only, real-only, mixed, and fine-tuning from synthetic weights, across two objects with different material properties and three lightweight edge-deployable detectors, YOLOX, YOLO26, and LW-DETR. Our evaluation show that fine-tuning from synthetic weights consistently outperforms real-only training, and that mixed training effectively recovers performance under scarce real-data conditions, with findings validated across both convolutional and transformer-based architectures. The proposed approach enables scalable defect detection without the burden of large real annotated datasets, making it practical for on-device industrial inspection. The pipeline scripts, 3D model, and both synthetic and real annotated scratch datasets for a glossy toy Ferrari car will be made available through the project website upon acceptance.
Authors: Chuanzhi Xu, Zihan Deng, Huiqi Liang, Chengkun Yue, Zhanlin Cui, Pengfei Ye, Weidong Cai
Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy. However, if we apply traditional image assessment methods to scientific figure quality assessment, limitations emerge: classic IQA models capture perceptual quality or aesthetics but cannot judge whether a figure serves the paper's scientific argument; CLIP-based methods assess generic image-text correspondence, yet lack understanding of manuscript context; and zero-shot LLM/VLM judges, when repurposed for figure scoring, often yield overly concentrated scores with limited fusion of visual and textual evidence. We introduce an annotated dataset of 3,857 scientific figures from peer-reviewed conference papers, each rated along four peer-review-oriented dimensions: Clarity, Relevance, Informativeness, and Structure. We propose SciFigAlign, a fine-tuned multimodal scorer that grounds figure quality assessment in manuscript evidence. Given a figure crop, caption, citing paragraphs, and light paper context, SciFigAlign fine-tunes CLIP and SciBERT end-to-end with per-modality cross-attention and CubeMLP fusion, jointly optimizing SmoothL1 regression with a within-paper ranking hinge loss. Under paper-level splits, SciFigAlign achieves a macro MAE of 0.3524 and a within-paper pairwise accuracy of 81.64% on the test set with n = 396, a 59% relative error reduction over the best LLM-as-judge baseline with MAE 0.864. Ablations confirm that manuscript-grounded inputs, citing-context denoising, and ranking supervision are all critical, showing that scientific figure assessment requires learned alignment between visual content and manuscript evidence rather than prompting alone, even with state-of-the-art VLMs.
Authors: Feixiang Liu, Qiang Qiu, Lanbo Sun, Nan Wei, Huawei Shen, Xueqi Cheng
Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts. Under a fixed forced-choice interface, Visual Credit Audit (VCA) separates two estimands: whether the benchmark image gives the model's declared decision more support than text-only and blank controls, and whether the model responds to relation-specific visual evidence. The first audit is training- and label-free and does not require an answer flip. Applying labels yields dependence-credited correctness (D-CC); on correct items, it equals same-control gold-aligned positive gain, while prediction alignment extends the audit to errors. Across four open MLLMs and two spatial benchmarks, 12.73-26.25% of decisions are correct yet uncredited. Matched same-split image permutation reduces D-CC by 21.25-47.80 points, with every paired 95% interval above zero. Fixed-pixel relation contrasts and a 3x3 evidence-source factorial show why null controls cannot identify relation response. Among controlled correct-but-uncredited agreement decisions, response to relation reversal spans 81.57-100.00%, while 32.11% pooled change answer. Independently audited outcomes on 108 geometry-compatible edits provide a bounded natural-image correspondence check. VCA thereby decomposes benchmark success into correctness, additional image support, and relation-consistent response.
Authors: Zihan Deng, Chuanzhi Xu, Huiqi Liang, Haoyang Li, Xiaozhen Zhong, Lequan Yu
Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers. However, existing image quality assessment (IQA) methods are predominantly designed for natural photographs or AI-generated content, which cannot be directly applied to scientific papers. The few existing studies on scholarly charts remain confined to visual-surface comparisons, failing to verify caption alignment, citation relevance, or visual misleadingness. To address this, we propose SciFigQual-Bench, a full-text contextual benchmark that evaluates scientific images across five dimensions (clarity, layout, caption fit, context relevance, and misleading risk). The data covers top computer-science conferences from 2020 to 2025; 6,308 images were independently scored by multiple domain experts in five dimensions and aggregated into gold-standard annotations. Unlike previous scientific figure benchmarks, our dataset binds each image to its caption, citing sentence, and manuscript context. To enable automated evaluation on this benchmark, we designed a staged cross-modal evaluation framework SFQ-Agent to achieve auditable and refined scoring through the collection and fusion of modal evidence. Multiple mainstream large models were evaluated on the test subset eval1200, and SFQ-Agent (F3) equipped with GPT-5.6-Sol achieved the lowest overall average absolute error (0.418) and the highest consistency rate (93.4%), consistently outperforming both direct evaluation and auxiliary (Sidecar) visual language model evaluation schemes.
Authors: Philippe Baumstimler, Jean-Mathieu Gagnon, S\'ebastien Gagn\'e, Mathieu Duchesneau, Cl\'ement Playout, Lama S\'eoud
Abstract: Anterior eye segment (AES) segmentation is a key component of both ocular biometrics and emerging clinical image analysis applications. However, heterogeneous acquisition conditions and limited annotations in medical settings hinder the robustness and generalization of existing methods. Foundation models (FMs) such as DINOv3 offer strong transfer capabilities, but efficiently adapting their representations to dense prediction tasks remains challenging. In this study, we investigate robust AES segmentation in clinical settings, and propose a lightweight architecture built upon a distilled DINOv3 ViT-Small backbone. We introduce a step-attention feature refinement module that progressively adapts multi-level transformer representations before convolutional decoding, enabling efficient exploitation of pretrained features with few parameters. We evaluate the proposed approach on a private dataset of 333 clinically acquired AES images spanning eight ophthalmic acquisition protocols and annotated for seven anatomical classes. Compared with convolutional and transformer-based baselines, including DINOv3-based methods, our approach achieves the best overall performance, reaching 85.55\% mIoU when fully fine-tuned. It also demonstrates the strongest robustness to domain shift across four unseen public AES segmentation datasets. These results establish a strong baseline for robust AES segmentation in clinical settings and highlight the importance of decoder design for effectively adapting FMs representations to medical segmentation tasks.
Authors: Jiatong Li, Leo Liang, Linghe Kong, Yulun Zhang
Abstract: Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as color drift, motion stagnation, and eventual visual collapse. In this paper, we characterize this phenomenon from a frequency-domain perspective: error accumulation appears as a pronounced energy drift in the low-frequency bands. We further investigate the effectiveness of attention sink in the frequency domain, and find that it improves the video quality by alleviating the spectral energy drift to some extent, but cannot fully resolve it. Motivated by the above analysis, we propose FreqForcing, a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA). The proposed SSA leverages the low-frequency components of anchor attention to maintain long-horizon visual stability, while preserving dynamic motion through the high-frequency components of local attention. Our FreqForcing extends Self-Forcing pretrained on 5s clips to two-minute generation, achieving 24x extrapolation. Extensive experiments show that FreqForcing outperforms existing training-free methods quantitatively and qualitatively while remaining competitive with representative training-based approaches.
Authors: Hao Tan, Jun Lan, Zichang Tan, Ajian Liu, Zijian Yu, Chuanbiao Song, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei
Abstract: The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generated Image (AIGI) detection increasingly essential. While multi-modal large language models (MLLMs) offer a transparent alternative to black-box binary scoring, we observe that current MLLM-based detectors still exhibit notable perception bottlenecks in capturing fine-grained anomalies. They primarily focus on how visual evidence is organized and synthesized, leaving the intrinsic perception less optimized. To mitigate this gap, we present Veritas++, a perception-enhanced reasoning framework that establishes reliable perception as the foundation of authenticity reasoning. Rather than directly optimizing the model's explanatory ability, we ground AIGI detection on three basic perception abilities, i.e., capturing fine-grained visual details, semantic anomalies and pixel-level differences. Building on this insight, we introduce Perception-oriented Learning (PoRL), which replaces open-ended description supervision with verifiable rewards to explicitly strengthen these capacities. To further integrate enhanced perception with reasoning, we introduce Value-aware On-Policy Distillation (VaOPD), an adaptive distillation mechanism that prioritizes high-value distillation signals over uniform supervision, internalizing perception-aware reasoning through a privileged self-teacher. Extensive experiments across standard, in-the-wild and emerging benchmarks demonstrate that Veritas++ achieves promising generalization. The perception learning effectively bridges the perception gap and yields seamless gains on detection, while VaOPD further enables efficient capability evolvement without sacrificing existing performance. Code and checkpoints are available at https://github.com/EricTan7/VeritasPP.
Authors: Itbaan Safwan, Ramail Khan, Muhammad Annas Shaikh, Muhammad Atif Tahir
Abstract: Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model must answer free-form clinical questions about an image. While recent vision-language models (VLMs) achieve promising answer accuracy on this task, clinical adoption also requires the model's internal representations to reflect the visual evidence behind its answers. We propose a simple multi-task fine-tuning recipe that constructs auxiliary grounding and description tasks from an existing VQA dataset with minimal additional annotation: expert-annotated polyp masks are reused directly, while a GI-domain pretrained classifier with Grad-CAM localization provides weak supervision for finding categories that lack ground-truth masks. Three small VLM backbones are fine-tuned with low-rank adaptation under matched VQA-only and multi-task recipes on Kvasir-VQA-x1, and we show consistent accuracy gains together with improved implicit alignment between answer tokens and the relevant image region, evaluated on both in-distribution and out-of-distribution data.
Authors: \'Alvaro D\'iaz-Laureano, Roger Mar\'i, El\'ias Masquil, Pablo Arias, Gabriele Facciolo
Abstract: Accurate 3D reconstruction from satellite imagery typically relies on near-simultaneous stereo pairs, limiting its applicability to diachronic settings where multi-date images exhibit varying seasonal and illumination conditions. Training dense stereo matching models robust to appearance changes is a long-standing challenge, as aligned multi-date imagery and ground-truth geometry are costly to obtain at scale. We propose SeasonStereo, a scalable framework that addresses disparity estimation from diachronic satellite images by training on synthetic image pairs with controlled seasonal appearance variation, while leveraging zero-shot geometric priors from foundation models. SeasonStereo matches the accuracy of state-of-the-art LiDAR-supervised models, while producing sharper geometric details without requiring aligned real multi-date training products or LiDAR-derived labels. As a result, SeasonStereo offers a practical path toward large-scale 3D reconstruction from heterogeneous satellite images with reduced supervision cost.
Authors: Piyush Jain, Kousik Dasgupta, Rajarshi Roy, Subarna Tripathi
Abstract: As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitoring, the opacity of their spatial judgments limits operator trust and auditability. MLLMs demonstrate strong reasoning but often struggle with fine-grained spatial understanding and object hallucination. Prior work, ByDeWay, introduced Layered-Depth-Based Prompting (LDP), a training-free framework that mitigates hallucinations by structuring prompts using monocular depth estimation. However, coarse depth layering falls short in resolving object-to-object spatial relationships within the same geometric plane, such as projective ("left of", "above") and topological ("inside", "touching") relations. We propose ByDeWay-V2, which integrates explicit spatial relational context alongside depth cues, expressed as human-readable predicates that serve as auditable evidence for downstream decision support. Using an open-vocabulary object detector (YOLO-World-L), our framework computes pairwise geometric relations between detected objects and injects them as structured spatial predicates into the MLLM prompt, bridging 3D scene depth and 2D spatial semantics without any training. We evaluate ByDeWay-V2 on the Visual Spatial Reasoning (VSR) and BLINK benchmarks across multiple MLLMs, with hallucination grounding assessed via POPE. On the BLINK spatial subset, ByDeWay-V2 achieves a 46 percent relative F1 improvement over LDP for Qwen2.5-VL, and recovers BLIP-Base's spatial reasoning on VSR from near-random performance to a competitive F1 of 0.53. Our lightest configuration operates under a strict 40-token context budget on CPU, showing the framework's suitability for resource-constrained, real-time decision-support settings.
Authors: Roshan Kenia, Stephanie L McNamara, William Lotter
Abstract: CT vision-language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume representations that dilute fine-grained anatomical signals. Fine-grained vision-language pre-training addresses this by aligning anatomy-level visual features with anatomy-specific text, but in doing so discards the global context that whole-volume models provide. Furthermore, existing fine-grained approaches train from scratch, making them computationally expensive. We introduce Anatomy Contextualized Adaptation (ACA), a lightweight framework that adapts frozen CT foundation model representations for anatomy-level vision-language alignment while enhancing global contextualization. ACA uses TotalSegmentator to decompose CT volumes into anatomy-level embeddings, which are refined via a transformer that captures cross-anatomy relationships, and aligned to both per-anatomy and scan-level text extracted from radiology reports. Evaluated on Merlin and CT-RATE, ACA consistently outperforms both the frozen foundation model baselines and existing fine-grained methods in zero-shot finding classification, while requiring less than one hour of training once embeddings are cached. The attention weights learned by ACA's inter-anatomy transformer additionally indicate plausible cross-anatomy context routing. Altogether, these results support ACA as a lightweight approach for adapting CT foundation models to anatomically grounded vision-language alignment while preserving and enhancing global anatomical context.
Authors: Siyao Li, Jiawei Gu, Shuai Liu, Kairui Hu, Zekun Li, Linjie Li, Chengcheng Tang, Po-Chen Wu, Ivan Shugurov, Lingni Ma, Michael Zollhoefer, Sizhe An, Abhay Mittal, Amy Zhao, Ranjay Krishna, Manling Li, Ziwei Liu, Chuan Guo
Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous full-body motion with real physical consequences, including gravity and collisions. The body can therefore act freely in the physical world, while execution-side disturbances, balance and motor errors, are factored out. What remains measurable is the model's action intelligence: its moment-to-moment choice of what the body should execute next. Based on this framework, we build HumanCLAW-Bench: 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes. We test nine state-of-the-art VLMs and find that none solves the benchmark; the best model reaches only a 16.8% success rate. Recognizing the target is not the bottleneck. What current VLMs lack is embodied self-awareness: they lose track of their own body, failing to tell where it is, whether it has reached the goal, or whether it has hit an obstacle.
Authors: Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys
Abstract: Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding. The dominant approaches to this problem are severely limited: Simultaneous Localization and Mapping (SLAM) is sensitive to initialization and transient failures due to its causal, incremental nature; it is often over-optimized for real-time operation and generally requires known camera calibration; while Structure-from-Motion (SfM) typically forgoes any image ordering, enabling optimal initialization and global optimization, but lacks robustness to visual symmetries and extreme motions. To bridge this gap, we introduce a system that combines the strong sequential constraints of SLAM with the flexibility and global optimization of offline SfM, enabling the metric reconstruction of arbitrary, long, uncalibrated videos. This system leverages recent advances in wide-baseline dense image matching, treats temporal ordering as a first-class citizen for reliable loop closure, and augments global optimization with metric monocular depth priors. As a result, thorough evaluations on diverse, challenging datasets that exhibit extreme motion and visual symmetries reveal that our approach is significantly more robust and accurate than both state-of-the-art SLAM and SfM, classical or learned, with given or unknown camera calibration. The code is publicly available at https://github.com/cvg/vidmap.
Authors: Hengyi Xie, Chenfei Yao, Xianjin Wu, Xuanyang Xi, Yiping Tang, Di Xu, Yingying Zhu, Dingkang Liang, Xiang Bai, Han Ding
Abstract: Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional $V \to L \to A$ pathway as a direct $V + L \to A$ mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA independently encodes visual observations and language instructions, directly exchanges information between them through lightweight bidirectional vision-language interaction, and predicts continuous action chunks with a compact decoder. This simple design constructs task-conditioned representations directly from visual and linguistic features, significantly reducing the computational and memory costs of VLA inference. On LIBERO, TurboVLA achieves 97.7% average success with only 0.2B parameters, 31.2 ms inference latency, and 0.9 GB inference VRAM on a consumer-grade RTX 4090, matching or outperforming substantially larger VLA policies. These results establish TurboVLA as a simple and effective alternative to the prevailing LLM-centric VLA paradigm, offering a new perspective on how vision, language, and action can be connected for efficient robotic manipulation. Code is available at https://github.com/H-EmbodVis/TurboVLA.
Authors: Puneet Velidi, Michelle F. Miranda, Farouk Nathoo, Ashery Mbilinyi, C\'edric Beaulac
Abstract: Glioma grading from tumor contours is often treated as a pixel problem even when the signal of interest is shape. We align closed contours with a functional shape-alignment framework, separate global deformation from residual Fourier shape, and organize these quantities as frequency-ordered tokens. In five-fold patient-disjoint cross-validation on BraTS~2020 tumor contours, with model selection performed using grouped inner validation, a compact multilayer perceptron (MLP) achieves the highest mean balanced accuracy at 71.5\%, compared with 65.9\% for ResNet-18 and 63.3\% for ViT-Tiny. It also gives the highest mean low-grade glioma F1 at 54.9\%. Its pooled out-of-fold balanced accuracy is 72.4\% (patient-bootstrap 95\% CI: 66.4--77.8\%). The selected MLPs use 2.9k--117.3k parameters across folds, at least 46 times fewer than the pixel baselines. In a controlled noise-free simulation, shape-based models reach 56.3--71.5\% balanced accuracy while the pixel models remain at 50.0--52.5\%. This work demonstrates how incorporating a shape-based inductive bias at the representation level can improve interpretability and scalability while enabling substantial dimensionality reduction.
Authors: Zehao Cao, Bowei Xu, Xun Cao, Zhan Ma, Hao Chen
Abstract: Prompt-based video streaming transmits compact semantic prompts instead of pixel-level content for generative reconstruction, enabling ultra-low-bitrate communication. However, the state-of-the-art Promptus framework is vulnerable to network fluctuation, where partially received prompts lead to catastrophic quality collapse. We propose ScalablePromptus, which enhances Promptus with semantic and color-aware prompt inversion, spherical linear interpolation for intermediate frames, and--most critically--a dropout training strategy that produces rank-ordered prompt representations. This allows the receiver to reconstruct meaningful video from arbitrarily truncated prompts without any adaptation. Under stable networks, ScalablePromptus achieves modest quality gains. Under lossy conditions, it reduces the performance degradation caused by truncation by 82%-95% compared to the baseline, making prompt-based streaming robust enough for real-world deployment.
Authors: Panagiotis Fytas, Ian Selby, Clemens Karner, Judith Babar, Simon Baker, Jake Beckford, Timothy J. Sadler, Shahab Shahipasand, Arthikkaa Thavakumar, John Li Chen, Alex Sawer, Michael Roberts, Jonathan Weir-McCall, J. H. F. Rudd, Carola-Bibiane Sch\"onlieb, Anna Korhonen, Anna Breger
Abstract: Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment. However, commonly used report-derived labels for pathology classification or generic image quality metrics for reconstruction may not reliably reflect clinical judgment. We systematically investigate how evaluation-reference choices affect model performance and ranking in both pathology classification and image quality assessment (IQA). To enable controlled comparison across evaluation references, we collected paired expert image- and report-derived labels for thoracic findings from a clinical cohort at Cambridge University Hospitals (CUH) and curated a subset of the public MIMIC-CXR dataset, along with expert ratings of diagnostic image quality. We show that for supervised image classifiers (ResNet, DenseNet), several zero-shot and fine-tuned vision-language models (e.g., MedKLIP, GLoRIA, and ConVIRT), changing the label source leads to substantial differences not only in performance estimates but also in model rankings. In parallel, alignment of IQA measures with expert judgment depends heavily on the choice of measure, and commonly used IQA metrics such as SSIM and PSNR often fail to align with expert assessments of diagnostic usability. Our results demonstrate that evaluation choices are crucial: they can determine which models and methods appear best and are therefore selected for further development or deployment. The selection of evaluation references should therefore be treated as a central component of clinical validity in CXR machine learning, and justified with respect to the pathology, imaging task, and intended downstream clinical use.
Authors: Yiming Cai, Fangjie Yu, Meiqing Yu, Ziyue Shi, Pengfei Yuan, Yong Guo
Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure. We introduce CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines. CG-World explicitly records intermediate states, including multimodal semantics, spatial structure, skeletal and controller states, motion curves, camera and lighting parameters, physics caches, contact events, and multi-pass renderings. CG-World v1 contains approximately 850,000 temporally aligned segments of 1-5 seconds. It separates latent states, observations, relations, events, and branch metadata, and organizes them into unified spatiotemporal samples. To support intervention learning and counterfactual reasoning, CG-World defines a branch lineage covering factual trajectories, observation interventions, action interventions, mechanism interventions, and strict counterfactual branches, with intervention targets, invariants, and alternative outcomes explicitly recorded. We evaluate the dataset on geometry-conditioned video generation, action prediction, and closed-loop vision-language-action policy transfer. Results show that CG-World provides reusable structured supervision for controlled generation, action modeling, and embodied policy transfer. We plan to expand CG-World through continued data collection and community collaboration toward a shared data infrastructure for world models, Physical AI, and embodied intelligence.
Authors: Hung Nguyen, Kim Nhat Minh Nguyen, Van Duc Vu, Van-Danh Le, Hoang Huy Le, Dinh Tuan Nguyen, Pham Tuyen Le, Van-Truong Nguyen, Quan Nguyen
Abstract: Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models, they generally assume textual rather than the more natural speech inputs. In this paper, we investigate whether a well-established text-conditioned model can be transferred to speech in a data-efficient manner. Using ALBEF as a case study, we conduct diagnostic analyses showing that a lightweight MLP-based projector effectively adapts it to speech, while preserving semantic discrimination and robustness. Motivated by these findings, we introduce Speech2Grasp, a framework for data-efficient transfer of text-conditioned grasp detection to speech. Real-world humanoid robot experiments show that Speech2Grasp outperforms cascaded ASR-based pipeline, while reducing inference latency. Our findings suggest a practical paradigm for extending established text-conditioned systems to speech.
Authors: Sami Azirar, Enrico Pallotta, Jan Nogga, J\"urgen Gall, Sven Behnke, Hermann Blum
Abstract: World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. However, current video-based world models often struggle to capture the physical constraints that govern manipulation, particularly contact. Further, their action conditioning is often constrained to specific embodiments such as parallel grippers. We propose \emph{Contact Flow}, an embodiment-agnostic action representation that encodes manipulation through the trajectory of 3D contact points between an actor and a target object. By discarding actor-specific appearance and kinematics, Contact Flow provides a shared conditioning signal for both human demonstrations and robotic execution. Therefore, we can train a large-scale video generative model on both human and robotic object interaction videos conditioned on Contact Flow, yielding a world model that predicts physically plausible manipulation outcomes. We integrate this model into a propose-imagine-verify-act pipeline, where generated rollouts are assessed by a vision-language model before execution. Experiments on the DROID dataset and real-world tabletop manipulation tasks demonstrate that Contact Flow enables transfer between human demonstrations and different robotic embodiments.
Authors: Shiyong Meng, Bolei Chen, Ping Zhong, Yang Wan, Rongzhi Wang, Jiazhi Xia, Jianxin Wang
Abstract: Visual Floorplan Localization (FLoc) has emerged as a promising solution for indoor localization by matching egocentric images against minimalist structural maps. However, due to cross-modal information asymmetry and repetitive indoor layouts, visual FLoc is fundamentally challenged by multimodal pose distributions, where visually identical observations map to distinct, spatially separated locations. Existing ray-matching-based methods tackle this by explicitly predicting sparse geometric or semantic rays, which inherently incur information loss and demand resource-intensive preprocessing alongside exhaustive matching during inference. In this paper, we bypass the intermediate ray-matching paradigm and propose a coarse-to-fine visual FLoc framework that progresses from uncertainty to determinism. In the coarse stage, we design an image-conditioned pose diffusion model to parameterize the continuous multimodal pose distribution, effectively routing stochastically initialized pose particles toward distinct candidate modes. In the refinement stage, we propose a localized refiner that predicts bounded sub-meter pose residuals from candidate-centered floorplan crops, where structural ambiguities are largely eliminated. Our method effectively balances global multi-hypothesis tracking and local sub-meter refinement without requiring any offline map preprocessing or test-time lookup tables. Comprehensive results on the S3D (full) and ZInD benchmarks demonstrate that our approach achieves state-of-the-art accuracy and robustness.
Authors: Gahye Lee, Gyoonseo Kim, Wonjong Jang, Jooeun Son, Seungyong Lee
Abstract: Reconstructing articulated objects with multiple movable parts is essential for understanding object structure and enabling physical interaction. However, this reconstruction task poses significant challenges due to the entanglement of geometry, appearance, and motion parameters during optimization. Existing methods rely primarily on photometric supervision, which commonly fails to disentangle these interdependent components, resulting in poor part decomposition with blurred boundaries and geometric artifacts. To address this limitation, we introduce StructureGS, a reconstruction framework for articulated objects that integrates structure-aware guidance into 3D Gaussian Splatting. Our approach leverages oriented bounding boxes of object parts to enforce two key structural properties: spatial coherence, which constrains each part's geometry to remain compact and spatially coherent within its designated region, and structural connectivity, which enforces physically plausible contact relationships between adjacent parts. These properties are realized through structure-aware losses that inject explicit structural constraints into the optimization process. Extensive experiments demonstrate that our method achieves state-of-the-art performance in articulated object reconstruction, producing high-quality results with well-defined part geometries.
Authors: Jian Xiong, Wenbo Jiang, Zihan Wang, Rui Zhang, Wenshu Fan, Hongwei Li, Guowen Xu
Abstract: Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a publicly available handwritten note or signature sample to generate forged recommendation letters or authorization forms, leading to document fraud, identity misuse, and misleading decisions. However, existing protections against unauthorized image editing or synthesis transfer poorly to handwriting style mimicry. Designed for natural images with complex backgrounds, they often optimize perturbations over the whole image. For sparse handwriting images, such global perturbations become conspicuous in blank background regions and largely degrade the visual quality. In this work, we propose InkShield, a proactive writing-style defense that protects reference images before release. InkShield selects a decoy writer to define a style-displacement direction, optimizes perturbations with a frozen handwriting-generation surrogate, and confines them to ink-stroke edges to avoid conspicuous background artifacts. On IAM, the average Top-1/Top-5 rates at which generated samples are retrieved as the target writer by two independent writer evaluators decrease from 11.94%/36.52% to 2.03%/8.79%. Meanwhile, the protected references remain visually close to the originals (LPIPS 0.0078), and the generated text remains readable. InkShield also exhibits transferability to other handwriting generators. Overall, InkShield provides practical protection against unauthorized handwriting style mimicry.
Authors: Bum Jun Kim
Abstract: Reports on how sparsification, compression, and lottery tickets change model behavior have been mixed in the prior literature, with beneficial effects observed in some studies and adverse effects in others. Moreover, prior work has not considered actual deployment conditions, where decision logic is already fixed for the incumbent. To assess these mixed findings from a practical standpoint, we study the production-replacement question at the deployment level, namely whether an accuracy-matched lottery ticket or another sparse challenger can replace an incumbent dense model without reconfiguring downstream decision logic. We therefore audit a broad, protocol-specific panel of deployment-relevant behaviors spanning calibration, OOD response, class-level reliability, representations, and downstream policy decisions, and summarize clean-accuracy-excluded deviations with a behavioral-compatibility distance. Across extensive experiments, sparse candidates repeatedly recover dense-reference accuracy yet remain behaviorally different; in several study-band-matched settings, LTs also show lower corruption accuracy. In small-gap settings with fixed-threshold policy diagnostics, lottery-ticket replacement changes 7% to 10% of accept--review decisions. This churn creates precisely the burden that drop-in replacement is meant to avoid: reconfiguring and revalidating downstream decision logic. These findings establish the limits of clean-accuracy certification: Establishing compatibility with a fixed incumbent is distinct from attributing churn uniquely to sparsity or treating every measured deviation as harmful. Our theory explains the routing result: Even exact pointwise top-1 agreement cannot bound fixed-threshold decision changes, and small confidence shifts near the operating boundary can generate first-order routing churn.
Authors: Zuojin Tang, Feifan Luo, Haoyun Liu, Botai Yuan, Dekang Qi, Ronghan Chen, Yandan Yang, Tong Lin, Xinyuan Chang, Mu Xu, Bin Liu, De Ma, Zhiheng Ma
Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future observations without the structure required for joint generation with robot actions. Existing structured methods add temporal constraints but retain deterministic transition points, so residual errors in locally inferred transitions may propagate and compound under recursive composition. We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian. Reconstruction conditioned on the reference frame grounds the mean in observed visual change, while normalized composition and reversal over equal-gap triplets constrain both the mean and dimension-wise variance. Variance composition uses a lightweight shared-correlation coefficient to account for dependence between adjacent transitions that share an intermediate frame, whereas reversal negates the mean and preserves the variance. For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions. On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos. Under the same controlled $\pi_0$ transfer protocol, it also improves policy performance on MetaWorld MT50, LIBERO, and real-world manipulation tasks. Controlled ablations show that normalized mean constraints account for most of the reconstruction gain, while learned variance and correlation-aware composition provide complementary improvements in downstream control.
Authors: Xinyue Li, Aous Naman, David Taubman
Abstract: This work proposes to augment the lifting steps of the conventional wavelet transform with additional neural network assisted lifting steps. These additional steps reduce residual redundancy (notably aliasing information) amongst the wavelet subbands, and also improve the visual quality of reconstructed images at reduced resolutions. The proposed approach involves two steps, a high-to-low step followed by a low-to-high step. The high-to-low step suppresses aliasing in the low-pass band by using the detail bands at the same resolution, while the low-to-high step aims to further remove redundancy from detail bands, so as to achieve higher energy compaction. The proposed two lifting steps are trained in an end-to-end fashion; we employ a backward annealing approach to overcome the non-differentiability of the quantization and cost functions during back-propagation. Importantly, the networks employed in this paper are compact and with limited non-linearities, allowing a fully scalable system; one pair of trained network parameters are applied for all levels of decomposition and for all bit-rates of interest. By employing the proposed approach within the JPEG 2000 image coding standard, our method can achieve up to 17.4% average BD bit-rate saving over a wide range of bit-rates, while retaining quality and resolution scalability features of JPEG 2000.
Authors: Amir Nazemi, Mohammad Hadi Sepanj, Nicholas Pellegrino, Chris Czarnecki, Paul Fieguth
Abstract: Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, instead drawing only a single sample from a Gaussian distribution from which to generate their solution. In this paper, we introduce a particle-filtering-based framework for a nonlinear exploration of the solution space in the initial stages of reverse SDE methods. Our proposed particle-filtering-based latent diffusion (PFLD) method and proposed problem formulation and framework can be applied to any diffusion-based solution for linear or nonlinear inverse problems. Our experimental results show that PFLD outperforms the SoTA solver PSLD on the FFHQ-1K and ImageNet-1K datasets on inverse problem tasks of super resolution, Gaussian debluring and inpainting.
Authors: Shuangquan Feng, Virginia R. de Sa
Abstract: Automatic facial action unit (AU) recognition is used widely in facial expression analysis. Most existing AU recognition systems aim for cross-participant non-calibrated generalization (NCG) to unseen faces without further calibration. However, due to the diversity of facial attributes across different identities, accurately inferring AU activation from single images of an unseen face is sometimes infeasible, even for human experts -- it is crucial to first understand how the face appears in its neutral expression, or significant bias may be incurred. Therefore, we propose to perform one-frame calibration (OFC) in AU recognition: for each face, a single image of its neutral expression is used as the reference image for calibration. With this strategy, we develop a Calibrating Siamese Network (CSN) for AU recognition and demonstrate its remarkable effectiveness with a simple iResNet-50 (IR50) backbone. On the DISFA, DISFA+, and UNBC-McMaster datasets, we show that our OFC CSN-IR50 model (a) substantially improves the performance of IR50 by mitigating facial attribute biases (including biases due to wrinkles, eyebrow positions, facial hair, etc.), (b) substantially outperforms the naive OFC method of baseline subtraction as well as (c) a fine-tuned version of this naive OFC method, and (d) also outperforms state-of-the-art NCG models for both AU intensity estimation and AU detection. The code is available at https://github.com/ShuangquanFeng/CSN.
Authors: Wenhui Xiao, Remi Chierchia, Rodrigo Santa Cruz, Xuesong Li, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat
Abstract: Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications such as scene understanding, 3D content generation, and robotics. Despite significant research progress, a thorough review of recent innovations, applications, and challenges is lacking. This survey compiles key theoretical advancements and alternative scene representations and investigates emerging challenges. It further explores applications on reconstruction, highlights NeRFs' impact on computer vision and robotics, and reviews essential datasets and toolkits. By identifying gaps in the literature, this survey discusses open challenges and offers directions for future research.
Authors: Xuanming Cui, Jaiminkumar Ashokbhai Bhoi, Chionh Wei Peng, Adriel Kuek, Ser Nam Lim
Abstract: Dynamic Scene Graph Generation (DSGG) aims to capture objects and their evolving relations in videos. Despite recent progress, the practicality and quality of generated scene graphs remain limited compared to the rapid advances in Multimodal Large Language Models (MLLMs). In this work, we revisit DSGG from two fundamental perspectives: task setup and model design. From the task setup perspective, we identify two key limitations of the current recall-oriented evaluation protocol: (i) a severe precision-recall trade-off, and (ii) uninformative and redundant relation generation. To better assess practical usefulness, we introduce five additional metrics that provide a more comprehensive evaluation of the quality of generated dynamic scene graphs. From the model design perspective, we explore directly using MLLMs for scene graph generation and establish a strong MLLM-based DSGG baseline through three design changes. First, we replace the conventional bottom-up pipeline with a top-down reason-then-locate strategy. Second, we reformulate frame-wise dynamic graphs as Temporal Relation Set (TRS) prediction, improving both efficiency and performance. Third, we introduce Importance-Aware Finetuning (IAF) to encourage more relevant and diverse relation generation. Extensive experiments on Action Genome, VidVRD, and PVSG show that our approach consistently achieves state-of-the-art performance.
Authors: Shifang Zhao, Yiheng Lin, Lu Han, Yao Zhao, Yunchao Wei
Abstract: While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To address this gap, we introduce OmniAD, a novel framework that unifies anomaly detection and understanding for fine-grained analysis. OmniAD is a multimodal reasoner that combines visual and textual reasoning processes. The visual reasoning provides detailed inspection by leveraging Text-as-Mask Encoding to perform anomaly detection through text generation without manually selected thresholds. Following this, Visual Guided Textual Reasoning conducts comprehensive analysis by integrating visual perception. To enhance few-shot generalization, we employ an integrated training strategy that combines supervised fine-tuning (SFT) with reinforcement learning (GRPO), incorporating three sophisticated reward functions. Experimental results demonstrate that OmniAD achieves a performance of 79.1 on the MMAD benchmark, surpassing models such as Qwen2.5-VL-7B and GPT-4o. It also shows strong results across multiple anomaly detection benchmarks. These results highlight the importance of enhancing visual perception for effective reasoning in anomaly understanding. All codes and models will be publicly available.
Authors: Niclas Popp, Kevin Alexander Laube, Matthias Hein, Lukas Schott
Abstract: Large foundation models trained on extensive datasets demonstrate strong zero-shot capabilities in various domains. Knowledge distillation has become an established tool for transferring knowledge from foundation models to small student networks when data and model size are constrained. However, the efficacy of distillation is often hampered by limited training data coverage. This can result in a covariate shift between training and test data which in turn can lead the student to exploit spurious features or even shortcut learning. We address this problem by introducing a novel diffusion-based data augmentation strategy that generates images by maximizing the disagreement between the teacher and the student, effectively creating challenging samples that the student struggles with, thus mitigating the problem of covariate shift. Experiments demonstrate that, compared to state-of-the-art diffusion-based data augmentation baselines, our approach is best or second-best in sample mean accuracy and improves the worst group and mean group accuracy on CelebA-HQ, SpuCo Birds and BAR as well as the spurious score on Spurious ImageNet under covariate shift.
Authors: Yujun Wang, Aniri, Jinhe Bi, Soeren Pirk, Yunpu Ma
Abstract: Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mitigate this issue, yet the mechanism remains opaque. We first empirically show that their improvements systematically coincide with redistributions of cross-modal attention. Building on this insight, we propose Attention-Steerable Contrastive Decoding (ASCD), which directly steers the attention scores during decoding. ASCD combines (i) positive steering, which amplifies automatically mined text-centric heads-stable within a model and robust across domains-with (ii) negative steering, which dampens on-the-fly identified critical visual tokens. The method incurs negligible runtime and memory overhead and requires no additional training. Across five MLLM backbones and three decoding schemes, ASCD reduces hallucination on POPE, CHAIR, and MMHal-Bench by up to 38.2 percent while improving accuracy on standard VQA benchmarks, including MMMU, MM-VET, ScienceQA, TextVQA, and GQA. These results position attention steering as a simple, model-agnostic, and principled route to safer, more faithful multimodal generation.
Authors: Pei-Kai Huanga, Ya-Ting Chan, Kuan-Wen Chen, Chiou-Ting Hsu, Xiaoding Wang, Md. Jalil Piran
Abstract: Many remote Heart Rate (HR) measurement methods focus on estimating remote photoplethysmography (rPPG) signals from video clips lasting around 10 seconds but often overlook the need for HR estimation from ultra-short video clips. In this paper, we aim to accurately measure HR from ultra-short 2-second video clips by specifically addressing two key challenges. First, to overcome the limited number of heartbeat cycles in ultra-short video clips, we propose an effective periodicity-guided rPPG estimation method that enforces consistent periodicity between rPPG signals estimated from ultra-short clips and their much longer ground truth signals. Next, to mitigate estimation inaccuracies due to spectral leakage, we propose including a generator to reconstruct longer rPPG signals from ultra-short ones while preserving their periodic consistency to enable more accurate HR measurement. Extensive experiments on four rPPG estimation benchmark datasets demonstrate that our proposed method not only accurately measures HR from ultra-short video clips but also outperform previous rPPG estimation techniques to achieve state-of-the-art performance.
Authors: Nikhil Reddy Varimalla, Yunfei Xu, Meng Fan Wang, Arkadiy Saakyan, Smaranda Muresan
Abstract: As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts. To advance cultural norm awareness evaluation in VideoLLMs, we introduce VideoNorms, a dataset of cultural norm annotations from popular US and Chinese TV shows annotated with adherence or violation labels and (non-)verbal evidence. Through a human-AI collaboration framework, each item was first annotated by a large VideoLLM, and then reviewed by at least three trained monocultural annotators with significant lived experience in the target culture, resulting in a dataset of over 3,000 human judgments. Human verification showed disparity in US and Chinese norm extraction performance, cautioning against fully automatic approaches cultures under-represented in training data. Hierarchical linear modeling analysis of $7$ open-weight VideoLLMs' performance revealed that: 1) models perform worse in Chinese compared to US, particularly for norm adherence prediction; 2) models have more difficulty in providing non-verbal evidence compared to verbal evidence for norm adherence/violation predictions. Ablation studies confirm video modality is indeed necessary for accurate performance, and scaling model size does not yield classification score improvements. Our findings and data contribute to culturally grounded video model training and evaluation.
Authors: Binyan Xu, Fan Yang, Di Tang, Xilin Dai, Kehuan Zhang
Abstract: Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison rate required for a successful attack induces a proportional, and thus noticeable, drop in Clean Accuracy (CA), undermining their stealthiness. This paper presents a new paradigm for clean-image attacks that minimizes this accuracy degradation by optimizing the trigger itself. We introduce Generative Clean-Image Backdoors (GCB), a framework that uses a conditional InfoGAN to identify naturally occurring image features that can serve as potent and stealthy triggers. By ensuring these triggers are easily separable from benign task-related features, GCB enables a victim model to learn the backdoor from an extremely small set of poisoned examples, resulting in a CA drop of less than 1%. Our experiments demonstrate GCB's remarkable versatility, successfully adapting to six datasets, five architectures, and four tasks, including the first demonstration of clean-image backdoors in regression and segmentation. GCB also exhibits resilience against most of the existing backdoor defenses.
Authors: Zhongbin Guo, Jiahe Liu, Wenyu Gao, Yushan Li, Xiaomin He, Chengzhi Li, Ping Jian
Abstract: Text-driven 3D reconstruction requires masks that understand free-form instructions and remain stable under viewpoint changes. We present LISA-3D, a two-stage framework that adapts the instruction-following segmenter LISA with geometry-aware Low-Rank Adaptation (LoRA) layers while keeping the SAM-3D reconstructor frozen. During training, paired RGB-D frames and camera poses define a differentiable reprojection loss that enforces cross-view agreement without additional 3D-text annotations. At deployment, the adapted segmenter can produce an RGBA prompt for SAM-3D from one RGB image; when registered RGB-D views are available, optional logit fusion further improves the prompt. On ScanRefer and Nr3D, geometry-aware tuning improves both 2D masks and lifted 3D reconstructions while updating only 11.6M parameters. Our results separate geometry-aware training gains from optional multi-view inference gains, providing a modular route from language grounding to object-centric 3D reconstruction.
Authors: Chen-Yang Wang, Ge-Peng Ji, Song Shao, Ming-Ming Cheng, Deng-Ping Fan
Abstract: Camouflage relies heavily on context, but current metrics used in camouflaged object segmentation ignore contextual cues. We identify two major drawbacks of these metrics: first, the Dimension Flaw - a predicted foreground map usually contains both pixel labels and probability scores, whereas ground truth provides only one-dimensional binary labels; second, the Range Flaw - these metrics struggle to capture full-range pixel dependencies. Thus, we propose Context-measure, a novel context-aware evaluation paradigm built on a probabilistic pixel correlation framework. It augments the ground truth with pixel-level contextual affinity and builds a perception cycle, achieving greater consistency with human perception. Extensive experiments using four meta-measures show that our Context-measure comprehensively outperforms all widely adopted metrics for camouflaged object segmentation. To our knowledge, this is the first metric designed for camouflaged scenarios. Code is available at https://github.com/pursuitxi/Context-measure.
Authors: Luca Cazzola, Ahed Alboody
Abstract: The acquisition cost for large, annotated motion datasets remains a critical bottleneck for skeletal-based Human Activity Recognition (HAR). Although Text-to-Motion (T2M) generative models offer a compelling, scalable source of synthetic data, their training objectives, which emphasize general artistic motion, and dataset structures fundamentally differ from HAR's requirements for kinematically precise, class-discriminative actions. This disparity creates a significant domain gap, making generalist T2M models ill-equipped for generating motions suitable for HAR classifiers. To address this challenge, we propose KineMIC (Kinetic Mining In Context), a transfer learning framework for few-shot action synthesis. KineMIC adapts a T2M diffusion model to an HAR domain by hypothesizing that semantic correspondences in the text encoding space can provide soft supervision for kinematic distillation. We operationalize this via a kinetic mining strategy that leverages CLIP text embeddings to establish correspondences between sparse HAR labels and T2M source data. This process guides fine-tuning, transforming the generalist T2M backbone into a specialized few-shot Action-to-Motion generator. We validate KineMIC using HumanML3D as the source T2M dataset and a subset of NTU RGB+D 120 as the target HAR domain, randomly selecting just 10 samples per action class. Our approach generates significantly more coherent motions, providing a robust data augmentation source that delivers a +23.1% accuracy points improvement. Animated illustrations and supplementary materials are available at https://lucazzola.github.io/kinemic-page/.
Authors: Haiyun Wei, Fan Lu, Yunwei Zhu, Zehan Zheng, Weiyi Xue, Lin Shao, Xudong Zhang, Ya Wu, Guang Chen
Abstract: Generating realistic and diverse LiDAR point clouds is crucial for autonomous driving simulation. Although previous methods achieve LiDAR point cloud generation from user inputs, they struggle to attain high-quality results while enabling versatile controllability, due to the imbalance between the complex distribution of LiDAR point clouds and the simple control signals. To address the limitation, we propose LiDARDraft, which utilizes the 3D layout to build a bridge between versatile conditional signals and LiDAR point clouds. The 3D layout can be trivially generated from various user inputs such as textual descriptions and images. Specifically, we represent text, images, and point clouds as unified 3D layouts, which are further transformed into semantic and depth control signals. Then, we employ a rangemap-based ControlNet to guide LiDAR point cloud generation. This pixel-level alignment approach demonstrates excellent performance in controllable LiDAR point clouds generation, enabling "simulation from scratch", allowing self-driving environments to be created from arbitrary textual descriptions, images and sketches.
Authors: Anurag Bagchi, Zhipeng Bao, Homanga Bharadhwaj, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert
Abstract: What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pre-trained video diffusion model into an action-conditioned world model, enabling precisely controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models by injecting appropriately compressed motor commands through lightweight conditioning layers. This allows our model to follow actions faithfully while preserving generalization and realism. Our approach scales naturally across embodiments and action spaces -- from 3-DoF mobile robots to 25-DoF humanoids, where predicting egocentric joint-angle-driven dynamics is substantially more challenging. The model produces coherent rollouts for both navigation and manipulation, requiring only modest fine-tuning. To evaluate physical correctness independent of appearance, we introduce the Structural Consistency Score (SCS), which measures whether stable scene elements evolve consistently with the provided actions. Our method improves SCS by up to 65\% over the prior state of the art, Navigation World Models; applies seamlessly to three different video diffusion model architectures; and effectively utilizes Internet priors to generalize to unseen environments, including navigation and manipulation inside paintings. Finally, we demonstrate the applicability of EgoWM to robotic planning.
Authors: Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski
Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but their quality is often degraded by noise from low-dose acquisition, patient motion, or scanner limitations, affecting both clinical interpretation and downstream analysis. Traditional filtering approaches often over-smooth and lose fine anatomical details, while deep learning methods, including CNNs, GANs, and transformers, may struggle to preserve such details or require large, computationally expensive models, limiting clinical practicality. We propose PatchDenoiser, a lightweight, energy-efficient multi-scale patch-based denoising framework. It decomposes denoising into local texture extraction and global context aggregation, fused via a spatially aware patch fusion strategy. This design enables effective noise suppression while preserving fine structural and anatomical details. PatchDenoiser is ultra-lightweight, with far fewer parameters and lower computational complexity than CNN, GAN, and transformer based denoisers. On the 2016 Mayo Low-Dose CT dataset, PatchDenoiser consistently outperforms state-of-the-art CNN- and GAN-based methods in PSNR and SSIM. It is robust to variations in slice thickness, reconstruction kernels, and HU windows, generalizes across scanners without fine-tuning, and reduces parameters by ~9x and energy consumption per inference by ~27x compared with conventional CNN denoisers. PatchDenoiser thus provides a practical, scalable, and computationally efficient solution for medical image denoising, balancing performance, robustness, and clinical deployability.
Authors: Xinchang Wang, Yunhao Chen, Yuechen Zhang, Congcong Bian, Zihao Guo, Xingjun Ma, Hui Li
Abstract: Recent image generators produce photo-realistic content that undermines the reliability of downstream recognition systems. As visual appearance cues become less pronounced, appearance-driven detectors that rely on forensic cues or high-level representations lose stability. This motivates a shift from appearance to behavior, focusing on how images respond to controlled perturbations rather than how they look. In this work, we identify a simple and universal behavioral signal. Natural images preserve stable semantic representations under small, structured perturbations, whereas generated images exhibit markedly larger feature drift. We refer to this phenomenon as robustness asymmetry and provide a theoretical analysis that establishes a lower bound connecting this asymmetry to memorization tendencies in generative models, explaining its prevalence across architectures. Building on this insight, we introduce Robustness Asymmetry Detection (RA-Det), a behavior-driven detection framework that converts robustness asymmetry into a reliable decision signal. Evaluated across 14 diverse generative models and against more than 10 strong detectors, RA-Det achieves superior performance, improving the average performance by 7.81 percent. The method is data- and model-agnostic, requires no generator fingerprints, and transfers across unseen generators. Together, these results indicate that robustness asymmetry is a stable, general cue for synthetic-image detection and that carefully designed probing can turn this cue into a practical, universal detector. The source code is publicly available at Github.
Authors: Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubi\'c, Davide Scaramuzza, Wenhui Wang
Abstract: Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks exploit this low-latency advantage by updating predictions event by event, but still suffer from two bottlenecks: recurrent architectures are difficult to train efficiently on long sequences, and improving accuracy often increases per-event computation and latency. Linear attention is appealing because it enables parallel training and recurrent inference. However, its dense state updates make per-event computation scale with the state size, yielding a poor accuracy-efficiency trade-off for object detection, where accurate localization requires fine-grained spatial states. The key challenge is therefore to introduce sparse state activation that exploits the spatial sparsity of events while preserving efficient parallel training. We propose Spatially-Sparse Linear Attention (SSLA), which introduces a mixture-of-spaces state decomposition and a scatter-compute-gather training procedure, enabling state-level sparsity as well as training parallelism. Building on SSLA, we develop an end-to-end asynchronous linear attention model, SSLA-Det, for low-latency event-based object detection. On Gen1 and N-Caltech101, SSLA-Det achieves state-of-the-art accuracy among asynchronous methods, reaching 0.375 mAP and 0.515 mAP, respectively, while reducing per-event computation by over 20 times compared with the strongest prior asynchronous baseline, demonstrating the potential of linear attention for low-latency event-based vision.
Authors: Shuai Lu, Meng Wang, Jia Guo, Jiawei Du, Bo Liu, Shengzhu Yang, Weihang Zhang, Huazhu Fu, Huiqi Li
Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hindered by lacking domain-specific knowledge. In this work, we identify two structural deficiencies hindering reliable medical reasoning: 1) the Perception Gap, where general-purpose visual encoders fail to resolve fine-grained pathological cues (e.g., microaneurysms); and 2) the Reasoning Gap, where sparse visual evidence is progressively overridden by massive language priors in deeper transformer layers, leading to ungrounded hallucinations. To bridge these gaps, we propose EyExIn, a data-efficient framework designed to anchor retinal VLMs with expert knowledge via a Deep Expert Injection mechanism. Our architecture employs an Expert-Aware Dual-Stream encoding strategy that decouples visual representation into a general stream for anatomical context and a specialized expert stream for pathological semantics. To ensure high-fidelity integration, we design a Semantic-Adaptive Gated Fusion module, which dynamically amplifies subtle lesion signals while filtering irrelevant background noise. Furthermore, we introduce Adaptive Deep Expert Injection to embed persistent "Vision Anchors" by integrating fused visual features as residual biases directly into intermediate LLM layers. This mechanism creates a visual shortcut that forces the reasoning stack to remain strictly grounded in visual evidence. Extensive experiments across four benchmarks demonstrate that our model consistently outperforms massive proprietary systems. EyExIn significantly enhances domain-specific knowledge embedding and achieves state-of-the-art precision in ophthalmic visual question answering, advancing the development of trustworthy ophthalmic AI.
Authors: Dillan Imans, Phuoc-Nguyen Bui, Duc-Tai Le, Hyunseung Choo
Abstract: Retinal fundus imaging enables low-cost and scalable hypertension (HTN) screening, but HTN-related retinal cues are subtle, yielding high-variance predictions. Brain MRI provides stronger vascular and small-vessel-disease markers of HTN, yet it is expensive and rarely acquired alongside fundus images, resulting in modality-siloed datasets with disjoint MRI and fundus cohorts. We study this unpaired MRI-fundus regime and introduce Clinical Graph-Mediated Distillation (CGMD), a framework that transfers MRI-derived HTN knowledge to a fundus model without paired multimodal data. CGMD leverages shared structured biomarkers as a bridge by constructing a clinical similarity kNN graph spanning both cohorts. We train an MRI teacher, propagate its representations over the graph, and impute brain-informed representation targets for fundus patients. A fundus student is then trained with a joint objective combining HTN supervision, target distillation, and relational distillation. Experiments on our newly collected unpaired MRI-fundus-biomarker dataset show that CGMD consistently improves fundus-based HTN prediction over standard distillation and non-graph imputation baselines, with ablations confirming the importance of clinically grounded graph connectivity. Code is available at https://github.com/DillanImans/CGMD-unpaired-distillation.
URLs: https://github.com/DillanImans/CGMD-unpaired-distillation.
Authors: Jinzhe Tu, Ruilei Guo, Zihan Guo, Junxiao Yang, Shiyao Cui, Minlie Huang
Abstract: Recent works have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a perceptual misalignment between current MLLMs and humans, and also introduces potential safety concerns. To systematically investigate this failure, we introduce IlluChar, a comprehensive and challenging illusion dataset, and uncover a key underlying mechanism for the models' failure: high-frequency attention bias, where the models are easily distracted by high-frequency background textures in illusion images, causing them to overlook hidden patterns. To address the issue, we propose the Strategy of Multi-Scale Perception (SMSP), a plug-and-play framework that aligns with human visual perceptual strategies. By suppressing distracting high-frequency background signals, SMSP generates images closer to human perception. Our experiments demonstrate that SMSP significantly improves the performance of all evaluated MLLMs on illusion images, for instance, increasing the accuracy of Qwen3-VL-8B-Instruct from 13.0% to 84.0%. Our work provides novel insights into MLLMs' visual perception, and offers a practical and robust solution to enhance it. Our code is publicly available at https://github.com/Tujz2023/SMSP.
Authors: Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev
Abstract: In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs.
Authors: Zijian He, Renjie Liu, Yihao Wang, Weizhi Zhong, Huan Yuan, Kun Gai, Guangrun Wang, Guanbin Li
Abstract: World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators repeatedly extend existing scenes under user control. Motivated by this gap, we study text-guided 3D scene expansion via free-form view insertion. Starting from a real scene captured by multi-view images, a user specifies a text expansion intent, which a generative model materializes as an inserted view extending the scene coverage. Unlike simple object editing or style transfer within a fixed scene, the inserted view may be 3D-misaligned with the original reconstruction, introducing geometric shifts, hallucinated content, or view-dependent artifacts that disrupt global multi-view consistency. To address this challenge, we propose SceneExpander, which applies test-time adaptation to a parametric feed-forward 3D reconstruction model with two complementary distillation signals: anchor distillation stabilizes the captured scene using geometric cues from the captured views, while inserted-view self-distillation retains insertion-supported predictions to accommodate the misaligned view. Experiments on ETH scenes and online data demonstrate improved expansion behavior and reconstruction quality under misalignment.
Authors: Shuai Xiang, James Burridge, Shouyang Liu, Hao Lu, Tokihiro Fukatsu, Yinqiang Zheng, Wei Guo
Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organs, growth stages, and field conditions. General-purpose vision foundation models offer a natural route to label efficiency, but their web-scale pretraining objectives transfer weakly to agricultural imagery, where semantics are often determined by fine organ geometry inside repetitive, texture-dominated scenes. We introduce SPROUT, a diffusion foundation model for multi-crop plant phenotyping. SPROUT learns from 2.6~million unlabeled open-field images using a VAE-free pixel-space Diffusion Transformer, and selects transferable features with a label-free effective-rank criterion over denoising timesteps. This design shifts pretraining from crop-based invariance to structure-preserving denoising, making the representation better aligned with dense phenotyping tasks. We evaluate SPROUT across dense phenotyping tasks, including organ segmentation, crop-weed parsing, depth estimation, and counting. SPROUT consistently improves over strong web-pretrained baselines, with the largest gains on dense structural prediction, and shows favorable label and compute efficiency compared with general-purpose and crop-specific foundation models.
Authors: Shaoyang Cui, Lingbei Meng, Yaodi Luo, Peize He
Abstract: Video-grounded numerical reasoning requires Vision-Language Models (VLMs) to identify, track, and combine quantitative evidence across frames, actions, and scene changes. Existing benchmarks provide fragmented coverage: general VideoQA includes counting among broader tasks, while dedicated benchmarks focus on repetition counting, ultra-long-video enumeration, or instructional mathematics. We introduce VidNum, a manually curated and independently verified benchmark containing 1,167 multiple-choice questions. Its three task groups distinguish Direct and Distinct Enumeration, Conditioned and Structured Enumeration, and Compositional Quantitative Reasoning. Question-level annotations further identify the evidence target, counting structure, and required reasoning operation. The best evaluated VLM reaches 59.8% accuracy, compared with 98.2% for human annotators, and no evaluated open-weight model exceeds 45%. Stratified analyses reveal that failures are not uniformly distributed: structured target construction and action-grounded compositional reasoning form recurring bottlenecks across models. Zero-shot chain-of-thought prompting is not a reliable remedy: it recovers some errors but breaks previously correct answers, with effects that vary across models and task structures. VidNum therefore supports diagnostic analysis beyond a single aggregate score.
Authors: Vishal V. Batchu, Michelangelo Conserva, Alex Wilson, Anna M. Michalak, Varun Gulshan, Philip G. Brodrick, Andrew K. Thorpe, Christopher V. Arsdale
Abstract: Anthropogenic methane (CH4) point sources are critical drivers of near-term climate forcing, safety hazards, and system-inefficiencies. Space-based imaging spectroscopy is an emerging tool for identifying emissions globally, but existing approaches largely rely on manual plume identification. Here, we present the Methane Analysis and Plume Localization with EMIT (MAPL-EMIT) model, an end-to-end vision transformer framework that leverages the complete radiance spectrum from the Earth Surface Mineral Dust Source Investigation (EMIT) instrument to jointly retrieve methane enhancements across all pixels within a scene. This approach brings together spectral information with spatial context to significantly lower detection limits. MAPL-EMIT simultaneously supports enhancement quantification, plume delineation, and source localization, even for overlapping plumes. The model was trained on 3.6 million physics-based synthetic plumes injected into global EMIT radiance data. Synthetic evaluation confirms the model's ability to identify plumes with high recall and precision and to capture weaker plumes relative to existing matched-filter approaches. On real-world benchmarks, MAPL-EMIT captures 84% of known hand-annotated NASA-L2B plume complexes across a test set of 1084 EMIT granules, while capturing roughly 1.5 times as many plausible plumes compared to human analysts. Further verification against coincident airborne data, top-emitting landfills, and controlled release experiments confirms the model's ability to identify previously uncaptured sources. By incorporating model-generated metrics such as spectral fit scores and estimated noise levels, the framework can limit false-positives. Overall, MAPL-EMIT enables high-throughput implementation on the full EMIT data catalog, shifting methane monitoring to a rapid, scalable paradigm for global plume mapping at the facility scale.
Authors: Wei Bao, Yuehan Wang, Tianhang Zhou, Siqi Li
Abstract: The integration of frame-based RGB cameras with event streams constitutes a promising paradigm for robust object detection under challenging dynamic conditions. Nevertheless, effectively modeling intricate multi-modal interactions and reconciling the semantic heterogeneity between RGB and event data remain formidable challenges for high-precision detection. In this paper, we present Hyper-FEOD, a novel high-performance detection framework that synergistically strengthens cross-modal representation learning through two core hypergraph-driven components. Specifically, we first design a Sparse Hypergraph-enhanced Cross-Modal Fusion (SHCF) module that exploits event activity cues to identify motion-critical sparse tokens and performs high-order relational reasoning through hypergraph modeling. This design effectively captures intricate high-order dependencies and rich contextual correlations across modalities. Second, we develop a Fine-Grained Mixture-of-Experts (FG-MoE) module tailored to handle the heterogeneous semantic demands arising from distinct visual regions. By deploying specialized hypergraph experts with varying hyperedge connectivity pattern and incorporating a spatial gating mechanism, FG-MoE adaptively routes features to enable precise enhancement at target regions. Coupled with an auxiliary router loss, the proposed framework ensures stable end-to-end training and optimal feature refinement. Comprehensive experiments conducted on widely-adopted RGB-Event benchmarks show that Hyper-FEOD delivers superior detection performance and consistently outperforms existing state-of-the-art approaches by a notable margin.
Authors: Kaizhen Tan, Yang Feng, Heqing Du, Hanzhe Hong, Siru Tao, Xin Xu
Abstract: Visual token pruning is widely used to reduce the inference cost of multimodal large language models (MLLMs), but it is usually evaluated only by accuracy. We study how pruning affects calibration, defined as the agreement between confidence and correctness, and show that the selection rule matters more than the token budget alone. On POPE with LLaVA-1.5, coverage-based pruning from 576 to 128 tokens reduces expected calibration error from 0.041 to 0.016 without a statistically significant accuracy loss. In contrast, attention-based selection preserves confidence while accuracy deteriorates, becoming less calibrated than random pruning at aggressive budgets. Across pruning conditions, kept-set coverage is strongly associated with accuracy (Spearman $\rho=+0.89$) but not with mean confidence ($\rho=-0.03$), producing a strong inverse relation with overconfidence ($\rho=-0.92$); controlled kept-set interventions support this evidence-coverage account. Two boundaries limit it: query-conditioned FastV is more overconfident than its coverage predicts, and on language-prior-dominated ScienceQA, coverage ceases to order calibration. The selector ordering otherwise generalizes to GQA and LLaVA-NeXT, and coverage beats random on Qwen2-VL, although the calibration gain over the unpruned model is task- and model-dependent. We also identify an evaluation pitfall in FastV: zeroing rather than removing pruned tokens can reduce accuracy to chance. Visual token pruning therefore changes confidence quality as well as efficiency, and calibration should be evaluated alongside accuracy when comparing pruning methods.
Authors: Yikun Liu, Yuan Liu, Haicheng Wang, Zhongyin Zhao, Le Tian, Xiao Zhou, Jiangchao Yao, Yanfeng Wang, Weidi Xie
Abstract: Large Multimodal Models (LMMs) excel at visual perception but struggle with real-time, knowledge-intensive queries due to their reliance on static parametric knowledge. While multimodal search agents offer a promising solution, developing them from vanilla LMMs presents two major challenges: the lack of open recipes to cultivate search agency from scratch, and the severe context explosion (attention dilution) that occurs during long-horizon multi-turn investigations. In this paper, we address both challenges by developing a native multimodal search agent. First, we introduce an open training recipe featuring Agentic Seeding, a formative training stage that bootstraps tool-use and planning abilities directly from a non-agentic foundation. Second, to overcome the context bottleneck, we propose V-Fold, an adaptive memory management mechanism. V-Fold retains recent interactions as high-fidelity text while folding stale historical context into the visual space via rendering, exploiting the model's cross-modal alignment to preserve raw evidence without text token redundancy. Combining these innovations, we present POINTS-Seeker-8B, which achieves state-of-the-art performance among models of comparable scale across six multimodal search benchmarks.
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: Yagiz Nalcakan, Hyeongjin Ju, Incheol Park, Sanghyeop Yeo, Youngwan Jin, Shiho Kim
Abstract: Vision foundation models (VFMs) pretrained on large-scale RGB data provide strong general-purpose representations, yet infrared perception, which is essential for robotics and driving in low light and adverse weather, still relies on backbones built per sensor. Existing transfer methods bridge the visible-infrared gap for only a single band or a single RGB-IR pair, leaving no unified backbone that spans the infrared spectrum. We present SpectraDINO, a modality-conditioned adaptation of an RGB vision foundation model that supports NIR, SWIR, and LWIR with a single shared ViT. All modality-specific behavior is conditioned on the active sensor via lightweight input stems, learned modality embeddings, and per-modality bottleneck adapters, while the transformer weights remain shared. We propose a staged protocol to distill the frozen DINOv2 teacher into a spectral student via cosine distillation, symmetric contrastive alignment, patch-level correspondence, and a queue-based neighborhood-preservation loss, and then selectively fine-tune the deeper blocks to adapt without forgetting RGB priors. Across seven detection and segmentation benchmarks spanning all three infrared bands, this single conditioned backbone matches or surpasses modality-specific methods, improving mIoU over the best published results by 2.6 points on FMB and 1.4 on SemanticRT, and exceeding identically fine-tuned foundation-model baselines by 2.7 mAP on SWIR detection.
Authors: Paarth Prasad, Ruchika Malhotra
Abstract: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.
Authors: Qiming Li, Zekai Ye, Xiaocheng Feng, Weihong Zhong, Libo Qin, Ruihan Chen, Lei Huang, Baohang Li, Kui Jiang, Yaowei Wang, Ting Liu, Bing Qin
Abstract: Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or decoding strategies which significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly enhanced when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-guided Visual Attention Steering (CAST), a training-free, plug-and-play hallucination mitigation method that leverages the attention activation pattern corresponding to caption queries to enhance LVLMs' visual perception capability. Specifically, we use probing techniques to identify attention heads that are highly sensitive to caption queries and estimate optimized steering directions for their outputs. This steering strengthens LVLM's fine-grained visual perception capabilities, thereby effectively mitigating object hallucination. CAST reduced object hallucination by an average of 6.03% across five widely used LVLMs and five benchmarks including both discriminative and generative tasks, demonstrating state-of-the-art performance while adding little inference cost and preserving other foundational capabilities.
Authors: Yijing Wang, Ruonan Li, Qilin Wang, Rongqiang Zhao, Jie Liu
Abstract: LiDAR-based semantic segmentation is essential for autonomous-driving perception, yet dense point-wise annotations are costly, and long-tailed outdoor scenes make small safety-critical objects difficult to discover without supervision. Existing unsupervised methods face three key challenges: they struggle to preserve small and sparsely observed objects under substantial scale variation, have difficulty enforcing intra-region consistency and inter-region discrimination during cross-modal transfer, and lack an efficient feature-preserving mechanism for contextual propagation over superpoint graphs. We therefore propose DDS, an unsupervised 3D semantic segmentation framework. First, a coarse-to-fine multi-granularity mask cascade provides complementary 3D region cues for objects across different scales, improving the preservation of small and sparsely observed objects. Second, region-guided multi-level distillation transfers self-supervised visual knowledge through point-level alignment, mask-level prototype alignment, and prototype-level contrastive learning, enhancing intra-region consistency and inter-region discrimination. Third, restart-based graph diffusion efficiently propagates contextual information among superpoints while anchoring the refined representation to the initial distilled features and avoiding explicit graph eigendecomposition. Experiments on real-world driving datasets show that DDS outperforms representative unsupervised baselines, improving oAcc, mAcc, and mIoU by up to 2.9%, 9.7%, and 4.1%, respectively. These results demonstrate the effectiveness and transferability of DDS for unsupervised 3D scene understanding in autonomous-driving scenarios.
Authors: Amrita Mazumdar, Seonwook Park, Rajarshi Roy, Nikhil Srihari, Shengze Wang, Yuhao Zhou, Julia Wang, Koki Nagano, Shalini De Mello
Abstract: Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonverbal cues, such as nods, smiles, and gestures. To support successful human-agent interaction, agents must model full-duplex audiovisual conversation; however, existing full-duplex benchmarks evaluate only speech. In this work, we present VideoFDB, the first benchmark to evaluate full-duplex audio-visual-to-audio-visual (AV2AV) conversational agents. VideoFDB contributes (i) 237 dyadic clips spanning 11 nonverbal conversational dynamics from real-world video calls, (ii) a taxonomy separating perception from generation behaviors, and (iii) a rubric-based LM-as-judge evaluation framework with interpretable axes for assessing conversational quality with respect to nonverbal conversational dynamics. Across open- and closed-source vision-speech agents, we find systematic failure modes: captioning collapse and visual-stream ignorance, and we show that current systems exploit vision for explicit visual question answering but not for the streaming joint audiovisual grounding required in natural conversation. We further evaluate cascaded speech-to-avatar systems and find that their architecture fundamentally precludes the production of full-duplex nonverbal cues. As the first benchmark for full-duplex AV2AV interaction, VideoFDB establishes a foundation for systematic evaluation and, we hope, will accelerate the advancement and development of next-generation multimodal conversational agents.
Authors: Hang He, Chuhuai Yue, Chengqi Dong, Chengcheng Wan, Ting Su, Haiying Sun, Jiajun Chai, Xiaohan Wang, Guojun Yin
Abstract: Visual DeepSearch tasks require multimodal large language models (MLLMs) to resolve complex visual queries by repeatedly inspecting image regions, grounding reasoning in visual evidence, and connecting fine-grained clues across multiple steps. However, existing benchmarks primarily evaluate single-step visual understanding or isolated visual-query response generation. They have limited difficulty, limited search horizons, and single-pass image inspection, and thus fail to evaluate models' ability to iteratively revisit visual evidence and reason across multiple steps. In this work, we introduce VistaHop, a benchmark designed specifically to evaluate Visual DeepSearch. It evaluates repeated image inspection, visual-anchor grounding, and long-horizon evidence traversal across different visual regions. VistaHop comprises 600 images, 25 visual search scenarios, and 600 Visual DeepSearch tasks. We also propose VistaArena, a unified evaluation framework that supports tool-based interactions, including visual retrieval, image inspection, and evidence-grounded reasoning. Experiments show that even state-of-the-art MLRMs remain far from solving VistaHop, with the best-performing model, SenseNova-MARS-32B, achieving only 26.33% Pass@1. These findings highlight the importance of specialized benchmarks and improved agentic methods for Visual DeepSearch.
Authors: Enhan Zhao, Wei Wu, Yuanrui Zhang, Xueliang Zhao, Di He
Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs). Existing approaches largely rely on large-scale, statically curated datasets, where all training samples are treated uniformly regardless of the model's evolving capabilities. This static paradigm is inherently data-inefficient: training capacity is often spent on samples that are either trivial or overly difficult for the model at its current stage. To address this limitation, we propose Ouroboros-Spatial, a self-evolving training framework in which the model plays dual roles as a proposer and a solver. In each iteration, a frozen proposer generates spatial question-answer (QA) pairs from 3D scene metadata and raw video frames, together with executable code for deriving reliable ground truth. A learnable solver is then fine-tuned on the accepted samples, and its per-sample prediction confidence is used as a difficulty signal. This signal is fed back to the proposer in the next iteration, guiding it to generate questions better matched to the solver's current capabilities. Through this closed-loop design, the training distribution co-evolves with model ability, reducing redundant trivial examples while filtering out ambiguous or uninformative samples with limited learning value. Across six spatial reasoning benchmarks, Ouroboros-Spatial substantially improves Qwen3-VL-4B and Qwen3-VL-8B while using an order of magnitude fewer training examples than recent large-scale curated datasets. On VSI-Bench, it yields absolute gains of 9.9 and 6.8 points for the 4B and 8B models, respectively, enabling both to outperform a wide range of strong open-source and proprietary baselines.
Authors: Zhou Tao, Fang Zhang, Zewen Ding, Shida Wang, Xiaokun Sun, YongXiang Hua, Haoyu Cao, Linli Xu
Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even when high-resolution inputs preserve the necessary local details. We identify this limitation as visual context rot: decisive evidence may exist in the full image, yet fail to be reliably selected and used amid redundant visual context. We propose LOCUS (LOcal visual CUe Search), a training framework that teaches MLLMs to internalize local evidence search through a verifiable proxy task. During training, LOCUS provides a local crop as a visual cue and optimizes the model to recover its spatial support in the full image using an IoU-based reward. The visual cue is used only during training, leaving the standard image-question inference interface unchanged. Experiments across fine-grained perception, hallucination, general understanding, and reasoning benchmarks show that LOCUS improves localization-sensitive visual understanding while preserving broad capabilities. Attention analyses further indicate stronger focus on task-relevant evidence regions, suggesting that training-time visual cue search provides an effective route to internalized fine-grained evidence selection.
Authors: Zhongqiang Song, Guanying Chen, Yuqi Zhang, Yin Zou, Chuanyu Fu, Zhiyuan Yuan, Chuan Huang, Shuguang Cui, Xiaochun Cao
Abstract: This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level scenarios, models trained primarily on street-view and indoor datasets exhibit significant domain gaps when applied to aerial viewpoints. To tackle these challenges, we introduce AerialMetric, a benchmark dataset designed to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints. The dataset consists of four complementary subsets collected from different sources, jointly covering real-world photogrammetry data, controlled aerial acquisition settings, photorealistic synthetic scenes, and in-the-wild Internet imagery. Totally, AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth. Based on this dataset, we conduct systematic evaluations of existing state-of-the-art models under aerial settings and investigate the impact of viewpoint, altitude, and camera parameters on metric depth prediction. In addition, by fine-tuning representative metric depth model on our dataset, we establish a comprehensive aerial benchmark and achieve state-of-the-art performance across diverse aerial imagery. Our dataset, code, and model weight are publicly available at https://kuieless.github.io/AerialMetric-ECCV2026-page/.
URLs: https://kuieless.github.io/AerialMetric-ECCV2026-page/.
Authors: Baiqin Wang, Sen Chen, Jiankuo Zhao, Xiangyu Liu, Zhen Lei, Xiangyu Zhu
Abstract: Conversational talking face generation has recently attracted increasing attention, aiming to synthesize interactive talking videos where characters speak, listen, and respond dynamically to each other. This task presents three core challenges: 1) Flexibility: enabling multi-round dialogues with an arbitrary number of participants; 2) Naturalness: maintaining coherent motion and appropriate non-verbal feedback throughout the interaction; and 3) Efficiency: achieving real-time generation and low computation overhead for long-term continuous online conversation. Despite recent advances, existing methods still fall short in balancing all three requirements. To bridge this gap, we introduce InterTalk, a novel and efficient framework designed for highly interactive conversational talking face generation. Built upon a motion-based architecture, InterTalk supports real-time conversation synthesis. Our method achieves strong flexibility by explicitly modeling multi-round conversational dynamics among each participant, eliminating constraints on their numbers. To enhance interactivity, we incorporate motion feedback from multiple participants and introduce an iterative generation strategy for more natural behaviors. Besides, we disentangle motion into several facial components, enabling targeted refinements for natural response such as precise lip sync and realistic eye blinking. Finally, we construct a new multi-person conversational dataset and enrich it with 3D face-based data augmentation. Extensive experiments demonstrate that InterTalk achieves superior interaction quality while maintaining real-time performance at 30 FPS.
Authors: Meng Du, Hongchang Chen, Ran Li, Junjie Zhang, Qi Ouyang, Shibo Zhang, Shuxin Liu
Abstract: Rapid advances in AI video generation pose increasing security risks and call for reliable detectors with strong cross-domain generalization. Although existing methods perform well under in-domain evaluation, their performance degrades substantially on unseen generators. A key reason is shortcut learning, where detectors rely on domain-specific bias rather than intrinsic forensic cues. To address this issue, we propose G2VD, a generalizable AI-generated video detection framework based on counterfactual intervention and causal disentanglement. First, G2VD introduces a counterfactual intervention pipeline (CFIPipeline) that constructs counterfactual samples through VAE-based reconstruction and subsequent frequency-domain and pixel-domain alignment, thereby weakening spurious correlations between domain-specific bias and authenticity labels. Building on this intervention, we further design a causal disentanglement classifier that combines two domain-anchored branches with complementary objectives and a constraint based on the Hilbert-Schmidt Independence Criterion (HSIC), encouraging the causal and non-causal representations to capture intrinsic forensic cues and domain-specific bias, respectively. Experiments across four public datasets demonstrate strong cross-domain performance and consistent gains over baseline methods. In the challenging GenVidBench setting, G2VD achieves over 90\% overall ACC, with improvements of 0.194 in F1 and 0.104 in AUC over comparable state-of-the-art methods, while using only 10\% of the available training data. Code is available at https://github.com/DMOSCAR-98/G2VD.
Authors: Keonvin Park, Yong Ann Voeurn, Hyeokjun Kweon, Doyun Lee
Abstract: Reliable seam segmentation is essential for autonomous robotic welding in construction, where harsh illumination, specular reflections, and thin weld geometries often degrade segmentation performance. This study proposes a reflection-robust seam segmentation framework that enhances a BiSeNetV2 backbone through transfer learning and a hybrid Cross-Entropy--Lov\'asz loss. Rather than increasing architectural complexity, the proposed framework improves reflection robustness through learning-stability-oriented optimization. Experimental results show that the proposed method achieves 81.76\% Joint IoU and 90.73\% mIoU, improving Joint IoU by +22.36 percentage points over the OHEM-based baseline while maintaining identical FLOPs, parameter count, and inference speed. The proposed approach also recovers 96.33\% of severe zero-IoU failure cases under reflective conditions. Comparative experiments across BiSeNetV2, DeepLabV3+, UNet, and SegFormer further demonstrate that the proposed optimization strategy is particularly effective for lightweight real-time segmentation architectures. Qualitative analyses additionally show improved seam continuity and reflection robustness in challenging welding environments. These findings suggest that the proposed framework provides a practical and lightweight perception solution for robotic welding applications involving reflective metallic surfaces.
Authors: Sharayu N. Deshmukh, Md Rashidunnabi, Nelton Tiago Gemo, Kurundkar G. D., Mahamune M. R., Nilesh K. Deshmukh
Abstract: Deepfake image detection is served by three fundamentally different paradigms - commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors - that are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. Models are ranked primarily by the Matthews correlation coefficient (MCC), with ROC-AUC reported as a threshold-independent measure of ranking ability. Rather than maximizing size, it emphasizes real-world difficulty through a taxonomy of eight edge-case families such as face swaps, text-to-video stills, AI photo edits, avatar compositing, opaque-provenance images, and compressed research frames. Commercial APIs achieve the strongest median performance, followed by vision LLMs and open-source detectors, though individual open-source models remain competitive with the best LLMs. Across all 36 models, MCC and ROC-AUC are strongly correlated (Pearson r ~ 0.86); the more consequential finding is narrower and one-directional: a subset of otherwise strong rankers are miscalibrated at their shipped default threshold, so a high ROC-AUC can overstate real-world deployability. Separately, raw accuracy and F1 are unreliable on this corpus's imbalanced class split, since a model that predicts "fake" indiscriminately scores deceptively well on both while offering no real discriminative skill. No single metric is safe in isolation: MCC and specificity should always accompany ROC-AUC and accuracy. We release the complete evaluation framework and results. Code and data: https://github.com/sharayu-20/vendorbench-100
Authors: Alessia Infantino, Claudio Schiavella, Irene Amerini
Abstract: Recent advances in generative Artificial Intelligence have made synthetic face images increasingly realistic, creating new challenges for multimedia forensics. Source attribution methods should identify the generator of an image when the source is known, but also handle samples produced by unseen models. Most existing approaches, however, address synthetic face attribution in a closed-set setting, assuming that test samples can only originate from generators observed during training. This assumption does not hold in real-world scenarios, where new generators continuously appear and detecting an image as unknown is not sufficient, since rejected samples should also be organized according to their underlying sources. We introduce Face-Trace, a pipeline for open-set synthetic face source attribution that combines known generator classification, energy-based rejection, and unknown generator discovery. A classifier trained on frozen I-JEPA embeddings attributes known generators, while rejected samples are represented by combining projected I-JEPA features with complementary forensic traces and grouped to identify coherent sets of samples produced by unknown generators. We also extend the discovery stage to an incremental scenario, where rejected samples arrive over time. Experiments on the WILD dataset show 96.73% closed-set attribution accuracy, while rejection reaches 71.25% balanced accuracy and rejected samples are clustered into meaningful unknown-generator groups, with an Adjusted Rand Index of 0.81, a Normalized Mutual Information of 0.90, and an overall purity of 87.74%. In the incremental setting, the discovered generator space is progressively extended while maintaining a final purity of 99.23%, and cross-dataset experiments suggest that the pipeline can operate beyond the original data distribution.
Authors: Tomasz Stanczyk, Yuan Gao, Hardik Agarwal, Seongro Yoon, Tiantao Zhang, Vincent Calcagno, Francois Bremond
Abstract: Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately evaluate long-term identity preservation, where objects must be tracked consistently over extended durations. We introduce WaspMOT, a benchmark designed to address this gap through long-duration tracking of Trichogramma wasps in controlled ecological experiments. The dataset contains 10 sequences of approximately 12,000 frames each (over 8 minutes at 25 FPS), with dense MOTChallenge annotations and oracle detections to isolate association performance. Unlike existing benchmarks, WaspMOT forms a closed-set tracking scenario where all individuals remain present throughout the sequence, requiring consistent identity assignment across thousands of frames despite abrupt jumps, occlusions, and highly similar appearance. We establish a benchmark by evaluating five tracking-by-detection methods, including ByteTrack, BoT-SORT, C-BIoU, OC-SORT, and McByte, under a unified protocol. Results show that all methods suffer from significant trajectory fragmentation, highlighting the difficulty of long-term identity preservation even with perfect detections. A simple spatial tracklet stitching baseline consistently improves performance, indicating that substantial gains remain possible. WaspMOT provides a new benchmark for studying long-term association and reveals limitations of current tracking approaches that are not observable on conventional datasets. The benchmark will be made publicly available at the project repository: https://github.com/tstanczyk95/WaspMOT/ .
Authors: Xiaoyun Dong, Qian Xu, Yun Wang, Yang Lu, Jen-Ming Wu, Jianping Wang
Abstract: Reconstructing 4D driving scenes in the wild (e.g., internet and AI-generated videos) is critical for diverse autonomous driving simulation. While recent Gaussian Scene Graph (GSG) methods achieve impressive visual quality, they heavily rely on precise priors, such as accurate camera poses and LiDAR depth, or manual annotations. When initialized with noisy priors estimated from in-the-wild videos, existing GSG methods suffer from optimization ambiguity (e.g., entangling camera and agent poses) and topological failures (e.g., missing objects), causing severe rendering artifacts. To enable robust in-the-wild reconstruction, we introduce Adaptive Gaussian Graph (AGG), a self-correcting 4D framework. Our Semantically-Guided Tick-Tock Strategy leverages 2D foundation features to explicitly decouple static background and camera pose updates from dynamic agent learning. Concurrently, our Adaptive Topology Evolution module actively rectifies graph structures by spawning missing agents, reassigning misclassified Gaussians, and pruning false positives. To rigorously evaluate this in-the-wild setting, we introduce Wild-30, a challenging benchmark of internet and generative videos. Extensive experiments on KITTI and Wild-30 validate that AGG consistently outperforms state-of-the-art approaches in visual fidelity and robustness under noisy priors.
Authors: Hengyuan Zhang, Jingna Sun, Meiguang Jin, Junfeng Ma
Abstract: Production-ready audio-driven avatar generation requires efficient inference without sacrificing fidelity or motion expressiveness. However, existing acceleration methods often compromise quality through restrictive architectural choices, such as causal attention and short temporal horizons, or by reducing model capacity and resolution. Without such compromises, we propose AptAvatar, a 14B-parameter long-form audio-driven avatar generation framework that delivers fast and expressive inference. For efficiency in production-level applications, AptAvatar addresses the extreme two-step generation challenge. To bridge the gap between the multi-step teacher model and the two-step student model, we introduce Endpoint-Anchored Distribution Distillation. It augments vanilla distribution matching with a dedicated Anchor Score Estimator trained on the trajectory-endpoint distribution defined from a frozen pretrained 4-step bridge generator. This provides an attainable endpoint-level anchor for the evolving two-step student. To improve long-horizon consistency, we further introduce Self-Generated History Replay, which reuses cached outputs from earlier generator checkpoints as history conditions during chunk-wise training. This approximates inference-time conditioning on self-generated histories without costly online rollouts, mitigating quality degradation from accumulated history errors. Extensive experiments demonstrate that AptAvatar generates vivid 720p long-form avatar videos with only 2 NFEs, achieving a 60x speedup while preserving visual fidelity and long-horizon identity. Code is available at https://github.com/TaoLiveAIGC/AptAvatar
Authors: Sungguk Cha, DongWook Kim, Mintae Kim, Youngsub Han, Byoung-Ki Jeon, Sangyeob Lee
Abstract: Finding a long document relevant to a multi-part request is not the same as establishing that it contains every requested piece of evidence. We study this gap for conjunctive document retrieval, where two or three explicit conditions must be supported on different pages of one document. We use n-Clue as a controlled measurement instrument: 1{,}000 queries over 2{,}021 documents pair all-condition golds with naturally occurring documents that satisfy only a subset, and a complete-first success requires a top-10 gold to precede every released subset qrel. Across 70 configurations, condition-wise decomposition improves two dense backbones by 6.8--7.3 points and lexical--visual fusion adds 8.7, while four generic rerankers all reduce Gold-NDCG; these directions replicate on a four-source stress set. Scaling one dense family from 0.6B to 8B changes complete-first success by 0.0 points. The strongest displayed hybrid illustrates the resulting gap: it finds a gold for 81.1\% of queries but succeeds complete-first on only 35.8\%, and the gap persists across condition count, target length, candidate density, query rendering, and the four-source stress set. Finally, page-aware visual systems surface stored support for every condition on only 5.1--5.3\% of queries. These results identify condition coverage, rather than gold discovery alone, as the central bottleneck.
Authors: Shengyi Wang, Niantong Li, Guangzheng Hu, Hong Qi, Fei Ding, Weixu Qiao, Jinlin Wang, Xiaotong Lv, Peng Han, Zimeng Li, Fanshu Ding, Yushu Wang, Han Wu, Jingjing Chen, Chongxiao Wang, Yanhao Wu, Chenglong Huang, Xiaoqian Zhu, Jie Tian, Hua Li, Jingjing Fan, Mingshuang Tang, Zhong Li, Hengxia Qiang, Weibin Chen, Jinyang Zhen, Bing Zhao, Lin Qu, Jing Li, Hu Wei
Abstract: Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria by which films are actually made and judged, so they assess basic video plausibility rather than film-grade craft. We introduce FilmBench, a text-to-video (T2V) and reference-to-video (R2V) benchmark grounded in the professional Cinematic Language of the film- academy tradition and co-developed with directors and faculty from the Beijing Film Academy and the Hujing Digital Media & Entertainment Group film studio. It rests on three choices. First, prompts are reverse-engineered from clips of award-winning films spanning 20 cinematic genres and chosen by professional directors, so every prompt is anchored to a verified live-action reference; the prompts follow real shot lists, and most script multiple shots (1,056 of the 1,169 prompts are multi-shot), unlike prior single-clip benchmarks. Second, evaluation follows a three-level Cinematic taxonomy of 3 axes, 12 components and 35 (T2V) +3 (R2V-only) sub-metrics. Third, we develop an in-house expert-grade automatic evaluation agent and open-source its core suite of Cinematic Language operators (FilmOps). Benchmarking leading video generation models (9 for T2V, 7 for R2V), the evaluator reproduces the human model ranking at model-level Spearman \r{ho} = 0.95 (T2V) and 0.96 (R2V). Scores fall well below prior web-style benchmarks, with two consistent gaps in dynamic aesthetics and a marked single- to multi-shot performance drop that widens for weaker models.
Authors: Hang Xing, Guangjun Liu, Yan Xia, Xueming Ding
Abstract: Few-shot segmentation (FSS) commonly assumes clean pixel-level support masks, yet practical support supervision often uses boxes, scribbles, coarse masks, or pseudo-masks. These weak annotations may include texture-similar distractors and background context alongside the target, contaminating class prototypes or visual prompts before query prediction. We introduce SADe, a predictor-agnostic support decontamination layer that estimates the reliability of selected support patches without query information. Central to SADe is sparse autoencoder (SAE) atom evidence: dense similarity may respond to both target and texture-similar context, whereas contrasting atom activations inside and outside the weak-support region provides factor-level reliability cues. A lightweight router combines atom evidence with dense similarity and episode statistics to predict patch reliability and generate a cleaned support mask. Trained once on synthetic weak-support episodes from FSS-1000, the router is frozen for all target evaluations. The resulting mask supports standalone prediction or can be supplied to heterogeneous FSS models through native support interfaces without altering query-side inference. Under a matched weak-support protocol, SADe achieves the highest query mIoU in six of nine standalone prompt-shot combinations. With the same ProMi query head, it is within 0.03 mIoU of SAM3-derived masks under tight boxes and surpasses them by 11.17 and 19.49 points under box-r2 and box-r4, respectively. As a plug-in, SADe improves over raw support in 70 of 72 matched box-family comparisons across four frozen downstream models and two datasets. On point and scribble prompts, its average performance remains close to the corresponding raw-support baseline. Ablations and atom-removal controls show that atom evidence contributes reliability information beyond dense similarity.
Authors: Behnam Asadi
Abstract: Automated photogrammetric inspection emits metric measurements from reconstructions whose correctness is normally unknown without an external survey. Can a reconstruction estimate its own reliability with no ground truth, and what would such an estimate measure? We formalise a track-leakage-free hold-out protocol: a deterministic image subset is withheld, and each withheld view is re-localised by resection against only those 3D points supported by at least two retained images, so no view is tested against structure it helped create. We evaluate it on five GNSS-referenced captures (four RTK-fixed) across four sites, 13 ETH3D laser-scan scenes, a EuRoC flight, and 30 IMC 2025 scenes. The protocol is computationally well-posed -- good reconstructions score near-perfect self-consistency (median rotation error 0.003 deg) -- but it does not measure accuracy, for a structural rather than statistical reason. It saturates: confidence stays pinned at 1.00 while true error swings 14.1x within a single capture, and holds at 1.00 on survey-grade truth at 3.4 m, 4.3 m, and 1.7 m / 13 deg. It is blind to coherent distortion: corruption that fragments a reconstruction is caught (1.00 -> 0.96), but corruption yielding a single, internally self-consistent, globally distorted model is not -- at three of four captures such models were wrong by 55-106 m at confidence 1.00. On IMC 2025 the same dichotomy appears with no injected degradation: confidence separates failed from successful reconstructions (rho = 0.68) yet ranks nothing among the successful ones (rho = 0.01). A capture-level meta-analysis of the continuous signal is underpowered and sign-unstable (k = 5, 95% CI [-0.45, +0.75]); the negative result does not rest on it. Track-leakage-free hold-out therefore measures internal geometric consistency: a qualitative fragmentation warning, not a substitute for control-point accuracy assessment.
Authors: Prathyush Sajith, Emadeldeen Hamdan, Ahmet Enis Cetin
Abstract: Stereo depth estimation for driving, robotics and augmented reality must run at high resolution under tight latency budgets, yet in transformer-based matchers the global self-attention that aggregates scene context grows quadratically with the number of pixels and comes to dominate runtime. We show that the joint self-attention stage of a stereo transformer, whose role is to spread context across both views, can be replaced by a data-independent Walsh-Hadamard token mixer that mixes tokens globally in the transform domain at log-linear cost, while the data-dependent cross-attention that performs left-right correspondence is retained. On synthetic driving data the mixer matches the attention baseline in end-point error while reducing model compute by a factor of 2.46 and single-image inference latency by a factor of 2.65. A complexity analysis shows the benefit is governed by the ratio of sequence length to channel width, which explains why high-resolution stereo matching is a particularly favorable setting and why classification transformers are not; we confirm this token-to-channel scaling on non-stereo long-sequence benchmarks. Furthermore, we introduce a hybrid log-disparity loss function designed to up-weight small-disparity pixels corresponding to long-range objects. This approach reduces the error on distant objects without incurring any additional computational overhead.
Authors: Jos\'e Thi\'ery Messigb\'ed\'e Hagbe, Gani Kawsar Gounou, Songbian Karim Zim\'e
Abstract: In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer who sustained real losses receives no payout, while unnecessary expert review is operationally costly but reversible. Standard multi-class classifiers optimize global accuracy but provide no mechanism to operationalize or control this asymmetric cost structure at inference time. We propose CascadeCropNet, a two-stage cascade architecture calibrated to satisfy a target recall constraint (Rec-Damaged >= 0.95) through threshold selection. A lightweight Sentinel model performs binary health triage; samples exceeding a calibrated damage probability threshold tau are escalated to a specialist Expert model for fine-grained diagnosis. This design provides explicit, deployment-time control over the safety-efficiency trade-off without retraining. Evaluated on the Eyes on the Ground dataset (23,804 images from Kenyan smallholder maize farms), the cascade achieves Rec-Damaged = 0.974 at tau = 0.5, reducing missed damage cases by up to 54% relative to a flat baseline. Under evaluation alignment, the representational gap reduces to +0.008 F1-macro, confirming the contribution is architectural rather than representational. Under input degradation, the system prioritizes escalation over confident misclassification, reflecting error containment through architectural isolation rather than intrinsic model robustness. These results demonstrate that cascade architectures can operationalize safety-oriented decision constraints through calibrated routing in settings where reliability matters more than aggregate accuracy. These properties depend on threshold calibration and deployment conditions and do not constitute guarantees under arbitrary distribution shift.
Authors: Yimao Guo, Zuomin Qu, Wei Lu
Abstract: The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks, which require defenders to possess GPUs with substantial memory resources (VRAM) to generate adversarial examples. To address this issue, we propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.
Authors: A. Contreras, D. Porres, R. Abad, P. Cano, A. Levy, G. Villalonga, A. M. L\'opez, A. Hern\'andez-Sabat\'e
Abstract: The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of sensor data with ground-truth annotations. While modular architectures are widely used, end-to-end driving paradigms offer a promising alternative by directly mapping sensor inputs to control actions. However, their adoption is limited by challenges in interpretability and explainability. To address this, we present LAIA (Labelled Attention for Intelligent Automobiles), a novel synthetic dataset designed to enrich end-to-end driving research with human attention data. Collected using the CARLA simulator in closed-loop environments, LAIA comprises over 15 hours of driving from 44 participants across carefully crafted scenarios designed to evoke natural responses. Each sequence includes RGB images under six weather conditions, semantic and instance segmentation, depth, optical flow, CAN bus signals, and synchronized eye-tracking data. LAIA enables applications including training attention-aware end-to-end AI drivers, predicting driver behavior, developing methods to detect anomalous driver-attention patterns, and improving model explainability. In this work, we use LAIA to compare human attention with the perceptual attention emerging in our end-to-end driving models, thereby providing insight into their behavior.
Authors: Kyujin Han, Seungjoo Shin, Sunghyun Cho
Abstract: Most video editing systems still lack explicit layered video representations, limiting their ability to perform realistic compositing, object reuse, and consistent manipulation. This limitation is especially pronounced in video object insertion and video layer decomposition, where existing methods rely on implicit inference or per-scene optimization due to the absence of explicit foreground-layer supervision. We introduce TriLayer, a large-scale triplet video dataset containing aligned composite, background, and foreground videos, where the foreground layers include both object appearance and associated visual effects. This explicit supervision enables models to learn layered video representations directly rather than inferring them implicitly. Building on this dataset, we propose DBL-Diffusion, a dual-branch diffusion framework that jointly models RGB composites and RGBA foreground layers through shared denoising and cross-branch interaction. We instantiate the framework in two tasks: DBL-Insert for layered object insertion, which generates explicit RGBA layers for realistic compositing and flexible post-editing, and DBL-Decompose for video layer decomposition, which recovers foreground and background layers using triplet supervision. Experiments demonstrate that explicit layer modeling substantially improves both insertion fidelity and decomposition quality.
Authors: Podakanti Satyajith Chary, Barath Parthiban, Pranesh Velmurugan, Adeeba Khan, Nagarajan Ganapathy
Abstract: Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H at the video level is difficult, since the signal arises from disagreement across and within facial, vocal, linguistic, and bodily modalities, and manifests differently across individuals. The proposed PRISM-AH (Predictive Reasoning over Interacting Streams for Multimodal Ambivalence/Hesitancy Recognition), is a framework that treats A/H as a multimodal conflict that unfolds over time. Frozen vision, audio, and text encoders are aligned into short time windows and passed to a lightweight streaming model that scores cross-modal dissonance, predicts each next window to expose a hesitation surprise signal, discovers behaviour prototypes, and is conditioned on participant metadata. Dense window-level annotations supervise the model as an auxiliary objective, and the decision threshold is calibrated for macro F1. A knowledge-guided large language model then reasons over structured evidence using the expert cue taxonomy of the dataset, and its verdict is fused late only when validation performance improves. On the labelled public test partition of 525 videos, PRISM-AH attains a macro F1 of 0.6133, compared to the reported zero-shot baseline of 0.2827. The reasoning gain is validated to transfer from validation to the larger test partition.
Authors: Mustafa Fuad Rifet Ibrahim, Tunc Alkanat, Felix Manthey, Maurice Meijer, Alexander Schlaefer, Peer Stelldinger
Abstract: Wearable cardiovascular sensor patches promise continuous, unobtrusive monitoring, but their tight energy, memory, and compute budgets make it unclear whether physiological signals should be analyzed on the device or streamed to the cloud for processing. We study this inference-versus-transmission trade-off for a resource-constrained patch that records synchronized electrocardiogram (ECG) and phonocardiogram (PCG) signals. We propose an end-to-end, multi-modal convolutional neural network (CNN) with early fusion that classifies the two modalities directly on the device, without hand-crafted features. Trained and validated on the PhysioNet/Computing in Cardiology Challenge 2016 dataset, the floating-point model attains an accuracy of 0.975, which is competitive with the best reported results. At the same time, it reduces the parameter count and computational cost by approximately three orders of magnitude. We deploy an 8-bit integer version of the model on a microcontroller with an integrated neural processing unit (NPU) and measure its inference energy. We also benchmark the energy required for Bluetooth Low Energy (BLE) communication on a representative evaluation kit across a range of payload sizes. NPU inference consumes approximately one-seventh of the energy required for CPU inference. For realistic per-second payloads, local inference is also several times more energy efficient than continuous raw-data streaming. These results show that on-device intelligence, rather than constant transmission, is the more energy-efficient basis for always-on wearable cardiovascular monitoring at the edge.
Authors: Shuyuan Hu, Tao Lin, Kai Ye, Tianwei Zhang
Abstract: Large Language Models (LLMs) enable non-experts to specify open-world multi-robot tasks, but the generated plans are often kinematically infeasible and inefficient in long-horizon settings. Formal methods such as Linear Temporal Logic (LTL) offer correctness and optimality guarantees, yet they are typically offline and scale poorly. To bridge this gap, we propose a neuro-symbolic framework that grounds human instructions into hierarchical LTLf specifications (i.e., LTL on finite traces) and solves the resulting Simultaneous Task Allocation and Planning (STAP) problem. Unlike static approaches, our system handles stochastic environmental changes-such as user motion or updated instructions-through a receding horizon planning (RHP) loop with real-time perception, dynamically refining plans over a hierarchical state space. Experiments in simulation and on real robots demonstrate that our approach significantly outperforms baseline methods in success rate and interaction fluency while reducing replanning overhead.
Authors: Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented cohorts, simulate disease trajectories, and support privacy-preserving data sharing. Latent diffusion has been the go-to solution for modeling imaging data, but it places two competing demands on the tokenizer: encoder embeddings must retain the clinical information that downstream tasks act on, and the decoder must reconstruct anatomically faithful volumes. Existing reconstruction-driven tokenizers achieve the second at the expense of the first. To address this, we introduce a fully volumetric masked-autoencoder (MAE) based tokenizer for 3D brain MRI latent diffusion, decoupling encoder and decoder: a frozen 3D MAE encoder produces clinically informative embeddings, while a dedicated CNN decoder reconstructs voxels from a linear projection of those embeddings. We pretrain the encoder on 35,309 volumes from 18 public cohorts spanning four modalities, ten disease categories, and 200+ acquisition sites, and demonstrate its dual utility in two settings. First, on a 23-task linear-probing benchmark, the encoder outperforms or matches SOTA models (i.e., BrainIAC, BrainSegFounder, and MedicalNet) on 21 of 23 tasks. Second, a conditional diffusion transformer (DiT) trained on these clinically informative embeddings supports both conditional generation across six variables and patient-specific longitudinal forecasting. Together these results establish a single 3D brain-MRI embedding space capable of both downstream clinical tasks and controllable generation.
Authors: Tanel P\"arnamaa, Martin Lumiste, Ardi Loot, Evgenii Indenbom, Andrei Znobishchev, Ando Saabas
Abstract: Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce deterministic results across diverse hardware platforms, leading to catastrophic decoding failures. We introduce MLVC, a hardware-robust neural video codec designed for practical cross-platform inference. The key idea is to explicitly transmit scale parameters through the hyperprior, which guarantees entropy coding consistency across devices without requiring bit-exact arithmetic. While this increases bitrate overhead, we recover most of the coding efficiency through architectural improvements (gated memory, ReGLU activation), a long-term reference recovery mechanism, and domain-specific perceptual training. On the VCD video conferencing benchmark, MLVC achieves >70% BD-rate (MOS) improvement over hardware HEVC, the strongest deployable baseline, while reaching subjective quality competitive with DCVC-RT, which cannot operate across diverse platforms. Both the encoder and decoder run at 100 FPS on average on commodity NPUs from Apple, Intel, and Qualcomm. MLVC is the first neural video codec to combine competitive compression performance, real-time speed, and cross-platform robustness across diverse consumer devices, making it suitable for widespread deployment. Code is available at https://github.com/microsoft/mlvc.
Authors: Sabahattin Mert Daloglu, Ceren Coskun, Harvey Castro, Soner Hacihaliloglu, Ilker Hacihaliloglu
Abstract: Breast ultrasound is widely used for screening, yet automated analysis remains challenging due to speckle noise, acquisition variability, and weak separation of benign and malignant cases in standard ultrasound imaging. Graph convolutional networks (GCNs) have recently emerged as a promising approach by leveraging relationships among similar patient samples. However, it remains unclear how the choice of image encoder influences graph construction and downstream classification performance. In this work, we systematically evaluate five image encoders spanning convolutional and transformer-based architectures for GCN-based breast ultrasound classification. Image embeddings are used to construct cosine similarity k-nearest-neighbor graphs, which are classified using a single-layer GCN with a linear classification head. Across three patientwise cross-validation folds, higher-capacity encoders consistently improve graph homophily and downstream classification performance, yielding gains in accuracy, AUC, sensitivity, specificity, and F1-score. Moreover, test-set graph homophily exhibits a strong linear correlation with classification accuracy, with higher-capacity encoders consistently occupying the high-homophily, high-accuracy region suggesting that encoder-driven improvements in graph structure are a key mechanism underlying the observed performance gains. These findings establish encoder selection as a critical factor in graph-based breast ultrasound classification and identify graph homophily as a key indicator linking representation quality to downstream classification performance.
Authors: Jialu Zhang, Yong Du, Xianda Guo, Shunwang Sun, Xinqi Liu, Yue Sun, Guodong Lu, Wei Sui, Jituo Li
Abstract: Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different agents, making prediction ambiguous when relying solely on vision. Existing studies mainly rely on reinforcement learning, which requires large-scale interaction and careful reward design, making it difficult to support scalable pretraining and real-world adaptation. In contrast, imitation-learning-based approaches remain limited. To address these challenges, we propose an imitation-learning-based embodiment-aware navigation framework with a modular multi-stage design. In pretraining, we construct a cross-embodiment navigation dataset from Internet videos and introduce embodiment geometry as conditional tokens to reduce action ambiguity under the same observation. In fine-tuning, we design a multimodal information injection mechanism based on a decoupled architecture. Specifically, we design a trajectory augmentation strategy to generate high-risk samples, which are used to train spatial perception and risk-aware correction separately, thereby explicitly incorporating embodiment geometry for safe navigation. Experimental results show that the proposed method effectively improves navigation performance across different embodiment settings, demonstrating the effectiveness of incorporating embodiment geometry into embodied navigation.
Authors: Kiran Nair, Smriti Regmi, Rodrigue Rizk
Abstract: Existing adaptive inference methods for Large Language Models rely on observational heuristics, such as hidden-state similarity or activation magnitudes, to drop redundant modules. However, these correlation-based metrics often fail to capture subtle, non-linear structural computations vital for semantic accuracy. We introduce CausalGate, an intervention-guided framework for compute-efficient transformer inference. During a calibration phase, CausalGate isolates individual Attention and MLP sub-layers, zeros out their respective outputs, and measures the exact semantic damage via the Kullback-Leibler divergence of the final logit distribution. To eliminate runtime routing overhead, this structural importance hierarchy is distilled into a global set of static, lightweight scalar gates using an Exponential Moving Average smoothing objective paired with a differentiable pairwise ranking loss. Evaluated on TinyLlama-1.1B, Qwen2.5-3B, and Llama-3.1-8B across language modeling and commonsense reasoning benchmarks, CausalGate consistently outperforms prominent dynamic routing and layer-skipping baselines, translating theoretical compute savings into concrete hardware latency reductions with zero operational overhead.
Authors: Haobo Wang, Baoli Sun, Anqi Zou, Dongsheng Huang, Zelin Lv, Ning Wang, Rui Li, Dongzhan Zhou, Weiyu Guo, Zhihui Wang, Wanli Ouyang
Abstract: The deployment of embodied agents in self-driving laboratories could accelerate scientific discovery, yet their reliability is constrained by the irreversible and safety-critical nature of chemical experiments. Progress is further hindered by scarce failure data and the lack of fine-grained evaluation protocols. To address these challenges, we introduce LabRobFail, a failure-centric framework for learning and evaluating robotic failure analysis in chemical laboratories. LabRobFail-Sim injects controllable failures at the control, physics, and semantic levels, enabling the construction of LabRobFail-Data, which contains over 20,000 trajectories across 70+ task scenarios, five failure categories, and 11 fine-grained failure types. LabRobFail-Bench evaluates six capabilities spanning task understanding, failure detection, temporal localization, severity assessment, failure classification, and actionable correction. We further develop LabRobFail-VLM, a domain-specialized vision-language model that generates structured failure diagnoses and recovery instructions. On seen environments, it achieves 90.83% failure-detection accuracy and 77.21% temporal-localization accuracy, substantially outperforming general-purpose VLMs. When integrated as a real-time supervisor, it improves downstream task success rates by 4-16 percentage points, demonstrating the value of fine-grained failure understanding for closed-loop recovery and reliable laboratory autonomy. Our code and data are available at https://github.com/Su-ISE-2001/SciRobo