Authors: Yanchen Guan, Haicheng Liao, Chengyue Wang, Xingcheng Liu, Jiaxun Zhang, Keqiang Li, Zhenning Li
Abstract: Anticipating traffic accidents is a critical yet unresolved problem for autonomous driving, hindered by the inherent complexity of modeling interactions between road users and the limited availability of diverse, large-scale datasets. To address these issues, we propose a dual-path framework. On the one hand, we employ a video synthesis pipeline that, guided by structured prompts, derives feature distributions from existing corpora and produces high-fidelity synthetic driving scenes consistent with the statistical patterns of real data. On the other hand, we design a graph neural network enriched with semantic cues, enabling dynamic reasoning over both spatial and semantic relations among participants. To validate the effectiveness of our approach, we release a new benchmark dataset containing standardized, finely annotated video sequences that cover a broad spectrum of regions, weather, and traffic conditions. Evaluations across existing datasets and our new benchmark confirm notable gains in both accuracy and anticipation lead time, highlighting the capacity of the proposed framework to mitigate current data bottlenecks and enhance the reliability of autonomous driving systems.
Authors: Sungjun Cho
Abstract: Hybrid-capture novel view synthesis combines images at substantially different camera distances (e.g., aerial drone and ground-level views). Standard 3D Gaussian Splatting (3DGS), trained for 30K iterations with one rendered view per optimizer step, under-fits the minority regime by 1-3 dB on five hybrid-capture benchmarks. We isolate the lever that closes this gap. Among compute-matched alternatives -- vanilla 60K iterations, magnitude corrections (GradNorm), direction-aware near/far gradient surgery, projective preconditioning, confidence-gated sample-level surgery, and a random two-view-per-step control -- the simplest structural change wins: rendering two views per optimizer step. The pairing rule (geometry-defined near/far, random, or active loss-disparity) does not change PSNR beyond seed variance on any of the five scenes; the structural change of having two views per step does. We propose a variance-decomposition framework that predicts and explains this finding: under bimodal camera regimes, between-regime gradient variance turns out to be small relative to within-regime variance in 3DGS, so structured and random pairings are variance-equivalent in expectation, and the variance halving from two-view accumulation itself is the dominant effect. We verify the framework on five scenes whose camera-altitude bimodality coefficients span [0.55, 1.00], and we report the negative result that direction-aware projection, magnitude correction, confidence gating, and an active loss-disparity pairing all fall within seed variance of random two-view pairing. The two-view structural lever transfers cleanly to the Scaffold-GS and Pixel-GS backbones. We position this work as an honest characterization of which training-side axes do and do not move PSNR for hybrid-capture 3DGS, together with the framework that explains why.
Authors: Sundas Iqbal, Qing Tian, Danish Ali, Jianping Gou, Weihua Oue
Abstract: Person re-identification (Re-ID) aims to match images of the same individual across non-overlapping camera views and remains challenging due to domain shifts caused by variations in illumination, background, camera characteristics, and population distributions. Although supervised models perform well under matched training and testing conditions, their performance degrades significantly when deployed in unseen environments. Existing intermediate domain approaches such as IDM and IDM++ alleviate this gap by constructing bridge feature distributions between domains; however, they rely on fixed mixing strategies and joint source-target access, limiting their applicability to multi-source and source-free settings. To address these limitations, this paper proposes Adaptive Intermediate Domain Adaptation (AIDA), also referred to as Source-Free Multi-Source Intermediate Domain Adaptation (SF-MIDA). The proposed framework treats intermediate-domain learning as a dynamically regulated process, where feature mixing and regularization strength are adaptively controlled using feedback signals derived from model uncertainty and training stability. A multi-source intermediate domain generator synthesizes diverse intermediate representations, while a pseudo-mirror regularization strategy preserves identity consistency under domain perturbations. Extensive experiments across domain generalization and source-free settings demonstrate the effectiveness of the proposed framework.
Authors: Himanshu Singhal, Suresh Sundaram
Abstract: Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, restricting them to 1D architectures and preventing the use of pretrained 2D vision backbones. We bridge this gap with GAFSV-Net, which represents each signature as a six-channel asymmetric Gramian Angular Field image: three kinematic channels (pen speed, pressure derivative, direction angle) are each encoded into complementary GASF and GADF matrices that capture pairwise temporal co-occurrence and directional transition structure respectively. A dual-branch ConvNeXt-Tiny encoder processes GASF and GADF independently, with bidirectional cross-attention enabling each branch to query discriminative patterns from the other before metric-space projection. Training uses semi-hard triplet loss with skilled-forgery hard-negative injection; verification is performed via cosine similarity against a small enrollment prototype. We evaluate on DeepSignDB and BiosecurID, outperforming all sequence-based baselines trained under identical objectives, demonstrating that the representational gain of 2D temporal encoding is consistent and independent of training procedure, with ablations characterising each design choice's contribution.
Authors: Udayanga G. W. K. N. Gamage, Yan Zeng, Cesar Cadena, Matteo Fumagalli, Silvia Tolu
Abstract: Real-time object detection on energy-constrained platforms is critical for applications such as UAV-based inspection, autonomous navigation, and mobile robotics. Spiking neural networks (SNNs) on neuromorphic hardware are believed to be significantly more energy-efficient than conventional artificial neural networks (ANNs). In this work, we present a comprehensive methodology for designing general SNN detection architectures targeting neuromorphic platforms, along with the engineering adaptations required to deploy them on the state-of-the-art Neuromorphic processor, Intel Loihi 2. We benchmark SNN-based object detection on Loihi 2 using both frame-based and event-based datasets, comparing performance with ANN-based detection on the NVIDIA Jetson Orin Nano, NVIDIA Jetson Nano B01, and the Apple M2 CPU. Our results show that SNNs on Loihi 2 can perform real-time detection while achieving the lowest per-inference dynamic energy among all platforms. Also, Loihi 2 outperforms the other platforms in terms of power consumption, though ANNs on Jetson Orin Nano achieve higher inference rates. Furthermore, our ANN-to-SNN distillation-aware training enables SNNs to recover 87-100% of the detection accuracy of their ANN counterparts while maintaining lower inference latency; without distillation, SNNs exhibit an 11-27% accuracy drop. These results highlight the potential of neuromorphic systems for energy-efficient, real-time object detection at the edge.
Authors: Bala Prenith Reddy Gopu, Patrick Quinn, George M. Nehma, Madhur Tiwari, Matt Ueckermann, David Hinckley, Christopher McKenna
Abstract: On-orbit inspection imagery is crucial as it enables characterization of non-cooperative resident space objects, providing the geometry and structural condition essential for active debris removal and on-orbit servicing mission planning. However, most existing neural implicit surface reconstruction methods have been confined to synthetic or hardware-in-the-loop data with known camera poses and controlled illumination. In this work, we present a pipeline for neural implicit surface reconstruction of non-cooperative space objects from monocular inspection imagery. We demonstrate it on publicly released ISS inspection footage from the STS-119 mission and publicly released on-orbit inspection footage of an H-IIA rocket upper stage. We find that segmentation-based background removal is essential for successful camera pose estimation from real on-orbit footage, where background variation between frames caused direct processing to fail entirely. We further incorporate photometric correction of per-frame exposure variations and analyze its behavior across datasets, finding that performance in shadowed regions varies with the illumination characteristics of the input footage.
Authors: Jingxiang Chen, Mohamed Ibrahim, Yang Liu
Abstract: We present VkSplat, a high-performance, cross-vendor 3D Gaussian Splatting (3DGS) training pipeline implemented fully in Vulkan compute, addressing performance and compatibility limitation of existing training pipelines. With various optimizations, we achieve $3.3\times$ speed and $33\%$ VRAM reduction over CUDA+PyTorch baseline, maintaining quality, and demonstrating compatibility across GPU vendors. To the best of our knowledge, this is the first fully-Vulkan-based 3DGS training pipeline that achieves state-of-the-art performance. Code: \href{https://github.com/harry7557558/vksplat}{https://github.com/harry7557558/vksplat}
URLs: https://github.com/harry7557558/vksplat, https://github.com/harry7557558/vksplat
Authors: Aishani Pathak, Hasti Seifi
Abstract: Egocentric pose estimation for Augmented Reality (AR) and assistive devices requires not just accurate predictions but guaranteed uncertainty regions. Conformal prediction (CP) provides such guarantees without retraining, but we show that standard CP with a single fixed threshold achieves nominal 90% overall coverage while covering only ~60% of the hardest 25% of frames (Q4) -- a ~30 percentage-point conditional coverage gap consistent across 12 participants, 3 predictors, and 3 horizons (108 evaluations) on EPIC-Fields. We further show that a geodesic SE(3) nonconformity score identifies physically harder frames than Euclidean scoring, with only 15-26% Q4 overlap and 2-3x higher ground-truth camera displacement for geodesic Q4 frames. To close the coverage gap, we propose DINOv2-Bridge adaptive CP: a two-stage difficulty estimator trained on a single source participant that transfers cross-participant without any images at test time, improving Q4 coverage from ~0.75 to ~0.93 while maintaining overall coverage at the 90% target.
Authors: Xijia Wei, Yuan Fang, Kevin Chetty, Youngjun Cho, Nadia Bianchi-Berthouze
Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted intermediate representations such as sparse point clouds or spectrogram images, where the rich spatiotemporal information naturally present in radar video streams is discarded for model learning, while such signal processing adds system complexity. In addition, existing solutions are mainly conducted in an end-to-end supervised manner without leveraging unlabelled raw video streams to learn generalized representations. In this study, we present MAEPose, a masked autoencoding-based human pose estimation approach that operates directly on mmWave spectrogram videos. MAEPose learns spatiotemporal motion-aware generalized representations from unlabelled radar video, and leverages its heatmap decoder for multi-frame pose estimation predictions. We evaluate it across three datasets based on leave-one-person-out cross-validation with rigorous statistical testing. MAEPose consistently outperforms state-of-the-art baselines by up to 22.1% in MPJPE p<0.05, and maintains robust accuracy under zero-shot bystander interference with only a 6.5% error increase. Ablation studies confirm that both the pre-training and the heatmap decoder contribute substantially, while modality analysis indicates that leveraging Range-Doppler video as input achieves better pose estimation performance than Range-Azimuth or their fusion, with lower computational cost.
Authors: Osmar Luiz Ferreira de Carvalho, Osmar Ab\'ilio de Carvalho J\'unior, Anesmar Olino de Albuquerque, Daniel Guerreiro e Silva
Abstract: SAM2 produces high-quality zero-shot segmentation on natural images, but applying it to large remote sensing scenes exposes two problems: (1) its mask generator faces an inherent quality-coverage trade-off: strict thresholds yield precise masks but leave most of the image unsegmented, while relaxed thresholds increase coverage at the cost of mask quality; and (2) large images must be tiled, fragmenting objects across tile boundaries. We propose Remote SAMsing, an open-source pipeline that solves both problems without modifying SAM2 or requiring training data. For coverage, a multi-pass algorithm runs SAM2 repeatedly on each tile, painting accepted masks black between passes to simplify the scene for the next iteration, and relaxing quality thresholds only when coverage gains stagnate, ensuring that the most precise masks are always captured first. For spatial consistency, contextual padding and a parameter-free best-match merge reconstruct objects fragmented across tile boundaries. Evaluated on seven scenes (5~cm to 4.78~m GSD), the pipeline raises coverage from 30--68\% (single-pass SAM2) to 91--98\%. Ablation experiments quantify the contribution of each component to coverage and detection quality. Per-class evaluation shows that SAM2 transfers well to discrete RS objects (buildings 95\%, cars 82--93\% Det@0.5) with segment boundaries 3--8$\times$ more precise than SLIC and Felzenszwalb baselines. Tile size functions as an implicit scale parameter: reducing it from $1{,}000$ to 250 raises Det@0.5 from 56\% to 85\%, outperforming SAM2's built-in multi-scale mechanism. The pipeline generalizes to MNF false-color imagery without retraining (99.5\% ASA) and scales to production-sized images: a 1.94 billion pixel Potsdam mosaic achieved 97\% coverage without quality degradation.
Authors: Vincenzo Polizzi, David B. Lindell, Jonathan Kelly
Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a cross-modal framework that learns an RGB and Event Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models. Instead of task-specific training, we leverage low-rank adaptation (LoRA) to bridge the modality gap, effectively unlocking the geometric and semantic priors of frozen RGB backbones for asynchronous event streams. We demonstrate that REALM effectively maps events into the ViT-based foundation latent space. Our method allows us to perform downstream tasks like depth estimation and semantic segmentation by simply transferring linear heads trained on the RGB teacher. Most significantly, REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures. Code and models are available upon acceptance.
Authors: Yujin Jeong, Arnas Uselis, Iro Laina, Seong Joon Oh, Anna Rohrbach
Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different dataset sizes: (1) concept generalization, where each individual concept is observed during training under potentially imbalanced data distributions, and (2) compositional generalization, where specific combinations of concepts are systematically held out. To study these regimes, we introduce mosaic (Multi-Object Spatial relations, AttrIbution, Counting), a controlled framework for dataset generation. By training diffusion models on mosaic, we find that scene complexity plays a dominant role rather than concept imbalance, and that counting is uniquely difficult to learn in low-data regimes. Moreover, compositional generalization collapses as more concept combinations are held out during training. These findings highlight fundamental limitations of diffusion models and motivate stronger inductive biases and data design for robust multi-object compositional generation.
Authors: Maryam Sadat Hosseini Azad, Shahriar Baradaran Shokouhi, Amir Abbas Hamidi Imani, Shahin Atakishiyev, Randy Goebel
Abstract: The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making processes, it is not possible to recognize their efficiency, predict system failures, or effectively implement them in real-world applications. Due to the inevitable use of deep learning in fully automated driving systems, many methods have been proposed to explain their behavior; however, they suffer from flawed reasoning and unreliable metrics, which have prevented a comprehensive understanding of complex models in autonomous vehicles and hindered the development of truly reliable systems. In this study, we propose a multi-scale attention-based model in which driving decisions are fed into the reasoning component to provide case-specific explanations for each decision simultaneously. For quantitative evaluation of our model's performance, we employ the F1-score metric, and also proposed a new metric called the Joint F1 score to demonstrate the accurate and reliable performance of the model in terms of Explainable Artificial Intelligence (XAI). In addition to the BDD-OIA dataset, the nu-AR dataset is utilized to further validate the generalization capability and robustness of the proposed network. The results demonstrate the superiority of our reasoning network over the classic and state-of-the-art models.
Authors: Alan Gomes, Anderson Gon\c{c}alves, Samuel Felipe dos Santos, Nathan Felipe Alves, Magna Soelma Beserra de Moura, Bruna de Costa Alberton, Leonor Patricia C. Morellato, Ricardo da Silva Torres, Jurandy Almeida
Abstract: Plant phenology-the study of recurrent life cycle events-is essential for understanding ecosystem dynamics and their responses to climate change impacts. While Unmanned Aerial Vehicles (UAVs) and near-surface cameras enable high-resolution monitoring, identifying plant species across time remains computationally challenging. State-of-the-art approaches, specifically Multi-Temporal Convolutional Networks (CNNs), rely on rigid multi-branch architectures that scale poorly with longer time series and require large spatial context windows. In this paper, we present an extensive study on optimizing Vision Transformers (ViTs) for efficient spatio-temporal vegetation pixel classification. We conducted a comprehensive ablation study analyzing seven key design dimensions, including: (i) data normalization; (ii) spectral arrangement; (iii) boundary handling; (iv) spatial context window shape and size; (v) tokenization strategies; (vi) positional encoding; and (vii) feature aggregation strategies. Our method was evaluated on two datasets from the Brazilian Cerrado biome, Serra do Cip\'o (aerial imagery) and Itirapina (near-surface imagery). Experimental results demonstrate that our ViT approach offers a substantial improvement in computational efficiency while maintaining competitive classification performance. Notably, our ViT reduces Floating Point Operations (FLOPs) by an order of magnitude and maintains constant parameter complexity regardless of the time series length, whereas the CNN baseline scales linearly. Our findings confirm that ViTs are a robust, scalable solution for resource-constrained phenological monitoring systems.
Authors: Zhili Li, Kangyang Chai, Zhihao Wang, Xiaowei Jia, Yanhua Li, Gengchen Mai, Sergii Skakun, Dinesh Manocha, Yiqun Xie
Abstract: Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response. However, existing SR studies and benchmarks typically use fidelity metrics such as PSNR or SSIM, whereas the true utility of super-resolved images lies in supporting downstream tasks such as land cover classification, biomass estimation, and change detection. To bridge this gap, we introduce GeoSR-Bench, a downstream task-integrated SR benchmark dataset to evaluate SR models beyond fidelity metrics. GeoSR-Bench comprises spatially co-located, temporally aligned, and quality-controlled image pairs from about 36,000 locations across diverse land covers, spanning resolutions from 500m to 0.6m. To the best of our knowledge, GeoSR-Bench is the first SR benchmark that directly connects improved image resolution from SR models with downstream Earth monitoring tasks, including land cover segmentation, infrastructure mapping, and biophysical variable estimation. Using GeoSR-Bench, we benchmark GAN, transformer, neural operator, and diffusion-based SR models on perceptual quality and downstream task performance. We conduct experiments with 270 settings, covering 2 cross-platform SR tasks, 9 SR models, 3 downstream task models, and 5 downstream tasks for each SR task. The results show that improvements in traditional SR metrics often do not correlate with gains in task performance, and the correlations can be negative, indicating that these metrics provide limited guidance for selecting superior models for downstream tasks. This reveals the need to integrate downstream tasks into SR model development and evaluation.
Authors: Minghui Chen, Chenxu Yang, Hengjie Zhu, Dayan Wu, Zheng Lin, Qingyi Si
Abstract: Large Vision-Language Models (LVLMs) often suffer from hallucinations, generating descriptions that include visual details absent from the input image. Recent preference alignment methods typically rely on supervision distilled from stronger models such as GPT. However, this offline paradigm introduces a Supervision-Perception Mismatch: the student model is forced to align with fine-grained details beyond its perceptual capacity, learning to guess rather than to see. To obtain reliable self-supervision for online learning, we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we propose \textbf{O}nline \textbf{S}elf-\textbf{CA}lib\textbf{R}ation (OSCAR), a framework that integrates Monte Carlo Tree Search with a Dual-Granularity Reward Mechanism to construct preference data and iteratively refines the model via Direct Preference Optimization. Extensive experiments demonstrate that OSCAR achieves state-of-the-art performance on hallucination benchmarks while improving general multimodal capabilities.
Authors: Zihan Zhou, Luxi Chen, Jingzhi Zhou, Yuhao Wan, Min Zhao, Baoyu Fan, Chongxuan Li
Abstract: Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, we introduce Pose-Aware Diffusion (PAD), a novel end-to-end diffusion framework that synthesizes 3D geometry directly within the observation space. By unprojecting monocular depth into a partial point cloud and explicitly injecting it as a 3D geometric anchor, PAD abandons canonical assumptions to enforce rigorous spatial supervision. This native generation intrinsically resolves pose ambiguity, producing high-fidelity pose-aligned assets. Extensive experiments demonstrate that PAD achieves superior geometric alignment and image-to-3D correspondence compared to state-of-the-art methods. Additionally, PAD naturally extends to compositional 3D scene reconstruction via a simple union of independently generated objects, highlighting its robust ability to preserve precise spatial layouts.
Authors: Wenjie Zhao, Jia Li, Mingrui Liu, Jing Wang, Yunhui Guo
Abstract: ``How long can I live and remain free of cancer?'' is often the first question a patient asks after receiving a cancer diagnosis and treatment. Accurate survival prediction helps alleviate psychological distress and supports risk stratification and personalized treatment planning. Recent survival prediction frameworks have shown strong performance using computed tomography (CT) images. However, variations in imaging acquisition introduce out-of-distribution (OOD) samples caused by covariate shifts that undermine model reliability. Despite this challenge, to our knowledge, no existing benchmark systematically studies OOD detection in cancer survival prediction. To address this gap, we introduce the Cancer sURvival bEnchmark for OOD Detection (CURE-OOD), the first benchmark for systematically evaluating OOD detection in survival prediction under controlled acquisition-induced distribution shifts. CURE-OOD defines scanner-parameter-based training, in-distribution (ID), and OOD test splits across four survival prediction tasks. Our experiments show that covariate shifts notably reduce survival prediction performance. It also shows that mainstream classification-oriented OOD detectors can fail in survival prediction. Finally, we include HazardDev as a simple survival-aware reference baseline for OOD detection. CURE-OOD enables systematic analysis of how distribution shifts affect both downstream survival performance and OOD detectability.
Authors: Nhat-Tan Do, Le-Huy Tu, Nhi Ngoc-Yen Nguyen, Dieu-Phuong Nguyen, Trong-Hop Do
Abstract: Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the complexities of real-world, non-linear motion (e.g., sudden stops, sharp turns). While recent research has gravitated towards increasingly complex and computationally expensive generative models to tackle this problem, their practical utility is often constrained. This paper challenges that paradigm, arguing that such complexity is not only unnecessary but can be outperformed by a more efficient, purpose-built approach. We introduce the Temporal Convolutional Motion Predictor (TCMP), a novel framework for MOT that leverages a modified Temporal Convolutional Network (TCN) featuring dilated convolutions and a regression head. This design allows for effective motion prediction across arbitrary temporal context lengths. Experimental results demonstrate that our approach achieves state-of-the-art performance, specifically improves upon the previous best method in several key metrics: HOTA (a measure of overall tracking accuracy) increases from 62.3% to 63.4%, IDF1 (a measure of identity preservation) rises from 63.0% to 65.0%, and AssA (a measure of association accuracy) improves from 47.2% to 49.1%. Significantly, TCMP achieves this performance while being highly efficient; it has only 0.014 times the parameters and requires only 0.05 times the computational cost (FLOPs) compared to the SOTA method. while is only 0.014 times the size (in terms of parameters) and requires only 0.05 times the computational cost (in terms of FLOPs). These findings highlight the robustness of our method to advance MOT systems by ensuring adaptability, accuracy, and efficiency in complex tracking environments.
Authors: Dakota Hester, Vitor S. Martins, Lucas B. Ferreira, Thainara M. A. Lima, Juliana A. Ara\'ujo
Abstract: Developing robust techniques for super-resolution of satellite imagery involves navigating commonly observed trade-offs between spectral fidelity and perceptual quality. In this work, we introduce a flow matching model for 4x super-resolution of 10-m Sentinel-2 visible and near-infrared bands over the conterminous United States (CONUS) using a dataset of 120,851 10-m Sentinel-2 and 2.5-m resampled NAIP imagery pairs acquired on the same day. Our results showed that the flow matching model outperformed diffusion and Real-ESRGAN models in pixel-wise accuracy in a single sampling step using the Euler method. When evaluated with a second-order Midpoint solver, our model generated perceptually realistic super-resolved imagery in only 20 sampling steps, effectively navigating the perception-distortion trade-off at inference time without retraining. We used this model to produce a super-resolved 2.5-m 4-band CONUS imagery product derived from 2025 10-m Sentinel-2 annual composites, consisting of over 1.58 trillion pixels. We further evaluated the use of super-resolved data on a land cover classification task using semantic segmentation models. Finally, we generated a yearly 2.5-m land cover product for the Chesapeake Bay watershed for 2020-2025. An accuracy assessment against 25,000 ground truth points revealed an overall accuracy of 89.11% for the annual land cover product. We conclude that flow matching is an effective generative modeling approach for super-resolution of Sentinel-2 imagery compared to diffusion and Generative Adversarial Network-based methods, and has strong implications for expanding access to high-resolution imagery for geospatial applications that demand fine spatial detail.
Authors: Ben Wan, Yan Feng, Zihan Tang, Weizhe Huang, Yuting Zeng, Jia Wang, Tongxuan Liu
Abstract: DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR, we find that a distinct two-stage reading trajectory: the model initially prioritizes the majority of high-norm tokens, then subsequently redistributes its attention to the remaining ones. Motivated by this insight, we propose RTPrune, a two-stage token pruning method tailored for DeepSeek-OCR. In the first stage, we prioritize high-norm visual tokens that capture salient textual and structural information. In the second stage, the remaining tokens are paired and merged based on optimal transport theory to achieve efficient feature aggregation. We further introduce a dynamic pruning ratio that adapts to token similarity and textual density for OCR tasks, enabling a better efficiency-accuracy trade-off. Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23$\times$ faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large.
Authors: YuSheng Lin, Ji-Hwa Tsai, Chun-Shu Wei
Abstract: Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused view. This center bias conflicts with content-driven human attention, creating a geometric-semantic dissociation between visual features and EEG responses. We propose SIMON, a saliency-aware multi-view framework for zero-shot EEG-to-image retrieval. SIMON combines foreground segmentation and saliency prediction to select fixation centers via Saliency-Aware Sampling (SAS), then generates foveated views that emphasize informative object regions while suppressing background clutter. On THINGS-EEG, SIMON achieves state-of-the-art performance in both intra-subject and inter-subject settings, reaching an average Top-1 accuracy of 69.7% and 19.6%, respectively, consistently outperforming recent competitive baselines. Analyses across sampling granularity, EEG channel topology, and visual/brain encoder backbones further support the robustness of saliency-aware multi-view integration. Our code and models are publicly available at https://github.com/simonlink666/SIMON.
Authors: Kang Yang, Tianci Bu, Peng Wang, Deying Li, Yongcai Wang
Abstract: Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.
Authors: Zhenhua Ning, Xin Li, Jun Yu, Guangming Lu, Yaowei Wang, Wenjie Pei
Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to adapt to diverse scenes with complex geometries. In this paper, we propose a paradigm shift for density control from rigid heuristics to fully learnable policies. Specifically, we introduce \textbf{LeGS}, a framework that reformulates density control as a parameterized policy network optimized via Reinforcement Learning (RL). Central to our approach is the tailored effective reward function grounded in sensitivity analysis, which precisely quantifies the marginal contribution of individual Gaussians to reconstruction quality. To maintain computational tractability, we derive a closed-form solution that reduces the complexity of reward calculation from $O(N^2)$ to $O(N)$. Extensive experiments on the Mip-NeRF 360, Tanks \& Temples, and Deep Blending datasets demonstrate that \textbf{LeGS} significantly outperforms state-of-the-art methods, striking a superior balance between reconstruction quality and efficiency. The code will be released at https://github.com/AaronNZH/LeGS
Authors: Huangbiao Xu, Huanqi Wu, Xiao Ke, Yuxin Peng
Abstract: Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availability during training to provide reconstruction supervision or cross-modal priors. This paper tackles the more challenging setting of IML under training-time incomplete observations, which precludes reliance on a ``God's eye view'' of complete data. We propose LIMSSR (LLM-Driven Incomplete Multimodal Sequence-to-Score Reasoning), a framework that reformulates this challenge as a conditional sequence reasoning task. LIMSSR leverages the semantic reasoning capabilities of Large Language Models via Prompt-Guided Context-Aware Modality Imputation and Multidimensional Representation Fusion to infer latent semantics from available contexts without direct reconstruction. To mitigate hallucinations, we introduce a Mask-Aware Dual-Path Aggregation to dynamically calibrate inference uncertainty. Extensive experiments on three Action Quality Assessment datasets demonstrate that LIMSSR significantly outperforms state-of-the-art baselines without relying on complete training data, establishing a new paradigm for data-efficient multimodal learning. Code is available at https://github.com/XuHuangbiao/LIMSSR.
Authors: Kerui Chen, Jinglu Wang, Jianrong Zhang, Ming Li, Yan Lu, Hehe Fan
Abstract: Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based preprocessing, yet often suffer from information loss, high cost, and reliance on textual intermediates. We propose MACF, an end-to-end Multi-Agent Collaboration Framework that decouples per-agent perception budgets from global video complexity, enabling scalable video understanding while preserving visual fidelity. MACF partitions videos into segments for locally budgeted agents and enables holistic reasoning via an agent-native latent communication protocol. Each agent encodes partial observations into compact, task-sufficient tokens in a shared embedding space, allowing efficient and information-preserving collaboration by a central coordinator. We introduce a curriculum training strategy that progressively enforces semantic alignment, evidence summarization, and cross-agent coordination. Extensive experiments on diverse video understanding benchmarks show that MACF consistently outperforms state-of-the-art MLLMs and multi-agent systems under identical budget constraints, demonstrating the effectiveness of our latent collaboration for scalable video understanding.
Authors: Shadid Yousuf, S. M. Mahbubur Rahman, Mohammed Imamul Hassan Bhuiyan
Abstract: The deployment of artificial intelligence in medical imaging is hindered by high computational complexity and resource-intensive processing of volumetric data. Although chest computed tomography (CT) volumes offer richer diagnostic information than projection radiography, their use in AI-based diagnosis remains limited due to the computational burden of processing uncompressed volumetric images (typically stored in NIfTI or DICOM format). Addressing the growing need for low-resource deployment and efficient electronic data transfer, we investigate the utilization of JPEG-compressed chest CT volumes for thoracic abnormality detection. We propose Feature Attention Style Transfer (FAST), a novel distillation framework that transfers both activation patterns and structural relationships from high-fidelity CT representations to a spatiotemporal visual encoder operating on compressed inputs. By combining Gram-matrix-based attention style preservation with dual-attention feature alignment, FAST enables robust feature extraction from degraded volumes. Furthermore, we introduce Structured Factorized Projection (SFP), leveraging Block Tensor Train decomposition as a parameter-efficient alternative to dense projection layers, reducing projection-head parameters by almost half. Our contrastive learning pipeline, CT-Lite, integrates these components with a SigLIP-based multimodal alignment objective. Experiments on CT-RATE, NIDCH, and Rad-ChestCT demonstrate that CT-Lite achieves AUROC within 5-7\% of the uncompressed-input baseline across all three datasets, despite operating on compressed inputs with significantly fewer parameters, paving the way for AI-based clinical evaluation under resource constraints.
Authors: Yearim Kim, Sangyu Han, Nojun Kwak
Abstract: Modern vision models achieve remarkable accuracy, but explaining where evidence arises, what the model encodes, and how internal computations assemble that evidence remains fragmented. We introduce an iERF-centric framework that unifies local, global, and mechanistic interpretability around a single analysis unit: the pointwise feature vector (PFV) paired with its instance-specific Effective Receptive Field (iERF). On the local side, Sharing Ratio Decomposition (SRD) expresses each PFV as a mixture of upstream PFVs via sharing ratios and propagates iERFs to construct class-discriminative saliency maps. SRD yields high-resolution, activation-faithful explanations, is robust to targeted manipulation and noise, and remains activation-agnostic across common nonlinearities. For the global view, we introduce Concept-Anchored Feature Explanation (CAFE), which utilizes the iERF as a semantic label, grounding abstract latent vectors in verifiable pixel-level evidence. With CAFE, we address the challenge of non-localized sparse autoencoder latents--especially in Transformers, where early self-attention mixes distant context. To answer how representations are composed through depth, we propose the Interlayer Concept Graph with Interlayer Concept Attribution (ICAT), which quantifies concept-to-concept influence while isolating layer pairs; an interlayer insertion, deletion protocol identifies Integrated Gradients as the most faithful instantiation. Empirically, across ResNet50, VGG16, and ViTs, our framework outperforms baselines in both fidelity and robustness, successfully interprets dispersed SAE features, and exposes dominant concept routes in correct, misclassified, and adversarial cases. Grounded in iERFs, our approach provides a coherent, evidence-backed map from pixels to concepts to decisions.
Authors: Phuong Ngoc Nguyen, Kaito Shiku, Ryoma Bise, Seiichi Uchida, Shinnosuke Matsuo
Abstract: Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce the reliance on costly human annotation within the active learning paradigm. To this end, we find that the reliability of VLMs varies significantly with label granularity in fine-grained recognition tasks: they perform poorly on fine-grained labels but can provide accurate coarse-grained labels. Leveraging this property, we propose an active learning framework that combines fine-grained human annotations with coarse-grained VLM-generated weak labels through instance-wise label assignment. We further model the systematic noise in VLM-generated labels using a small set of trusted full labels. Experiments on CUB200 and FGVC-Aircraft show that the proposed framework consistently outperforms existing active learning methods under the same annotation budget.
Authors: Yongpeng Cao, Yuji Yamakawa
Abstract: Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common activities, collecting sufficient labeled data for supervised learning is challenging, making zero-shot approaches a practical alternative for semantic understanding without task-specific training. While recent advances in large-scale pretrained models enable such zero-shot reasoning, the impact of temporal resolution, especially for rapid and fine-grained motions, remains underexplored. In this study, we investigate how temporal resolution affects zero-shot semantic understanding of high-speed human actions. Using kendo as a representative case of rapid and subtle motion patterns, we propose a training-free pipeline that combines a pre-trained video-language model for semantic representation with large language model-based reasoning for pairwise action comparison. Through controlled experiments across multiple frame rates (120 Hz, 60 Hz, and 30 Hz), we show that higher temporal resolution significantly improves semantic separability in zero-shot settings. We further analyze the role of tracking-based human joint information under both full and partial observation scenarios. Quantitative evaluation using a nearest-class prototype strategy demonstrates that high-speed video provides more stable and interpretable semantic representations for fast actions. These findings highlight the importance of temporal resolution in training-free action recognition and suggest that high-speed perception can enhance semantic understanding capabilities.
Authors: Yonghao Zhao, Yupeng Gao, Jian Yang, Jin Xie, Beibei Wang
Abstract: Recent advances in Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made it standard practice to reconstruct 3D scenes from multi-view images. Removing objects from such 3D representations is a fundamental editing task that requires complete and seamless inpainting of occluded regions, ensuring consistency in geometry and appearance. Although existing methods have made notable progress in improving inpainting consistency, they often neglect global lighting effects, leading to physically implausible results. Moreover, these methods struggle with view-dependent non-Lambertian surfaces, where appearance varies across viewpoints, leading to unreliable inpainting. In this paper, we present 3D Gaussian Object Removal in the Intrinsic Space (GOR-IS), a novel framework for physically consistent and visually coherent 3D object removal. Our approach decomposes the scene into intrinsic components and explicitly models light transport to maintain global lighting effects consistency. Furthermore, we introduce an intrinsic-space inpainting module that operates directly in the material and lighting domains, effectively addressing the challenges posed by non-Lambertian surfaces. Extensive experiments on both synthetic and real-world datasets demonstrate that our framework substantially improves the physical consistency and visual coherence of object removal, outperforming existing methods by 13% in perceptual similarity (LPIPS) and 2dB in peak signal-to-noise ratio (PSNR). Code is publicly available at https://applezyh.github.io/GOR-IS-project-page/
Authors: Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo
Abstract: Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.
Authors: Nan Lei, Yuan-Ming Li, Ling-An Zeng, Liang Xu, Zhi-Wei Xia, Hui-Wen Huang, Fa-Ting Hong, Wei-Shi Zheng
Abstract: Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue from both data acquisition to the generated results, which significantly undermines the realism and usability. Previous generative models either ignored this issue or introduced computationally expensive mesh-level loss functions to alleviate inter-body collisions. In this paper, we propose a general-purpose and computationally efficient optimization strategy named PhysiGen to explicitly integrate collision-aware physical constraints for human-human interaction generation. Specifically, we simplify the high-resolution human body mesh into geometric primitives to greatly reduce the cost of inter-person collision detection. Moreover, we identify the collision regions as the guidance of the optimization directions. PhysiGen is plug-and-play and can be readily integrated into existing human interaction generation models. Extensive cross-dataset and cross-model experiments show that our method can effectively reduce interpenetration and significantly improve visual coherence and physical plausibility compared to the state-of-the-art methods.
Authors: Weichen Liu, Yixin Yang, Changsheng Chen, Alex Kot
Abstract: Suspect face generation remains a technical challenge in crime investigations. Traditional sketch-drawing workflows suffer from low efficiency and quality, while diffusion-based approaches still face intrinsic limitations on conditional ambiguity for text-to-image models and sampling variance for one-shot generation. We proposed IdentiFace, a novel diffusion-based framework for identifiable suspect face generation, which addressed these issues through (1) multi-modal input design to strengthen conditional control, and (2) an iterative generation pipeline enabling identifiable feature adjustment. We additionally contributed a facial identity loss and two task-specific datasets. Comprehensive experiments on synthetic datasets and in real-world scenarios indicate that IdentiFace achieves superior performance over existing methods, especially in terms of identity retrieval, and shows strong potential for practical applications.
Authors: Rajalakshmi Palaniappan, Christoph Karg, Nemesio Navarro-Arambula, Peter Hirsch, Kristin Kraeker, Lisa Mais, Dagmar Kainmueller
Abstract: Blood vessel segmentation and -tracing are essential tasks in many medical imaging applications. Although numerous methods exist, the prevailing segment-then-fix paradigm is fundamentally limited regarding its suitability for modeling the task of complete and topologically accurate vascular network reconstruction. Here, we propose an approach to extract topologically more accurate vascular graphs from 3D image data, building upon highly successful ideas from the related biomedical tasks of cell segmentation and -tracking. Our approach first predicts voxel-wise vessel direction vectors joint with standard vessel segmentation masks. Second, to extract the vascular graph from these predictions, we introduce a direction-vector-guided extension of the TEASAR algorithm. Our approach achieves state-of-the-art performance on three benchmark datasets, spanning both synthetic and real imagery. We further demonstrate the applicability of our approach to challenging 3D micro-CT scans of rat heart vasculature. Finally, we propose meaningful and interpretable measures of topological error, namely false splits and false merges for graphs. Overall, our approach substantially improves the topological accuracy of reconstructed vascular graphs, being able to separate closely apposed vessel segments and handle multiple vascular trees within a single volume.
Authors: Nadav Z. Cohen, Ofir Abramovich, Ariel Shamir
Abstract: Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure. However, this very property limits control over, and predictability of, specific visual attributes, as the noise is not human-interpretable. In this work, we investigate the characteristics of the input noise in diffusion models. We show that, although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the images global structure and color composition, while high-frequency components control finer details. Building on this observation, we demonstrate that simple manipulations of the low-frequency noise using low-frequency image priors can effectively condition the generation process to reconstruct these low-frequency visual cues. This allows us to define a simple, training-free method with minimal overhead that steers overall image structure and color, while letting high-frequency components freely emerge as fine details, enabling variability across generated outputs.
Authors: Heejoon Moon, Jongwoo Lee, Jeonggon Kim, Je Hyeong Hong
Abstract: The emergence of deep neural networks capable of revealing high-fidelity scene details from sparse 3D point clouds has raised significant privacy concerns in visual localization involving private maps. Lifting map points to randomly oriented 3D lines is a well-known approach for obstructing undesired recovery of the scene images, but these lines are vulnerable to a density-based attack that can recover the point cloud geometry by observing the neighborhood statistics of lines. With the aim of nullifying this attack, we present a new privacy-preserving scene representation called \emph{sphere cloud}, which is constructed by lifting all points to 3D lines crossing the centroid of the map, resembling points on the unit sphere. Since lines are most dense at the map centroid, the sphere cloud mislead the density-based attack algorithm to incorrectly yield points at the centroid, effectively neutralizing the attack. Nevertheless, this advantage comes at the cost of i) a new type of attack that may directly recover images from this cloud representation and ii) unresolved translation scale for camera pose estimation. To address these issues, we introduce a simple yet effective cloud construction strategy to thwart new attack and propose an efficient localization framework to guide the translation scale by utilizing absolute depth maps acquired from on-device time-of-flight (ToF) sensors. Experimental results on public RGB-D datasets demonstrate sphere cloud achieves competitive privacy-preserving ability and localization runtime while not excessively compensating the pose estimation accuracy compared to other depth-guided localization methods.
Authors: Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha, Mirela Ostrek, Justus Thies
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address this, 2D Gaussian Splatting (2DGS) was proposed to enable view-consistent and geometrically accurate surface reconstruction from multi-view images. However, 2DGS can be sensitive to the initialization of the Gaussian primitives. Reliance on Structure-from-Motion (SfM) initializations, which can produce poor estimates on challenging image sets, may lead to subpar results. In this work, we enhance 2DGS by incorporating monocular depth and normal priors to improve both geometric accuracy and robustness. We propose a depth-guided initialization strategy for Gaussians and introduce a clustering-based technique for pruning degenerate Gaussians. We evaluate our method on the DTU dataset, where it achieves state-of-the-art results in mesh reconstruction while preserving high-quality novel view synthesis.
Authors: Luru Jing, Cong Cong, Yanyuan Chen, Yongzhi Cao
Abstract: Federated learning (FL) offers a promising framework for collaborative digital pathology by enabling model training across institutions. However, real-world deployments face heterogeneity arising from diverse multiple instance learning (MIL) architectures and heterogeneous feature extractors across institutions. We propose FedHD, a novel FL framework that performs local Gaussian-mixture feature alignment tailored for WSI analysis. Instead of exchanging model parameters, each client independently distills semantically rich synthetic feature representations aligned with the distribution of real WSIs. To preserve diagnostic diversity, FedHD adopts a one-to-one distillation strategy, generating a synthetic counterpart for each real slide to avoid over-compression. During federation, a curriculum-based integration strategy progressively incorporates cross-site synthetic features into local training once performance plateaus. Furthermore, an optional interpretation module reconstructs pseudo-patches from synthetic embeddings, enhancing transparency. FedHD is architecture-agnostic, privacy-preserving, and supports personalized yet collaborative training across diverse institutions. Experiments on TCGA-IDH, CAMELYON16, and CAMELYON17 show that FedHD consistently outperforms state-of-the-art federated and distillation baselines.
Authors: Aharon Azulay, Jan Dubi\'nski, Zhuoyun Li, Atharv Mittal, Yossi Gandelsman
Abstract: The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the substitute term, (3) replacing harmful text in images (e.g., on book covers) with benign words while visual context preserves the original meaning, and (4) visual analogy puzzles whose solution requires inferring a prohibited concept. Evaluating across six frontier VLMs, our visual attacks bypass safety alignment and expose a cross-modality alignment gap: text-based safety training does not automatically generalize to harmful intent conveyed visually. For example, our visual cipher achieves 40.9% attack success on Claude-Haiku-4.5 versus 10.7% for an equivalent textual cipher. To further our insight into the attack mechanism, we present preliminary interpretability and mitigation results. These findings highlight that robust VLM alignment requires treating vision as a first-class target for safety post-training.
Authors: Jiayu Li, Jiaxin Qi, Sheng Zhou, Jiaqiang Huang, Xiansheng Hua
Abstract: Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise, as mislabeled samples generate disproportionately large gradients that can overwhelm pre-trained priors. We argue that because CLIP already provides a near-optimal initialization, adaptation should be inherently conservative, particularly against the extreme gradient updates common in noisy settings. To this end, we propose Double-Softmax Prompt Tuning (DSPT), a hyperparameter-free method for intrinsic gradient suppression. By applying a sequential probabilistic normalization, DSPT induces a self-adaptive saturation zone that suppresses gradients from high-error noisy samples while maintaining informative updates. We also provide both theoretical analysis and empirical evidence about how this mechanism achieves adaptive suppression. This design transforms ``gradient vanishing'', traditionally a training bottleneck, into a principled noise-filtering shield for label-noise prompt tuning. Extensive experiments confirm that this simple, drop-in design achieves state-of-the-art robustness across various noisy benchmarks, outperforming methods with complex architectures and handcrafted hyperparameters.
Authors: Lukas Ostendorf, Lennart Reiher, Onn Haran, Lutz Eckstein
Abstract: Perception for automated driving is largely based on onboard environmental sensors, such as cameras and radar, which are cost-effective but limited by line-of-sight and field-of-view constraints. These inherent limitations may cause onboard perception to fail under occlusions or poor visibility conditions. In parallel, cooperative awareness via vehicle-to-everything (V2X) communication is becoming increasingly available, enabling vehicles and infrastructure to share their own state as object-level information that complements onboard perception. In this work, we study how such V2X information can be integrated into 3D object detection and how robust the resulting system is to realistic V2X imperfections. Using the nuScenes dataset, we emulate object-level cooperative awareness messages from ground truth, injecting controlled noise and object dropout to mimic real-world conditions such as latency, localization errors, and low V2X penetration rates. We convert these messages into a dedicated bird's-eye view (BEV) input and fuse them into a BEVFusion-style detector. Our results demonstrate that while object-level cooperative information can substantially improve detection performance, achieving an NDS of 0.80 under favorable conditions, models trained on idealized data become fragile and over-reliant on V2X. Conversely, our proposed noise-aware training strategy, coupled with explicit confidence encoding, enhances robustness, maintaining performance gains even under severe noise and reduced V2X penetration.
Authors: Hao Wei, Yanhui Zhou, Chenyang Ge, Saeed Anwar, Ajmal Mian
Abstract: Most recent extreme rescaling methods struggle to preserve semantically consistent structures and produce realistic details, due to the severely ill-posed nature of low- to high-resolution mapping under scaling factors of $16\times$ or higher. To alleviate the above problems, we propose FaithEIR, a diffusion-based framework for extreme image rescaling. Inspired by singular value decomposition, we develop learnable reversible transformation that enables invertible downscaling and upscaling in the latent space. To compensate for information loss due to quantization, we propose an adaptive detail prior, a high-frequency dictionary that captures the empirical average of commonly occurring structures in the training data. Finally, we design a lightweight pixel semantic embedder to provide semantic conditioning for the pretrained diffusion model. We present extensive experimental results demonstrating that our FaithEIR consistently outperforms state-of-the-art methods, achieving superior reconstruction fidelity and perceptual quality. Our code, model weights, and detailed results are released at https://github.com/cshw2021/FaithEIR.
Authors: Hang Wang, Chao Shen, Chenhao Lin, Minghui Yang, Lei Zhang, Cong Wang
Abstract: The proliferation of advanced AI video synthesis techniques poses an unprecedented challenge to digital video authenticity. Existing AI-generated video (AIGV) detection methods primarily focus on uni-modal or spatiotemporal artifacts, but they overlook the rich cues within the visual-textual cross-modal space, especially the temporal stability of semantic alignment. In this work, we identify a distinctive fingerprint in AIGVs, termed cross-modal temporal artifact (CMTA). Unlike real videos that exhibit natural temporal fluctuations in cross-modal alignment due to semantic variations, AIGVs display unnaturally stable semantic trajectories governed by given input prompts. To bridge this gap, we propose the CMTA framework, a cross-modal detection approach that captures these unique temporal artifacts through joint cross-modal embedding and multi-grained temporal modeling. Specifically, CMTA leverages BLIP to generate frame-level image captions and utilizes CLIP to extract corresponding visual-textual representations. A coarse-grained temporal modeling branch is then designed to characterize temporal fluctuations in cross-modal alignment with a GRU. In parallel, a fine-grained branch is constructed to capture intricate inter-frame variations from integrated visual-textual features with a Transformer encoder. Extensive experiments on 40 subsets across four large-scale datasets, including GenVideo, EvalCrafter, VideoPhy, and VidProM, validate that our approach sets a new state-of-the-art while exhibiting superior cross-generator generalization. Code and models of CMTA will be released at https://github.com/hwang-cs-ime/CMTA
Authors: Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli
Abstract: Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically similar examples during generation, BlenderRAG improves compilation success rates from 40.8% to 70.0% and semantic normalized alignment from 0.41 to 0.77 (CLIP similarity) across four state-of-the-art LLMs, without requiring fine-tuning or specialized hardware, making it immediately accessible for deployment. The dataset and code will be available at https://github.com/MaxRondelli/BlenderRAG.
Authors: Houyuan Chen, Hong Li, Xianghao Kong, Tianrui Zhu, Shaocong Xu, Weiqing Xiao, Yuwei Guo, Chongjie Ye, Lvmin Zhang, Hao Zhao, Anyi Rao
Abstract: Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs that are activated when a modality serves as the generation target, preserving the strong priors of the VDM. Cross-Modal Self-Attention (CMSA) shares keys and values across modalities while keeping modality-specific queries, facilitating information exchange and inter-modal alignment. We instantiate UniVidX in two domains: UniVid-Intrinsic, for RGB videos and intrinsic maps including albedo, irradiance, and normal; and UniVid-Alpha, for blended RGB videos and their constituent RGBA layers. Experiments show that both models achieve performance competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github.io/UniVidX.github.io/
Authors: Jaeyoung Chung, Suyoung Lee, Kyoung Mu Lee
Abstract: We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established during the early stages of the diffusion process and exhibits high sensitivity to the initial noise. Such characteristics compromise stability in tasks like inpainting and editing, where the model must ensure strict alignment with the existing context while synthesizing a new structure. In this paper, we introduce a strategy to optimize the initial noise within the structured 3D latent diffusion framework, ensuring high-fidelity 3D inpainting. Specifically, we update the initial noise by leveraging a backpropagation approximation grounded in the rectified flow model, with the spectral parameterization specially designed for robust and efficient structured 3D latent optimization. Experiments demonstrate consistent improvements in contextual consistency and prompt alignment over representative training-free inpainting baselines, establishing initial noise control as an independent dimension for 3D inpainting, orthogonal to conventional sampling trajectory manipulation.
Authors: Seowung Leem, Yunchao Yang, Adam J. Woods, Ruogu Fang
Abstract: The systemic, metabolic, lifestyle factors have established associations with Alzheimer's Disease (AD) through epidemiologic and AD-specific biomarker studies. Whether colored fundus photography (CFP) contains retinal structural signatures corresponding to these AD-related risk domains remains unclear. To determine whether deep learning (DL) models can predict 12 AD-related risk factors from CFP and to characterize the retinal structures underlying these predictions, thereby assessing whether CFP reflects pathways to AD vulnerability. Using UK Biobank CFPs, DL models were trained using 62,876 images from 44,501 unique participants to predict 12 factors linked to AD incidence: 6 categorical (sex, smoking, sleeplessness, economic status, alcohol use, depression) and 6 continuous (age, age at completing education, BMI, systolic, diastolic blood pressure, HbA1c). Model performance, model saliency, and saliency-derived scores (CAM-Score) were evaluated and compared to retinal morphometry. The scores were also compared between incident-AD cases (average 8.55 years before onset) and matched controls. Performance of DL ranged from AUROC= 0.5654-0.9480 for categorical and R2=-0.0291-0.7620 for continuous factors, outperforming most of the morphometry-machine learning models. Saliency-based score consistently highlighted biologically meaningful regions, particularly the optic nerve head and retinal vasculature. It also aligned with present morphometric variations. Several saliency-based scores differed significantly between incident AD and matched controls, suggesting potential overlap between retinal correlates of risk factors and preclinical AD-associated changes. CFP encodes retinal signatures linked to AD risk factors. Although not diagnostic, DL-derived retinal representations may uncover biologically meaningful risk-related structural changes mirroring the potential AD vulnerability.
Authors: Vishal, Arnav Aditya, Nitin Kumar, Saurabh J. Shigwan
Abstract: Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to common conditions. This imbalance poses a dual challenge for Open-Set Recognition (OSR): models must maintain high classification accuracy on known classes while reliably rejecting unknown samples unseen during training in the clinical settings. While recently proposed Deep Simplex Classifier (DSC)~\cite{cevikalp2024reaching} and UnCertainty-aware Deep Simplex Classifier (UCDSC)~\cite{Aditya_2026_WACV} successfully leverage Neural Collapse to ensure maximal inter-class separation, they rely on a uniform margin that does not account for the varying densities of medical classes. In this paper, we propose DMDSC an enhanced framework featuring a dynamic margin approach. Our approach automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance. Extensive experiments conducted on diverse medical benchmarks on BloodMNIST\cite{medmnistv2}, OCTMNIST\cite{medmnistv2}, DermaMNIST\cite{medmnistv2}, and BreaKHis~\cite{spanhol2015dataset} datasets, demonstrate that our framework outperforms state-of-the-art methods.
Authors: Zahid Hassan Tushar, Sanjay Purushotham
Abstract: Aerosol Optical Depth (AOD) retrieval is essential for Earth observation, supporting applications from air quality monitoring to climate studies. Conventional physics-based AOD retrieval methods formulate the problem as a pixel-wise inversion, relying on radiative transfer modeling, memory-intensive look-up tables, and auxiliary meteorological data. While recent data-driven approaches have shown promise, many fail to exploit the spatial-spectral coherence of hyperspectral imagery, leading to spatially inconsistent and noise-sensitive retrievals. We present the first study exploring Foundation AI models for AOD retrieval and propose ViTCG, a Vision Transformer with Channel-wise Grouping-based spatial regression framework that reduces retrieval bias and error. ViTCG uses hyperspectral top-of-atmosphere radiance as input and jointly models spatial context and spectral information. Validation with PACE radiance observations demonstrates a 62% reduction in mean squared error compared to state-of-the-art foundation models, including Prithvi, and produces spatially coherent AOD fields.
Authors: Zhanjie Hu, Bolin Zhang, Jianhua Wang, Jianbo Zheng, Chenchen Yan, Takahiro Komamizu, Ichiro Ide, Jiangbo Qian
Abstract: Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. Recently, Graph Convolutional Networks (GCN) have been widely adopted in TVG to model temporal relations among video clips and enhance contextual reasoning by constructing clip-level graphs. Despite their effectiveness, existing GCN-based TVG methods encounter three critical bottlenecks: 1) Most methods construct graph nodes using either static or dynamic features alone, resulting in incomplete visual representation and overlooking complementary semantics, 2) Most methods construct temporal graphs in a query-agnostic manner, leading to inefficient feature interaction within the temporal graph representation, and 3) Most methods often suffer from a single-granularity semantic matching, while direct training on complex temporal localization task may lead to slow convergence and suboptimal precision. To address these challenges, we propose Static and Dynamic Graph Alignment Network (SDGAN). First, SDGAN jointly exploits static and dynamic visual features to construct two complementary temporal graphs and performs Position-wise Nodes Alignment, enabling more expressive and robust visual representation. Second, SDGAN introduces Query-Clip Contrastive Learning and Adaptive Graph Modeling to explicitly align visual clips with their corresponding textual queries, yielding query-aware visual representations. Third, SDGAN incorporates multi-granularity temporal proposals within Progressive Easy-to-Hard Training Strategy, effectively bridging coarse-grained semantic localization and fine-grained temporal boundary refinement. Extensive experiments on three benchmark datasets demonstrate that SDGAN achieves superior performance across complex TVG scenarios. Codes and datasets are available at https://github.com/ZhanJieHu/SDGAN.
Authors: Guandong Li, Mengxia Ye
Abstract: Image editing instructions are heterogeneous: a color swap, an object insertion, and a physical-action edit all demand different spatial coverage and different reasoning depth, yet existing reasoning-based editors apply a single fixed inference recipe to every instruction. We argue that adaptivity along both the spatial and temporal axes is the missing degree of freedom, and we present PhysEdit, an editing framework built around this principle. PhysEdit introduces two inference-time modules that compose without retraining the backbone. At its core, (1) Complexity-Adaptive Reasoning Depth (CARD) predicts edit complexity directly from the instruction and reference image and allocates the reasoning step count N_r and reasoning-token length r per sample -- turning a previously fixed inference schedule into a conditional-computation problem. CARD is supported by (2) a Spatial Reasoning Mask (SRM) that extracts an instruction-conditioned spatial prior from cross-attention to confine reasoning to regions that semantically require it. On the full 737-case ImgEdit Basic-Edit Suite, PhysEdit delivers a 1.18x wall-clock speedup (64.3s vs. 76.1s per sample) over a strong reasoning baseline while slightly improving instruction adherence (CLIP-T 0.2283 vs. 0.2266, +0.7%) and matching identity preservation within noise (CLIP-I 0.8246 vs. 0.8280). The speedup is category-dependent and reaches 1.52x on appearance-level edits, validating CARD's adaptive allocation as the principal source of efficiency gain. A 30-sample pilot with full ablations isolates the contribution of each module.
Authors: Tongxu Zhang
Abstract: Knee osteoarthritis (OA) assessment involves a natural but often underused label hierarchy: a coarse binary OA decision and a fine-grained Kellgren--Lawrence (KL) severity grade. Existing deep learning studies commonly treat these targets as separate classification problems, either reducing OA assessment to disease presence or directly optimizing noisy ordinal KL labels. In this work, we ask whether this clinical hierarchy can serve as a representation-level supervisory prior. Rather than introducing a complex architecture, we use a deliberately simple dual-head model with a shared encoder and two task-specific heads as a probe of hierarchical supervision. We compare single-OA, single-KL, and dual-head training across multiple 3D backbones under the same test protocol. Beyond standard classification metrics, we perform paired statistical comparisons, analyze latent severity-axis geometry, and examine saliency overlap with cartilage regions. The results show that dual-head supervision produces backbone-dependent gains, with clear improvements in KL-related metrics for selected backbones. More importantly, the gains are accompanied by a more ordered coarse-to-fine latent organization and, for responsive backbones, stronger anatomical alignment of saliency with cartilage. These findings suggest that even simple hierarchical dual-head supervision can reshape disease representations under noisy coarse/fine labels, providing a useful inductive bias for OA diagnosis and severity grading.
Authors: Yinghao Chen, Yeying Jin, Xiang Chen, Yanyan Wei, Ziyang Yan, Yaowen Fu
Abstract: Unsupervised deraining has attracted attention for its ability to learn the real-world distribution of rain without paired supervision. However, the lack of strong constraints makes it difficult for the network to converge, especially with the complex diversity of rain degradation. A key motivation is that high-quality deraining results occasionally emerge during training, which can be leveraged to guide the optimization process. To overcome these challenges, we introduce RGSUD (Reward-Guided Self-Reinforcement Unsupervised Image Deraining), comprising two key stages: reward recycling and self-reinforcement (SR) training. For the former stage, we propose an Image Quality Assessment (IQA)-based dynamic reward recycling mechanism that selects optimal derained outputs during training and continuously collects high-quality deraining images. In latter stage, we incorporate these rewards into the model's optimization process, constraining the optimization space and improving alignment between derained outputs and clean images. By leveraging IQA-based self-reinforced loss and dynamically updated rewards, we enhance the quality of synthesized pseudo-paired data and stabilize the optimization. Extensive experiments demonstrate that our method achieves SOTA performance across multiple datasets, including paired synthetic, paired real, and unpaired real images, outperforming existing unsupervised deraining approaches in both subjective and objective IQA metrics. Additionally, we show that the self-reinforcement strategy is adaptable to other unsupervised deraining methods and our deraining framework demonstrates strong generalization across existing supervised deraining networks.
Authors: Qiancheng Zhou, Wenhua Zhang
Abstract: Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs. Current state-of-the-art (SOTA) methods achieve high precision by recovering mask supervision through explicit, offline pseudo-label construction, such as multi-stage active learning and physics-driven mask generation. In this paper, we study a minimalist alternative: generating point-to-mask supervision online through in-batch, point-anchored feature-affinity propagation. We instantiate this paradigm as GSACP, an end-to-end testbed that directly supervises the detector using hard-margin feature affinity gated by local image priors, entirely eliminating external label-evolution loops. This compact design, however, exposes an optimization bottleneck. Because the affinity target is generated from the same feature representation being optimized, training forms a self-referential loop. We theoretically formalize this as \emph{Self-Referential Propagation Drift}, a representation-supervision entanglement that can sharpen true boundaries or distort the feature space to satisfy its own targets. To systematically isolate these failure modes, we apply a protocolized single-variable ablation procedure spanning local EMA teacher decoupling, hard-background contrastive separation, and adaptive support geometry. On the SIRST3 dataset, GSACP-Final establishes a new ultra-low false-alarm operating regime, achieving a highly competitive $0.6674$ mIoU while demonstrating a $38\% relative reduction in false-positive artifacts ($\mathrm{Fa}$) compared with PAL. By systematically deconstructing the end-to-end paradigm, we map its performance boundaries and show that in-batch feature propagation provides a compact alternative for deployment scenarios where false-alarm suppression is paramount.
Authors: Mohammad Aamir Sohail, Gabriela Pinheiro, Yasemin Poyraz Kocak, Batuhan Hangun, Emre Camkerten, Simge Yigit, Hafize Asude Ertan
Abstract: Edge detection refers to identifying points in a digital image where intensity changes sharply, indicating object boundaries or structural features. Corners are locations where gray-level intensity changes abruptly in multiple directions and are widely used in feature extraction, object tracking, and 3D modeling. In this study, we present a quantum implementation of Sobel-based edge detection and Harris-style corner detection. Two quantum image encoding methods - Flexible Representation of Quantum Images (FRQI) and Quantum Probability Image Encoding (QPIE) - are used to encode the input data and are comparatively analyzed. The proposed approach introduces a quantum gradient computation scheme based on lag-2 differences, enabling the evaluation of gradient-like features in superposition. To improve detection quality and reduce false positives, a classical post-processing step is applied to candidate corner points identified by the quantum circuit. Results show that the proposed quantum circuits produce outputs consistent with classical Sobel and Harris operators. Furthermore, the QPIE-based configuration yields more stable and coherent results than FRQI, especially under limited measurement shots. While gradient computation can be performed efficiently at the circuit level, the overall cost remains dominated by state preparation, measurement, and classical post-processing. All experiments are conducted under noiseless simulation, and performance on NISQ hardware may be affected by noise and measurement limitations. Therefore, this work demonstrates a functional and scalable quantum realization of classical edge and corner detection methods rather than an end-to-end speedup.
Authors: Lin Che, Xi Wang, Marc Pollefeys, Konrad Schindler, Martin Raubal, Peter Kiefer
Abstract: Urban perception describes how people subjectively evaluate urban environments, shaping how cities are experienced and understood. Existing computational approaches primarily model urban perception directly from street view images, but largely ignore the human perceptual process through which such judgments are formed. In this paper, we introduce Place Pulse-Gaze, an urban perception dataset that augments street view images with synchronized eye-tracking recordings and individual perception labels. Based on this dataset, we propose a Gaze-Guided Urban Perception Framework to study how gaze behavior contributes to the modeling of subjective urban perception. The framework systematically investigates three complementary settings: gaze-only modeling, gaze fusion with explicit semantic scene representations, and gaze fusion with implicit richer visual representations. Experiments show that gaze alone already carries useful predictive signals for subjective urban perception, and that integrating gaze with scene representations further improves prediction under both semantic and richer visual representations. Overall, our findings highlight the importance of incorporating human perceptual processes into urban scene understanding and open a direction for gaze-guided multimodal urban computing.
Authors: Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang, Jiaolong Yang, Kyoung Mu Lee
Abstract: 3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid layouts and suffer from inconsistencies in object scale throughout the entire world. In this work, we introduce a novel framework, Map2World, that first enables 3D world generation conditioned on user-defined segment maps of arbitrary shapes and scales, ensuring global-scale consistency and flexibility across expansive environments. To further enhance the quality, we propose a detail enhancer network that generates fine details of the world. The detail enhancer enables the addition of fine-grained details without compromising overall scene coherence by incorporating global structure information. We design the entire pipeline to leverage strong priors from asset generators, achieving robust generalization across diverse domains, even under limited training data for scene generation. Extensive experiments demonstrate that our method significantly outperforms existing approaches in user-controllability, scale consistency, and content coherence, enabling users to generate 3D worlds under more complex conditions.
Authors: Xihao Chen, Yangyang Guo, Roger Zimmermann
Abstract: Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial GPU memory overhead due to the large number of vision tokens processed during the prefill stage. To tackle this problem, we propose LightKV, a novel approach that reduces KV cache size by exploiting the redundancy among vision-token embeddings. Guided by text prompts, LightKV employs cross-modality message passing to aggregate informative messages across vision tokens and progressively compress them during prefill. This prompt-aware guidance distinguishes our method from prior vision-only compression strategies. We evaluate LightKV on eight open-source LVLMs across eight public benchmark datasets, e.g., MME and SeedBench. Experimental results demonstrate that with only 55% of the original vision tokens, LightKV (a) halves the vision-token KV cache size, (b) reduces computation by up to 40%, and (c) preserves general-purpose performance while significantly outperforming existing baselines.
Authors: Xinyuan Zhao, Yihang Wu, Ahmad Chaddad, Sarah A. Alkhodair, Reem Kateb
Abstract: Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges with convolutional neural network (CNN)-based, transformer-based, and contrastive language-image pre-training (CLIP)-based methods, including late fusion of image features, lack of factor-aware conditioning, and impractical capacity scaling. To address these challenges, we propose Globally-conditioned Multi-scale Gaze estimation (GMGaze), which leverages a multi-scale transformer architecture. Specifically, the model first introduces semantic prototype conditioning, which modulates the CLIP global image embedding using four learned prototype banks (i.e., illumination, background, head pose and appearance) to generate two complementary context-biased global tokens. These tokens, along with the CLIP patch and CNN tokens, are fused at the first layer. This early unified fusion prevents information loss common in late-stage merging. Finally, each token passes through sparse Mixture-of-Experts modules, providing conditional computational capacity without uniformly increasing dense parameters. For cross-domain adaptation, we incorporate an adversarial domain adaptation technique with a feature separation loss that encourages the two global tokens to remain de-correlated. Experiments using four public benchmarks (MPIIFaceGaze, EYEDIAP, Gaze360, and ETH-XGaze) show that GMGaze achieves mean angular errors of 2.49$^\circ$, 3.22$^\circ$, 10.16$^\circ$, and 1.44$^\circ$, respectively, outperforming previous baselines in all within-domain settings. In cross-domain evaluations, it provides state-of-the-art (SOTA) results on two standard transfer routes.
Authors: Yan Fang, Mengcheng Lan, Zilong Huang, Weixian Lei, Yunqing Zhao, Yujie Zhong, Yingchen Yu, Qi She, Yao Zhao, Yunchao Wei
Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \textbf{Simplicity}: a single transformer jointly models visual and textual tokens; (2) \textbf{Scalability}: it scales effectively with both data and model size; and (3) \textbf{Performance}: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.
Authors: Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Zefeng He, Muxin Fu, Daizong Liu, Wei-Long Zheng, Yu Cheng
Abstract: While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition function, causing visual attention to decay inversely with generated sequence length. To counteract this, we propose Persistent Visual Memory (PVM), a lightweight learnable module designed to ensure sustained, on-demand visual perception. Integrated as a parallel branch alongside the Feed-Forward Network (FFN) in LVLMs, PVM establishes a distance-agnostic retrieval pathway that directly provides visual embeddings for precise visual perception, thereby structurally mitigating the signal suppression inherent to deep generation. Extensive experiments on Qwen3-VL models demonstrate that PVM brings notable improvements with negligible parameter overhead, delivering consistent average accuracy gains across both 4B and 8B scales, particularly in complex reasoning tasks that demand persistent visual perception. Furthermore, in-depth analysis reveals that PVM can resist length-induced signal decay and accelerate internal prediction convergence.
Authors: George Stoica, Sayak Paul, Matthew Wallingford, Vivek Ramanujan, Abhay Nori, Winson Han, Ali Farhadi, Ranjay Krishna, Judy Hoffman
Abstract: Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each training sample supervises only a single trajectory and intermediate point, yielding an extremely sparse and high-variance training signal. This under-constrained supervision can cause flow collapse, where the learned dynamics memorize specific source-target pairings, mapping diverse inputs to overly similar outputs, failing to generalize. We introduce Posterior-Augmented Flow Matching (PAFM), a theoretically grounded generalization of FM that replaces single-target supervision with an expectation over an approximate posterior of valid target completions for a given intermediate state and condition. PAFM factorizes this intractable posterior into (i) the likelihood of the intermediate under a hypothesized endpoint and (ii) the prior probability of that endpoint under the condition, and uses an importance sampling scheme to construct a mixture over multiple candidate targets. We prove that PAFM yields an unbiased estimator of the original FM objective while substantially reducing gradient variance during training by aggregating information from many plausible continuation trajectories per intermediate. Finally, we show that PAFM improves over FM by up to 3.4 FID50K across different model scales (SiT-B/2 and SiT-XL/2), different architectures (SiT and MMDiT), and in both class and text conditioned benchmarks (ImageNet and CC12M), with a negligible increase in the compute overhead. Code: https://github.com/gstoica27/PAFM.git.
Authors: Siyang Li, Yize Chen, Zijie Zhu, Yuxin Pan, Yan Guo, Ming Huang, Hui Xiong
Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for two reasons. First, the non-stationary and uncertain nature of time series data lead to inevitable temporal distribution shifts between historical training and future testing data, while current Supervised FineTuning (SFT)-based methods are prone to overfitting and may degrade generalization. Second, training data availability varies across forecasting tasks, requiring TSFMs to generalize well under diverse data regimes. To address these challenges, we introduce the Time series Reinforcement Finetuning (TimeRFT) paradigm for TSFM downstream adaptation, which consists of two task-specific training recipes: i) A forecasting quality-based temporal reward mechanism that conducts a multi-faceted evaluation of the contribution of each prediction step to overall forecasting accuracy. ii) A forecasting difficulty-based data selection strategy to identify time series samples with generalizable predictive patterns and informative training signals. Extensive experiments demonstrate TimeRFT can consistently outperform SFT-based adaptation methods across various real-world forecasting tasks and training data regimes, enhancing prediction accuracy and generalization against unforeseen distribution shifts.
Authors: Vishwanath Saragadam, Niki Nezakati, Amit Roy-Chowdhury, Vivek Boominathan
Abstract: Traditional glass-based optics are typically optimized for narrow spectral bands, such as the visible (400-700nm) or shortwave infrared (1000-1800nm). While the emergence of VIS-SWIR sensors (400-1700nm) offers transformative potential, refractive optics struggle to focus this entire range simultaneously. Mirrors represent a promising achromatic alternative; however, they are often sidelined by field curvature, and off-axis aberrations. This paper introduces Computational Mirrors, a framework that enables high-resolution, wide-field-of-view imaging across the complete VIS-SWIR spectrum using a single sensor. Our method is built on the observation that distinct regions of the field of view reach focus at varying distances from the mirror. By capturing a minimal focal stack (2-4 images), we utilize a computational backend to recover a sharp, all-in-focus image. A key contribution of this work is SeidelConv, a novel, physics-inspired, spatially-varying point spread function (PSF) model designed to accurately characterize and correct the off-axis aberrations inherent in simple concave mirrors. We demonstrate the efficacy of our approach using a first-of-its-kind 50mm F/1 optical system equipped with a VIS-SWIR sensor. Our system produces sharp images across RGB, NIR, and SWIR wavelengths without requiring refocusing, revealing material details invisible within individual spectral bands. We further validate the scalability of our approach with a 100mm F/2 system optimized for long-range imaging.
Authors: Yanchen Guan, Haicheng Liao, Chengyue Wang, Zhenning Li
Abstract: Traffic accidents are routinely documented in textual reports, yet physically grounded accident reconstruction remains difficult because detailed scene measurements and expert reconstructions are scarce, costly and hard to scale. Here we formulate accident reconstruction from publicly accessible reports and scene measurements as a parameterized multimodal learning problem. We construct CISS-REC, a dataset of 6,217 real-world accident cases curated from the NHTSA Crash Investigation Sampling System, and develop a reconstruction framework that grounds report semantics to road topology and participant attributes, reconstructs lane consistent pre-impact motion, and refines collision relevant interactions through localized geometric reasoning and temporal allocation. Our method outperforms representative baselines on CISS-REC, achieving the strongest overall reconstruction fidelity, including improved accident point accuracy and collision consistency. These results show that public accident reports can serve as scalable computational substrates for quantitatively verifiable accident reconstruction, with potential value for traffic safety analysis, simulation and autonomous driving research.
Authors: Hao Luo, Wanpeng Zhang, Yicheng Feng, Sipeng Zheng, Haiweng Xu, Chaoyi Xu, Ziheng Xi, Yuhui Fu, Zongqing Lu
Abstract: Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to actions, but sparse action supervision often encourages shortcut mappings rather than representations of dynamics, contact, and task progress. Recent world-action models introduce future prediction through video rollouts, yet pixel-space prediction is a costly and indirect substrate for control, as it may model visual details irrelevant to action generation and introduces substantial training or inference overhead. We present Being-H0.7, a latent world-action model that brings future-aware reasoning into VLA-style policies without generating future frames. Being-H0.7 inserts learnable latent queries between perception and action as a compact reasoning interface, and trains them with a future-informed dual-branch design: a deployable prior branch infers latent states from the current context, while a training-only posterior branch replaces the queries with embeddings from future observations. Jointly aligning the two branches at the latent reasoning space leads the prior branch to reason future-aware, action-useful structure from current observations alone. At inference, Being-H0.7 discards the posterior branch and performs no visual rollout. Experiments across six simulation benchmarks and diverse real-world tasks show that Being-H0.7 achieves state-of-the-art or comparable performance, combining the predictive benefits of world models with the efficiency and deployability of direct VLA policies.
Authors: Bohan Hou, Gen Li, Jindou Jia, Tuo An, Xinying Guo, Sicong Leng, Haoran Geng, Yanjie Ze, Tatsuya Harada, Philip Torr, Oier Mees, Marc Pollefeys, Zhuang Liu, Jiajun Wu, Pieter Abbeel, Jitendra Malik, Yilun Du, Jianfei Yang
Abstract: World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have advanced rapidly with the rise of foundation models and large-scale video generation. However, the literature remains fragmented across architectures, functional roles, and embodied application domains. To address this gap, we present a comprehensive review of world models from a robot-learning perspective. We examine how world models are coupled with robot policies, how they serve as learned simulators for reinforcement learning and evaluation, and how robotic video world models have progressed from imagination-based generation to controllable, structured, and foundation-scale formulations. We further connect these ideas to navigation and autonomous driving, and summarize representative datasets, benchmarks, and evaluation protocols. Overall, this survey systematically reviews the rapidly growing literature on world models for robot learning, clarifies key paradigms and applications, and highlights major challenges and future directions for predictive modeling in embodied agents. To facilitate continued access to newly emerging works, benchmarks, and resources, we will maintain and regularly update the accompanying GitHub repository alongside this survey.
Authors: YiFeng Wang, Zhun Sun, Keisuke Sakaguchi
Abstract: We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit activation-weight quantization. By constructing an input-side residual Hessian from activation quantization residuals (G_x), ARHQ analytically identifies and isolates error-sensitive weight directions into a high-precision low-rank branch. This is achieved via a closed-form truncated SVD on the scaled weight matrix W G^{1/2}_x . Experimental results on Qwen3-4B-Thinking-2507 demonstrate that ARHQ significantly improves layer-wise SNR and preserves downstream reasoning performance on ZebraLogic even under aggressive quantization. The code is available at https://github.com/BeautMoonQ/ARHQ.
Authors: Ali Emre Oztas, Mahir Demir, James Garside, Mikel Luj'an
Abstract: Video and image streaming on edge devices requires low latency. To address this, Neural Networks (NNs) are widely used, and prior work mainly focuses on accelerating them with single hardware units such as Graphics Processing Units (GPUs), Field Programmable Gate Arrays (FPGAs), and Deep Learning Processing Units (DPUs). However, further reductions in latency can be observed by combining these units. In this paper, partitioning CNN inference across DPU and GPU (Split CNN Inference) is proposed. The first partition runs on the AI engines (DPU) of a Versal VCK190, which consists of initial CNN layers processing the input images. The DPU processes the first partition near the source of the data. Pipelined asynchronously, a GPU runs the remaining layers. The GPU (NVIDIA RTX 2080) processes the second partition, albeit having reduced the data transfer between the data source (storage/camera) and the GPU. Furthermore, a Graph Neural Network (GNN)-based partition index prediction method is proposed to automate the partitioning of CNNs needed for the Split Inference. Well established models such as LeNet-5, ResNet18/50/101/152, VGG16, and MobileNetv2 are analyzed. Results demonstrate up to 2.48x latency improvement over DPU-only execution and up to 3.37x over GPU-only execution. The trained GNN model splits the layers between the appropriate devices with 96.27% accuracy.
Authors: Qianfan Shen, Ningxiao Tao, Qiyu Dai, Tianle Chen, Minghan Qin, Yongjie Zhang, Mengyu Chu, Wenzheng Chen, Baoquan Chen
Abstract: We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, expert-tuned parameters, and labor-intensive workflows, limiting their scalability to the real world. Recent scene modeling advances like 3D Gaussian Splatting (3DGS) enable high-fidelity real-world scene reconstruction, yet lack physical grounding for combustion. To bridge this gap, we propose FieryGS, a physically-based framework that integrates physically-accurate and user-controllable combustion simulation and rendering within the 3DGS pipeline, enabling realistic fire synthesis for real scenes. Our approach tightly couples three key modules: (1) multimodal large-language-model-based physical material reasoning, (2) efficient volumetric combustion simulation, and (3) a unified renderer for fire and 3DGS. By unifying reconstruction, physical reasoning, simulation, and rendering, FieryGS removes manual tuning and automatically generates realistic, controllable fire dynamics consistent with scene geometry and materials. Our framework supports complex combustion phenomena -- including flame propagation, smoke dispersion, and surface carbonization -- with precise user control over fire intensity, airflow, ignition location and other combustion parameters. Evaluated on diverse indoor and outdoor scenes, FieryGS outperforms all comparative baselines in visual realism, physical fidelity, and controllability. Project page can be found at https://pku-vcl-geometry.github.io/FieryGS/.
Authors: Yajvan Ravan, Adam Rashid, Alan Yu, Kai McClennen, Gio Huh, Kevin Yang, Zhutian Yang, Qinxi Yu, Xiaolong Wang, Phillip Isola, Ge Yang
Abstract: We introduce Lucid-XR, a generative data engine for creating diverse and realistic-looking multi-modal data to train real-world robotic systems. At the core of Lucid-XR is vuer, a web-based physics simulation environment that runs directly on the XR headset, enabling internet-scale access to immersive, latency-free virtual interactions without requiring specialized equipment. The complete system integrates on-device physics simulation with human-to-robot pose retargeting. Data collected is further amplified by a physics-guided video generation pipeline steerable via natural language specifications. We demonstrate zero-shot transfer of robot visual policies to unseen, cluttered, and badly lit evaluation environments, after training entirely on Lucid-XR's synthetic data. We include examples across dexterous manipulation tasks that involve soft materials, loosely bound particles, and rigid body contact. Project website: https://lucidxr.github.io
Authors: Yuhui Lu, Wenjing Liu, Kun Zhan
Abstract: Standard diffusion models for graph generation typically rely on uniform time-stepping, an approach that overlooks the non-homogeneous dynamics of distributional evolution on complex manifolds. In this paper, we present an information-geometric framework that reinterprets the diffusion sampling trajectory as a parametric curve on a Riemannian manifold. Our key observation is that the Fisher-Rao metric provides a principled measure of the intrinsic distance. By analyzing this metric, we derive the Drift Variation Score (DVS), a geometry-aware indicator that quantifies the instantaneous rate of distributional change. Unlike prior heuristic-based adaptive samplers, our DVS solver enforces a constant informational speed on the statistical manifold, automatically maintaining a uniform rate of distributional change along the sampling trajectory. This equal arc-length strategy ensures that each discretization step contributes equally to the information speed. Theoretical analysis verifies that DVS characterizes the local stiffness of the sampling dynamics in the Fisher-Rao sense. Experimental results on molecule and social network generation show that DVS significantly improves structural fidelity and sampling efficiency. Code is at https://github.com/kunzhan/DVS
Authors: Manav Batavia, Cheng Chen, Anna Natalie Chlopecki, Timothy Duff, William Huang, Aolong Li, Wanchun Shen
Abstract: We introduce the package \texttt{EliminationTemplates} for the Macaulay2 computer algebra system, which provides tools for constructing automatic solvers for families of zero-dimensional radical ideals depending on algebraically independent parameters. This article provides a self-contained description of how elimination templates are constructed for such families and their specialization properties. Additionally, we describe the main functionality and datatypes provided by our package, and illustrate its usage on several examples, including applications from computer vision from which elimination templates originated.
Authors: Kaiwen Zuo, Shuyuan Yang, Zonghe Chua
Abstract: Grasp force estimation can help prevent robots from damaging delicate objects during manipulation and improve learning-based robotic control. Integrating force sensing into deformable grippers negotiates trade-offs in cost, complexity, mechanical robustness, and performance. With the growing integration of RGB-D wrist cameras into robotic systems for control purposes, camera-based techniques are a promising solution for indirect visual force estimation. Current approaches mostly utilize end-to-end deep learning, which can be brittle when generalizing to new scenarios, while existing model-based approaches are unsuited to grasping and modern grasper geometries. To address these challenges, we developed a model-based visual force sensing approach integrating an iterative contact localization with generalization to unseen objects. The system extracts structural key points from wrist camera RGB-D images of deforming fin-ray-shaped soft grippers, and uses these key points to define parameters of an inverse finite element analysis simulation in Simulation Open Framework Architecture. The iterative contact localization sub-system utilizes a deep learning-based online 3D reconstruction and pose estimation pipeline to dynamically update contact location, and is robust to visual occlusion and unseen objects. Our system demonstrated an average root mean square error of 0.23 N and normalized root mean square deviation of 2.11% during the load phase, and 0.48 N and 4.34% over the entire grasping process when interacting with different objects under various conditions, showcasing its potential for real-time model-based indirect force sensing of soft grippers.
Authors: Charles Weng, Dingwen Li, Alexander Martin
Abstract: Single-prompt first-token probabilities from zero-shot vision-language model (VLM) safety classifiers are treated as decision scores, but we show they are unreliable under semantically equivalent prompt reformulation: even when the binary label is constrained to a fixed output position, equivalent prompts can induce materially different unsafe probabilities for the same sample. Across multimodal safety benchmarks and multiple VLM families, cross-prompt variance is strongly associated with prompt-level disagreement and higher error, making it a useful fragility diagnostic. A training-free mean ensemble improves NLL on all 14 dataset-model evaluation pairs and ECE on 12/14 relative to a train-selected single-prompt baseline, and wins more head-to-head NLL comparisons than labeled temperature scaling, Platt scaling, and isotonic regression applied to the same prompt. Ranking gains are consistent against the train-selected baseline on both AUROC and AUPRC, and against the full 15-prompt distribution remain consistent on AUPRC while softening on AUROC. Labeled calibration on top of the mean provides further gains when labels are available, identifying prompt averaging as a strong label-free first stage rather than a replacement for calibration. We frame this as a reliability stress test for zero-shot VLM first-token safety scores and recommend prompt-family evaluation with mean aggregation as a standard label-free reliability baseline.
Authors: Wei Liu, Hongkai Liu, Zhiying Deng, Yee Whye Teh, Wee Sun Lee
Abstract: LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple preceding layers (commonly known as backward spreading) for cooperative editing. Although widely used for a long time, its underlying basis have not been systematically investigated. In this paper, we first conduct a systematic study of its foundations, which helps clarify its capability boundaries, practical considerations, and potential failure modes. Then, we propose a simple and elegant alternative that replaces backward spreading with forward-propagation. Instead of optimizing the target at the last editing layer, we optimize the anchor point at the first editing layer, and then propagate it forward to obtain accurate and mutually compatible target hidden-states for all subsequent editing layers. This approach achieves the same computational complexity as existing methods while producing more accurate layer-wise targets. Our method is simple, without interfering with either the computation of the initial target hidden state or any other components of the subsequent editing pipeline, and thus constituting a benefit for a wide range of LLM parameter editing methods.
Authors: Akira Takahashi, Ryosuke Sawata, Shusuke Takahashi, Yuki Mitsufuji
Abstract: Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model room-acoustic effects such as reverberation or room impulse responses (RIRs), and thus offer limited controllability over these effects. However, we hypothesize that such V2A models implicitly have semantic knowledge of the relationship between spatial audio and the corresponding vision cues. In this paper, we revisit a V2A model for the sake of the above, and propose the way to utilize the pretrained model as prior for physically grounded room-acoustic processing. Based on one of the state-of-the-art V2A models, MMAudio, we propose MMAudioReverbs that is a unified framework dealing with i) dereverberation and ii) room impulse response (RIR) estimation without network architectural modification, and fine-tuned on a small dataset. Experimental results showed that audio and visual cues respectively have advantage depending on the type of physical room acoustics. It implies that foundation V2A models can be used for physically grounded room-acoustic analysis.
Authors: Hongrui Zheng, Liejun Wang, Zhiqing Guo
Abstract: The advancement of generalized deepfake disruption is constrained by the interruption imbalance, a fundamental bottleneck inherent to the generation of universal perturbations. We reveal that conventional static gradient normalization fundamentally struggles to resolve architectural conflicts, causing the optimization to bias towards susceptible models while neglecting resistant ones. We argue that achieving high and uniform effectiveness requires resolving this imbalance by reaching an adaptive equilibrium. We propose the Adaptive Equilibrium Framework (AEF), which employs a dynamic weighting mechanism that utilizes real-time loss feedback to adaptively assign greater interruption weights to the most resistant models. This approach shifts the optimization from an average-case problem to finding a dynamic balance, driving the perturbation to a uniformly effective equilibrium state. Comprehensive experiments validate that AEF achieves a more balanced interruption performance, maintaining a consistent interruption success rate across the evaluated diverse architectures.
Authors: Ge Luo, Jun-Jie Huang, Qi Yu, Tianrui Liu, Ke Liang, Yuming Xiang, Wentao Zhao, Xinwang Liu, Meng Wang
Abstract: Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learning. However, most existing deep unfolding image fusion methods are derived from alternating minimization, which updates the features of different modalities separately. This design introduces considerable computational and memory overhead, limiting deployment on resource-constrained edge devices. To address this issue, we propose CDNet, a lightweight Combined Dictionary Unfolding Network for multi-source image fusion. Rather than introducing a new sparse coding prior or empirically compressing an existing fusion network, CDNet translates the unique-common decomposition prior of coupled dictionary learning into a structurally constrained joint unfolding architecture. The resulting CDBlock follows a block-sparse interaction topology and performs a model-derived joint update of common and modality-specific representations, thereby streamlining feature learning and improving efficiency.In addition, we design a compact High- and Low-frequency Image Fidelity loss for unsupervised training without ground-truth images. We evaluate CDNet on four tasks, including multi-exposure image fusion, infrared and visible image fusion, medical image fusion, and infrared and visible image fusion for semantic segmentation. Experimental results show that CDNet achieves competitive or superior fusion performance with high efficiency. For infrared and visible image fusion, CDNet outperforms competing methods on four of six metrics on the TNO dataset and five of six metrics on the RoadScene dataset. In particular, it surpasses the second-best method by 1.23 dB and 1.59 dB in PSNR on TNO and RoadScene, respectively.
Authors: Xianbo Cai, Hideyuki Ichiwara, Masaki Yoshikawa, Tetsuya Ogata
Abstract: Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while collecting large-scale data is costly and limited demonstrations may lead to localization drift. Existing approaches make different trade-offs: action-chunking policies such as ACT enable low-latency execution and data efficiency but rely on dense visual features without explicit spatial consistency, generative methods such as Diffusion Policy improve expressiveness but can incur iterative sampling latency, vision-language-action and voxel-based methods enhance generalization and geometric grounding but require higher computational cost and system complexity. We introduce a multistage spatial attention module that extracts stable 2D attention points and jointly predicts future attention sequences with a temporal alignment loss. Built upon ACT with a pretrained ResNet visual prior, a multistage attention module extracts task-relevant 2D attention points as a local spatial modality for action prediction. To maintain consistent object tracking, we introduce a self-supervised objective that aligns predicted attention sequences with visual features from future frames, suppressing drift without keypoint annotations and improving stability of the vision-to-action mapping under limited data. Experiments on simulated and real-world fine manipulation tasks, conducted on the ALOHA bimanual platform, evaluate task success, attention drift, inference latency, and robustness to visual disturbances. Results indicate improvements in localization stability and task performance while maintaining low-latency inference under the tested conditions.
Authors: Kazuya Tateishi, Akira Takahashi, Atsuo Hiroe, Hirofumi Takeda, Shusuke Takahashi, Yuki Mitsufuji
Abstract: Recent advances in multimodal generation have enabled high-quality audio generation from silent videos. Practical applications, such as sound production, demand not only the generated audio but also explicit sound event labels detailing the type and timing of sounds. One straightforward approach involves applying a standard sound event detection to the generated audio. However, this post-hoc pipeline is inherently limited, as it is prone to error accumulation. To address this limitation, we propose MMAudio-LABEL (LAtent-Based Event Labeling), an event-aware audio generation framework built on a foundational audio generation model as its backbone that jointly generates audio and frame-aligned sound event predictions from silent videos. We evaluate our method on the Greatest Hits dataset for onset detection and 17-class material classification. Our approach improves onset-detection accuracy from 46.7% to 75.0% and material-classification accuracy from 40.6% to 61.0% over baselines. These results suggest that jointly learning audio generation and event prediction enables a more interpretable and practical video-to-audio synthesis.
Authors: Mengke Zhao, Guang-Xing Li, Duo Xu, Keping Qiu
Abstract: Complex physical systems, from supersonic turbulence to the macroscopic structure of the universe, are governed by continuous multiscale dynamics. While modern machine learning architectures excel at mapping the high-dimensional observables of these systems, it remains unclear whether they internalize the governing physical laws or merely interpolate discrete statistical correlations. Standard Explainable AI (XAI) architectures, particularly perturbation-based and gradient-saliency methods, rely on pixel-wise perturbations, which generate unphysical artifacts and push inputs off the valid empirical distribution. To resolve this, we introduce a diagnostic framework driven by Constrained Diffusion Decomposition (CDD), a diffusion-based multiscale data decomposition algorithm that enables physically constrained data generation and model evaluation via scale-aware modifications. Applying this framework to a Denoising Diffusion Probabilistic Model (DDPM), we execute deterministic interventions directly within the continuous, CDD-based scale space. We demonstrate that under moderate physical perturbations, the unconstrained generative model exhibits localized structural freezing and non-linear instability rather than continuous PDE-like responses. The network fails to maintain cross-scale continuity, causing the generative trajectory to diverge when pushed into unseen physical states. By synthesizing a continuum of physically coherent states, this scale-informed methodology establishes a controlled test ground to evaluate algorithmic vulnerabilities, providing the rigorous physical constraints necessary for future architectures to respect the multiscale causality of the natural universe.
Authors: Minhee Lee, Sangyoon Lee, Jiwook Lee, Minki Hong, Kyuyoung Kim, Wonhwa Kim, Jaeho Lee
Abstract: Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high speed in vivo optical biopsy for handheld scenarios. However, Lissajous scanning traces a resonant trajectory and samples only the visited pixels per frame; at high frame rates, many pixels remain unvisited, creating structured holes. In this work, we introduce the first benchmark for high-rate Lissajous CLE, consisting of low-quality video clips paired with high-quality reference images. The reference images are wide-FOV mosaics obtained by stitching stabilized, slow-scan frames of the same tissue, enabling temporally aligned supervision. Using this dataset, we propose MIRA, a lightweight recurrent framework for Lissajous CLE restoration that iteratively aggregates temporal context through feature reuse and displacement alignment. Our experiments demonstrate that MIRA outperforms both lightweight and high-complexity baselines in restoration quality while maintaining a favorable computational efficiency suitable for clinical deployment.
Authors: Yao Ni, Jeremie Houssineau, Yew Soon Ong, Piotr Koniusz
Abstract: Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modelling. Existing methods for uncertainty modelling face a fundamental dilemma: Bayesian approaches provide principled estimates but remain computationally prohibitive, while efficient second-order predictors lack rigorous derivations connecting their specific objectives to epistemic uncertainty quantification. To resolve this dilemma, we introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr), a principled framework leveraging possibility theory. We define a possibilistic posterior over parameters, projects this posterior to the prediction space via supremum operators, and approximates the projected posterior using learnable Dirichlet possibility functions. This projection-and-approximation strategy yields a simple training objective with closed-form solutions. Extensive experiments across diverse benchmarks demonstrate that our approach achieves competitive or superior uncertainty quantification performance compared to state-of-the-art evidential deep learning methods while maintaining both principled derivation and computational efficiency. Code will be available at https://github.com/MaxwellYaoNi/DAPPr.
Authors: Montana Hoover, Jing Liang, Tianrui Guan, Dinesh Manocha
Abstract: We introduce Paired-CSLiDAR (CSLiDAR), a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement: refining a ground-scan pose within a 50 m-radius aerial crop. The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites and per-scan reference 6-DoF alignments for sub-meter root-mean-square error (RMSE) evaluation. Because aerial scans capture rooftops and canopy while ground scans capture facades and under-canopy, the two modalities share only a fraction of their geometry, primarily the terrain surface, causing standard registration methods and learned correspondence models to converge to metrically incorrect local minima. We propose Residual-Guided Stratified Registration (RGSR), a training-free, geometry-only refinement pipeline that exploits the shared ground plane through height-stratified ICP, reversed registration directions, and confidence-gated accept-if-better selection. RGSR achieves 86.0% S@0.75 m and 99.8% S@1.0 m on the primary benchmark of 9,012 scans, outperforming both the confidence-gated cascade at 83.7% and GeoTransformer at 76.3%. We validate RMSE-based pose selection with independent survey control and trajectory consistency, and show that added Fourier-Mellin BEV proposals can reduce RMSE while increasing actual pose error under extreme partial overlap. The dataset and code are being prepared for public release.
Authors: Yan Zhang, Daiqing Wu, Huawen Shen, Yu Zhou, Can Ma
Abstract: Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capability for autonomous GUI agents. Recent reinforcement learning methods (e.g., GRPO) have achieved strong performance, but they rely on expensive multiple rollouts and suffer from sparse signals on hard samples. These limitations make on-policy self-distillation (OPSD), which provides dense token-level supervision from a single rollout, a promising alternative. However, its applicability to GUI grounding remains unexplored. In this paper, we present GUI-SD, the first OPSD framework tailored for GUI grounding. First, it constructs a visually enriched privileged context for the teacher using a target bounding box and a Gaussian soft mask, providing informative guidance without leaking exact coordinates. Second, it employs entropy-guided distillation, which adaptively weights tokens based on digit significance and teacher confidence, concentrating optimization on the most impactful and reliable positions. Extensive experiments on six representative GUI grounding benchmarks show that GUI-SD consistently outperforms GRPO-based methods and naive OPSD in both accuracy and training efficiency. Code and training data are available at https://zhangyan-ucas.github.io/GUI-SD/.
Authors: Haojian Huang, Jiahao Shi, Yinchuan Li, Yingcong Chen
Abstract: Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually ambiguous. Recent systems therefore combine multiple skills (e.g., detection, segmentation, interaction-imagination), yet most orchestrate them with fixed pipelines that are poorly matched to per-instance difficulty, offer limited targeted recovery from intermediate errors, and fail to reuse experience from recurring objects. These failures expose a systems problem: test-time grounding must acquire the right evidence, decide whether that evidence is reliable enough to commit, and do so under bounded inference cost without access to labels. We propose Affordance Agent Harness, a closed-loop runtime that unifies heterogeneous skills with an evidence store and cost control, retrieves episodic memories to provide priors for recurring categories, and employs a Router to adaptively select and parameterize skills. An affordance-specific Verifier then gates commitments using self-consistency, cross-scale stability, and evidence sufficiency, triggering targeted retries before a final judge fuses accumulated evidence and trajectories into the prediction. Experiments on multiple affordance benchmarks and difficulty-controlled subsets show a stronger accuracy-cost Pareto frontier than fixed-pipeline baselines, improving grounding quality while reducing average skill calls and latency. Project page: https://tenplusgood.github.io/a-harness-page/.
Authors: Jingxi Pu, Tonghua Liu, Zhilin Guan, Siqiao Li, Yang Ming, Zheng Cong, Wei Zhang, Fangwei Li
Abstract: With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed tomography reduces radiation exposure to patients, it also introduces more noise, which may interfere with visual interpretation by physicians and affect diagnostic results. To address this problem, inspired by Cycle-GAN for unsupervised learning, this paper proposes an end-to-end unsupervised low-dose computed tomography denoising framework. The proposed framework combines a U-Net structure for multi-scale feature extraction, an attention mechanism for feature fusion, and a residual network for feature transformation. It also introduces perceptual loss to improve the network for the characteristics of medical images. In addition, we construct a real low-dose computed tomography dataset and design a large number of comparative experiments to validate the proposed method, using both image-based evaluation metrics and medical evaluation criteria. Compared with classical methods, the main advantage of this paper is that it addresses the limitation that real clinical data cannot be directly used for supervised learning, while still achieving excellent performance. The experimental results are also professionally evaluated by imaging physicians and meet clinical needs.
Authors: Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Ahmet Enis Cetin, Ulas Bagci
Abstract: Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two complementary methods that leverage the Discrete Cosine Transform (DCT) to enhance the efficiency and performance of Vision Transformers. First, we address the initialization problem by introducing a simple yet effective DCT-based initialization strategy for self-attention, where projection weights are initialized using DCT coefficients. This structure-preserving approach consistently improves classification accuracy on the CIFAR-10 and ImageNet-1K benchmarks. Second, we propose a DCT-based attention compression technique that exploits the decorrelation properties of the frequency domain. By observing that high-frequency DCT coefficients typically correspond to noise, we truncate high-frequency components of the input patches, thereby reducing the dimensionality of the query, key, and value projections without sacrificing accuracy. Experiments on Swin Transformer models demonstrate that the proposed compression method achieves a substantial reduction in computational overhead while maintaining comparable performance.
Authors: Chingis Oinar, Miao Cao, Shanshan Fu
Abstract: Mercari is the largest C2C e-commerce marketplace in Japan, having more than 20 million active monthly users. Search being the fundamental way to discover desired items, we have always had a substantial amount of data with implicit feedback. Although we actively take advantage of that to provide the best service for our users, the correlation of implicit feedback for such tasks as image quality assessment is not trivial. Many traditional lines of research in Machine Learning (ML) are similarly motivated by the insatiable appetite of Deep Learning (DL) models for well-labelled training data. Weak supervision is about leveraging higher-level and/or noisier supervision over unlabeled data. Large Language Models (LLMs) are being actively studied and used for data labelling tasks. We present how we leverage a Chain-of-Thought (CoT) to enable LLM to produce image aesthetics labels that correlate well with human behavior in e-commerce settings. Leveraging LLMs is more cost-effective compared to explicit human judgment, while significantly improving the explainability of deep image quality evaluation which is highly important for customer journey optimization at Mercari. We propose a cost-efficient LLM-driven approach for assessing and predicting image quality in e-commerce settings, which is very convenient for proof-of-concept testing. We show that our LLM-produced labels correlate with user behavior on Mercari. Finally, we show our results from an online experimentation, where we achieved a significant growth in sales on the web platform.
Authors: Shangkun Sun, Ruyang Liu, Haoran Tang, Yixiao Ge, Haibo Lu, Wei Gao, Jiankun Yang, Chen Li
Abstract: In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long videos through extremely extended context lengths. However, this comes at the cost of significantly increased computational overhead due to the massive number of visual tokens, making efficiency a major bottleneck. In this paper, we identify the root of this inefficiency as the high redundancy in video content. To address this, we propose a novel pooling strategy that enables aggressive token compression while retaining instruction-relevant visual semantics. Our model, Prompt-guided Pooling LLaVA (PPLLaVA), introduces three key components: a CLIP-based visual-prompt alignment module that identifies regions of interest based on user instructions, a prompt-guided pooling mechanism that adaptively compresses the visual sequence using convolution-style pooling, and a clip context extension module tailored for processing long and complex prompts in visual dialogues. With up to 18x token reduction, PPLLaVA maintains strong performance across tasks, achieving state-of-the-art results on diverse video understanding benchmarks-ranging from image-to-video tasks such as captioning and QA to long-form video reasoning-while significantly improving inference throughput. Codes have been available at https://github.com/farewellthree/PPLLaVA.
Authors: Chong Zhong, Yunhao Liu, Yang Li, Xiang Fu, Jin Yang, Danjuan Yang, Meiyan Li, Jinfeng Xu, Aiyi Liu, Alan H. Welsh, Xingtao Zhou, Bo Fu, Catherine C. Liu
Abstract: The advancement of AI-assisted myopia screening necessitates the joint diagnosis of both-eye (OU) high myopia (HM) status and the prediction of axial length (AL). This clinical requirement introduces a complex mixed-type (binary-continuous) multitask learning task with bi-domain (OU) image covariates, giving rise to two key challenges: i) capture the inter-ocular asymmetry of OU images within a cutting-edge foundation model; ii) model and estimate the conditional dependence structure among mixed-type multivariate responses given image covariates. We address the challenges by: i) imposing residual adapters on the Vision Transformer foundation model to capture the OU similarity and heterogeneity simultaneously; ii) developing a four-dimensional copula loss that is implementable in PyTorch based on a latent variable expression for the Gaussian copula likelihood, and proposing a computationally efficient fast Monte Carlo Expectation Maximization (fMCEM) algorithm to estimate copula parameters. We further formulate a specific overfitting problem called stronger covariance phenomenon in multitask learning. We reveal the disturbance of the phenomenon to estimation of copula parameters and theoretically demonstrate the numerical stability of the proposed fMCEM algorithm against the disturbance. The application to our annotated OU ultra-widefield fundus image dataset and simulation on synthetic data demonstrate that our method stably enhances the predictive capabilities on both classification and regression tasks.
Authors: Vsevolod Skorokhodov, Nikita Durasov, Pascal Fua
Abstract: Gaussian Splatting has become a popular technique for various 3D Computer Vision tasks, including novel view synthesis, scene reconstruction, and dynamic scene rendering. However, the challenge of natural-looking object insertion, where the object's appearance seamlessly matches the scene, remains unsolved. In this work, we propose a method, dubbed D3DR, for inserting a 3DGS-parametrized object into a 3DGS scene while correcting its lighting, shadows, and other visual artifacts to ensure consistency. We reveal a hidden ability of diffusion models trained on large real-world datasets to implicitly understand correct scene lighting, and leverage it in our pipeline. After inserting the object, we optimize a diffusion-based Delta Denoising Score (DDS)-inspired objective to adjust its 3D Gaussian parameters for proper lighting correction. We introduce a novel diffusion personalization technique that preserves object geometry and texture across diverse lighting conditions, and utilize it to achieve consistent identity matching between original and inserted objects. Finally, we demonstrate the effectiveness of the method by comparing it to existing approaches, achieving 2.0 dB PSNR improvements in relighting quality.
Authors: Alexander Lobashev, Maria Larchenko, Dmitry Guskov
Abstract: We propose SW-Guidance, a training-free approach for image generation conditioned on the color distribution of a reference image. While it is possible to generate an image with fixed colors by first creating an image from a text prompt and then applying a color style transfer method, this approach often results in semantically meaningless colors in the generated image. Our method solves this problem by modifying the sampling process of a diffusion model to incorporate the differentiable Sliced 1-Wasserstein distance between the color distribution of the generated image and the reference palette. Our method outperforms state-of-the-art techniques for color-conditional generation in terms of color similarity to the reference, producing images that not only match the reference colors but also maintain semantic coherence with the original text prompt. Our source code is available at https://github.com/alobashev/sw-guidance/.
Authors: Udayanga G. W. K. N. Gamage, Xuanni Huo, Luca Zanatta, T Delbruck, Cesar Cadena, Matteo Fumagalli, Silvia Tolu
Abstract: Small unmanned aerial vehicle (UAV)-based visual inspections are a more efficient alternative to manual methods for examining civil structural defects, offering safe access to hazardous areas and significant cost savings by reducing labor requirements. However, traditional frame-based cameras, widely used in UAV-based inspections, often struggle to capture defects under low or dynamic lighting conditions. In contrast, dynamic vision sensors (DVS), or event-based cameras, excel in such scenarios by minimizing motion blur, enhancing power efficiency, and maintaining high-quality imaging across diverse lighting conditions without saturation or information loss. Despite these advantages, existing research lacks studies exploring the feasibility of using DVS for detecting civil structural defects. Moreover, there is no dedicated event-based dataset tailored for this purpose. Addressing this gap, this study introduces the first event-based civil infrastructure defect detection dataset, capturing defective surfaces as a spatio-temporal event stream using DVS. In addition to event-based data, the dataset includes grayscale intensity image frames captured simultaneously using an active pixel sensor (APS). Both data types were collected using the DAVIS346 camera, which integrates DVS and APS sensors. The dataset focuses on two types of defects: cracks and spalling, and includes data from both field and laboratory environments. The field dataset comprises 318 recording sequences, documenting 458 distinct cracks and 121 distinct spalling instances. The laboratory dataset includes 362 recording sequences, covering 220 distinct cracks and 308 spalling instances. We evaluated the dataset using four real-time object detection models.The results demonstrate the applicability of DVS cameras for robust detection of civil infrastructure defects under challenging lighting conditions.
Authors: Yuan Gao, Shaobo Xia, Sheng Nie, Cheng Wang, Xiaohuan Xi, Bisheng Yang
Abstract: Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed in real-world scenarios often suffer from performance degradation due to continuous domain shifts caused by environmental and sensor changes. Continuous Test-Time Adaptation (CTTA) enables adaptation to evolving unlabeled domains, but its application to ALS point clouds remains underexplored, hindered by the lack of benchmarks and the risks of catastrophic forgetting and error accumulation. To address these challenges, we propose APCoTTA (ALS Point cloud Continuous Test-Time Adaptation), a novel CTTA framework tailored for ALS point cloud semantic segmentation. APCoTTA consists of three key components. First, we adapt a gradient-driven layer selection mechanism for ALS point clouds, selectively updating low-confidence layers while freezing stable ones to preserve source knowledge and mitigate catastrophic forgetting. Second, an entropy-based consistency loss discards unreliable samples and enforces consistency regularization solely on reliable ones, effectively reducing error accumulation and improving adaptation stability. Third, a random parameter interpolation mechanism stochastically blends adapted parameters with source model parameters, further balancing target adaptation and source knowledge retention. Finally, we construct two benchmarks, ISPRSC and H3DC, to address the lack of CTTA benchmarks for ALS point cloud segmentation. Extensive experiments demonstrate that APCoTTA achieves superior performance on both benchmarks, improving mIoU by approximately 9\% and 14\% over direct inference. The new benchmarks and code are available at https://github.com/Gaoyuan2/APCoTTA.
Authors: Shuo Yang, Haocheng Xi, Yilong Zhao, Muyang Li, Jintao Zhang, Han Cai, Yujun Lin, Xiuyu Li, Chenfeng Xu, Jianfei Chen, Song Han, Kurt Keutzer, Ion Stoica
Abstract: Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens, sparse attention reduces computational costs and offers a promising acceleration approach. However, we identify that existing methods fail to approach optimal generation quality under the same computation budget for two reasons: (1) Inaccurate critical token identification: current methods cluster tokens based on position rather than semantics, leading to imprecise aggregated representations. (2) Excessive computation waste: critical tokens are scattered among non-critical ones, leading to wasted computation on GPUs, which are optimized for processing contiguous tokens. In this paper, we propose SVG2, a training-free framework that maximizes identification accuracy and minimizes computation waste, achieving a Pareto frontier trade-off between generation quality and efficiency. The core of SVG2 is semantic-aware permutation, which clusters and reorders tokens based on semantic similarity using k-means. This approach ensures both a precise cluster representation, improving identification accuracy, and a densified layout of critical tokens, enabling efficient computation without padding. Additionally, SVG2 integrates top-p dynamic budget control and customized kernel implementations, achieving up to 2.30x and 1.89x speedup while maintaining a PSNR of up to 30 and 26 on HunyuanVideo and Wan 2.1, respectively. Our code is open-sourced at \href{https://github.com/svg-project/Sparse-VideoGen}{https://github.com/svg-project/Sparse-VideoGen}.
URLs: https://github.com/svg-project/Sparse-VideoGen, https://github.com/svg-project/Sparse-VideoGen
Authors: Yue Yao, Zelin Wen, Yan Tong, Xinyu Tian, Xuqing Li, Xiao Ma, Dongliang Xu, Tom Gedeon
Abstract: Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. In this paper, we explore a simple but effective approach for applying test-time scaling to chest X-ray report generation. Specifically, we introduce a lightweight Thought Graph Traversal (TGT) framework that guides the model to reason through organ-specific findings in a medically coherent order. This framework integrates structured medical priors into the prompt, enabling deeper and more logical analysis with no changes to the underlying model. To further enhance reasoning depth, we apply a reasoning budget forcing strategy that adjusts the model's inference depth at test time by dynamically extending its generation process. This simple yet powerful combination allows a frozen radiology VLLM to self-correct and generate more accurate, consistent chest X-ray reports. Our method outperforms baseline prompting approaches on standard benchmarks, and also reveals dataset biases through traceable reasoning paths. Code and prompts are open-sourced for reproducibility at https://github.com/glerium/Thought-Graph-Traversal
Authors: Jiacong Wang, Zijian Kang, Haochen Wang, Haiyong Jiang, Jiawen Li, Bohong Wu, Ya Wang, Jiao Ran, Xiao Liang, Chao Feng, Jun Xiao
Abstract: In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This narrow focus limits their ability to handle complex visual reasoning tasks that demand comprehensive understanding of image details. To address these limitations, this paper introduces VGR, a novel reasoning multimodal large language model (MLLM) with enhanced fine-grained visual perception capabilities. Unlike traditional MLLMs that answer the question or reasoning solely on the language space, our VGR first detects relevant regions that may help to solve problems, and then provides precise answers based on replayed image regions. To achieve this, we conduct a large-scale SFT dataset called VGR -SFT that contains reasoning data with mixed vision grounding and language deduction. The inference pipeline of VGR allows the model to choose bounding boxes for visual reference and a replay stage is introduced to integrates the corresponding regions into the reasoning process, enhancing multimodel comprehension. Experiments on the LLaVA-NeXT-7B baseline show that VGR achieves superior performance on multi-modal benchmarks requiring comprehensive image detail understanding. Compared to the baseline, VGR uses only 30\% of the image token count while delivering scores of +4.1 on MMStar, +7.1 on AI2D, and a +12.9 improvement on ChartQA.
Authors: Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov, O\u{g}uzhan Fatih Kar, Amir Zamir
Abstract: Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond question answering remains unclear. In this paper, we benchmark popular MFMs (GPT-4o, o4-mini, Gemini 1.5 Pro and Gemini 2.0 Flash, Claude 3.5 Sonnet, Qwen2-VL, Llama 3.2) on standard computer vision tasks (semantic segmentation, object detection, image classification, depth and surface normal prediction) using established datasets (e.g., COCO, ImageNet, etc). The main challenges in performing this analysis are: 1) most models are trained to output text and cannot natively express versatile domains, such as segments or 3D geometry, and 2) many leading models are proprietary and accessible only at an API level, i.e., there is no weight access to adapt them. We address these by translating vision tasks into text-promptable, API-compatible formats via prompt chaining, creating a standardized benchmarking framework. We observe that: 1) The MFMs are not close to the state-of-the-art specialist models at any task. 2) They are respectable generalists; this is remarkable, as they are presumably trained on image-text-based tasks. 3) They perform semantic tasks notably better than geometric ones. 4) GPT-4o performs the best among non-reasoning models, securing the top position in 4 out of 6 tasks. 5) Reasoning models, e.g., o3, show improvements in geometric tasks. 6) While prompt chaining techniques affect performance, better models are less sensitive to prompt variations. 7) An analysis of models with native image generation, such as the latest GPT-4o, shows they exhibit failure modes, such as hallucinated objects or misalignment between input and output.
Authors: Xiaoran Sun, Liyan Wang, Yeying Jin, Kin-man Lam, Zhixun Su, Yang Yang, Jinshan Pan, Cong Wang
Abstract: Most existing low-light image enhancement (LLIE) methods rely on pre-trained model priors, low-light inputs, or both, while neglecting the semantic guidance available from normal-light images. This limitation hinders their effectiveness in complex lighting conditions. In this paper, we propose VLM-IMI, a framework that adapts large vision-language models with iterative and manual instructions for generative LLIE. VLM-IMI mainly contains two branches: Normal-Light Instruction Prior Generation (NL-IPG) and Instruction-aware Light Enhancement Diffusion (IA-LED). The NL-IPG incorporates textual descriptions of the desired normal-light content as enhancement cues, enabling semantically informed restoration. IA-LED incorporates instruction priors from the NL-IPG to guide the diffusion process, enabling precise illumination enhancement. To effectively integrate cross-modal priors, we introduce a learnable instruction prior fusion module, which dynamically aligns and fuses image and text features, promoting the generation of detailed and semantically coherent outputs. During inference, as the ground-truth normal-light images are not available, we propose an inference with an iterative instructions strategy to refine textual instructions, progressively improving visual quality. Our VLM-IMI also inherently supports manual instruction control by allowing users to directly input custom instructions into the LLM to generate user-expected outputs. Experiments across diverse scenarios demonstrate that VLM-IMI outperforms SOTA methods in terms of perception and realism. The source code is available at: https://github.com/sunxiaoran01/VLM-IMI.
Authors: Rongzhen Zhao, Wenyan Yang, Juho Kannala, Joni Pajarinen
Abstract: Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA \textit{iteratively} refining cold-start query slots. For video, such aggregation proceeds by SA \textit{recurrently} shared across frames, with queries cold-started on the first frame while transitioned from the previous frame's slots thereafter. However, cold-start queries lack sample-specific cues thus hindering precise aggregation on image or video's first frame; Non-first frames' queries are already sample-specific thus requiring aggregation transforms different from the first frame. We address these issues with our \textit{SmoothSA}: (1) To smooth SA iterations on image or video's first frame, we \textit{preheat} cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we \textit{differentiate} the homogeneous aggregation transforms by using full and single iterations respectively. Comprehensive experiments on object discovery, recognition and visual reasoning validate our method's effectiveness. Further visual analyses illuminate the underline mechanisms. Our \textit{source code}, \textit{model checkpoints} and \textit{training logs} are provided on https://github.com/Genera1Z/SmoothSA.
Authors: Sami Sadat, Mohammad Irtiza Hossain, Junaid Ahmed Sifat, Suhail Haque Rafi, Md. Waseq Alauddin Alvi, Md. Khalilur Rhaman
Abstract: A deep learning real-time smoking detection system for CCTV surveillance of fire exit areas is proposed due to critical safety requirements. The dataset contains 8,124 images from 20 different scenarios along with 2,708 raw samples demonstrating low-light areas. We evaluated three advanced object detection models: YOLOv8, YOLOv11, and YOLOv12, followed by development of a custom model derived from YOLOv8 with added structures for challenging surveillance contexts. The proposed model outperformed the others, achieving a recall of 78.90 percent and mAP at 50 of 83.70 percent, delivering optimal object detection across varied environments. Performance evaluation on multiple edge devices using multithreaded operations showed the Jetson Xavier NX processed data at 52 to 97 milliseconds per inference, establishing its suitability for time-sensitive operations. This system offers a robust and adaptable platform for monitoring public safety and enabling automatic regulatory compliance.
Authors: Toghrul Karimov, Hassan Imani, Allan Kazakov
Abstract: Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, the impact of reduced precision on model robustness to real-world input degradations such as noise, blur, and compression artifacts is a significant concern. This paper presents a comprehensive empirical study evaluating the robustness of YOLO models (nano to extra-large scales) across multiple precision formats: FP32, FP16 (TensorRT), Dynamic UINT8 (ONNX), and Static INT8 (TensorRT). We introduce and evaluate a degradation-aware calibration strategy for Static INT8 PTQ, where the TensorRT calibration process is exposed to a mix of clean and synthetically degraded images. Models were benchmarked on the COCO dataset under seven distinct degradation conditions (including various types and levels of noise, blur, low contrast, and JPEG compression) and a mixed-degradation scenario. Results indicate that while Static INT8 TensorRT engines offer substantial speedups (~1.5-3.3x) with a moderate accuracy drop (~3-7% mAP50-95) on clean data, the proposed degradation-aware calibration did not yield consistent, broad improvements in robustness over standard clean-data calibration across most models and degradations. A notable exception was observed for larger model scales under specific noise conditions, suggesting model capacity may influence the efficacy of this calibration approach. These findings highlight the challenges in enhancing PTQ robustness and provide insights for deploying quantized detectors in uncontrolled environments. All code and evaluation tables are available at https://github.com/AllanK24/QRID.
Authors: Janis Keuper, Margret Keuper
Abstract: The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negative social implications. The machine learning community has been engaging this problem with an extensive series of publications proposing algorithmic solutions for the detection of "fake", e.g. entirely generated or partially manipulated images. While there is undoubtedly some progress towards technical solutions of the problem, we argue that current and prior work is focusing too much on generative algorithms and "fake" data-samples, neglecting a clear definition and data collection of "real" images. The fundamental question "what is a real image?" might appear to be quite philosophical, but our analysis shows that the development and evaluation of basically all current "fake"-detection methods is relying on only a few, quite old low-resolution datasets of "real" images like ImageNet. However, the technology for the acquisition of "real" images, aka taking photos, has drastically evolved over the last decade: Today, over 90% of all photographs are produced by smartphones which typically use algorithms to compute an image from multiple inputs (over time) from multiple sensors. Based on the fact that these image formation algorithms are typically neural network architectures which are closely related to "fake"-image generators, we state the position that today, we need to re-think the concept of "real" images. The purpose of this position paper is to raise the awareness of the current shortcomings in this active field of research and to trigger an open discussion whether the detection of "fake" images is a sound objective at all. At the very least, we need a clear technical definition of "real" images and new benchmark datasets.
Authors: Yuhan Zhu, Xiangyu Zeng, Chenting Wang, Xinhao Li, Chunxu Liu, Yicheng Xu, Ziang Yan, Yi Wang, Limin Wang
Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This work asks: Can off-the-shelf MLLMs serve as powerful retrievers without additional training? We present FreeRet, a plug-and-play framework that turns any MLLM into a two-stage retriever. FreeRet first derives semantically grounded embeddings directly from the model for fast candidate search, and then exploits its reasoning ability for precise reranking. The framework contributes three advances: bypassing lexical alignment layers to obtain semantically faithful embeddings, conditioning representation generation with explicit priors, and mitigating framing effect in reranking via neutral choice framing. On the MMEB and MMEB-V2 benchmarks spanning 46 datasets, FreeRet substantially outperforms models trained on millions of pairs. Beyond benchmarks, FreeRet is model-agnostic and scales seamlessly across MLLM families and sizes, preserves their generative abilities, supports arbitrary modality combinations, and unifies retrieval, reranking, and generation into end-to-end RAG within a single model. Our findings demonstrate that pretrained MLLMs, when carefully harnessed, can serve as strong retrieval engines without training, closing a critical gap in their role as generalists.
Authors: Chenhui Xu, Fuxun Yu, Michael J. Bianco, Jacob Kovarskiy, Raphael Tang, Qi Zhang, Zirui Xu, Will LeVine, Brandon Dubbs, Heming Liao, Cassandra Burgess, Suvam Bag, Jay Patravali, Rupanjali Kukal, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Jinjun Xiong
Abstract: Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far behind that of common domains. In this work, we validate an important conclusion: indirect verifiable rewards, derived from seemingly unrelated metadata, are sufficient to induce sophisticated and generalizable geospatial reasoning across a wide range of downstream tasks (25+). We present Geo-R1 as one empirical instantiation of this paradigm. Rather than relying on limited task-specific annotations (i.e., direct rewards), Geo-R1 utilizes scalable, verifiable indirect proxy rewards based on cross-view alignment with metadata (geolocation information) to drive reinforcement learning at scale. Such indirect rewards successfully motivate the model to discover and internalize zero-shot geospatial reasoning across diverse tasks, achieving extraordinary zero-shot transfer on out-of-distribution benchmarks and even surpassing fully supervised specialists on certain benchmarks. These findings indicate that optimizing for indirect verifiable rewards may provide a scalable pathway to unlock generalized reasoning capabilities in rare domains with massive unlabeled data archives. Our code is availavle at: https://github.com/miniHuiHui/Geo-R1.
Authors: Fabio Montello, Ronja G\"uldenring, Lazaros Nalpantidis
Abstract: Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have focused on dynamically merging tokens according to the image complexity. Token merging works well for classification but is less suited to dense prediction. We propose ClustViT, where we expand upon the Vision Transformer (ViT) backbone and address semantic segmentation. Within our architecture, a trainable Cluster module merges similar tokens along the network guided by pseudo-clusters from segmentation masks. Subsequently, a Regenerator module restores fine details for downstream heads. Our approach achieves up to 2.18x fewer GFLOPs and 1.64x faster inference on three different datasets, with comparable segmentation accuracy. Our code and models will be made publicly available.
Authors: Shan Xiong, Jiabao Chen, Ye Wang, Jialin Peng
Abstract: Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can help mitigate domain shifts and reduce the high costs of annotating each domain, they typically have relatively low performance in practical applications. Thus, we investigate weakly supervised domain adaptation (WDA) that utilizes additional sparse point labels on the target domain, which require minimal annotation effort and minimal expert knowledge. To take full use of the incomplete and imprecise point annotations, we introduce a multitask learning framework that jointly conducts segmentation and center detection with a novel cross-teaching mechanism and class-focused cross-domain contrastive learning. While leveraging unlabeled image regions is essential, we introduce segmentation self-training with a novel instance-aware pseudo-label (IPL) selection strategy. Unlike existing methods that typically rely on pixel-wise pseudo-label filtering, the IPL semantically selects reliable and diverse pseudo-labels with the help of the detection task. Comprehensive validations and comparisons on challenging datasets demonstrate that our method outperforms existing UDA and WDA methods, significantly narrowing the performance gap with the supervised upper bound. Furthermore, under the UDA setting, our method also achieves substantial improvements over other UDA techniques.
Authors: Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du
Abstract: Diffusion bridge models establish probabilistic paths between arbitrary paired distributions and exhibit great potential for universal image restoration. Most existing methods merely treat them as simple variants of stochastic interpolants, lacking a unified analytical perspective. Besides, they indiscriminately reconstruct images through global noise injection and removal, inevitably distorting undegraded regions due to imperfect reconstruction. To address these challenges, we propose the Residual Diffusion Bridge Model (RDBM). Specifically, we theoretically reformulate the stochastic differential equations of generalized diffusion bridge and derive the analytical formulas of its forward and reverse processes. Crucially, we leverage the residuals from given distributions to modulate the noise injection and removal, enabling adaptive restoration of degraded regions while preserving intact others. Moreover, we unravel the fundamental mathematical essence of existing bridge models, all of which are special cases of RDBM and empirically demonstrate the optimality of our proposed models. Extensive experiments are conducted to demonstrate the state-of-the-art performance of our method both qualitatively and quantitatively across diverse image restoration tasks. Code is publicly available at https://github.com/MiliLab/RDBM.
Authors: Song Yan, Chenfeng Wang, Wei Zhai, Xinliang Bi, Jian Yang, Yancheng Cai, Yusen Zhang, Yunwei Lan, Tao Zhang, GuanYe Xiong, Min Li, Zheng-Jun Zha
Abstract: Diffusion models initialize generation from an isotropic Gaussian latent, yet changing only the random seed can substantially alter prompt faithfulness, composition, and visual quality. We explain this gap by distinguishing the Euclidean geometry of the prior from the semantic geometry induced by the sampler: the effective map from initial noise to semantic outcome has many semantic-invariant directions and a much smaller set of semantic-sensitive directions. This induces a degenerate pullback semi-metric on the latent space and provides a geometric view of the seed lottery. Guided by this view, we propose a training-free inference procedure that estimates a prompt-aligned horizontal proxy from a single high-noise cold-start probe and applies tangential seed injection followed by spherical retraction to remain on the prior's typical shell. Across image, video, and 3D generation benchmarks, the method improves alignment and quality metrics over standard sampling.
Authors: Chenying Liu, Wei Huang, Xiao Xiang Zhu
Abstract: Land Use and Land Cover (LULC) mapping is a fundamental task in Earth Observation (EO). However, current LULC models are typically developed for a specific modality and a fixed class taxonomy, limiting their generability and broader applicability. Recent advances in foundation models (FMs) offer promising opportunities for building universal models. Yet, task-agnostic FMs often require fine-tuning for downstream applications, whereas task-specific FMs rely on massive amounts of labeled data for training, which is costly and impractical in the remote sensing (RS) domain. To address these challenges, we propose LandSegmenter, an LULC FM framework that resolves three-stage challenges at the input, model, and output levels. From the input side, to alleviate the heavy demand on labeled data for FM training, we introduce LAnd Segment (LAS), a large-scale, multi-modal, multi-source dataset built primarily with globally sampled weak labels from existing LULC products. LAS provides a scalable, cost-effective alternative to manual annotation, enabling large-scale FM training across diverse LULC domains. For model architecture, LandSegmenter integrates an RS-specific adapter for cross-modal feature extraction and a text encoder for semantic awareness enhancement. At the output stage, we introduce a class-wise confidence-guided fusion strategy to mitigate semantic omissions and further improve LandSegmenter's zero-shot performance. We evaluate LandSegmenter on six precisely annotated LULC datasets spanning diverse modalities and class taxonomies. Extensive transfer learning and zero-shot experiments demonstrate that LandSegmenter achieves competitive or superior performance, particularly in zero-shot settings when transferred to unseen datasets. These results highlight the efficacy of our proposed framework and the utility of weak supervision for building task-specific FMs.
Authors: Kaixuan Zhang, Minxian Li, Mingwu Ren, Jiankang Deng, Xiatian Zhu
Abstract: High Dynamic Range (HDR) 3D reconstruction is pivotal for professional content creation in filmmaking and virtual production. Existing methods typically rely on multi-exposure Low Dynamic Range (LDR) supervision to constrain the learning process within vast brightness spaces, resulting in complex, dual-branch architectures. This work explores the feasibility of learning HDR 3D models exclusively in the HDR data space to simplify model design. By analyzing 3D Gaussian Splatting (3DGS) for HDR imagery, we reveal that its failure stems from the limited capacity of Spherical Harmonics (SHs) to capture extreme radiance variations across views, often biasing towards high-radiance observations and underfitting. While increasing the maximum SH degree improves training fitting, it leads to severe overfitting and excessive parameter overhead. To address this, we propose \textit{Luminance--Chromaticity Decomposition Gaussian Splatting} (LCD-GS). By decoupling luminance and chromaticity into independent parameters, LCD-GS significantly enhances learning flexibility with minimal parameter increase (\textit{e.g.}, one extra scalar per primitive). Notably, LCD-GS maintains the original training and inference pipeline, requiring only a change in color representation. This explicit decomposition naturally enables primitive-level local and global luminance editing during inference. Extensive experiments on synthetic and real datasets demonstrate that LCD-GS consistently outperforms state-of-the-art methods in reconstruction fidelity and dynamic-range preservation even with a simpler, more efficient architecture, providing an elegant paradigm for professional-grade HDR 3D modeling. Code and datasets will be released.
Authors: Yilan Zhang, Li Nanbo, Changchun Yang, J\"urgen Schmidhuber, Xin Gao
Abstract: The integration of histology images and gene profiles has shown great promise for improving survival prediction in cancer. However, current approaches often struggle to model intra- and inter-modal interactions efficiently and effectively due to the high dimensionality and complexity of the inputs. A major challenge is capturing critical prognostic events that, though few, underlie the complexity of the observed inputs and largely determine patient outcomes. These events, manifested as high-level structural signals such as spatial histologic patterns or pathway co-activations, are typically sparse, patient-specific, and unannotated, making them inherently difficult to uncover. To address this, we propose SlotSPE, a slot-based framework for structural prognostic event modeling. Specifically, inspired by the principle of factorial coding, we compress each patient's multimodal inputs into compact, modality-specific sets of mutually distinctive slots using slot attention. By leveraging these slot representations as encodings for prognostic events, our framework enables both efficient and effective modeling of complex intra- and inter-modal interactions, while also facilitating seamless incorporation of biological priors that enhance prognostic relevance. Extensive experiments on ten cancer benchmarks show that SlotSPE outperforms existing methods in 8 out of 10 cohorts, achieving an overall improvement of 2.9%. It remains robust under missing genomic data and delivers markedly improved interpretability through structured event decomposition.
Authors: Dashti A. Ali, Aras T. Asaad, Jacob J. Peoples, Ahmad Bashir Barekzai, Camila Vilela, Hala Khasawneh, Jayasree Chakraborty, Jo\~ao Miranda, Mohammad Hamghalam, Natalie Gangai, Natally Horvat, Richard K. G. Do, Alice C. Wei, Amber L. Simpson
Abstract: The development of machine learning models based on computed tomography (CT) imaging has been a major focus due to the promise that imaging holds for diagnosis, staging, and prognostication. These models often rely on the extraction of hand-crafted features where incorporating robust feature engineering improves the performance of these models. Topological data analysis (TDA), based on the mathematical field of algebraic topology, focuses on data from a topological perspective, extracting deeper insight and higher dimensional structures. Persistent homology (PH), a fundamental tool in TDA, extracts topological features such as connected components, cycles, and voids. A popular approach to construct PH from 3D CT images is to utilize 3D cubical complex filtration, a method adapted for grid-structured data. However, this approach is subject to poor performance and high computational cost with higher resolution images. This study introduces a novel patch-based PH construction approach designed for volumetric CT imaging data that improves performance and reduces computational time. This study conducts a series of experiments to comprehensively analyze the performance of the proposed method and benchmarks against the cubical complex algorithm and radiomic features. Our results highlight the dominance of the patch-based TDA approach in terms of both classification performance and computational time. The proposed approach outperformed the cubical complex method and radiomic features, achieving average improvement of 7.2%, 3.6%, 2.7%, 8.0%, and 7.2% in accuracy, AUC, sensitivity, specificity, and F1 score, respectively, across all datasets. Finally, we provide a convenient Python package, Patch-TDA, to facilitate the utilization of the proposed approach.
Authors: Piyush Bagad, Andrew Zisserman
Abstract: Our objective is to build an embedding model that captures the nuanced relationship between a search query and candidate videos. We cover three aspects of nuanced retrieval: (i) temporal, (ii) negation, and (iii) multimodal. For temporal nuance, we consider chiral actions that need distinguishing between temporally opposite actions like "opening a door" vs. "closing a door". For negation, we consider queries with negators such as "not", "none" that allow user to specify what they do not want. For multimodal nuance, we consider the task of composed retrieval where the query comprises a video along with a text edit instruction. The goal is to develop a unified embedding model that handles such nuances effectively. To that end, we repurpose a Multimodal Large Language Model (MLLM) trained to generate text into an embedding model. We fine-tune it with a contrastive loss on text alone with carefully sampled hard negatives that instill the desired nuances in the learned embedding space. Despite the text-only training, our method achieves state of the art performance on all benchmarks for nuanced video retrieval. We also analyze how this improvement is achieved, and show that text-only training reduces the modality gap between text and video embeddings leading to better organization of the embedding space.
Authors: Jiawei Ge, Jiuxin Cao, Xinyi Li, Xuelin Zhu, Chang Liu, Bo Liu, Chen Feng, Ioannis Patras
Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supervision such as scribble annotations. Despite recent progress, existing WSCOD methods still lag far behind fully supervised ones due to two major limitations: (1) the pseudo masks generated by general-purpose segmentation models (e.g., SAM) and filtered via rules are often unreliable, as these models lack the task-specific semantic understanding required for effective pseudo labeling in COD; and (2) the neglect of inherent annotation bias in scribbles, which hinders the model from capturing the global structure of camouflaged objects. To overcome these challenges, we propose ${D}^{3}$ETOR, a two-stage WSCOD framework consisting of Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing. In the first stage, we introduce an adaptive entropy-driven point sampling method and a multi-agent debate mechanism to enhance the capability of SAM for COD, improving the interpretability and precision of pseudo masks. In the second stage, we design FADeNet, which progressively fuses multi-level frequency-aware features to balance global semantic understanding with local detail modeling, while dynamically reweighting supervision strength across regions to alleviate scribble bias. By jointly exploiting the supervision signals from both the pseudo masks and scribble semantics, ${D}^{3}$ETOR significantly narrows the gap between weakly and fully supervised COD, achieving state-of-the-art performance on multiple benchmarks.
Authors: Anne Harrington, A. Sophia Koepke, Shyamgopal Karthik, Trevor Darrell, Alexei A. Efros
Abstract: Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance mechanisms, or by generating a large pool of candidates and refining them. In this work, we take a different direction and aim for diversity in generations via noise optimization. Specifically, we show that a simple noise optimization objective can mitigate mode collapse while preserving the fidelity of the base model. We also analyze the frequency characteristics of the noise and show that alternative noise initializations with different frequency profiles can improve both optimization and search. Our experiments demonstrate that noise optimization yields superior results in terms of generation quality and diversity.
Authors: Teng-Fang Hsiao, Bo-Kai Ruan, Yu-Lun Liu, Hong-Han Shuai
Abstract: 3D editing has emerged as a critical research area to provide users with flexible control over 3D assets. While current editing approaches predominantly focus on 3D Gaussian Splatting or multi-view images, the direct editing of 3D meshes remains underexplored. Prior attempts, such as VoxHammer, rely on voxel-based representations that suffer from limited resolution and necessitate labor-intensive 3D mask. To address these limitations, we propose \textbf{VecSet-Edit}, the first pipeline that leverages the high-fidelity VecSet Large Reconstruction Model (LRM) as a backbone for mesh editing. Our approach is grounded on a analysis of the spatial properties in VecSet tokens, revealing that token subsets govern distinct geometric regions. Based on this insight, we introduce Mask-guided Token Seeding and Attention-aligned Token Gating strategies to precisely localize target regions using only 2D image conditions. Also, considering the difference between VecSet diffusion process versus voxel we design a Drift-aware Token Pruning to reject geometric outliers during the denoising process. Finally, our Detail-preserving Texture Baking module ensures that we not only preserve the geometric details of original mesh but also the textural information. More details can be found in our project page: https://github.com/BlueDyee/VecSet-Edit/tree/main
Authors: Haoyuan Li, Qihang Cao, Tao Tang, Kun Xiang, Zihan Guo, Jianhua Han, Hang Xu, JiaWang Bian, Xiaodan Liang
Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence. Code can be found at https://github.com/Li-Hao-yuan/GeoThinker.
Authors: Aydin Ayanzadeh, Prakhar Dixit, Sadia Kamal, Milton Halem
Abstract: Wildfires are a growing threat to ecosystems, human lives, and infrastructure, with their frequency and intensity rising due to climate change and human activities. Early detection is critical, yet satellite-based monitoring remains challenging due to faint smoke signals, dynamic weather conditions, and the need for real-time analysis over large areas. We introduce WildfireVLM, an AI framework that combines satellite imagery wildfire detection with language-driven risk assessment. We construct a labeled wildfire and smoke dataset using imagery from Landsat-8/9, GOES-16, and other publicly available Earth observation sources, including harmonized products with aligned spectral bands. WildfireVLM employs YOLOv12 to detect fire zones and smoke plumes, leveraging its ability to detect small, complex patterns in satellite imagery. We integrate Multimodal Large Language Models (MLLMs) that convert detection outputs into contextualized risk assessments and prioritized response recommendations for disaster management. We validate the quality of risk reasoning using an LLM-as-judge evaluation with a shared rubric. The system is deployed using a service-oriented architecture that supports real-time processing, visual risk dashboards, and long-term wildfire tracking, demonstrating the value of combining computer vision with language-based reasoning for scalable wildfire monitoring. The code and dataset are publicly available on GitHub at https://github.com/Ayanzadeh93/_WildfireVLM_.
Authors: A. Said Gurbuz, Sunghwan Hong, Ahmed Nassar, Marc Pollefeys, Peter Staar
Abstract: Modern computer-use agents (CUA) must perceive a screen as a structured state, what elements are visible, where they are, and what text they contain, before they can reliably ground instructions and act. Yet, most available grounding datasets provide sparse supervision, with insufficient and low-diversity labels that annotate only a small subset of task-relevant elements per screen, which limits both coverage and generalization; moreover, practical deployment requires efficiency to enable low-latency, on-device use. We introduce ScreenParse, a large-scale dataset for complete screen parsing, with dense annotations of all visible UI elements (boxes, 55-class types, and text) across 771K web screenshots (21M elements). ScreenParse is generated by Webshot, an automated, scalable pipeline that renders diverse urls, extracts annotations and applies VLM-based relabeling and quality filtering. Using ScreenParse, we train ScreenVLM, a compact, 316M-parameter vision language model (VLM) that decodes a compact ScreenTag markup representation with a structure-aware loss that upweights structure-critical tokens. ScreenVLM substantially outperforms much larger foundation VLMs on dense parsing (e.g., 0.592 vs. 0.294 PageIoU on ScreenParse) and shows strong transfer to public benchmarks. Moreover, finetuning foundation VLMs on ScreenParse consistently improves their grounding performance, suggesting that dense screen supervision provides transferable structural priors for UI understanding. Project page: https://saidgurbuz.github.io/screenparse/.
Authors: Xiaoru Dong, Ruiqin Li, Xiao Han, Zhenxuan Wu, Jiamin Wang, Jian Chen, Qi Jiang, SM Yiu, Xinge Zhu, Yuexin Ma
Abstract: Human driving behavior is inherently diverse, yet most end-to-end autonomous driving (E2E-AD) systems learn a single average driving style, neglecting individual differences. Achieving personalized E2E-AD faces challenges across three levels: limited real-world datasets with individual-level annotations, a lack of quantitative metrics for evaluating personal driving styles, and the absence of algorithms that can learn stylized representations from users' trajectories. To address these gaps, we propose Person2Drive, a comprehensive personalized E2E-AD platform and benchmark. It includes an open-source, flexible data collection system that simulates realistic scenarios to generate scalable and diverse personalized driving datasets; style vector-based evaluation metrics with Maximum Mean Discrepancy and KL divergence to comprehensively quantify individual driving behaviors; and a personalized E2E-AD framework with a style reward model that efficiently adapts E2E models for safe and individualized driving. Extensive experiments demonstrate that Person2Drive enables fine-grained analysis, reproducible evaluation, and effective personalization in end-to-end autonomous driving. Our dataset and code will be released after acceptance.
Authors: Jiabao Chen, Shan Xiong, Jialin Peng
Abstract: Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent unsupervised domain adaptation (UDA) strategies often demonstrate limited and biased performance, which hinders their practical applications. In this study, we explore sparse points and local human preferences as weak labels in the target domain, thereby presenting a more realistic yet annotation-efficient setting. Specifically, we develop Prefer-DAS, which pioneers sparse promptable learning and local preference alignment. The Prefer-DAS is a promptable multitask model that integrates self-training and prompt-guided contrastive learning. Unlike SAM-like methods, the Prefer-DAS allows for the use of full, partial, and even no point prompts during both training and inference stages and thus enables interactive segmentation. Instead of using image-level human preference alignment for segmentation, we introduce Local direct Preference Optimization (LPO) and sparse LPO (SLPO), plug-and-play solutions for alignment with spatially varying human feedback or sparse feedback. To address potential missing feedback, we also introduce Unsupervised Preference Optimization (UPO), which leverages self-learned preferences. As a result, the Prefer-DAS model can effectively perform both weakly-supervised and unsupervised DAS, depending on the availability of points and human preferences. Comprehensive experiments on four challenging DAS tasks demonstrate that our model outperforms SAM-like methods as well as unsupervised and weakly-supervised DAS methods in both automatic and interactive segmentation modes, highlighting strong generalizability and flexibility. Additionally, the performance of our model is very close to or even exceeds that of supervised models.
Authors: Hongbo Zheng, Afshin Bozorgpour, Dorit Merhof, Minjia Zhang
Abstract: Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are efficient but less effective at global reasoning. Linear attention offers \(\mathcal{O}(N)\) scaling, but often produces diffuse feature aggregation that weakens boundary-sensitive prediction. We introduce a gated differential linear-attention mixer for medical image segmentation. Its global path, Gated Differential Linear Attention (GDLA), performs differential subtraction between two kernelized attention branches over complementary query/key subspaces to suppress redundant responses, and employs a data-dependent gate for token refinement. A parallel local token-mixing branch with depthwise convolution strengthens neighborhood interactions for better refinement, and the two branches are fused while preserving \(\mathcal{O}(N)\) complexity. When instantiated in a pretrained Pyramid Vision Transformer (PVT)-based encoder--decoder model, \name achieves state-of-the-art results on the evaluated 2D medical segmentation benchmarks spanning CT, MRI, ultrasound, and dermoscopy, with a favorable accuracy--efficiency trade-off over closely related baselines. The code is publicly available at \href{https://github.com/xmindflow/gdla}{https://github.com/xmindflow/gdla}.
URLs: https://github.com/xmindflow/gdla, https://github.com/xmindflow/gdla
Authors: Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu
Abstract: Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize clues based solely on the query, overlooking the video's intrinsic structure and varying relevance across segments. To address this, we propose VideoDetective, a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering. Specifically, we divide a video into various segments and represent them as a visual-temporal affinity graph built from visual similarity and temporal proximity. We then perform a Hypothesis-Verification-Refinement loop to estimate relevance scores of observed segments to the query and propagate them to unseen segments, yielding a global relevance distribution that guides the localization of the most critical segments for final answering with sparse observation. Experiments show our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long. Our code is available at https://videodetective.github.io/
Authors: Zhe Zhang, Jing Li, Wanli Xue, Xu Cheng, Jianhua Zhang, Qinghua Hu, Shengyong Chen
Abstract: Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transferable knowledge is limited to the predictions of a black-box source model. Existing approaches exploit such knowledge via pseudo-label refinement or by leveraging vision-language models (ViLs), but they often fail to reconcile the inherent discrepancy between task-specific knowledge from black-box models and language-aligned semantic priors of ViLs, resulting in suboptimal integration and degraded adaptation performance. To address this challenge, we propose adaptive Dual-Teacher Distillation with Subnetwork Rectification (DDSR), a framework that explicitly reconciles these complementary yet inconsistent knowledge sources. DDSR employs an adaptive prediction fusion strategy to integrate predictions from the black-box source model and a ViL, generating reliable pseudo-labels for the target domain. A subnetwork-based regularization mechanism mitigates overfitting to noisy supervision by enforcing output consistency and gradient divergency. Furthermore, progressively improved target predictions iteratively refine both pseudo-labels and ViL prompts, enhancing semantic alignment. Finally, class-wise prototypes are used to further optimize target predictions via self-training. Extensive experiments on multiple benchmark datasets demonstrate that DDSR consistently outperforms state-of-the-art methods, including those with access to source data or source model parameters.
Authors: Felix Wimbauer, Fabian Manhardt, Michael Oechsle, Nikolai Kalischek, Christian Rupprecht, Daniel Cremers, Federico Tombari
Abstract: The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective for scene initialization, existing approaches suffer from a trade-off between visual fidelity and explorability: autoregressive expansion suffers from context drift, while panoramic video generation is limited to low resolution. We present Stepper, a unified framework for text-driven immersive 3D scene synthesis that circumvents these limitations via stepwise panoramic scene expansion. Stepper leverages a novel multi-view 360{\deg} diffusion model that enables consistent, high-resolution expansion, coupled with a geometry reconstruction pipeline that enforces geometric coherence. Trained on a new large-scale, multi-view panorama dataset, Stepper achieves state-of-the-art fidelity and structural consistency, outperforming prior approaches, thereby setting a new standard for immersive scene generation.
Authors: Isaac Corley, Alex Stoken, Gabriele Berton
Abstract: Cross-modal optical-SAR (Synthetic Aperture Radar) registration is a bottleneck for disaster-response via remote sensing, yet modern image matchers are developed and benchmarked almost exclusively on natural-image domains. We evaluate twenty-four pretrained matcher families--in a zero-shot setting with no fine-tuning or domain adaptation on satellite or SAR data--on SpaceNet9 and two additional cross-modal benchmarks under a deterministic protocol with tiled large-image inference, robust geometric filtering, and tie-point-grounded metrics. Our results reveal asymmetric transfer--matchers with explicit cross-modal training do not uniformly outperform those without it. While XoFTR (trained for visible-thermal matching) and RoMa achieve the lowest reported mean error at $3.0$ px on the labeled SpaceNet9 training scenes, RoMa achieves this without any cross-modal training, and MatchAnything-ELoFTR ($3.4$ px)--trained on synthetic cross-modal pairs--matches closely, suggesting (as a working hypothesis) that foundation-model features (DINOv2) may contribute to modality invariance that partially substitutes for explicit cross-modal supervision. 3D-reconstruction matchers (MASt3R, DUSt3R), which are not designed for traditional 2D image matching, are highly protocol-sensitive and remain fragile under default settings. Deployment protocol choices (geometry model, tile size, inlier gating) shift accuracy by up to $33\times$ for a single matcher, sometimes exceeding the effect of swapping matchers entirely within the evaluated sweep--affine geometry alone reduces mean error from $12.34$ to $9.74$ px. These findings inform both practical deployment of existing matchers and future matcher design for cross-modal satellite registration.
Authors: Ming-Yang Ho, Alberto Bartesaghi
Abstract: Open-set 3D macromolecule detection in cryogenic electron tomography eliminates the need for target-specific model retraining. However, strict VRAM constraints prohibit processing an entire 3D tomogram, forcing current methods to rely on slow sliding-window inference over extracted subvolumes. To overcome this, we propose FullTilt, an end-to-end framework that redefines 3D detection by operating directly on aligned 2D tilt-series. Because a tilt-series contains significantly fewer images than slices in a reconstructed tomogram, FullTilt eliminates redundant volumetric computation, accelerating inference by orders of magnitude. To process the entire tilt-series simultaneously, we introduce a tilt-series encoder to efficiently fuse cross-view information. We further propose a multiclass visual prompt encoder for flexible prompting, a tilt-aware query initializer to effectively anchor 3D queries, and an auxiliary geometric primitives module to enhance the model's understanding of multi-view geometry while improving robustness to adverse imaging artifacts. Extensive evaluations on three real-world datasets demonstrate that FullTilt achieves state-of-the-art zero-shot performance while drastically reducing runtime and VRAM requirements, paving the way for rapid, large-scale visual proteomics analysis. All code and data will be publicly available upon publication.
Authors: Haojian Huang, Chuanyu Qin, Yinchuan Li, Yingcong Chen
Abstract: Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and demands careful regularization. Dynamic context methods zoom into focused evidence but often require curated pretraining and two-stage tuning, and their context remains bounded by a small model's capability. In contrast, larger models excel at instruction following and multi-modal understanding, can supply richer context to smaller models, and rapidly zoom in on target regions via simple tools. Building on this capability, we introduce an observation-level intervention: a frozen, tool-integrated teacher identifies the missing spatiotemporal dependency and provides a minimal evidence patch (e.g., timestamps, regions etc.) from the original video while the question remains unchanged. The student answers again with the added context, and training updates with a chosen-rollout scheme integrated into Group Relative Policy Optimization (GRPO). We further propose a Robust Improvement Reward (RIR) that aligns optimization with two goals: outcome validity through correct answers and dependency alignment through rationales that reflect the cited evidence. Advantages are group-normalized across the batch, preserving on-policy exploration while directing it along causally meaningful directions with minimal changes to the training stack. Experiments on various related benchmarks show consistent accuracy gains and strong generalization. Code will be available at https://jethrojames.github.io/FFR/.
Authors: Amr Sharafeldin, Shrisudhan Govindarajan, Thomas Walker, Aryan Mikaeili, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
Abstract: Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam representations to semantic decomposition tasks. Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations. Experimental results show that our method achieves superior object-level segmentation performance compared to state-of-the-art methods like Gaussian Grouping and SAGA.
Authors: Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl
Abstract: In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privacy. Traditional approaches to address these shortcomings, like federated learning, often impose significant computational burdens on individual clients, especially those with constrained resources. In response to these challenges, we introduce the novel approach CollaFuse for distributed collaborative diffusion models inspired by split learning. Our approach facilitates collaborative training of diffusion models while alleviating client computational burdens during image synthesis. This reduced computational burden is achieved by retaining data and computationally inexpensive processes locally at each client while outsourcing the computationally expensive processes to shared, more efficient server resources. Through experiments on the common datasets CelebA, CIFAR-10, and Animals-with-Attributes2, our approach demonstrates enhanced performance while decreasing information disclosure as it reduces the necessity for sharing raw data. These capabilities hold significant potential across various application areas, including the design of edge computing solutions. Thus, our work advances distributed machine learning by contributing to the evolution of collaborative diffusion models.
Authors: Jian Wang, Razieh Faghihpirayesh, Danny Joca, Polina Golland, Ali Gholipour
Abstract: Deep learning has shown significant value in medical image registration for motion correction, however, current techniques are either limited by the type and range of motion they can handle, or require iterative inference and/or retraining for new imaging data. To address these limitations, we introduce UniMo, a Unified Motion Correction framework that leverages deep neural networks to correct for various types of motion in medical imaging. UniMo exploits an alternating optimization scheme for a unified loss function to train an integrated model of 1) an equivariant neural network for global rigid motion correction and 2) an encoder-decoder network to correct local deformations. It features a geometric deformation augmenter that 1) enhances the robustness of global motion correction by addressing any local deformations, and 2) generates augmented data to improve the training process. UniMo is a hybrid model that uses both image intensities and shapes to achieve robust performance amid image appearance variations, and, therefore, it generalizes well to various medical imaging modalities without a need for network retraining. We trained and tested UniMo to track motion in fetal magnetic resonance imaging. Then we tested the trained model, without retraining, on various image modalities from three public datasets, including MedMNIST, lung CT, and BraTS. The results show that UniMo surpassed existing motion correction methods in terms of accuracy, and, notably, it enabled one-time training on a single modality while maintaining high stability and adaptability for inference across multiple unseen imaging datasets. By offering a unified solution, UniMo marks a significant advantage in challenging applications with a mixture of bulk motion and local deformations. https://github.com/IntelligentImaging/UNIMO
Authors: Yuxin Tian, Mouxing Yang, Yuhao Zhou, Jian Wang, Qing Ye, Tongliang Liu, Gang Niu, Jiancheng Lv
Abstract: Conventioanl federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Worsely, the F-LN problem is exacerbated by the heterogeneity of FL, whereas clients experience different labelnoise types, ratios, and data distribution. In this study, we first observe an intriguing phenomenon that the global model of FL exhibits a slow memorization of noisy labels, suggesting its ability to maintain reliable predictions and robust representations in FL. Motivated on this, we propose a novel method termed Federated Global Reviser (FedGR), a straightforward yet effective method comprising three modules that collaboratively rectify noisy labels and regularize local training. By exploiting above inherent property, FedGR improve the label-noise robustness of FL in a self-contained manner. Extensive experiments on three widely used F-LN benchmarks demonstrate the superior performance of FedGR, consistently outperforming seven state-of-the-art baselines even in severe label-noise and data heterogeneity. Code will be released as soon as possible.
Authors: Hanrui Wang, Shuo Wang, Chun-Shien Lu, Isao Echizen
Abstract: Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model inversion attacks reveal that identity information can still be recovered, exposing critical vulnerabilities. However, existing attacks are often computationally expensive and lack generalization, especially those requiring target-specific training. Even training-free approaches suffer from limited identity controllability, hindering faithful reconstruction of nuanced or unseen identities. In this work, we propose DiffMI, the first diffusion-driven, training-free model inversion attack. DiffMI introduces a novel pipeline combining robust latent code initialization, a ranked adversarial refinement strategy, and a statistically grounded, confidence-aware optimization objective. DiffMI applies directly to unseen target identities and face recognition models, offering greater adaptability than training-dependent approaches while significantly reducing computational overhead. Our method achieves 84.42%--92.87% attack success rates against inversion-resilient systems and outperforms the best prior training-free GAN-based approach by 4.01%--9.82%. The implementation is available at https://github.com/azrealwang/DiffMI.
Authors: Saeed Mohseni-Sehdeh, Walid Saad, Kei Sakaguchi, Tao Yu
Abstract: Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured data through a denoising process. When equipped with a guidance mechanism, these models can also generate samples from conditional distributions. In this paper, a novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme. The guidance term is defined as a piecewise function of the diffusion timestep, facilitating the use of different approximations during high-noise and low-noise phases. This design is shown to effectively balance computational efficiency with the accuracy of the guidance term. Unlike task-specific approaches that require retraining for each problem, the proposed method is problem-agnostic and readily adaptable to a variety of inverse problems. Additionally, it explicitly incorporates measurement noise into the reconstruction process. The effectiveness of the proposed framework is demonstrated through extensive experiments on image restoration tasks, specifically image inpainting and super-resolution. Using a class conditional diffusion model for recovery, compared to the \blue{pseudoinverse-guided diffusion model (\textrm{\(\Pi\)}GDM) baseline}, the proposed framework achieves a reduction in inference time of \(25\%\) for inpainting with both random and center masks, and \(23\%\) and \(24\%\) for \(4\times\) and \(8\times\) super-resolution tasks, respectively, while incurring only negligible loss in PSNR and SSIM.
Authors: Suyi Chen, Haibin Ling
Abstract: As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution. The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations. Gaussian mixture models (GMMs) provide a continuous, compact, and physically interpretable representation for molecular density and have recently gained interest in cryo-EM reconstruction. However, existing methods rely on external consensus maps or atomic models for initialization, limiting their use in self-contained pipelines. In parallel, differentiable rendering techniques such as Gaussian splatting have demonstrated remarkable scalability and efficiency for volumetric representations, suggesting a natural fit for GMM-based cryo-EM reconstruction. However, off-the-shelf Gaussian splatting methods are designed for photorealistic view synthesis and remain incompatible with cryo-EM due to mismatches in the image formation physics, reconstruction objectives, and coordinate systems. Addressing these issues, we propose cryoSplat, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation. In particular, we develop an orthogonal projection-aware Gaussian splatting, with adaptations such as a view-dependent normalization term and FFT-aligned coordinate system tailored for cryo-EM imaging. These innovations enable stable and efficient homogeneous reconstruction directly from raw cryo-EM particle images using random initialization. Experimental results on real datasets validate the effectiveness and robustness of cryoSplat over representative baselines. The code will be released at https://github.com/Chen-Suyi/cryosplat.
Authors: Anirudh Iyengar Kaniyar Narayana Iyengar, Srija Mukhopadhyay, Adnan Qidwai, Shubhankar Singh, Dan Roth, Vivek Gupta
Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task central to real-world applications such as scientific reporting, financial analysis, and public policy dashboards. Unlike prior benchmarks focusing on isolated, visually uniform charts, InterChart challenges models with diverse question types ranging from entity inference and trend correlation to numerical estimation and abstract multi-step reasoning grounded in 2-3 thematically or structurally related charts. We organize the benchmark into three tiers of increasing difficulty: (1) factual reasoning over individual charts, (2) integrative analysis across synthetically aligned chart sets, and (3) semantic inference over visually complex, real-world chart pairs. Our evaluation of state-of-the-art open- and closed-source VLMs reveals consistent and steep accuracy declines as chart complexity increases. We find that models perform better when we decompose multi-entity charts into simpler visual units, underscoring their struggles with cross-chart integration. By exposing these systematic limitations, InterChart provides a rigorous framework for advancing multimodal reasoning in complex, multi-visual environments.
Authors: Jordan Taylor, William Agnew, Maarten Sap, Sarah E. Fox, Haiyi Zhu
Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed "aesthetic" is inextricably linked to personal taste and cultural values, raising the question of whose taste is represented in visual generative AI models. In this work, we study an aesthetic evaluation model--LAION-Aesthetics Predictor (LAP)--that is widely used to curate datasets to train visual generative image models, like Stable Diffusion, and evaluate the quality of AI-generated images. To understand what LAP measures, we audited the model across three datasets. First, we examined the impact of aesthetic filtering on the LAION-Aesthetics Dataset (approximately 1.2B images), which was curated from LAION-5B using LAP. We find that the LAP disproportionally filters in images with captions mentioning women, while filtering out images with captions mentioning men or LGBTQ+ people. Then, we used LAP to score approximately 330k images across two art datasets, finding the model rates realistic images of landscapes, cityscapes, and portraits from western and Japanese artists most highly. In doing so, the algorithmic gaze of this aesthetic evaluation model reinforces the imperial and male gazes found within western art history. In order to understand where these biases may have originated, we performed a digital ethnography of public materials related to the creation of LAP. We find that the development of LAP reflects the biases we found in our audits, such as the aesthetic scores used to train LAP primarily coming from English-speaking photographers and western AI-enthusiasts. In response, we discuss how aesthetic evaluation can perpetuate representational harms and call on AI developers to shift away from prescriptive measures of "aesthetics" toward more pluralistic evaluation.
Authors: Zhexin Xu, Nikolas R. Sanderson, Hanna Jiamei Zhang, David M. Rosen
Abstract: We show that the factor graph and certifiable estimation paradigms, which have thus far been treated as essentially independent in the literature, can be naturally synthesized into a unified framework for certifiable factor graph optimization that combines the ease of use of the former with the strong performance guarantees of the latter. The key insight enabling our synthesis is that the core mathematical constructions used to develop certifiable estimators (Shor's relaxation and Burer-Monteiro factorization) inherit a factor graph structure from the original problem: applying these transformations to a QCQP-representable estimation task with an associated factor graph model yields a lifted problem with identical factor graph connectivity whose constituent variables and factors are simple one-to-one algebraic transformations (lifts) of those appearing in the original QCQP's factor graph. This correspondence enables the Riemannian Staircase methodology for certifiable estimation to be easily instantiated and deployed using the same mature, highly-performant factor graph libraries and workflows already ubiquitously employed throughout robotics and computer vision. Experimental evaluation on a variety of pose graph optimization, landmark SLAM, and range-aided SLAM benchmarks demonstrates that our certifiable factor graph optimization methodology enables the implementation of certifiable estimators that are functionally equivalent to current state-of-the-art hand-designed, problem-specific methods, while dramatically reducing the required implementation effort from the order of months to hours.
Authors: Zaid A. Abod, Furqan Aziz
Abstract: Complete and high-quality multi-modal Magnetic Resonance Imaging (MRI) is essential for accurate neuro-oncological assessment, as each contrast provides complementary anatomical and pathological information. However, acquiring all modalities (e.g., T1c, T1n, T2w, T2f) for every patient is often impractical due to prolonged scan times, cost, and patient discomfort, potentially limiting comprehensive tumour evaluation. We propose 3D-MC-SAGAN (3D Multi-Contrast Self-Attention Generative Adversarial Network), a unified 3D multi-contrast synthesis framework that generates high-fidelity missing modalities from a single T2w input while explicitly preserving tumour characteristics. The model employs a multi-scale 3D encoder--decoder generator with residual connections and a novel Memory-Bounded Hybrid Attention (MBHA) block to capture long-range dependencies efficiently, and is trained with a WGAN-GP critic and an auxiliary domain classification head to produce T2f, T1n, and T1c volumes within a unified network. To ensure anatomical and pathological fidelity, we incorporate a frozen 3D U-Net-based segmentation network that enforces a tumour-consistency constraint during training. A composite objective combining adversarial, reconstruction, perceptual, structural similarity, contrast-classification, and segmentation-guided losses further promotes both global realism and tumour-preserving structure. Extensive experiments on 3D brain MRI datasets demonstrate that 3D-MC-SAGAN achieves state-of-the-art quantitative performance and produces visually coherent, anatomically plausible contrasts with improved distributional realism. Importantly, the proposed method maintains tumour segmentation accuracy comparable to that achieved using fully acquired multi-modal inputs, highlighting its potential to reduce acquisition burden while preserving clinically meaningful information.
Authors: Stephan Xie, Ben Cohen, Mononito Goswami, Junhong Shen, Emaad Khwaja, Chenghao Liu, David Asker, Othmane Abou-Amal, Ameet Talwalkar
Abstract: Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising yet underexplored capability of foundation models. In this work, we present ARFBench, a TSQA benchmark that evaluates the understanding of multimodal foundation models (FMs) on time series anomalies prevalent in software incident data. ARFBench consists of 750 questions across 142 time series and 5.38M data points from 63 production incidents sourced exclusively from internal telemetry at Datadog. We evaluate leading proprietary and open-source LLMs, VLMs, and time series FMs and observe that frontier VLMs perform markedly better than existing baselines; the leading model (GPT-5) achieves a 62.7% accuracy and 51.9% F1. We next demonstrate the promise of specialized multimodal approaches. We develop a novel TSFM + VLM hybrid prototype which we post-train on a small set of synthetic and real data that yields comparable overall F1 and accuracy with frontier models. Lastly, we find models and human domain experts exhibit complementary strengths. We define a model-expert oracle, a best-of-2 oracle selector over model and expert answers, yielding 82.8% F1 and 87.2% accuracy and establishing a new superhuman frontier for future TSQA models. The benchmark is available at https://huggingface.co/datasets/Datadog/ARFBench.
Authors: Luis Barba, Johannes Kirschner, Benjamin Bejar
Abstract: Computed Tomography (CT) is a widely used imaging modality in medical and industrial applications. To limit radiation exposure and measurement time, there is a growing interest in sparse-view CT, where the number of projection views is significantly reduced. Deep neural networks have shown great promise in improving reconstruction quality in sparse-view CT, especially generative diffusion models. However, these methods struggle to scale to large 3D volumes due to several reasons: (i) the high memory and computational requirements of 3D models, (ii) the lack of large 3D training datasets, and (iii) the inconsistencies across slices when using 2D models independently on each slice. We overcome these limitations and scale diffusion-based sparse-view CT reconstruction to large 3D volumes by combining conditional diffusion with explicit data consistency. We propose Conditional Diffusion Posterior Alignment (CDPA) to enable scalable 3D sparse-view CT reconstruction. A 2D U-Net diffusion model is conditioned on an initial 3D reconstruction to improve inter-slice consistency, combined with data-consistency alignment to match measured projections. Experiments on synthetic and real Cone Beam CT (CBCT) data show state-of-the-art performance, with ablations that confirm the synergistic effects of the proposed pipeline. Finally, we show that the same principles also strengthen fast denoising U-Nets, yielding near-diffusion quality at a fraction of the computational cost.
Authors: Hiromitsu Goto, Tao Tao, Zheng-Lin Chia
Abstract: Quantitative analysis of the kinematic chain in sports motion is essential for performance evaluation and injury prevention. Conventional methods such as the kinematic-sequence (KS) and continuous relative phase (CRP) are confined to adjacent joint pairs and lack a unified framework for whole-body coordination, while segmental power-flow analysis requires force plates and inertial parameters that restrict it to laboratory environments. We apply Complex Hilbert Principal Component Analysis (CHPCA) separately to each motion phase (backswing and downswing) on markerless 3D pose estimation data, extracting the dominant whole-body phase pattern as a single complex eigenvector. The pipeline further includes a fully automatic signal-based phase segmentation (no priors on strike count or rest location) and an extension to 1,079 body-surface mesh vertices, so that the kinematic chain is represented as a continuous phase field across the body. On 14 hammer-striking trials of a single subject, the framework reveals (i) a trunk-anchored global phase architecture, (ii) a functional asymmetry between preparation and execution phases quantified by Mode-1 contribution (45.5% vs. 70.5%) and inter-trial Spearman consistency (0.38 vs. 0.58), and (iii) a consistent reorganisation across both skeletal joints and mesh vertices ($p < 10^{-10}$ on 1,079 vertices). As a methodological consistency check, pairwise phase differences from the Mode-1 eigenvector are compared against CRP on all 190 joint pairs by a permutation test ($\rho = 0.473$, $p = 0.0005$). A correspondence analysis between Mode-1 amplitude and kinetic-energy mobilisation variance further shows a strong positive correlation in the downswing ($\rho \approx 0.71$ on both skeleton and mesh) and no correlation in the backswing, indicating that the proposed framework bridges kinematic and kinetic descriptions of coordination through phase structure.