Authors: Chaowen Yan, Kaishen Wang, Yong Wang, Jianlong Xiong, Tao He
Abstract: Oracle Bone Inscriptions (OBIs) recognition plays a crucial role in understanding ancient Chinese culture. However, accurately recognizing OBIs remains highly challenging due to their complex, irregular, and often degraded shapes. Traditional methods rely on expert knowledge and manual analysis, which are time-consuming and error-prone. Although deep learning has greatly advanced general image recognition, existing methods struggle to capture the fine-grained details and subtle variations inherent in OBIs, resulting in limited performance. Even most recent and effective layer attention techniques are designed to capture fine-grained dependencies through enhanced inter-layer interactions, yet they still exhibit only marginal improvements in OBIs recognition. To address these limitations, we propose Multi-Scale Layer Attention (MSLA), a novel paradigm that explicitly models both multi-scale and cross-layer feature interactions. By enriching the representation with fine-grained details across multiple spatial scales, MSLA enables more accurate and robust OBIs recognition. Extensive experiments on large-scale OBIs datasets demonstrate that MSLA consistently outperforms existing attention mechanisms while maintaining computational efficiency.
Authors: Ying Chen, Jinyue Li, Qiankun Li
Abstract: Image quality is critical for accurate medical diagnosis. However, MRI, CT, and ultrasound images are often of low resolution and quality due to cost constraints, complicating the visualization of key anatomical structures and lesions. While such limitations are common in practice, traditional methods treat image enhancement as a separate preprocessing step, failing to fully leverage its potential synergy with image segmentation. To address this, we propose DiSIINet (Diffusion-based Symbiotic Information Interaction Network), which is built on the principle that enhancement and segmentation should mutually reinforce each other in a unified model. Based on Denoising Diffusion Implicit Models (DDIM), DiSIINet integrates an enhancement branch and a segmentation branch. These branches interact through a novel Symbiotic Information Interaction (SII) module, which facilitates dynamic, feature-level information exchange via cross-attention during the reverse diffusion process. This design enables both tasks to iteratively improve each other. The DDIM backbone ensures high-quality output and efficient inference through deterministic sampling. Experiments on multi-modal medical datasets (MRI, CT, ultrasound) show that DiSIINet achieves significant performance improvements compared to sequential or independent enhancement and segmentation approaches. The code is available at: https://github.com/Reconsider80/DiSIINet.
Authors: Rui Hao, Qiankun Li, Junyuan Mao, Linghao Meng, Dirui Xie, Dayu Tan, Zhigang Zeng
Abstract: Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations still undermine trustworthy use: models can produce fluent conclusions that conflict with imaging evidence. Existing mitigation strategies typically rely on additional training, external retrieval/knowledge bases, or multi-stage post-hoc verification, which increases cost and pipeline complexity and often generalizes poorly across models and tasks.To address this, we propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection. By leveraging ROI priors acquired using MedSAM in our implementation, we recalibrate the visual perception trajectory via ROI-guided activation modulation while anchoring the textual reasoning trajectory by mapping anatomical coordinates into discrete semantic tokens as verifiable external memory. Then we introduce a task-aware dynamic router to select modality-specific interventions based on task semantics, balancing perceptual grounding and linguistic fluency. We conduct systematic evaluations on 2 tasks and 5 datasets using \texttt{LLaVA-1.5-7B}, \texttt{LLaVA-Med-1.5-7B}, \texttt{Qwen3-VL-8B/32B}, and \texttt{InternVL-3.5-8B/38B}. Controlled ablations and visualizations further validate the framework, which consistently outperforms baselines across medical benchmarks, improving close-ended accuracy by up to $\sim\mathbf{6}\%\uparrow$ and reducing open-ended hallucinations by $\sim\mathbf{35}\%\downarrow$. The code has been made available on GitHub: \href{https://github.com/Henry991115/SPRG}{\textcolor{blue}{https://github.com/Henry991115/SPRG}}.
URLs: https://github.com/Henry991115/SPRG, https://github.com/Henry991115/SPRG
Authors: Zhiyao Shu, Jiacheng Yang, Yang Lu, Waishan Qiu, Chuan Li, Da Chen
Abstract: Urban-scale Visual Place Recognition (VPR) aims to identify the geographic location of a query image by matching it against a geo-tagged database. While recent methods achieve impressive performance, they overlook a serious long-tailed problem hidden in urban-scale datasets, which biases the model towards locations with abundant images and ignores less-visited areas, causing models to systematically favor frequently photographed locations while failing in sparsely covered areas. In this paper, we systematically characterize this imbalance challenge and propose Distribution-Aware Place Recognition (DAPR), a model-agnostic plug-in framework that rebalances gradient contributions across head and tail classes. Additionally, within classification-retrieval pipelines, DAPR applies a multi-scale distance search mechanism to compute per-class distributional compactness, providing complementary gains at the retrieval stage. On the large-scale SF-XL benchmark, our framework outperforms the previous classification-retrieval baseline by 18.3% on test set v1, and 6.7% on test set v2. As a plug-in module, it achieves consistent improvements across representative VPR methods on SF-XL, MSLS, and Pitts30k, demonstrating broad generalizability across different methods and benchmarks.
Authors: Dengxian Gong, Yuanzheng Wu, Haobo Yuan, Zhengdong Hu, Tao Zhang, Yikang Zhou, Shihao Chen, Quanzhu Niu, Kai Wang, Jason Li, Haochen Wang, Lu Qi, Shunping Ji, Ming-Hsuan Yang
Abstract: This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure to the entanglement of reasoning and perception within a single model, the MLLM reasons and localizes simultaneously, and inaccurate localization triggers additional reasoning turns that bloat the trajectory. To solve this problem, we propose PixelEyes, a multi-turn visual reasoning agent that explicitly decouples reasoning from perception, i.e., the reasoner decides what to look for, while a specialized perception tool answers where it is. Specifically, PixelEyes introduces 1) Mask-guided Visual Search. A referring segmentation model is invoked to provide mask-precise localization, freeing the reasoner from the need to compensate for imprecise grounding. 2) Semantic-region Breadth-first Search (BFS). To eliminate redundant loops caused by repeatedly cropping incorrect sub-regions, we organize exploration as a breadth-first search over semantic regions. To internalize these capabilities, we construct the PixelEyes-6K dataset by resynthesizing expert trajectories from existing data. This explicitly embeds our mask-guided search and BFS logic into the model. We further introduce Pinpoint-Bench, a zero-hint visual search benchmark, i.e., no location cues are provided in the question, with instance-level masks and bounding boxes that separate localization failures from reasoning failures, enabling fine-grained analysis of failure modes such as inattentional blindness. Recent state-of-the-art MLLMs and visual reasoning agents leave large headroom on Pinpoint-Bench, demonstrating its quality and difficulty. Code and models are open-sourced.
Authors: Luca Barsellotti, Martin Sundermeyer, Mattia Segu, Nikita Araslanov, Muhammad Ferjad Naeem, Marcella Cornia, Yongqin Xian, Maxim Berman
Abstract: Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computational cost of pixel decoding, textual modality fusion, and object decoding to make these architectures more suitable for mobile devices, real-time on-device inference at high frame rates remains an open challenge. In this paper, we introduce SegFS, a dual-stream fast-slow framework that significantly improves efficiency without sacrificing accuracy. On sparse keyframes, an open-vocabulary object-based model predicts instance-level representations. These representations are then projected back into the backbone feature space to condition a lightweight fast network, which efficiently relocalizes and segments the instances in subsequent frames. By shifting instance propagation from object decoding to feature-space conditioning, our approach decouples multimodal semantic understanding from dense mask prediction and enables efficient temporal propagation. The proposed fast branch achieves up to 14x lower latency than the mobile-oriented MOBIUS model, while maintaining competitive segmentation performance on standard OV-VIS benchmarks.
Authors: Yunhan Wang, Eshika Khandelwal, Edson Araujo, Walid Bousselham, Nina Shvetsova, Hilde Kuehne
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prompted to decide whether the two images depict the same class. The logit corresponding to an affirmative response is then used as a similarity score to assign the query image to the most likely class. While this already yields good results, we show that providing additional high-level information, such as the data domain, to the model further improves performance. Our evaluation provides an extensive analysis of various inference variants on a suite of twelve datasets, six established and six newly curated few-shot benchmarks spanning across diverse domains. The results show that the proposed simple decomposition technique can turn off-the-shelf MLLMs into powerful few-shot learners, significantly outperforming current state-of-the-art few-shot methods on both standard and novel domains. Code is available at https://github.com/yunhanwang1105/DeCoDe.
Authors: Hui Zhang, Xuanang Lei, Rui Wang, Julian Ferchow, Mirko Meboldt
Abstract: Quality control in industrial assembly is essential, and real-time monitoring of the assembly process is crucial for preventing costly defects and ensuring production reliability. Vision-based automated inspection offers a powerful solution for such real-time monitoring. However, due to the specialized industrial components and processes, training these models typically relies on task-specific real-world data, which is costly and labor-intensive to collect and annotate. In this paper, we propose a system that automatically generates realistic assembly sequences and further trains real-time inspection models using the synthetic data. It can be efficiently applied to a given task within an hour, requiring only CAD models and simple step descriptions. Focusing on practical challenges, our system integrates a physics-based motion generation module to capture the variance of different human assembly, designs domain-randomized rendering to deal with the environmental complexity and variation, and employs an object-detection-based step recognition module for robust sim-to-real transfer, leading to 92.4% accuracy on a real-world assembly case with 46.7%, 15.8% and 61.2% performance improvement, respectively. Overall, our system provides a practical solution for industrial assembly inspection without requiring expensive real-world data collection and annotation, with the effectiveness validated on real industrial assembly tasks.
Authors: Jianmin Liao, Lei Huang, Ronglong Fang, Ashley Prater-Bennette, Lixin Shen, Yuesheng Xu
Abstract: MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade coarse-to-fine residual hierarchy that progressively refines the reconstruction across resolution grades, improving representational fidelity and mitigating spectral limitations. To stabilize reconstruction optimization and suppress INR-induced artifacts, we further propose an explicit sparse proximal regularization (e.g., $\ell_0$-type) applied directly in the high-resolution image domain, which discourages spurious high-frequency patterns while preserving sharp structures. The resulting optimization is solved efficiently via a multi-grade proximal alternating scheme, and we establish convergence guarantees for the associated updates under standard regularity conditions. Experiments on mixed-degradation benchmarks demonstrate that MG-SpaIR consistently outperforms strong training-data-free baselines such as Deep Image Prior, providing a stable, interpretable, and data-efficient alternative to conventional learning-based restoration methods.
Authors: Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi
Abstract: Active learning (AL) performance is known to be budget-dependent, yet regimes are typically defined by heuristic label counts that fail to generalize across datasets or architectures. We characterize AL dynamics by reframing budget regimes as shifts in the dominant generalization mechanism. By reinterpreting PAC-style risk components as dynamic interacting terms, we prove that dominance shifts are structurally unavoidable, creating a moving bottleneck for generalization. We operationalize this using measurable proxies and a segmented regression procedure to identify a tripartite taxonomy: data-driven, transition, and model-driven phases. Our framework explains the long-standing observation that representativeness, coverage, and uncertainty strategies excel at different stages. Experiments across natural and medical imaging show that AL efficiency depends on the alignment between the strategy's inductive bias and the active bottleneck. Moreover, self-supervised representation shift transitions earlier along the labeling trajectory, highlighting the role of representation quality in shaping AL dynamics. Overall, this work provides a unified framework for the next generation of transition-aware AL algorithms.
Authors: Siyuan Li, Weiying Chen, Yilin Wang, Xinxin Zuo, Xingyu Li, Li Cheng
Abstract: Reconstructing 4D animals from monocular videos is challenging due to large inter-species variation, complex articulations, and the lack of reliable templates. Existing approaches typically rely on either strict category-specific priors that restrict generalization, or unconstrained generative models that sacrifice input fidelity. To bridge this gap, we present a progressive test-time optimization framework built on 3D Gaussian Splatting for high-fidelity 4D animal reconstruction from a single video. Our key insight is that a coarse shape prior suffices when coupled with a progressive strategy that disentangles articulated pose from non-rigid deformation. Specifically, we employ a symmetry-aware temporal encoding that exploits bilateral cues while absorbing camera estimation drift and a part-conditioned deformation mechanism guided by learnable part anchors and a learnable skinning field. Extensive experiments demonstrate that our approach generalizes robustly across diverse species, achieving superior geometric accuracy, temporal consistency, and visual fidelity compared to existing baselines, even under severe prior mismatch.
Authors: Kai Hu, Akash Bharadwaj, Weichen Yu, Matt Fredrikson
Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a task-level side channel induced by ViT-style patchification: when a synthetic grid image is aligned with the hidden patch grid, boundary cues are erased at tokenization, causing periodic accuracy drop. By sweeping the grid cell size and measuring these collapses, we infer the patch size; by introducing padding and a consistency-check test, we further identify whether preprocessing is dynamic- or fixed-resolution and recover the target resize resolution. Across open-source Qwen-VL variants and proprietary models including GPT and Claude, we reliably recover tokenizer-related parameters. Finally, we show that such leakage enables preprocessing-aware transfer attacks and model-targeted adversarial manipulation.
Authors: Aymeric Fleith, Julian Zirbel, Daniel Cremers, Niclas Zeller
Abstract: We introduce PRISM-VO, a novel pure optimization-based sparse photometric visual odometry framework for focused plenoptic cameras. The core of PRISM-VO is a novel photometric plenoptic bundle adjustment which jointly optimizes camera poses and inverse depth values of points in a sliding window. By combining geometric depth from a single plenoptic image with temporal multi-view constraints, PRISM-VO achieves accurate and drift-resilient motion estimation. Through explicit modeling of the plenoptic projection, PRISM-VO provides reliable metric-scale reconstructions, overcoming the scale ambiguity of monocular SLAM algorithms. Importantly, our approach relies solely on a single plenoptic sensor and avoids complex initialization, as depth priors are computed directly from plenoptic imaging. Experiments show that PRISM-VO outperforms the current state-of-the-art plenoptic visual odometry method on indoor and outdoor scenes. The proposed approach rivals other optimization- and learning-based methods while accurately and reliably recovering a metric scale of the scene. Project page: https://prism-vo.github.io/
Authors: H\'ector Laria, Yiping Han, Julian D. Santamaria, Kai Wang, Bogdan Raducanu, Joost van de Weijer, Alexandra Gomez-Villa
Abstract: Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse autoencoder analysis and zero-shot classification, we demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface: when damage is severe enough for FID and KID to respond, the model is already nearly unusable; when the model remains functional, FID and KID stay flat while specific classes silently suffer worst-case zero-shot accuracy drops of up to 18.9 points and concept-level distributions shift dramatically. This pattern appears at both ends of the adaptation spectrum (concept customization and concept unlearning), suggesting it is a systematic consequence of weight-level modification rather than an artifact of any particular method. To surface this hidden drift before deployment, we introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them. DriftScope optimizes a soft prompt to attribute drift at the token level without requiring access to real data or model internals. The result is an interpretable, concept-level audit that aggregate evaluation cannot provide.
Authors: Nouri Alexander Hilscher, Mateo de Mayo, Dominik Muhle, Christoph Otten genannt Hermes, Daniel Cremers
Abstract: Camera pose estimation from image streams is a critical component of spatial world models that integrate perception into planning and decision-making. Nearly all Visual Odometry (VO) and Simultaneous Localization and Mapping (V-SLAM) systems have focused on datasets containing raw, uncompressed videos. Many working systems instead use ubiquitous hardware units to efficiently compress and decode video streams, saving orders of magnitude in storage and bandwidth. However, this lossy compression introduces visual artifacts that hinder the performance of traditional tracking systems. We present VOCA, a causal stereo visual-odometry method that exploits codec information to improve tracking performance. We achieve state-of-the-art performance on causal VO for relative trajectory error, efficiency, and absolute trajectory error on compressed streams. This work highlights the potential of leveraging widely available video codec information for vision tasks.
Authors: Erich Robbi, Daniele Ravanelli, Andrea Passerini
Abstract: Robust segmentation of intraluminal thrombus is critical for risk assessment in Abdominal Aortic Aneurysm, yet it remains challenging due to heterogeneous thrombus features and low contrast with surrounding non-enhanced tissues. Domain shifts induced by different Computed Tomography Angiography (CTA) protocols further inhibit multi-center generalization of deep learning models. To address these challenges, we propose a patient-specific framework that integrates discriminative learning with anatomically informed priors. Our approach introduces two key components: (1) a patient-specific intensity normalization based on a Gaussian Mixture Model of local anatomy, and (2) an Uncertainty-Gated Anatomical Attention module that incorporates spatial priors while adaptively modulating their influence according to voxel-wise confidence. This design allows for anatomical guidance in ambiguous regions while suppressing unreliable priors. The proposed method achieves state-of-the-art performance on in-distribution test data and substantially outperforms existing alternatives in generalization to external multi-center CTA data, while remaining interpretable through an explicit separation of visual and anatomical evidence.
Authors: Siddhant Panpatil, Arth Singh, Mijin Koo, Chaeyun Kim, Haon Park, Dasol Choi
Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction that binary safety benchmarks obscure. We introduce EgoSafetyBench, an egocentric video benchmark of 1,200 robot-view scenarios annotated at half-second granularity, to evaluate VLMs as streaming guards across two tracks. The situational track (800 scenarios) spans four families, from routine and safe-but-suspicious scenes to obvious and contextual hazards. The visual-channel track (400 scenarios) targets in-scene text-a sign, sticker, or label visible in the scene-that can misrepresent the physical situation, pairing each misleading sign with a truthful version to test both whether a guard flags the text as misleading and whether the text corrupts its physical-safety judgment. Both tracks use contrastive ladders: near-identical scenarios differing only in a single visible deciding cue, so a correct call must hinge on that cue rather than the overall scene type. We evaluate ten open- and closed-source VLMs. We find that while guards reliably recognize videos containing hazards, they often miss specific hazardous moments, particularly contextual hazards. Furthermore, misleading in-scene signs degrade all tested guards: vulnerable models miss up to a third of hazards, while robust models over-intervene on safe content. Matched controls reveal that apparent safety robustness often reflects indiscriminate alarming rather than true physical reasoning.
Authors: Xin Li, Wenhui Zhu, Xuanzhao Dong, Xiwen Chen, Yanxi Chen, Yujian Xiong, Hao Wang, Oana M. Dumitrascu, Yalin Wang
Abstract: Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks through self-attention, enabling modeling of long-range dependencies. Early ViT-based segmentation methods typically retained U-Net-style decoders because pretrained ViT representations were insufficient to support accurate dense prediction. Recent advances in large-scale pretraining have redefined the representation capability of ViTs, reducing the reliance on U-Net-style decoder architectures in modern vision models. This prompts two questions: Is the U-Net paradigm still necessary for medical image segmentation? If not, how should an encoder-only segmentation framework be designed? Motivated by these questions, we explore key architectural choices for encoder-only medical image segmentation based on modern ViT backbones and establish a query-based encoder-only design with multi-level query modeling and learnable block fusion, realized in Encoder-only Segmentation (EoSeg). Extensive experiments across seven benchmark datasets spanning CT, MRI, histopathology, endoscopy, and dermoscopy validate the effectiveness of the proposed design across diverse medical imaging modalities, including mDice scores of 85.50% on Synapse, 91.73% on ACDC, and 93.27% on GlaS. The results demonstrate that a U-Net-style decoder is no longer necessary for medical image segmentation with modern ViT backbones and further show that EoSeg provides an effective encoder-only design. Code is available at: https://github.com/Retinal-Research/EoSeg
Authors: Samira Malek, Haichuan Zhang, Chul Lee, Vishal Monga
Abstract: While most image deblurring techniques directly restore the spatial image variable, we propose an amplitude and phase decomposition recognizing the importance of accurate phase estimation in recovering sharp image details. To that end, we first develop novel linear minimum mean squared (LMMSE) estimators of the amplitude and phase of the blurred, noisy image observation. An iterative optimization algorithm follows that recovers the sharp image using the aforementioned LMMSE estimators. Finally, matrix parameters that are statistically determined and fixed in the iterative algorithm are now learned using a training dataset of clean and degraded observations. Our deblurring engine is dubbed UPADNet (Unrolled Phase and Amplitude Decomposition Network), such that each iteration of the underlying phase and amplitude recovery algorithm is parameterized and trained end-to-end. Experiments over benchmark evaluation datasets such as GoPro, RealBlur and COCO datasets confirm that UPADNet outperforms state of the art deep networks including those based on algorithm unrolling in the image domain. The benefits of UPADNet are even more pronounced in high noise and limited training data regimes.
Authors: Afshar Shamsi, Xiao-Yu Guo, Hamid Alinejad-Rokny, Arash Mohammadi, Damien Teney, Ehsan Abbasnejad
Abstract: Test-Time Adaptation (TTA) seeks to improve model robustness under distribution shifts by adapting parameters using unlabeled target data. However, in the absence of supervision, entropy-based adaptation is fundamentally underconstrained: multiple distinct parameter updates can achieve similarly low entropy while inducing drastically different decision boundaries. This phenomenon, known as underspecification, renders standard TTA brittle and prone to collapse into spurious modes. In this work, we reinterpret TTA through a posterior-inspired lens induced by entropy minimization, where low-entropy solutions define a pseudo-likelihood over parameters. Instead of committing to a single point estimate, we introduce a particle-based diversification framework that explores multiple plausible adaptation trajectories simultaneously. Our method can be viewed as a structured exploration of multiple plausible adaptation solutions, implemented through multi-level diversification at the output, parameter, optimizer, and input levels. Crucially, the framework acts as a plug-and-play wrapper compatible with existing TTA methods. Extensive experiments on challenging benchmarks demonstrate consistent gains in stability and robustness, achieving improvements of 3-4% under mixed shifts, 2-3% with batch size one, and 1-2.5% under label shifts, outperforming state-of-the-art baselines. Our results suggest that treating TTA as a multi-hypothesis inference problem, rather than a single-point optimization task, is key to mitigating underspecification and enabling reliable real-world deployment.
Authors: Thinh Phan, Hao Vo, Khoa Vo, Thanh Ngo, Cuong Pham, Ngan Le
Abstract: The core challenge in multi-view pedestrian detection (MVPD) lies in effective aggregation of visual features from different viewpoints for robust occlusion reasoning. Recent approaches have addressed this by first projecting image-view features onto a Bird's Eye View (BEV) map, where ground localization is then performed. Despite impressive performance, the perspective transformation induces severe distortion, causing spatial structure break and degrading the quality of object feature extraction. The blurred and ambiguous features hinder accurate BEV point localization, especially in densely populated regions. Moreover, the strong mutual relationship between the BEV ground point and image bounding boxes is not capitalized on. Although multi-view consistency of 2D detections can serve as a powerful constraint in BEV space, these detections are commonly treated as auxiliary signals rather than being jointly optimized with the primary task.In this work, we propose \textbf{MVDGC}, a unified framework that \emph{jointly estimates pedestrian locations on the BEV plane and 2D bounding boxes in image views}. MVDGC employs a \emph{sparse set of 3D cylindrical queries} that embraces geometric context across both BEV and image views, enforcing dual spatial constraints for precise localization. Specifically, the geometric constraints is established by modeling each pedestrian as a vertical cylinder whose center lies on the BEV plane and whose projection casts a rectangular box in the image views. These queries function as shape anchors that directly extract 2D features from the intact image-view features using camera projection, eliminating projection-induced distortions. The 3D cylindrical query enables the unification of BEV and ImV localization into a single task: 3D cylinder position and shape refinement. Code is available at: https://github.com/UARK-AICV/MVDGC
Authors: Scott Chase Waggener, Sai Karthik Navuluru, Lakshman Tamil
Abstract: We present Aegis, a joint-embedding predictive architecture for breast cancer detection and density assessment in mammography. We train three Vision Transformer variants (Small/Base/Large) using self-supervised joint-embedding predictive architecture (JEPA) pre-training on 71,103 studies from 14 clinical sites, followed by supervised fine-tuning with progressive resolution scaling up to 2048x1536. On a curated 785-study test set, our largest model achieves area under the receiver operating characteristic curve (AUC) 0.949 for breast cancer triage with 93% sensitivity and 75% specificity at the optimal operating point. An ensemble combining our model with a U.S. Food and Drug Administration-cleared baseline further improves discrimination to 0.952 AUC. For breast density classification, the model achieves 0.953 AUC for binary (dense vs. non-dense) classification and 62.6% exact accuracy across four Breast Imaging Reporting and Data System (BI-RADS) categories, with 98.8% adjacent accuracy comparable to reported human inter-reader agreement. External validation on the public VinDr-Mammo dataset provides evidence of cross-population transfer under a different reference standard, with the largest model achieving 0.871 AUC for triage in a zero-shot setting.
Authors: Sakib Reza, Gauri Jagatap, Mohsen Moghaddam, Octavia Camps, Andrea Fanelli
Abstract: Temporal Action Localization (TAL) typically relies on segment annotations or offline access to full videos, limiting scalability and online use. We introduce Point-Supervised Online TAL (POTAL), which localizes actions in streaming videos using only one temporal point per instance. To solve POTAL, we propose OnPoint, an offline-to-online multi-level distillation framework that transfers knowledge from a point-supervised offline teacher to an online student via (i) pseudo-segment instance distillation, (ii) class-activation sequence distillation, and (iii) anticipatory window-level distillation. We further improve robustness by incorporating the original point labels into student training and by refining anchor decoding with actionness-guided attention calibration. Experiments on five datasets show OnPoint consistently outperforms strong baselines, establishing a solid foundation for POTAL.
Authors: Xiangyue Liu, Zijian Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Ping Tan
Abstract: Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuous generative objectives alongside discrete understanding tasks causes severe gradient conflicts. Existing architectures, including standard Mixture-of-Experts (MoE), are highly susceptible to representation overwriting. Even structurally partitioned paradigms like Mixture-of-Transformers (MoT) remain vulnerable to catastrophic forgetting, severely impeding multimodal scalability. In this work, we introduce Rosetta, a composable native multimodal pretraining framework designed for seamless and non-destructive modality expansion. Rosetta adopts a modular paradigm where core foundational knowledge is preserved within global shared experts, while modality-specific capabilities are distributed across plug-and-play experts. To guarantee non-destructive composition, we propose Momentum-Anchored Orthogonal Projection (MAOP). MAOP leverages the optimizer's momentum state as an implicit semantic anchor, selectively neutralizing conflicting gradient components from new modalities while preserving synergistic updates. Extensive evaluations demonstrate that, while standard MoE and MoT architectures suffer catastrophic forgetting of previously acquired knowledge, Rosetta robustly preserves established language and visual understanding. Furthermore, it delivers superior image generation and unlocks cross-modal synergy, paving the way for truly composable and unified multimodal foundation models. To facilitate further multimodal research, we release our code and checkpoints to the community. Project page at https://rosetta-lmm.github.io/.
Authors: Jingni Huang
Abstract: Human motion forecasting in unconstrained real-world videos remains challenging due to the ambiguity of future behaviors and the presence of noisy multimodal observations. While facial affect potentially provides complementary behavioral cues, its practical utility and mechanistic boundaries within motion forecasting frameworks remain poorly understood. In this work, we present a systematic study investigating the utility and temporal limitations of affect-conditioned forecasting in-the-wild. We establish a rigorous multimodal pipeline combining MediaPipe body pose trajectories with HSEmotion facial affect representations, and introduce the Gated Affect Transformer (GAT) to dynamically regulate cross-modal information flow. Through extensive multi-horizon evaluations under a strict subject-wise protocol, we demonstrate that naive early cross-modal concatenation consistently degrades forecasting accuracy relative to pose-only baselines. Conversely, our proposed gating mechanism stabilizes cross-modal integration by adaptively controlling the affective stream. Crucially, controlled counterfactual experiments using shuffled and randomized affect inputs reveal that the learned gate successfully suppresses unstructured cross-modal noise while remaining responsive to plausible affective signals. Furthermore, our empirical results indicate that facial affect features provide bounded, horizon-dependent predictive cues strictly within short-to-medium windows (e.g., 30 frames), whereas long-term trajectories remain predominantly governed by intrinsic kinematic continuity. Our findings provide empirical evidence that facial affect should be regarded as a complementary behavioral cue rather than a dominant driver of future motion, offering practical guidance for selective multimodal fusion in unconstrained human motion forecasting.
Authors: Yoonhyung Park, Minji Kim, Sungwon Moon, Jiyoung Lee
Abstract: Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping multimodal LLMs with this tactile sense, however, expose a zero-sum trade-off: the limited parameter budget of compact models forces a choice between acquiring the new sensory modality and preserving the established vision-language reasoning. We present Splash, a mask-isolated tactile alignment learning framework for MLLMs. Splash quantifies the significance of each pretrained parameter, and partitions the parameter space into a dormant and critical subspace. While the frozen critical subspace acts as a stable anchor to safeguard general visual knowledge, Splash updates the isolated dormant subspace to internalize tactile alignment towards LLMs. This selective, non-destructive expansion effectively prevents catastrophic forgetting and ensures non-destructive modality expansion. Extensive experiments show that Splash effectively achieves tactile reasoning without additional inference overhead in the LLM part, demonstrating state-of-the-art performance on visuo-tactile benchmarks, including SSVTP, TVL, and TacQuad, while preserving its original general-purpose capabilities.
Authors: Amirreza Rouhi, Rajat Aggarwal, Parikshit Sakurikar, Anoop M. Namboodiri, Sashi P. Reddi
Abstract: Foundation video diffusion models are increasingly viewed as world simulators for embodied agents, yet their pretraining on internet-scale generic video leaves them poorly aligned with real-world deployment domains. We study parameter-efficient adaptation of a pretrained foundation video world model to retail scenes: when synchronized egocentric and exocentric video of the same activity are available, which viewpoint of training data produces the strongest adapted model? We introduce RetailSMV (Retail Synchronized Multi-View), a corpus of 32,105 captioned retail clips from five supermarkets with synchronized ego/exo capture from the store-staff perspective (stocking, arranging, weighing, managing supply carts, scanning at checkout), rather than the customer-centric framing of prior retail video corpora, and train three matched Low-Rank Adaptation (LoRA) configurations of Cosmos3-Nano (egocentric-only, exocentric-only, combined) under identical hyperparameters. On a 200-clip held-out test set evaluated with seven complementary metrics under a strict paired statistical protocol, exocentric-only adaptation matches or exceeds combined adaptation on six of seven point estimates and is significantly better on LPIPS, PSNR, and DreamSim, despite training on only 15,985 exocentric clips (versus 32,105 for combined). A symmetric paired comparison further shows that adding exocentric data to egocentric-only training helps while adding egocentric data to exocentric-only training hurts. The absolute adaptation gap is largest at the shortest rollout time, identifying the near-horizon prediction window as the regime in which adaptation is most beneficial.
Authors: Manognya Lokesh Reddy, Zheng Liu
Abstract: Estimating the distance to a leading vehicle is a basic input to forward collision warning, adaptive cruise control, and automated emergency braking. Production systems obtain this distance from radar, laser scanners, or stereo camera pairs, which add cost, power draw, and packaging constraints. This paper asks whether a single ordinary camera can recover the same distance by using a target that is standardized in size and present on every road vehicle: the rear license plate. U.S. plates share a fixed outer size and a character height that is set by regulation and varies only narrowly between states, so the height of a plate character in the image is a direct measure of distance once the camera geometry is known. The proposed method (Typography-Based Monocular Distance Estimation) detects the plate, measures the height of its printed characters, identifies the issuing state to select the correct physical character height, and recovers distance from the camera projection. Three measurements taken from the same plate: the character height, the stroke width, and the character spacing. Together with the spacing of the two mounting holes and a single-image depth network, are combined so that a weak or corrupted measurement is given less weight automatically. The distance, its rate of change, and a time-to-collision estimate are smoothed across frames and used to raise a warning with the timing used by U.S. collision-warning regulations. The same plate that anchors the scale also identifies the vehicle, so the method returns a distance, a bearing, and an identity from one passive sensor. It reads scale from a printed standard instead of from time of flight or parallax, making it a cheap, low-maintenance complement to those sensors in a fault-tolerant perception stack, achieving the cost-effective distance estimation with error less than 0.13 m.
Authors: Yuxiao Wu, Weile Li, Boyi Zhu, Yumeng Liu, Youcheng Cai, Ligang Liu
Abstract: Reconstructing high-fidelity 3D models of highly articulated animals, such as dogs, from a single in-the-wild image remains a formidable challenge. In this paper, we introduce CORGI, a novel framework for consistency-aware 3D dog reconstruction from a single unconstrained image that completely eliminates the need for 3D supervision. To overcome generative inconsistencies and the lack of multi-view capture, our pipeline introduces three core components. First, we propose a Canonical-Driven Orbital Generation (CDOG) strategy, utilizing specialized Canonical and Orbit LoRAs to normalize arbitrary input poses and synthesize reliable 360-degree video observations. Second, we design a Consistency-aware Deformable 3DGS (CA-3DGS) module that anchors on a D-SMAL prior, explicitly modeling per-view generative errors through dedicated neural deformation fields to learn accurate vertex-level displacements. Finally, to eliminate structural distortions and recover high-frequency details, we introduce a self-supervised Deformation-Conditioned Generative Repair (DCGR) module. Extensive experiments demonstrate that CORGI achieves state-of-the-art performance, generalizing seamlessly across diverse dog breeds to produce geometrically accurate, visually coherent, and fully animatable 3D assets ready for downstream applications.
Authors: Ke Wu, Yanan Zhang, Yingjie Gao, Wenhao Li, Chenyu Zhou, XinZhu Ma, Jiaxin Chen, Di Huang
Abstract: Object detection for Unmanned Aerial Vehicles (UAVs) working in open and dynamic environments is a highly challenging task. While Vision-Language Models (VLMs) have offered a powerful solution for universal object detection, adapting them to UAV scenarios remains non-trivial due to a substantial domain gap between VLM pre-training data and aerial imagery. The prevailing Parameter-Efficient Fine-Tuning (PEFT) methods prove ineffective in bridging this gap, as VLMs' "natural-scene, foreground-dominant" visual priors misalign with the "bird's-eye-view, background-dominant, small-object" characteristics of UAV data. To address this issue, we propose DroneFINE, a novel PEFT paradigm comprising two domain-aware complementary modules tailored for VLM-based drone image detectors. Specifically, a data-dependent, foreground-aware, and multi-path adaptation mechanism named HyperAdapter is designed, which overcomes the static structural constraints of PEFT. In addition, a background suppression algorithm named SemanticGate is developed. It is a text-conditioned guidance strategy that employs background vocabulary to actively guide the model in suppressing responses from irrelevant regions. Extensive experiments on VisDrone and UAVDT demonstrate that DroneFINE significantly outperforms existing PEFT methods and achieves performance comparable to full fine-tuning while substantially reducing the number of trainable parameters.
Authors: Kensuke Nakamura, Byung-Woo Hong
Abstract: Personalized object localization (POL) localizes an object instance in a query image based on a few reference images with bounding-box annotations and a target object label. The pioneering method, IPLoc, solves this task through in-context inference with vision-language models (VLMs). However, it assumes that the query image always contains the target object. This assumption severely limits its applicability to real-world scenarios with many irrelevant images. To address this issue, we formulate a new task, personalized object identification and localization (POIL), by positioning POL within the broader few-shot object detection framework. POIL aims to localize the target object instance while rejecting query images that do not contain the reference object instance. We also present POIL datasets constructed from public sources. We further propose an in-context algorithm named IPLoc-ID for solving POIL with VLMs. IPLoc-ID first predicts a candidate bounding box and then determines whether it corresponds to the reference object instance. We introduce a self-posed query to connect these two steps within a single autoregressive generation framework. Through ablation studies and comprehensive experiments, we show that IPLoc-ID substantially suppresses false-positive detections on negative query images while maintaining localization performance comparable to IPLoc. Overall, IPLoc-ID effectively addresses the practical instance-level POIL task, which cannot be sufficiently solved by conventional object detection, few-shot object detection, or the localization-only IPLoc method.
Authors: Siyuan Yao, Ziqi Wang, Ruiqi Yu, Junqi Huang, Wenqi Ren, Xiaochun Cao
Abstract: Domain adaptive visual object tracking under adverse weather conditions has garnered significant attention in recent years. Despite the impressive performance, existing methods heavily rely on the large-scale video frames from both source and target domains, which is impractical under rigid resource constraints where source data is unavailable. To overcome this limitation, we propose SFDATrack, a generalized source-free domain adaptive tracker that merely leverages adverse weather samples from the target domain for robust state estimation. Specifically, SFDATrack first employs a mean-teacher backbone with Dual Interactive Mamba (DIM) blocks to distill the candidate target tokens that are resilient to weather variations from classified, augmented samples. Afterwards, we introduce a hyperspherical prototype projection (HPP) module to project these tokens onto multi-domain prototypes within a latent hyperspherical space. By enforcing both domain-specific and domain-invariant properties of the multi-domain prototypes, SFDATrack can be seamlessly adapted to diverse weather conditions with powerful generalizability. Extensive experiments evaluated on various benchmarks demonstrate that SFDATrack achieves superior performance compared to state-of-the-art approaches. The code is available at https://github.com/watcherBR0/sfdatrack.
Authors: Nuoyan Zhou, Zhijun Tu, Lei Yu, Kun Cheng, Jie Hu, Nannan Wang, Xinghao Chen
Abstract: Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However, VAR still suffers from inherent deficiencies in multi-scale representation learning. Specifically, lower scales primarily capture global semantics, while higher scales focus on fine-grained details. Employing a shared architecture across scales induces optimization conflicts. Moreover, due to the causal autoregressive process, inaccurate semantics at early scales can propagate and significantly degrade the final output. To address these issues, we introduce a scale-aware token-routed Mixture of Experts (MoE) architecture, allowing scale-adaptive expert selection, thereby facilitating decoupled representation learning across scales. In addition, we enhance semantic modeling at early scales by incorporating external self-supervised features. Unlike naive alignment, we analyse and design a residual feature aggregation scheme tailored to the VAR paradigm. Extensive experiments show that our method significantly improves both training efficiency and generation quality. On the ImageNet 256*256 benchmark, our model achieves a superior FID compared to the dense baseline while requiring only half of the default training epochs and a smaller parameter budget, with a merely marginal increase in training cost. Moreover, the performance gap further widens with larger training epochs.
Authors: Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao
Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on costly triplets, Zero-Shot CIR (ZS-CIR) alleviates this reliance through proxy tasks trained on image-text pairs. However, existing proxy tasks primarily enhance visual and textual representations to accommodate a predefined composition mechanism such as pseudo-word injection into a frozen text encoder or linear feature arithmetic. As a result, the composition function itself remains unlearned, limiting the model's ability to express diverse and fine-grained semantic modifications. To address this, we propose FoCo, which models composition as two coordinated stages: focusing on modification-relevant visual content, and then completing the target semantics. We realize these through two proxy tasks: text-anchored visual aggregation to selectively gather visual content guided by localized textual semantics, and context-conditioned semantic completion to transform these aggregated visuals with the remaining scene context into a coherent composed representation. The tasks are trained jointly with a cross-instance contrastive objective, encouraging semantic diversity and discouraging shortcut composition strategies. Extensive experiments on four ZS-CIR benchmarks show FoCo's state-of-the-art performance and improved generalization.
Authors: Jing Gao, Wei Wang, Feiran Wang, Yan Yan
Abstract: We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way humans organize spatial memory around stable and recognizable objects. LIST3R organizes long-sequence reconstruction around instance anchors, using them to reconnect fragmented subsequences and consolidate local observations into a coherent global 3D scene. Given a long video, our approach partitions it into overlapping subsequences and builds a structured local instance library for each partial reconstruction, maintaining persistent trackable anchors with semantic and geometric evidence. These anchors are matched across subsequences to recover revisited regions and provide object-aware constraints for fragment alignment, producing a consistent global reconstruction. During this process, the evolving geometric evidence updates the local instance libraries and progressively organizes them into a unified global 3D instance library. Experiments on long-sequence benchmarks show that our method produces more accurate trajectories and higher-quality 3D reconstructions, highlighting the effectiveness of persistent instance anchors for organizing long-horizon 3D reconstruction. Our code is available on the project page: https://yixn965.github.io/LIST3R/.
Authors: Faruk Alpay, Baris Basaran
Abstract: Colored sectors in a microbial range expansion encode more than lineage survival counts. We formulate a computer-vision inverse problem: from one endpoint image of an accretive multi-type expansion, recover the radius-indexed pairwise boundary-flow field and test whether the visual pattern is compatible with a transitive scalar fitness hierarchy. The observable is a geometric signal extracted from sector-boundary curves in log-polar coordinates. We prove endpoint observability and stability for frozen fronts, weighted transitive/cyclic decomposition, contact-complete circular design, physical-clock and mechanism non-identifiability, exact Gaussian cyclicity testing, and Bonferroni-valid interval scanning. The benchmark is deterministic: analytic endpoint images, blurred/noisy pixel round trips, scalar-null stress tests, public-image tracing, multi-resolution mechanistic endpoints, and a non-learning frozen-front simulator. The implementation recovers pairwise edge-flow histories from endpoint images, detects cyclic residuals in a mechanistic four-type expansion, and uses those residuals as forcing signals for a dimensionless active design-control layer covering reaction-diffusion control, phenotype-frontier optimization, protocol synthesis, Monte Carlo robustness, and a downstream population-state bridge.
Authors: Jaeah Lee, Hyunjin Kim, Jaewoong Cho, Gihyun Kwon
Abstract: We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geometric fidelity. Despite remarkable progress in 3D shape generation, large DiT-based models remain computationally prohibitive in resource-constrained settings. Furthermore, it is difficult to directly transfer existing diffusion model compression strategies developed for different domains to 3D generation, and prior 3D efficiency approaches focus primarily on inference speed rather than backbone compression. To address this limitation, we build a geometry-aware compression framework tailored to image-to-shape DiTs. Guided by the observation that 3D DiT layers exhibit non-uniform importance for geometry synthesis, we introduce a vitality-guided framework integrating structured pruning, adaptive quantization, and targeted fine-tuning. Our method achieves up to 66% model-size reduction across state-of-the-art image-to-3D models while maintaining synthesis fidelity comparable to full-sized counterparts. This highlights the potential of our framework as a plug-and-play solution for efficient 3D shape generation across diverse models.
Authors: Chong He, Yuechen Luo, Fang Li, Shaoqing Xu, Fuxi Wen
Abstract: End-to-end autonomous driving models often encounter performance bottlenecks, as training-time scaling leads to high computational costs and diminishing marginal returns. Existing planners typically adopt a one-shot generation paradigm, lacking secondary validation and active correction mechanisms to detect and revise suboptimal or unsafe trajectories during inference. To address this issue, we propose DriveVer, a lightweight, plug-and-play Test-Time Verifier that leverages the test-time scaling paradigm to enable autonomous driving systems to validate and refine trajectories without costly and heavy training. We construct a dedicated trajectory dataset based on the NAVSIM benchmark through condition-driven clustering and balanced sampling according to ego-vehicle states and navigation commands. Employing a dual-head architecture, DriveVer efficiently fuses candidate trajectories with multi-view visual representations and ego-vehicle kinematic features to simultaneously predict a safety confidence score and an absolute geometric refinement vector. Extensive experiments on the NAVSIM benchmark show that DriveVer significantly improves the performance of base planning models. Notably, as an extremely compact model with only 34M parameters, DriveVer introduces minimal computational overhead, achieving competitive results while maintaining real-time inference efficiency.
Authors: Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Mubarak Shah
Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics (e.g., FID, CLIPScore) that are insensitive to fine-grained semantic correctness, creating an illusion of high utility. We show that when utility is measured with structured evaluation, this illusion breaks: on TIFA (Text-to-Image Faithfulness evaluation with Question Answering), safety-aligned models suffer substantial drops in semantic fidelity, including failures in object counts, attributes, and relationships. To diagnose the source of this gap, we analyze the text-encoder prompt embedding space and uncover semantic collapse, a contraction of embedding spread coupled with distortion of inter-prompt similarity structure, which strongly correlates with structured utility loss. Guided by this insight, we propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure during adaptation. Our method restores structured utility (TIFA +5.0% over prior state-of-the-art) while maintaining strong safety performance and competitive coarse-grained utility scores. Our source code and trained models are available at https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/.
URLs: https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/.
Authors: Saad Wazir, Patrick Dominique Vibild, Dinh Phu Tran, Seongah Kim, Daeyoung Kim
Abstract: Medical image segmentation relies on the ability of encoder-decoder architectures to translate rich feature representations into accurate pixel-level predictions under challenging conditions such as low contrast, structural ambiguity, and scale variability. While recent advances in large-scale pretraining and transformer-based encoders have substantially improved feature extraction, segmentation accuracy remains constrained by decoder design, particularly in terms of cross-scale alignment, contextual integration, and boundary preservation. In this work, we revisit medical image segmentation from a decoder-centric perspective and propose a context-aware gated decoder that systematically regulates feature fusion and contextual aggregation throughout the decoding process. The proposed decoder integrates lightweight multi-scale channel recalibration, gated skip fusion with spatial competition and a global context aggregation mechanism that injects encoder-wide information into intermediate decoding stages. This design enables effective translation of strong pretrained encoder representations into spatially consistent predictions. Extensive experiments across 11 medical image segmentation benchmarks validate the effectiveness and demonstrate that the proposed approach consistently outperforms strong baselines while remaining computationally practical. Code: https://github.com/saadwazir/MedCAGD
Authors: Zhenhang Li, Xin Zhou, Hao Deng, Lijun Yin
Abstract: Recent brain decoding studies have made substantial progress in reconstructing externally perceived visual content from neural signals. However, using electroencephalography (EEG) recordings to guide facial expression editing remains largely unexplored and poses a distinct challenge: rather than recovering what a subject sees, it requires identifying facial-action related patterns from noisy EEG signals and grounding them in localized, identity-preserving expression edits. In this paper, we investigate EEG-conditioned facial image editing for fine-grained facial action unit (AU) control and propose MindAU, a unified framework for controlling facial AU edits from EEG signals. MindAU first learns noise-robust and AU-discriminative EEG representations through temporal masked reconstruction and AU classification supervision. It then bridges the modality gap via Dual-Stream Manifold Alignment, aligning EEG features with AU-level text semantics and identity-reduced visual displacement trajectories in the multimodal space of Qwen2.5-VL. Finally, MindAU incorporates EEG-aware Multimodal Rotary Positional Embeddings, landmark-guided reference masking, and AU-aware region supervision into a multimodal diffusion-based editor for high-fidelity identity-preserving editing. We also introduce E-CAFE, a curated benchmark for EEG-Conditioned Action-Unit Facial Editing with paired EEG-face editing samples and standardized evaluation protocols. Extensive experiments demonstrate the effectiveness of MindAU and suggest its potential as a step towards future assistive expression technologies for individuals with facial neuromuscular disorders.
Authors: Wei Sun, Weixia Zhang, Hongjian Zhan, Mingkai Lu, Yixuan Gao, Guangtao Zhai
Abstract: We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images. The framework jointly predicts global, target, and background quality scores by ensembling two complementary pipelines: (1) SigLIP2 vision encoders with multi-task regression heads, and (2) a LoRA-adapted Qwen3.5-9B multimodal large language model for quality score regression. The final global quality prediction is obtained by arithmetically averaging the outputs of both pipelines. Our method achieves 2nd place in the challenge, demonstrating its effectiveness. The code is available at https://github.com/sunwei925/DroneIQA-VLE.
Authors: Qiyan Luo, Yingdong Pi, Lekang Wen, Jie Yang, Xiaoyu Wang, Haiming Zhang, Mi Wang
Abstract: In the era of satellite constellations, multi-view optical satellite imagery is pivotal for Earth Observation (EO) and high-quality Digital Surface Model (DSM) reconstruction. Although feed-forward 3D foundation models have transformed computer vision, their deployment in satellite remote sensing is inherently constrained by the structural discrepancy between implicit perspective assumptions and explicit orbital pushbroom geometry. This geometric incongruity is further compounded by pronounced view-set heterogeneity. We present EO-VGGT, a framework that adapts a frozen perspective-driven model to orbital observations via explicit physical geometry embedding.First, the Geometry-Correlation Constrained Selection (GCCS) strategy prunes sub-optimal observations by balancing geometric diversity and radiometric consistency to optimize the input sequence. Second, a Sensor-Ray Encoder (SRE) parameterizes pixel-level pushbroom lines of sight derived from the Rational Function Model (RFM) into high-dimensional space-geometric tokens, reconciling the mathematical discrepancy between central projection and orbital kinematics. Third, a lightweight Ray-Pointing-Aware Adapter (RPAA) employs gated residual blocks to integrate these tokens directly into the frozen transformer backbone. Our findings underscore that integrating explicit physical geometry with optimized view selection is essential for robust feed-forward satellite 3D reconstruction.
Authors: Ji Ha Jang, Hayeon Kim, Chulwon Lee, Junghun James Kim, Se Young Chun
Abstract: CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions (>77 tokens) due to absolute positional encoding and pretraining on short captions. In long contexts, sentences are often reordered, summarized, or partially omitted. Although prior works extend CLIP with longer positional encodings, they often suffer from degraded image-text alignment under such text perturbations. We attribute this limitation to the Euclidean contrastive objective, which enforces strict one-to-one matching and lacks explicit mechanisms for modeling hierarchical relationships between global context and its constituent elements. To address this issue, we propose HyFL-CLIP, a hyperbolic fine-tuning framework that distills the well-established text-image alignment learned in Euclidean CLIP into hyperbolic space via cross-manifold similarity distillation, leveraging its geometry to capture hierarchical and entailment relations. Our method models hierarchical semantics by linking summarized token-wise features, long-context descriptions, constituent short textual components, and images, capturing part-whole relationships via hyperbolic entailment with Einstein midpoint aggregation. Experiments on diverse benchmarks, including long-context cross-modal retrieval, cross-modal retrieval with caption perturbations, intra-modality retrieval, and short-text cross-modal retrieval, show that HyFL-CLIP achieves more robust long-context understanding. In particular, it yields up to 19.5% improvement in long-text cross-modal retrieval under textual perturbations over the best prior method. We also show HyFL-CLIP can be seamlessly integrated into other model frameworks by applying it to Stable Diffusion XL (SDXL).
Authors: Guohao Sun, Xiaofang Wang, Yash Patel, Mengchen Liu, Zhiqiang Tao, Praveen Krishnan
Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning. We claim these failures result from a lack of explicit control over visual representation learning during the standard next-token prediction objective. As a result, visual embeddings thus become passively optimized and prone to injecting redundant or spurious signals. To counter this, we introduce Information-Regularized Attention (IRA), a stochastic attention mechanism that explicitly regulates the amount of visual information injected into the hidden states of intermediate transformer layers. This local reparameterization translates uncertainty about visual representations into local noise that is independent across data points. Beyond evaluating model performance, we also quantify embedding properties, where IRA produces smoother curvature trajectories and suppresses attention-sink across all layers, indicating a more stable transformation of the visual signal. Our results suggest that stochastic attention is not merely a regularizer but a key contributor to representation learning in a generative architecture, offering a new direction for building more reliable VLMs.
Authors: Seohyun Lee, Seoung Choi, Dohwan Ko, Jongha Kim, Hyunwoo J. Kim
Abstract: As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subsequently perform fine-grained, query-conditioned tasks (intra-video reasoning) within the retrieved content, such as temporal grounding. However, existing approaches typically treat retrieval as a preprocessing step, and consequently, when the initial retrieval fails, there is no mechanism to refine the search, leading to the failure of subsequent fine-grained intra-video reasoning. Moreover, while recent agentic frameworks have advanced video understanding, they typically assume that the query-relevant video is already given, focusing exclusively on intra-video reasoning tasks. To address these limitations, we propose VideoSearch-R1, an agentic framework for iterative video retrieval and reasoning through multi-turn interaction with a video search engine. Specifically, we introduce Soft Query Refinement (SQR) to refine search query tokens in a continuous latent space rather than rewriting queries in the discrete text space, enabling more efficient and fine-grained adjustments. SQR and its reasoning process are trained using Group Relative Policy Optimization (GRPO), guided by task-level reward signals derived from retrieval and downstream tasks. Building upon this, VideoSearch-R1 achieves state-of-the-art performance across three datasets on Video Corpus Moment Retrieval (VCMR), iteratively retrieving videos from large-scale corpora, refining search queries, and performing precise query-conditioned temporal grounding within the retrieved content. Our analyses show that SQR effectively refines the original query, requiring significantly fewer generated tokens than explicit text-level query refinement. Code and model checkpoints are publicly available at mlvlab.github.io/VideoSearch-R1.
Authors: Shijie Li, Yilin Gao, Siyuan Yang, Tieyuan Chen, Chaofan Gan, Zhihao He, Zicheng Zhao, Yuyu Guo, Weiyao Lin, Hang Yu
Abstract: Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimodal query and the final answer. However, this introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts. Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance. To address this, we propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective. A forward KL divergence trains the target-agnostic prior to match the posterior, while a novel reverse KL divergence simultaneously regularizes the posterior, preventing it from collapsing into inference-incompatible regions and mitigating this ``answer leakage''. We provide theoretical analysis formalizing this leakage as prior contamination and prove that our dual-KL objective reduces it. We instantiate AMVL in a latent-integrated MLLM and show that it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.
Authors: Yuan Qing, Chengzhi Mao, Boqing Gong
Abstract: Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT often packs multiple language tasks about the same image for conversational, multi-turn training, whereas existing benchmarks evaluate LVLMs in isolated, single-turn scenarios. The models can suffer from visual attention decay and contextual overfitting during multi-turn training, making it hard for them to realize their full potential in the mismatched test phase. To close the gap, we propose learning with Stochastic Turn Depth (StochasT), which stochastically groups language tasks for the same image into clusters of varying sizes (turn depth) while preserving their organic order. Hence, while StochasT draws on Dropout and stochastic depth for ResNets, it does not actually drop anything to maximize the utility of the training data. Furthermore, we introduce a challenging, benchmark-agnostic evaluation mechanism based on the Balanced Latin Square to measure LVLMs' robustness under varying contextual dependencies. Extensive experiments demonstrate that StochasT effectively grants LVLMs strong, harmonized capabilities for both single-turn and multi-turn use cases.
Authors: Leyuan Yu, Xiao Tang, Minghao Liu, Xinyuan Li, Xiaokai Bai, Sheng Zhou, Qunshu Lin, Weihao Xuan, Naoto Yokoya
Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene fixed. Can VLMs instead predict the consequences of hypothetically moving or rotating an object? We introduce MindEdit-Bench, a benchmark of six spatial reasoning tasks built from three-photo smartphone triplets of newly captured indoor scenes via an automatic in-the-wild 3D scene-graph extraction pipeline. Four tasks probe perception and perspective transformation over observed structure; two new tasks, L4 (spatial editing) and L5 (cross-view visibility editing), probe object-level counterfactual reasoning, where correct answers are absent from all input images. Each question provides 8-24 structured answer choices, enabling answer-letter-level diagnosis of spatial and fallback errors. The benchmark covers 120 private indoor scenes not drawn from public datasets, reducing public-data pretraining-overlap risk. Across 15 VLMs on 1,003 human-verified questions, task-wise mean VLM accuracy is only 8%-31%, versus 81%-97% human majority-vote accuracy. The pooled human--best-VLM gap is 53 pp, with at least 39 pp on every task. The structured answer space further reveals non-uniform failures, including weaker camera-depth-axis inference and fallback behavior on difficult visibility-editing cases.
Authors: Sai Karthikey Pentapati, Shashank Gupta, Rajesh Sureddi, Yuezhi Yang, Alan C. Bovik, Qixing Huang
Abstract: We introduce GenSP, a data-driven framework that learns consistent spherical parameterizations across a collection of genus-0 shapes. Instead of optimizing the parameterization of each shape independently, our method learns a neural generative model that predicts a continuous mapping from the unit sphere to shapes in a dataset. Under this formulation, spherical parameterizations are obtained through the inverse mappings of the learned generator, which encourages similar shapes to share consistent parameterizations. To make this formulation practical, we address several key challenges in learning such a generative model. First, we introduce a continuous neural deformation model that predicts surface points from sphere coordinates and latent shape codes, avoiding discretization artifacts common in mesh-based formulations. Second, we augment the training space with intermediate shapes that bridge the sphere and input shapes, allowing the model to learn meaningful deformations across a heterogeneous shape collection. Third, we compute reliable initial correspondences by propagating mappings along a spanning tree of training shapes in the latent space. Experiments on the ShapeNet dataset demonstrate that our approach significantly reduces geometric distortion and improves cross-shape consistency compared with state-of-the-art spherical parameterization methods.
Authors: Chenxun Deng, Zhongde Zhang, Ye Yuan, Chengyang Zhang, Yifan Zhang, Bohao Chen, Hongying Yan, Hang Zhou, Hua Han, Xi Chen
Abstract: Multi-animal tracking (MAT) is critical for wildlife monitoring and behavioral analysis, yet remains challenging due to uniform appearance, high density, and irregular motion. Existing methods typically follow heuristic- or query-based paradigms: the former relies on handcrafted geometric associations without end-to-end optimization, whereas the latter enables joint optimization but relies heavily on appearance embeddings. In such conditions, continuous geometric embeddings can be unstable, as small coordinate perturbations may disproportionately alter cross-frame attention weights, degrading identity association performance. To address this limitation, we propose HieDG, a Hierarchical Discrete Geometry-guided tracking framework that reformulates geometric dynamics as structured discrete representations within a query-based tracker. Instead of directly using raw geometric signals, HieDG employs a two-stage residual codebook to discretize position, scale, and velocity cues, transforming unstable continuous geometry into structured, stable discrete tokens. These tokens are aligned with visual embeddings and integrated into the tracking queries to enhance identity consistency. Extensive experiments on animal-specific benchmarks (AnimalTrack, BFT, and BuckTales) demonstrate state-of-the-art association performance with significant improvements in HOTA, AssA, and IDF1. Additional evaluations on generic multi-object tracking benchmarks, including DanceTrack and SportsMOT, show competitive performance, indicating the broader applicability of discretized geometric modeling beyond animal-specific scenarios.
Authors: Yuchen Zhang, Luanyuan Dai, Yiwei Wang, Xiwei Xu, Jianing Zhang, Johnny. r. zhang, Xianhui Meng, Yanbiao Ma, Jiayi Ma, Xiaoshuai Hao
Abstract: Aligning generative 3D reconstructions with partial monocular observations is a critical but under-explored challenge in computer vision. This task is inherently ill-posed due to severe asymmetries between noisy, sparse monocular inputs and dense generative priors, whose scale ambiguity and geometric hallucinations, combined with the lack of initial overlap, render traditional registration pipelines ineffective. To resolve these issues, we propose a training-free and interpretable geometric alignment framework that grounds generative 3D priors via a 3D similarity transformation (Sim(3)), which can recover accurate metric scale and pose. Specifically, we introduce an explicit scale factor to resolve metric ambiguity and employ a coarse-to-fine alignment strategy, leveraging geometry-aware descriptors for robust initialization and a decoupled closed-form solver for precision refinement. In addition, we introduce a Hallucination Filtering operation to effectively suppress outliers caused by hallucinated geometry. To evaluate alignment performance under these extreme conditions, we introduce GenPMOAlign--Where2Place, a rigorous benchmark specifically designed for Generative-to-Partial Monocular Observational Alignment. Experiments demonstrate that our method achieves stable and accurate registration, substantially outperforming both classical geometric pipelines and state-of-the-art learning-based baselines. Code and the benchmark will be publicly released.
Authors: Feng Yang, Jie Liu, Yubo Pang, Peilin Chen, Xinheng Lyu, Shiqi Wang, Howard Leung, Ping Chen
Abstract: Automated pathology report generation from Whole Slide Images (WSIs) has attracted increasing attention in digital pathology. However, existing methods are predominantly developed under single-organ settings, overlooking the multi-organ scenarios encountered in clinical practice, where organ types typically follow a long-tailed distribution. To address this gap, we identify two critical biases: (1) visual representation bias, where the encoder favors head-class patterns over tail-class discriminative features, and (2) textual decoding bias, where the decoder overfits to head-class narrative patterns, yielding diagnostically unreliable outputs for tail-class organs. To mitigate these two biases, we propose a novel Prior-anchored multi-Organ pathology report Generation framework (PriOrGen). Specifically, a Visual-Prototype Anchored Bottleneck module leverages the information bottleneck principle with learnable anchor representations to selectively retain diagnostically relevant visual information while filtering out head-biased redundancy. Secondly, a Meta-Report Anchored Bank module constructs an organ-specific meta-report anchored bank and retrieves organ-faithful textual priors to steer the decoder away from head-class narrative patterns. Extensive experiments on a multi-organ pathology dataset demonstrate that our method effectively mitigates long-tail biases and achieves superior report generation performance across both head and tail organ categories compared to state-of-the-art methods.
Authors: Xuepeng Liu, Ruili Li, Zetong Liu, Renyiming Li, Yan Li, Yin Dai, Chao Li, Yueyang Teng
Abstract: Positron emission tomography (PET) provides essential functional information for disease assessment, however reducing injected activity or acquisition time produces low-dose (LD) PET with stronger count dependent noise and less reliable uptake quantification. Diffusion models offer a promising solution for PET denoising by progressively recovering high-dose (HD) PET images from LD inputs. However, LD-to-HD PET denoising is still challenging due to insufficient anatomical guidance, unstable multi-scale feature propagation, and uncertain frequency domain uptake recovery. We propose AnF-DiffPET, an anatomy- and frequency-guided diffusion framework for computed tomography (CT) conditioned LD PET denoising. The framework integrates Anatomical-Frequency Guidance (AFG), Multi-Scale Cross-Transformer Reconstruction (MSCTR), and Frequency-Contrastive Hard Mining (FCHM) to enhance anatomy aware feature modulation and frequency domain consistency during denoising. Experimental results across four PET/CT datasets show that the proposed method improves image fidelity, anatomical consistency, and quantitative fidelity over representative CNN-based, GAN-based, transformer-based, and diffusion-based methods. The code and trained models will be publicly released upon acceptance.
Authors: Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo, Hoang M. Truong, Tuan-Anh Vu
Abstract: Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception. Yet annotating them densely is expensive, making self-supervised pretraining the natural route to transferable representations. Existing pretext tasks, however, are almost entirely intra-modal, and the few methods that transfer knowledge from 2D foundation models rely on a single global embedding per clip, discarding the rich per-patch semantics that these models compute. To address this gap, we propose Cross4D-JEPA, a teacher-student method that distills a frozen 2D foundation model, an image model DINOv2, or a video model V-JEPA 2, into a 4D point encoder. The proposed method combines (1) a dense cross-modal correspondence that maps every 3D point to the teacher patch feature it projects to, and (2) a per-point objective that trains the student to match these features in latent space with no masking, negatives, or decoder. We evaluate Cross4D-JEPA on four benchmarks, MSR-Action3D, DeformingThings4D, NTU-RGB+D 60, and HOI4D, against intra-modal and global cross-modal baselines. Experimental results show that, under a matched protocol, the proposed method consistently outperforms intra-modal and global cross-modal baselines across the four benchmarks and is competitive with heavier published 4D methods; further analysis attributes this gain primarily to the granularity of the correspondence rather than the teacher modality. Beyond recognition accuracy, the dense representation learned by Cross4D-JEPA transfers across domains, improves label efficiency, and improves full-label fine-tuning under the same training budget, while a 13x smaller encoder matches a heavyweight pooling backbone.
Authors: Xiaolong Shen, Zongxin Yang, Yi Yang
Abstract: Restoring incomplete or damaged 3D objects is crucial for cultural heritage preservation, occluded object reconstruction, and artistic design. Existing methods primarily focus on geometric completion, often neglecting texture restoration and struggling with relatively complex and diverse objects. We introduce Restore3D, a novel framework that simultaneously restores both the shape and texture of broken objects using multi-view images. To address limited training data, we develop an automated data generation pipeline that synthesizes paired incomplete-complete samples from large-scale 3D datasets. Central to Restore3D is a multi-view model, enhanced by a carefully designed Mask Self-Perceiver module with a Depth-Aware Mask Rectifier. The rectified masks learned by the self-perceiver guide an image integration and enhancement phase, helping retain observed shape and texture patterns while refining the generated regions and mitigating the low-resolution limitations of the base model, yielding high-resolution, semantically coherent, and view-consistent multi-view images. A coarse-to-fine reconstruction strategy is then employed to recover detailed textured 3D meshes from refined multi-view images. Experiments on synthetic and real broken-object benchmarks show that Restore3D improves multi-view restoration quality and textured-mesh reconstruction over representative inpainting, completion, and reconstruction baselines in the evaluated settings. Project Page: restore3dx.github.io
Authors: Kyuwon Kim, Sunjae Yoon, Chang D. Yoo
Abstract: Generating animation from a single 2D drawing is challenging because the output must preserve character appearance while remaining plausible and temporally coherent under motion. Existing drawing-based 3D animation pipelines often use sample-wise 2D refinement to align animated renderings with the input image, but such optimization tends to overfit to the observed view and fails to correct projection-induced artifacts in novel views. To address this limitation, we introduce SPECSIA-15K, a paired stylization dataset containing 14,980 artifact-corrupted projection/refinement-target pairs from 1,498 3DBiCar characters. We further present DraViE (Drawing-based View Enhancement), a lightweight plug-and-play module trained with data-level priors to remove novel-view artifacts while preserving style and motion plausibility. Experiments show consistent gains in novel-view fidelity and temporal coherence with lower per-character adaptation cost than sample-wise fine-tuning.
Authors: Qi Xun Yeo, Seungjun Lee, Yan Li, Gim Hee Lee
Abstract: Classic 3D scene graph generation approaches fail to work in real-time due to the heavy computational cost of environment mapping and the need to generate intermediate point-cloud representations. To alleviate this issue, a recent work eschews point clouds in favor of a lightweight Gaussian distribution for each object. This approximation drastically speeds up inference and enables real-time 3D scene graph generation. However, the representation has two key weaknesses. \textbf{1)} Each object is approximated by a single 3D Gaussian, which causes a severe loss of 3D geometric detail. \textbf{2)} The discrepancy between this approximation and the true object geometry exacerbates the inaccurate merging of object candidates during online inference. To address these issues, we propose \textbf{NoPA}, which represents each object as a separate non-parametric distribution. This formulation retains 3D geometric information while preserving real-time inference of the parametric Gaussian formulation. To build upon our novel object representation, we propose a tailored merging strategy to recover coherent object instances. Specifically, we leverage maximum mean discrepancy on kernel density estimates to enable robust merging of object candidates during online exploration while minimizing added computational complexity. The key is to maintain a fixed particle set per object. Furthermore, to rectify the relation loss caused by misclassified objects, NoPA propagates relationships between objects with high affinity. Experiments show that NoPA substantially outperforms current methods without sacrificing real-time inference speed.
Authors: Yanan Wang, Wen Li, Yibin Ying, Zhenghao Fei
Abstract: Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduction into an opaque black box, severely limiting interpretability and scalability. To address this, we propose GEAR-Seg (Grounded Explainable Agent for Reasoning Segmentation), an explicitly decoupled agent that shifts the paradigm by translating visual pixels into dense, attribute-rich text. By decoupling class-agnostic segmentation, semantic description, and Large Language Model (LLM) deduction, GEAR-Seg transforms implicit reasoning into an explicit, trackable logic chain. As a zero-shot inference framework, it achieves highly competitive performance across diverse reasoning and fine-grained referring segmentation benchmarks. Furthermore, GEAR-Seg inherently functions as a highly scalable data engine. Utilizing this engine, we construct GEAR-131K, a massive benchmark (over 38k images, 656k QA-mask pairs) introducing a multifaceted taxonomy tailored for complex real-world manipulation-oriented reasoning. Finally, distillation experiments demonstrate that lightweight models supervised exclusively by our automated pipeline closely match the upper-bound performance of costly human-annotated baselines.
Authors: Yu-Hsiang Chen, Wei-Jer Chang, Yi-Ting Chen, Masayoshi Tomizuka
Abstract: Controllable traffic simulation is critical for testing autonomous driving systems, yet existing approaches often require retraining large generative models with extensive annotated data. We introduce a lightweight control adaptation framework that enables multi-modal controllability (sketch, latent behavior codes, and text) for pretrained state-of-the-art diffusion and autoregressive traffic models. By modulating intermediate features through identity-initialized FiLM layers, our method efficiently adds new control modalities while preserving the base model's generative prior. Evaluated on Waymo Open Sim Agents Challenge, our approach demonstrates strong controllability with less than 1% of the paired control data. Through context-aware condition transfer, our framework enables counterfactual scenario generation and long-tail synthesis while maintaining stable closed-loop driving realism and safety. Our framework unlocks new possibilities for controllable traffic simulation, enabling targeted scenario generation through lightweight adaptation of pretrained generative models. Project page: https://ecosim-web.github.io/
Authors: Jihyeok Jung (KAIST AI), Jeewu Lee (Sogang University), Sanghyeop Kim (Sogang University), Chanhee Han (Ministry of Science and ICT), Seong Joon Oh (KAIST AI)
Abstract: Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in isolation. However, understanding first-person-view input and taking an egocentric perspective are separable abilities, especially when first-person body cues are absent or when other agents are present. To isolate egocentric perspective understanding, we introduce EgoGapBench, a diagnostic benchmark for measuring action selection in multi-agent egocentric scenes. We define the ability measured by this benchmark as Egocentric Action Selection (EAS): selecting an appropriate action from the agent's perspective in the presence of other agents. On EgoGapBench, humans answer reliably, whereas both open-source and proprietary MLLMs perform substantially worse and systematically select actions performed by other visible agents. Fine-tuning on existing egocentric data fails to close this gap and can even be detrimental. In contrast, fine-tuning on EgoGapBench training data improves accuracy but does not reach human performance. These results show that EAS is difficult to acquire from first-person-view data alone, and that MLLMs should be evaluated and trained not only for scene understanding but also for egocentric action selection.
Authors: Zijian Dong, Yi Lin, Ji Fang, Jianxiong Zhou, Kwun Kei Ng, Juan Helen Zhou
Abstract: Diffusion MRI probes brain microstructure with particular sensitivity to early cerebrovascular and neurodegenerative changes. Neurite Orientation Dispersion and Density Imaging (NODDI) decomposes the diffusion signal into three biophysically interpretable maps: neurite density index (NDI), orientation dispersion index (ODI), and free water fraction (FWF), capturing neurite packing, fiber coherence, and extracellular fluid. These 3D maps offer a rich substrate for transferable microstructural representations, yet integrating them is challenging: standard representation learning struggles to disentangle the unique information in each map from their shared and synergistic interactions. We present BrainFIBRE, the first foundation model for brain microstructure, pretrained on NODDI-derived maps from 55,592 UK Biobank participants. We propose Self-supervised Partial Information Decomposition (SPID), which extends PID-guided multimodal learning to the self-supervised regime for the first time. A novel Counterfactual Candidate Construction (CCC) paradigm perturbs inter-modality alignment through modality dropping and swapping, providing the contrastive signal for a Mixture-of-Experts architecture to disentangle unique, synergistic, and redundant information without any downstream label. On both Caucasian and Asian cohorts, BrainFIBRE achieves state-of-the-art performance across diverse tasks predicting age, sex, cerebrovascular and neurodegenerative markers, and cognition, while yielding neurobiologically interpretable representations that reveal task- and cohort-specific interaction patterns. BrainFIBRE establishes a versatile foundation for neuroimaging analysis at the microstructural level.
Authors: Seref Baris Cagliyan, Umut Ozdemir, Merve Tapli, Emre Akbas
Abstract: Concept Bottleneck Models (CBMs) provide interpretability by routing predictions through a layer of human-understandable concepts. However, defining an optimal concept set for a specific dataset remains an open challenge. Existing approaches rely on expensive expert annotations or LLM-generated lists based solely on class names. Even "open-vocabulary" variants typically depend on static concept sets, which restrict discovery and introduce label bias. Furthermore, traditional CBMs often suffer from information leakage, where unmodeled visual features bypass the bottleneck and compromise the integrity of the explanations. To overcome these limitations, we propose Caption Bottleneck Models (CaBM), a framework that circumvents the need for predefined concept sets by replacing rigid concept layers with free-form natural language. By representing images via LMM-generated captions and training a classifier strictly on this text, CaBM ensures a leakage-free architecture by construction. Additionally, by analyzing the text classifier post-training, CaBM autonomously discovers high-quality, dataset-specific concepts. Our results across fine- and coarse-grained benchmarks demonstrate that CaBM achieves competitive accuracy while preserving interpretability without the constraints of external dictionaries or manual labeling.
Authors: Mattia D'Urso, Christian Sormann, Mattia Rossi, Friedrich Fraundorfer
Abstract: We introduce \textbf{Edge-based Pose Optimization (EPO)}, a trackless geometric optimization framework specifically designed to boost the Structure-from-Motion reconstructions generated by 3D Foundation Models. These models achieve rapid inference by bypassing the time-consuming feature extraction and matching stages of traditional pipelines, where explicit correspondences between each 3D point and multiple images, referred to as tracks, are established. However, their geometric accuracy currently falls short of traditional pipelines. While this can be addressed in a post-processing step via Bundle Adjustment-like refinement, doing so requires extracting feature tracks, thus defeating the original speed advantage. Instead, our fully differentiable framework uses edge map alignment as a proxy for geometric optimization, avoiding feature extraction and track construction entirely. Through extensive evaluation across multiple datasets and tasks, we demonstrate that EPO matches or outperforms Bundle Adjustment-like methods while requiring significantly lower runtime and memory. Notably, its reduced memory footprint makes EPO suitable for consumer-grade hardware, where competing refinement methods cannot run.
Authors: Cong Liu, Xiaofang Li, Simon X. Yang
Abstract: Vision Transformers (ViTs) commonly rely on injected positional mechanisms to address self-attention's permutation invariance. Motivated by the spatial regularities of natural images, we ask whether spatial organization can be induced from data rather than explicitly injected. Under controlled, matched from-scratch training, we propose Active Spatial Guidance (Guidance), a training-only objective that disables positional injection and applies an auxiliary 2D coordinate-regression loss to the final-layer patch tokens. The guidance head is used only during training and removed for inference; the deployed model consists of a positional-injection-free ViT encoder and the task-specific prediction module. Using DINOv3 ViT backbones, Guidance consistently improves performance on ImageNet-100 classification, ADE20K semantic segmentation, and Hypersim monocular depth estimation, outperforming strong injected baselines such as learned absolute positional embeddings and rotary positional embeddings under identical training protocols. On ImageNet-100, broader comparisons against representative injected positional designs further support Guidance's effectiveness. Guidance also improves robustness under resolution transfer, and multi-resolution training further strengthens accuracy across input sizes. Overall, our results suggest that spatial inductive bias in ViTs need not be architecturally injected, but can be shaped through training-time supervision. The code used for training and evaluation is publicly available in https://github.com/cloudlc/asg.
Authors: Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo, Chang D. Yoo
Abstract: Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignments in the warped images, which disrupt residual learning used in warping-based methods and fundamentally limit the gains of correction, particularly on thin structures and high-frequency details. Driven by our insight that useful visual cues are not lost but locally preserved under slight displacement, we propose Geometry-Aware Deformable Aggregation (GADA). This method introduces an iterative refinement module with deformable offsets to actively correct spatial misalignments and recover these displaced cues. Furthermore, to address the limitations of standard pipelines where visibility checks (i.e., thresholding) often discard valid pixels and multi-view warped image fusion relies on naive mean aggregation, our module is coupled with an implicit confidence weighting mechanism that selectively suppresses unreliable evidence. Consequently, our approach outperforms prior warping-based Gaussian Splatting, preserving high-frequency quality while achieving 2.13 times faster FPS.
Authors: Chahan Vidal-Gor\`ene (CJM, LIPN), Nadi Tomeh (LIPN), Victoria Khurshudyan (Inalco, SeDyL)
Abstract: This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dataset of 66 pages and compare geometric heuristics, YOLO-based layout parsing, an end-to-end document model ECLAIR, and a hybrid method combining semantic zone detection with a generative LLM. Our hybrid method achieves the lowest error rates of all evaluated approaches, reducing ordering errors by up to 76% over the strongest geometric baseline, and remains robust in multi-page settings and under noisy OCR. Rather than targeting production the method is designed as a data bootstrapping strategy enabling rapid annotation in highly under-resourced scenarios. Alongside the dataset, we release a specialized Tesseract OCR model for historical Armenian print.
Authors: Bingchen Huang, Zhiling Wang, Yifu Chen, Yuanchao Du
Abstract: Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new imagery, each at the cost of a tool protocol, brittle code, or an expensive training pipeline. A fourth route makes vision dynamic without generating anything, by retrieving labeled exemplar images and reasoning over them, yet it remains underexplored despite being train-free. We present ReVisIT, a train-free framework that realizes this retrieval-based route by treating each retrieved image-label pair as a unit of visual thought. ReVisIT combines structured class definitions, per-query multimodal retrieval of exemplars, and alternating user/assistant injection of those exemplars before joint multi-attribute decoding, and degrades gracefully to whichever components a task admits. On VL-ICL Bench Fast Open MiniImageNet, Qwen3-VL-30B-A3B with ReVisIT reaches 98.5% at 4-shot, statistically indistinguishable from the 72B LLaVA-OneVision SOTA (98.7%) on this near-saturated task at about 1/2.4 the parameters, while the same backbone without the scaffold sits at chance. The turns layer alone adds 26.1 points to GPT-4.1 on free-form concept induction (Bongard-OpenWorld), and the full stack yields a 4-6 point macro gain across three backbones on MAAC-Bench, a new license-clean 27-class, 5-attribute benchmark, significant by paired bootstrap on the curator-derived attributes. Component analysis shows that retrieval-plus-turns is the universal lever while structured definitions are need-adaptive, and that 83% of the retrieval gain comes from retrieval quality rather than from the presence of exemplars. MAAC-Bench is released with a rubric-grounded LLM verification protocol that replaces author spot-check on subjective attributes.
Authors: Bolutife Atoki (imagine, LIRIS), Iuliia Tkachenko (imagine, LIRIS), Bertrand Kerautret (imagine, LIRIS), Carlos Crispim-Junior (imagine, LIRIS)
Abstract: Reconstruction-based generative models offer a natural framework for unsupervised out-of-distribution (OOD) detection, but multi-class normality modelling requires a single detector to capture multiple in-distribution manifolds and produce comparable anomaly scores across classes. We study this problem in copy detection pattern (CDP) authentication, where authentic and counterfeit samples are visually similar but differ in subtle printing-and-digitisation (P\&D) signatures. We propose a diffusion based multi-class normality framework in which a single class-conditional ControlNet is trained exclusively on authentic CDPs from multiple P\&D classes and detects counterfeits through reconstruction error under authentic-class conditioning. We further introduce dual template masking, which hides complementary regions of the input template and scores only withheld pixels, reducing reliance on visible binary structure. On the Indigo 1 x 1 Base dataset, the proposed method outperforms traditional and adapted generative baselines under multi-class authentic-versus-counterfeit evaluation, without using counterfeit samples for training or threshold calibration.
Authors: Boyang Dai, Chaoqi Chen, Yizhou Yu
Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, current approaches primarily focus on designing clustering objectives, often overlooking a critical bottleneck: standard vision backbones yield high-rank, entangled token representations that are ill-suited for unsupervised discovery of latent concepts and structures. In this paper, we propose Compositional Primitive Fields (CPF-GCD), a novel representation learning framework that reshapes the feature space to make such latent structure identifiable by enforcing a low-rank compositional organization. Our core hypothesis is that all categories, whether known or novel, can be expressed as compositions and spatial arrangements of a finite set of learnable visual primitives that capture reusable concepts. CPF instantiates this geometric constraint via a spatial field mechanism. Inserted between the backbone and the head, it rewrites noisy patch tokens through low-rank primitive mixtures, effectively decomposing images into reusable atomic parts and their spatial layouts. By explicitly modeling the spatial distribution of primitives, CPF enables novel categories to emerge naturally as new activation patterns over a shared vocabulary. This shifts the focus of representation from merely partitioning global embeddings to constructing a structured and separable primitive field. Extensive experiments demonstrate that CPF serves as a generic, plug-and-play module that consistently boosts performance across diverse GCD baselines, validating that identifying and leveraging low-rank compositional structure is a crucial inductive bias for open-world recognition.
Authors: Mengjingcheng Mo, Jiaxu Leng, Xinbo Gao
Abstract: Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, where static sampling fails to disambiguate semantically distinct events. To overcome this, we propose $Anom\text{-}\pi$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process within a dynamic environment. Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy, utilizing temporal atomic operators such as local backtracking, temporal expansion, and fine-grained sampling to endow the model with perceptual proactivity. To learn such complex interaction strategies under video-level weak supervision, we design Interactive Direct Preference Optimization (iDPO) to achieve trajectory-level policy alignment, guided by an Active Evidence Inquiry (AEI) utility that balances task success, informative evidence acquisition, and interaction cost. This approach enables the agent to learn to actively disambiguate hypotheses while suppressing redundant exploration. Extensive experiments demonstrate that our framework, with only 2B parameters, achieves highly competitive performance, significantly outperforming state-of-the-art large-scale VAU models in complex scenarios.
Authors: Max Gaber, Dimitri Gominski, Jaime C. Revenga, Stefan Oehmcke, Rasmus Fensholt, Martin Brandt
Abstract: Monitoring canopy height change is essential for understanding carbon sinks and forest dynamics. Remote sensing enables consistent, large-scale observations of such changes, increasingly integrated with deep learning architectures such as Geospatial Foundation Models (GFMs). However, existing methods and datasets frame the problem as binary change detection, which overlooks both the continuous nature of change, especially for vegetation, and the inherent uncertainty in labels. We present the Canopy Height Change (CHC) dataset, providing 3 $\mathrm{m}$ resolution continuous canopy height differences and associated spatially resolved uncertainties across 10598 $\mathrm{km}^2$ of northern and western Spain. The dataset is paired with a co-located time series of PlanetScope satellite imagery. Based on the dataset, we introduce the task of uncertainty-aware change regression, associated metrics and strategies for fine-tuning GFMs. Furthermore, we evaluate state-of-the-art GFMs and highlight promising directions and remaining challenges for advancing continuous canopy height change estimation.
Authors: Yunsung Lee, Hyeongmin Lee
Abstract: Training-free guidance (TFG) steers a pretrained diffusion model toward a desired attribute at inference. To be effective, this guidance must be applied from the earliest, high-noise steps of sampling. Because its objective (a classifier or energy) is defined on clean images, $\epsilon$- and $v$-prediction models must first estimate the clean image $\hat{x}$ from the noisy state at each step, and the accuracy of that estimate determines how easily guidance drifts off the data manifold. $x$-prediction, a recent alternative, outputs the clean image directly, removing this source of error even at high noise. This is our motivation. We provide a theoretical analysis of how each prediction target shapes this accuracy, and introduce guided-class FID (Child FID), a metric that exposes the manifold damage standard evaluation misses. Experiments on a new fine-grained bird benchmark and on style transfer confirm that $x$-prediction keeps guided samples on the manifold most reliably, making it the strongest foundation for training-free guidance. Code is available at https://github.com/ManLuML/on-manifold-tfg
Authors: Jiaxu Leng, Jiankang Zheng, Mengjingcheng Mo, Zhanjie Wu, Haosheng Chen, Ji Gan, Xinbo Gao
Abstract: Video anomaly detection (VAD) with multimodal large language models has shown strong potential, yet most existing methods still depend on large-scale annotations or expert-designed priors, limiting their ability to acquire anomaly knowledge with as little human intervention as possible. To address this, we propose Linguistic Relative Policy Optimization (LRPO), which distills group-relative semantic advantages from multiple reasoning trajectories into a linguistically expressed anomaly experience prior, and adapts the model by injecting this prior into the context to steer its output distribution without any parameter updates. LRPO builds two complementary experience representations: general experience captures transferable anomaly preferences across scenarios, while scenario experience models context-dependent anomaly rules for targeted refinement. To further improve the learned experience, we introduce an anomaly alignment reward that guides trajectory optimization to match human risk preferences and reinforce temporally grounded reasoning. Extensive experiments on XD-Violence, UCF-Crime, and UBnormal demonstrate that LRPO significantly outperforms existing state-of-the-art methods under tuning-free settings.
Authors: Zhengbo Zhang, Mark He Huang, Zhigang Tu, Ming-Hsuan Yang
Abstract: Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing methods rely on frame-query feature matching, which suffices for simple events but struggles with complex multi-stage queries that require understanding temporal ordering and causal structure -- a disparity we call the reasoning gap. We propose DART (Difficulty-Adaptive Routing for Temporal Grounding), which bridges this gap by coupling difficulty-aware routing with structured reasoning in large vision-language models. A query-conditioned Determinantal Point Process (DPP) serves a dual role: selecting diverse, query-relevant keyframes as temporal evidence, and providing spectral entropy as a difficulty indicator. Simple queries are routed to a Fast path for direct prediction, while complex queries follow a Slow path with Temporal Markup Prompting, which decomposes localization into global event analysis, per-frame temporal role annotation, and boundary extraction. On Charades-STA and ActivityNet Captions, DART achieves state-of-the-art zero-shot performance across both identically distributed and multiple out-of-distribution settings, improving mIoU by up to 3.5 points over the strongest baseline while using over 7 times fewer frames. The project homepage is available at https://dart-vtg.github.io/.
Authors: Ronghan Chen, Yandan Yang, Zuojin Tang, Dongjie Huo, Tong Lin, Haoning Wu, Haoyun Liu, Yuzhi Chen, Lulu Zheng, Botai Yuan, Tianlun Li, Mingxin Wang, Dekang Qi, Bin Hu, Wei Mei, Yuze Xuan, Haolong Yang, Yanqing Zhu, Mu Xu, Zhiheng Ma, Xinyuan Chang
Abstract: Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling, while existing World Action Models (WAMs) are still poorly aligned with the structure of mobile manipulation: they operate on coarse video chunks, model entangled navigation-manipulation actions, and train inverse dynamics under supervision that does not match autoregressive inference. As a result, they often miss fine-grained contact dynamics, suffer from action-distribution conflicts, and accumulate errors over long-horizon rollouts. We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls. To align action space, we design a dual-level Mixture-of-Transformers architecture that disentangles both modality representations and heterogeneous action subspaces such as base movement and arm manipulation. To align inference conditions, we propose the dream-forcing training strategy that progressively trains inverse dynamics on model-predicted videos, improving train-test alignment and robustness during autoregressive prediction. Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy. These results highlight the critical importance of granularity-aligned, action-disentangled, and inference-consistent world-action modeling.
Authors: Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov, Brian B. Moser, Andreas Dengel
Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself. We introduce the Lightweight Universal Mask Adapter (LUMA), a lightweight, backbone-agnostic mask-transformer head that treats any backbone as a black-box feature extractor, letting a set of queries read from its features through cheap cross-attention. LUMA matches the accuracy of EoMT, the state-of-the-art efficient ViT-segmenter, at lower cost, while attaching unchanged to isotropic, hierarchical, convolutional, and mixture-of-experts backbones alike. Holding this head fixed, we benchmark 20 backbones, 11 pretraining schemes and a range of resolutions on ADE20K and Cityscapes under one modern recipe. We find that ``efficient'' token mixers fail to deliver efficiency even at the high resolutions that motivate them, with plain ViT holding the throughput Pareto-front at every resolution. Additionally, the pretraining objective, not the architecture, the lever the field has tuned hardest, governs segmentation quality.
Authors: Kousik Das, Debaditya Roy
Abstract: Long-horizon egocentric question answering involves answering about events that have occurred hours or days in the past. This requires memory representations that remain both retrieval-effective and scalable over days or weeks of recording. Existing long-horizon egocentric QA methods construct memory as hierarchical textual summaries of observations. While effective for reducing memory size, summarization optimizes for descriptive compression rather than retrieval: repeated interactions are absorbed into coarse textual descriptions instead of being preserved as explicit, recurring memory units, making long-horizon evidence aggregation difficult. We propose Imprint, an interaction-centric memory framework that formulates long-horizon egocentric memory as an online memory compression problem rather than summarization. Incoming observations are first represented as structured Interaction Records and continuously organized into recurring interaction patterns. Using human memory consolidation signals of recurrence, recency, and distinctiveness, Imprint selectively retains and compresses interactions into a compact retrieval-oriented memory. We evaluate Imprint on EgoLifeQA, a seven-day egocentric benchmark containing questions that require reasoning over interactions occurring hours to days before the query. With the same LLM, Imprint improves QA accuracy from 31.0% to 35.8%, increases evidence-grounded answers by $6\times$ compared with EgoRAG, reduces memory footprint by $2.3\times$, and decreases retrieval latency by $11.8\times$. These results demonstrate that memory compression provides a scalable and retrieval-effective foundation for long-horizon egocentric question answering.
Authors: Richard Schwarzkopf, Jonas Merkert, Frank Bieder, Annika B\"atz, Alexander Blumberg, Carlos Fernandez, Felix Hauser, Fabian Immel, Christian Kinzig, Hendrik K\"onigshof, Fabian Konstantinidis, Martin Lauer, Willi Poh, Nils Rack, Kevin R\"osch, Yinzhe Shen, Marlon Steiner, Gleb Stepanov, Dominik Strutz, \"Omer \c{S}ahin Ta\c{s}, Julian Truetsch, Kaiwen Wang, Royden Wagner, Jan-Hendrik Pauls, Christoph Stiller
Abstract: Well-designed autonomous driving datasets have fundamentally shaped research progress, yet existing literature primarily describes what datasets contain rather than how to strategically design impactful ones. This is especially limiting for small and medium-sized labs and startups that cannot afford to misallocate scarce resources. We argue that impactful dataset creation begins with a diagnosis: whether a research question is blocked by a data problem or an evaluation problem, and proceeds by selecting the minimal data operator(s) that closes the resulting gap, recording new data only when no cheaper operator(s) suffices. We analyze the evolution of major autonomous driving (AD) datasets through this lens and distill a strategic framework spanning gap identification, operator choice, sensor suite design, and annotation strategy. We ground the framework in a running case study of our KITScenes dataset family. The datasets are available at: https://kitscenes.com/
URLs: https://kitscenes.com/
Authors: Xiaomeng Fu, Jia Li, Yiming Hu, Yong Wang, Hayden Kwok-Hay So, Jiao Dai, Xiangxiang Chu, Jizhong Han
Abstract: Autoregressive (AR) streaming models have emerged as a powerful paradigm for long video generation. However, the linearly growing Key-Value (KV) cache poses a significant bottleneck, leading to memory overload and degraded inference throughput. A common compression method is to drop redundant KV tokens, which often breaks long-range dependencies, resulting in temporal flickering and identity loss. In this paper, we propose Instance-Specific Parametric Absorption (ISPA), a novel framework that shifts the KV cache compression from discarding to distilling. The core idea is to transit a subset of layers from Full-Attention (F-Layers) to memory-efficient Local-Attention (L-Layers) by "absorbing" historical context into the model's weights. Specifically, during a brief warmup phase, ISPA monitors the output discrepancy between global and local attention. At the transition point, we solve a closed-form least-squares problem to compute an instance-specific weight modulation that compensates for the missing history. Experiments across architectures (1.3B to 14B) demonstrate that ISPA can remove up to 50\% of the KV cache with near-lossless visual quality. We hope this perspective encourages future work to explore parametric memory consolidation beyond external token-level cache management for streaming generative models.
Authors: Yingjie Dai, Tianyang Xu, Yanglin Deng, Xiao-Jun Wu, Josef Kittler
Abstract: Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In real-world deployments, such as egocentric vision, crowded surveillance, wearable devices, or edge robotics, limited field-of-view (FoV) frequently causes substantial joint visibility dropout, leading to severe performance degradation that existing models are largely unprepared to handle. To bridge this critical yet underexplored gap, we introduce PartialVisGraph, a novel hypergraph framework tailored for robust skeleton action recognition under constrained FoV. We first construct highly expressive hypergraphs by introducing learnable virtual hyperedges that form a soft incidence matrix, capturing flexible high-order dependencies beyond conventional pairwise graphs. We then propose the Single-Head Sample-Adaptive Transformer, which adaptively aggregates joint features onto hyperedges while explicitly incorporating a visibility prior. This prior selectively gates information flow, preventing occluded or out-of-view joints from corrupting reliable feature propagation. We further establish rigorous evaluation protocols with realistic FoV simulation benchmarks on NTU RGB+D 60 and 120. Extensive experiments demonstrate that PartialVisGraph consistently achieves state-of-the-art accuracy under partial visibility, with gains of up to 68.8\% on subsets with severe FoV restrictions compared to recent strong baselines, while remaining superior on full-visibility settings. Our approach offers a principled and practical pathway toward deployable skeleton-based action understanding in unconstrained environments.
Authors: Tianhong Zhou, Mingyang Han, Boyu Li, Yuxuan Jiang, Jiaxin Ye, Dongxiao Wang, Haoxiang Shi, Kunpeng Wang, Jun Song, Cheng Yu, Bo Zheng
Abstract: Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models exhibit dimensional bias, typically focusing on either semantic matching or temporal offset detection. Moreover, their data construction remains coupled, preventing independent assessment of temporal and semantic consistency. We propose AV-SyncBench, the first benchmark to fully separate temporal and semantic evaluation for audio-visual synchronization. Built from in-the-wild videos, it spans Voice, Music, and Sound across 10 scenarios and 5 challenge tasks. Data are automatically filtered and manually verified to ensure on-screen sound sources. The benchmark contains 3,269 videos and 38,390 samples, and we evaluate five representative models to quantify feature quality for alignment and downstream tasks. The code and dataset are available at: https://fgt7t6g.github.io/AV-SyncBench.
Authors: Eliott Thomas, Tri-Cong Pham, Mickael Coustaty, Aurelie Joseph, Gaspar Deloin, Vincent Poulain d'Andecy, Jean-Marc Ogier, Antoine Doucet
Abstract: Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images, a key step in document understanding pipelines. Accurate TSR depends on precise boundary localization: small errors in row or column boundaries can propagate into incorrect cell assignments and structural inconsistencies. Yet detection-based approaches treat table elements as generic objects, ignoring a fundamental property of table layout: rows and columns play structurally distinct roles and their boundaries carry unequal importance. We propose an Edge-constrained Fine-grained Localization loss (EFL) that formalizes this structural asymmetry by encoding table-specific geometric priors into the training objective: row-like elements are supervised with emphasis on their horizontal boundaries, while column-like elements prioritize vertical boundaries. Implemented within a real-time detector with distribution-based boundary refinement (D-FINE), EFL operates during training only and guides boundary refinement toward structurally meaningful adjustments with no change to the inference pipeline. The proposed approach, ConRTF, is also data-efficient, maintaining robust accuracy with as few as 2k--3k annotated tables. Experiments on PubTables-1M and two private datasets show consistent improvements over the optimized baseline and several real-time detectors including RT-DETRv2 and YOLOv10-11, with gains of up to +1.6 GriTS points at equal inference speed.
Authors: Zhaowen Zhu, Li Zhang, Yujie Chen, Tian Zhang, Yingjie Wang, Mingxia Zhan
Abstract: Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degradation in complex driving environments. Networks specifically designed to handle dynamic traffic participants tend to be overly complex, hindering their deployment on resource-constrained automotive edge devices. To address these limitations and move towards robust driving perception, we propose FlexDepth, a scale-driven and flexible family of self-supervised MDE models tailored for challenging road scenarios. FlexDepth employs a two-stage static-dynamic decoupled training strategy, enabling the independent assessment of confidence for both static backgrounds and dynamic road objects. Furthermore, it introduces a meticulously designed Scale-Driven Decoder (SDD) to dynamically select components based on scale size, facilitating efficient feature fusion and the output of high-precision depth maps. Extensive experiments on standard driving benchmarks demonstrate that without any auxiliary information, our model achieves state-of-the-art performance across arbitrary scales with minimal computational overhead. Our smallest model, Flex-Nano, requires only 0.7 GFLOPs and achieves 37.6 FPS on mobile platforms, ensuring reliable real-time perception while maintaining excellent zero-shot generalization. Our source code is avalible: https://github.com/startnew/flexdepth
Authors: Huanwen Liang, Yuhao Huang, Xiliang Zhu, Yuanji Zhang, Xuedong Deng, Xinru Gao, Guowei Tao, Yuhan Zhang, Dong Ni
Abstract: Prenatal anomaly classification and localization is of critical importance for fetal health and pregnancy management. Although ultrasound (US) is the primary modality for prenatal screening, accurate diagnosis remains challenging due to the low prevalence and high heterogeneity of anomalies. Existing deep learning methods for prenatal tasks rely on large-scale annotated datasets, which are difficult to obtain in practice. Although few-shot learning alleviates data scarcity, it typically requires fine-tuning for new categories, limiting its practicality in resource-limited clinical settings. To address these challenges, we propose a training-free framework for multi-class prenatal US anomaly classification and localization that operates with only a few reference images per class, representing the first exploration of this setting. Our framework comprises three key components: (1) a memory bank with multi-granular prototypes that explicitly models both class-level semantics and anomaly characteristics; (2) a prototype-driven soft merging mechanism that aggregates discriminative features to detect the anomaly region; and (3) a class-aware refinement strategy that leverages prototype consistency to improve category prediction. Extensively validated on a multi-center prenatal US dataset containing 1,149 cases, with a total of 2,357 images and 9 categories, our proposed method outperforms the competitors.
Authors: Le Ou, Xiliang Zhu, Huanwen Liang, Wenxiong Pan, Yuhao Huang, Yuxiang Deng, Xuan Sheng, Hong Yin, Juhua Xiao, Xin Zhou, Dong Ni
Abstract: Accurate fetal birth weight (FBW) estimation shortly before delivery is clinically valuable yet challenging due to its reliance on operator expertise, particularly in low-resource settings. To reduce this reliance, we study near-term birth-weight regression from blind-sweep ultrasound (US) videos acquired within 48 hours prior to delivery, with post-delivery weighing as ground truth. Accordingly, we propose a foundation model-driven key anatomy frame selection framework that enables accurate FBW regression despite the absence of plane constraints in blind sweeps. Our highlights are as follows: (1) We believe this is the first work to estimate FBW using blind-sweep US videos, enabling operator-independent assessment. (2) An Anatomy-Guided Frame Selection module equipped with a vision-language foundation model is proposed for keyframe collection in unconstrained sweeps. (3) A Redundancy-Aware Feature Compression module is designed to compress frame features while preserving task-relevant information, alleviating temporal redundancy. Extensively validated on prospectively collected data from 839 patients, our method achieves an MAE of 161.3 g, with 90.23% and 100% of cases falling within 10% and 15% absolute percentage error, outperforming typical Hadlock estimation and strong competitors. Codes are available at https://github.com/ouleoule/BlindSweep-EBW.
Authors: Xiao Zhao, Chang Liu, Mingxu Zhu, Zheyuan Zhang, Linna Song, Qingliang Luo, Chufan Guo, Kuifeng Su
Abstract: The bird's-eye view (BEV) representation enables multi-sensor features to be fused within a unified space, serving as the primary approach for achieving comprehensive 3D perception. However, the discrete grid representation of BEV leads to significant detail loss and limits feature alignment and cross-modal information interaction in multimodal fusion perception. In this work, we break from the conventional BEV paradigm and propose a new universal framework for multi-modal fusion based on 3D Gaussian representation. This approach naturally unifies multi-modal features within a shared and continuous 3D Gaussian space, effectively preserving edge and fine texture details. To achieve this, we design a novel forward-projection-based multi-modal Gaussian initialization module and a shared cross-modal Gaussian encoder that iteratively updates Gaussian properties based on an attention mechanism. GaussianFusion is inherently a task-agnostic model, with its unified Gaussian representation naturally supporting various 3D perception tasks. Extensive experiments demonstrate the generality and robustness of GaussianFusion. On the nuScenes dataset, it outperforms the 3D object detection baseline BEVFusion by 2.6 NDS. Its variant surpasses GaussFormer on 3D semantic occupancy with 1.55 mIoU improvement while using only 30% of the Gaussians and achieving a 450% speedup.
Authors: Eliott Thomas, Mickael Coustaty, Aurelie Joseph, Gaspar Deloin, Vincent Poulain d'Andecy, Jean-Marc Ogier
Abstract: Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their internal layout. Building task-specific training sets for this pipeline is costly, particularly for TSR which requires fine-grained structural annotations. Active learning (AL) can reduce this annotation burden, yet most AL strategies are designed for single-model tasks and do not account for inter-stage dependencies in cascaded architectures. In this work, we present the first adaptation of Uncertainty Herding (UHerding), a hybrid coverage-uncertainty sampling method originally proposed for image classification, to cascaded object detection pipelines. We propose two pipeline-aware extensions that exploit the TD-to-TSR dependency: RankFusion adds dual-manifold coverage over both detection and structure representation spaces, while CAPA further incorporates stage-dependent gating and per-task uncertainty calibration. Extensive experiments across two public (PubTables-1M and FinTabNet) and two private table extraction datasets, with various annotation budgets (from 71 to 500 documents) show that UHerding generalizes well to table extraction, outperforming each baseline. Among pipeline-aware variants, RankFusion achieves higher expected gains but at the cost of greater variance, while CAPA emerges as the most consistent strategy, outperforming standard UHerding on three out of four datasets.
Authors: Rusi Chen, Yuhao Huang, Hongyuan Zhang, Chao Tian, Shunan Ji, Yuhan Zhang, Dong Ni
Abstract: Accurate detection of end-systole (ES) and end-diastole (ED) frames is fundamental to echocardiographic assessment. Existing methods are typically developed in a view-specific manner, depend on auxiliary annotations or intensive visual modeling, which limits their generalizability. In multi-view modeling, keyframe detection is driven by shared cardiac motion, yet large appearance differences and motion patterns make unified modeling challenging. To address these issues, we propose FrameONE, a unified end-to-end framework for multi-view echocardiographic keyframe detection. FrameONE introduces a Hierarchical Motion Modeling strategy: an intra-view multi-task learning reduces appearance bias and promotes motion-focused representations within each view; an inter-view general motion learning module further separates view-agnostic dynamics from view-specific patterns, enabling shared yet flexible motion representation learning across views. Extensive experiments on 25,872 videos spanning four standard views demonstrate that FrameONE achieves state-of-the-art keyframe detection accuracy with strong cross-view generalization. Code is available at https://github.com/szuboy/FrameONE.
Authors: Changsheng Lu, Yuxin Chen, Haokun Gui, Rong Wang, Jie Yang, Harry Yang, Anton van den Hengel, Jiaya Jia
Abstract: With the emergence of various pre-trained vision and language models, computer vision is shifting from narrow-domain to open-domain recognition. The construction of a more powerful yet general keypoint detection (GKD) model to support diverse tasks has become increasingly important in the field. To this end, we firstly present a large-scale unified keypoint dataset called MegaKPT. The dataset is composed of over 1.3 million diverse object instances from twenty-nine existing datasets, and enjoys high-quality unified annotations with keypoint text descriptions. Based on MegaKPT, we develop GKDT, a simple, flexible and powerful DINOv3 based Transformer model for General Keypoint Detection. Our GKDT supports visual prompts, text prompts, or both. To enhance model training, we also propose a suite of useful strategies such as mix-modal prompted training and dynamic importance sampling. By testing over 22 test sets with seen or unseen objects, our single GKDT model shows strong performance and generality in detecting keypoints on broad categories, with most categories over 90\% PCK@0.1 accuracy, offering high practical applicability to real-world problems. The dataset, models, and codes will be released at https://github.com/AlanLuSun/General-Keypoint-Detection.
URLs: https://github.com/AlanLuSun/General-Keypoint-Detection.
Authors: Seongmin Kim, Kyucheol Shin, Heesun Jung, Jinseo Kim, Sungyong Baik
Abstract: Text-to-image personalization aims to generate a user-provided subject in novel scenes described by text. However, most existing methods encode subject identity (fidelity) and context (editability) through the same conditioning pathway, forcing the two to compete for attention-map resources. We refer to this phenomenon as conditioning entanglement and show that it induces a fidelity-editability trade-off. We further provide causal evidence by replacing the target subject token with a generic subject token, which produces shifts in attention allocation and corresponding changes in context adherence. To this end, we propose Decoupled Guidance (DeGu), a plug-and-play framework that routes subject identity and scene context through two independent guidance streams. We further introduce a spatial mixing mechanism that dynamically fuses these streams, ensuring each operates within its semantically relevant region without interference. Furthermore, DeGu can be readily applied to existing personalization methods without modifying the underlying backbone models, consistently improving the overall personalization performance while enabling inference-time control over the fidelity-editability balance, across diverse methods and backbones, including flow-matching Diffusion Transformers (DiTs).
Authors: Sang In Lee, Jihun Park
Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models. In this work, we leverage recursion to build effectively deeper Transformers with stronger representational capacity. However, in Vision Transformers, simply increasing recursion depth does not reliably improve performance, as existing recursive approaches do not fully utilize the intermediate representations produced throughout recursive computation. We propose Soft Mixture-of-Recursions (SoftMoR) and its Vision Transformer instantiation, Soft Recursive Vision Transformer (SR-ViT). SoftMoR learns token-wise mixture weights to softly combine outputs from all recursion steps, allowing intermediate representations to be utilized in a learnable and flexible way. Across diverse vision tasks, SR-ViT consistently improves as recursion depth increases with minimal parameter overhead. On ImageNet-1K, increasing recursion depth from 1 to 4 improves SR-ViT-S top-1 accuracy from 79.83% to 82.48% with only 1.7M additional parameters, outperforming the substantially larger DeiT-B while using approximately 27% of its parameters. These results demonstrate that SoftMoR provides a parameter-efficient path to deeper and stronger Vision Transformers through recursion.
Authors: Kyan Mahajan, Mohammad Saqlain
Abstract: Most adaptive-inference techniques for foundation models change what the model does - early exit, MoE routing, KV-cache compression, dynamic attention sparsity. The input that hits the backbone, however, remains a fixed-grid tokenisation indifferent to image content. We argue that this is a missed lever. We present SpiralFovea, a parameter-free, input-adaptive tokeniser in which token identity, location, scale, and count are all functions of local visual entropy and selection completes before any backbone parameter is queried. Around content-driven hotspot anchors, multi-scale spiral rings produce <= 78 patches that replace the standard 196-patch ViT grid at the input stage. Across four canonical fine-grained benchmarks, SpiralFovea yields +1.7-2.1 pp accuracy with a 60% reduction in input tokens, an 84% reduction in self-attention FLOPs at every transformer layer, and 18-29% throughput gains over the matched static tokenisation baseline. A controlled ablation on CUB-200-2011 Genus across four backbones reveals a clean diagnostic: the gain magnitude tracks inversely with the strength of the backbone's whole-image positional prior, isolating self-supervised foundation models as the regime where input-adaptive tokenisation is most valuable.
Authors: Lukas Kuhn, Giuseppe Serra, Randall Balestriero, Florian Buettner
Abstract: Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time, the role of vision-language encoders has shifted: they are increasingly deployed not as zero-shot classifiers but as the frozen visual backbone of vision-language models and dense prediction systems, which consume the full grid of patch tokens rather than a single pooled embedding. We introduce LeVLJEPA, the first fully non-contrastive end-to-end vision-language pretraining method. LeVLJEPA learns through cross-modal prediction with stop-gradient targets and per-modality distributional regularization, without negatives, temperature, momentum encoder, or teacher-student schedule, and trains stably at large scale. We find that the resulting encoder provides markedly stronger dense semantic features for downstream use: as a frozen vision-language-model backbone, LeVLJEPA is the strongest of the evaluated encoders across GQA, VQAv2, and POPE under two distinct language models, and outperforms contrastive baselines on semantic segmentation, while remaining on par on global readouts such as linear probing. These results establish non-contrastive pretraining as an effective means of producing dense semantic vision features.
Authors: Yaofei Duan, Yuhao Huang, Tianyu Zhang, Yuan Gao, Luyi Han, Xin Wang, Xinyu Xie, Xinglong Liang, Chunyao Lu, Muzhen He, Patrick Pang, Yue Sun, Ning Mao, Tao Tan, Ritse Mann
Abstract: Neoadjuvant chemotherapy (NAC) response prediction is clinically important for treatment stratification in breast cancer. However, robust pre-treatment pathological complete response (pCR) prediction remains challenging due to insufficient cross-modal modeling, multicenter imaging heterogeneity, and weak evidence-grounded interpretability. We propose ClinRAG-GRAPH, a Clinically informed Retrieval-Augmented Generation Graph framework, for pre-treatment pCR prediction from DCE-MRI, structured clinical variables, and biopsy-derived pathological biomarkers. ClinRAG-GRAPH constructs an intra-patient clinical-prior graph and applies a prior-guided relation-aware graph convolutional network for structured multimodal representation learning. To improve cross-center robustness, we introduce a dual-branch domain-adversarial learning strategy to suppress protocol-related MRI bias while preserving pCR-relevant features. To enhance interpretability, we further incorporate large language model (LLM)-driven subgraph RAG module that retrieves clinically analogous historical cases and integrates retrieved evidence for pCR inference. We assemble a large-scale multicenter NAC breast cancer cohort for extensive validation, drawing from two public sources and three in-house centers.Results show that ClinRAG-GRAPH achieves AUCs of 0.815 on the internal test set and 0.774/0.712 on two external test sets, demonstrating robust pre-treatment pCR prediction across centers. The code is available at the anonymized https://github.com/miccai26-1181/ClinRAG-GRAPH.
Authors: Halil Sina Kelebek, Julia Hindel, Kobus Hoffman, Lauren Hoffman, Andrew Loveridge, Bob Mandinyenya, Kudakwashe Ncube, Justin Seymour-Smith, Andrea Sibanda, Abhinav Valada, Matthew Wijers, Daniele De Martini
Abstract: Animal re-identification (ReID) in camera-trap surveys remains challenging due to low image quality, strong variation in illumination and viewpoint, and highly imbalanced numbers of observations per individual. As a result, current ReID performance is often insufficient for fully automated use, and practical workflows typically depend on expert review of algorithmically proposed candidate matches. Moreover, most existing approaches focus almost exclusively on visual cues and overlook auxiliary information routinely available in field studies, such as image timestamps and camera-trap locations. We introduce Spotted, a location-informed, human-in-the-loop animal ReID framework that integrates visual similarity with spatio-temporal feasibility priors derived from camera locations, thereby reducing the amount of required expert review. Our method (i) computes an image-model-agnostic feasibility score based on the minimum travel speed required for two detections to correspond to the same individual, (ii) uses these feasibility cues as pseudo-supervision to train a lightweight head on top of a frozen visual foundation model, and (iii) fuses adapted visual similarity with spatio-temporal feasibility to obtain a robust pairwise matching score. We additionally integrate an active pair sampling strategy to accelerate annotation by initially prioritizing uncertain predictions. We evaluate Spotted on three challenging camera-trap ReID datasets comprised of spotted hyenas and leopards, which we release as part of this work. Our model improves average top-5 identification accuracy by 9pp, 2pp and 9pp over the best baseline on our LeopardID102, SpottedHyenaID109 and SpottedHyenaID415 datasets, respectively. Further, we show that our human-in-the-loop strategy reduces the number of queried comparisons by up to 69pp while achieving equivalent positive matches.
Authors: Ziyu Ma, Shidong Yang, Yuxiang Ji, Yiming Hu, Tongwen Huang, Yong Wang, Jianfei Cai, Xiangxiang Chu
Abstract: High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs), as fine-grained details are often lost when the image is processed as a whole. Existing methods either require training to teach models where to look or heuristically divide the image into fixed regions, both of which struggle to generalize in complex HR scenes. In this work, we propose Hierarchical Entity Exploration (HEE), a training-free and model-agnostic framework that transforms static image understanding into dynamic, query-guided entity exploration. HEE first evaluates each region using a dual scoring mechanism to determine whether it already contains sufficient evidence to answer the question. If not, it applies object detection within the most promising region to extract fine-grained entities, clusters them into coherent subregions, and organizes them into a multi-level semantic hierarchy for deeper exploration. When deeper regions still fail to yield confident answers, a confidence-guided backtracking mechanism revisits alternative paths to ensure adaptive perception. Extensive results show that HEE outperforms training-free methods like ZoomEye and RAP in both accuracy and efficiency on two complex HR benchmarks (Visual Probe and HR-Bench), across different MLLMs such as Qwen2.5-VL and LLaVA-OneVision. Moreover, HEE demonstrates generalization on the MME-RealWorld benchmark.
Authors: Dain Kim, Jinseo Kim, Sungyong Baik
Abstract: Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations across gender and race. Existing approaches remain limited by costly retraining or by inference-time interventions that often degrade image quality and semantic alignment. We propose Text Embedding Steering (TES), a training-free framework that mitigates demographic bias by directly optimizing conditional text embeddings during the diffusion process. We show that a two-stage strategy - early-stage global alignment followed by iterative denoising-time refinement with CLIP-based feedback - enables stable and controllable attribute steering without modifying model parameters. Extensive experiments on Stable Diffusion demonstrate that TES outperforms existing training-free baselines in fairness while maintaining competitive image quality. These results highlight that inference-time text embedding optimization is a practical and scalable solution for fairness-aware generation in diffusion models.
Authors: Andrea Sanchietti, Riccardo Marin, Bharat Lal Bhatnagar, Yuanlu Xu, Gerard Pons-Moll
Abstract: While garments are essential for realistic digital humans, their topological variety makes them much harder to model than parametric bodies. Traditional tailoring relies on 2D sewing patterns, yet bridging these patterns to 3D geometry currently requires physical simulations. We present Stitched Embeddings, the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference within a single bidirectional latent space. By leveraging the geometric priors of a pretrained 3D foundation model, our approach overcomes the data scarcity typically associated with high-quality garment modeling. We propose to use the BoxMesh as a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator. This architecture achieves state-of-the-art accuracy in pattern reconstruction while significantly improving efficiency. Furthermore, our differentiable pipeline enables novel applications, including pattern recovery from meshes and 3D editing from 2D patterns. Finally, this work provides a scalable link between neural 3D vision and the physical garment manufacturing pipeline. Project Page: https://andreus00.github.io/stitchedembeddings
Authors: Zhenjia Li, Jinrang Jia, Yifeng Shi
Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration. Converting a single panorama into a persistent, renderable 3D representation for free-viewpoint navigation has attracted growing interest; existing methods either adopt iterative per-view completion that propagates inpainting results to update the underlying geometry, leading to progressive error accumulation and cumbersome multi-step pipelines, or leverage the temporal consistency priors of video generation models, yet the continuous-trajectory constraint intrinsic to such models limits their flexibility in covering scenes from multiple directions simultaneously. We present Pano2World, which takes a single indoor panorama as input and directly outputs a persistent, explorable 3D Gaussian scene. Given the source panorama, Pano2World first reconstructs a coarse 3D Gaussian proxy and renders it at adaptively sampled nearby poses to obtain geometrically aligned guidance panoramas; a panoramic diffusion model then jointly denoises all target views via View-Aware Attention Routing, where each target view simultaneously receives geometric constraints from its corresponding guidance panorama and global semantic guidance from the source panorama, naturally enforcing cross-view consistency. To avoid the information loss incurred by decoding the multi-view hidden features formed during joint denoising back to the pixel domain via VAE, we introduce Latent Feature Adapter, a geometry-aware bridge module that directly distills these hidden features into a scene latent, subsequently decoded into the final 3D Gaussian scene. Experiments demonstrate that Pano2World significantly outperforms existing methods on the multi-position panoramic novel-view synthesis benchmark.
Authors: Xuelin Zhu, Xiu-Shen Wei, Jiawei Ge, Shuai Xu, Bing Wang
Abstract: Multi-label image classification (MLIC), a fundamental task in computer vision, focuses on identifying multiple objects or concepts within an image, underpinning numerous read-world applications, such as autonomous driving, disease diagnosis, recommendation system, and mobile service robot. Over the past decade, deep learning paradigms based on convolutional neural networks, recurrent neural networks, and Transformers have significantly advanced this field, owing to their powerful capability in visual representation and relationship modeling. These advances have markedly improved the robustness, scalability, and generalization ability of MLIC models across diverse datasets and application domains. In this survey, we provide a comprehensive review of the deep learning-based literature on MLIC. Concretely, we first revisit the background, including problem definition, datasets, backbones and evaluation metrics. Next, we develop a plausible taxonomy for the deep learning-based MLIC approaches, organizing them into six groups: region-oriented methods, label-oriented methods, architecture-oriented methods, representation-oriented methods, learning-oriented methods, and data-oriented methods. Finally, we provide an insightful exposition of the underlying learning game in MLIC and its implications for other vision domains, and we empirically summarize the key challenges and research directions in MLIC while outlining promising avenues for future development. We believe this survey offers the research community a holistic and systematic perspective on MLIC, thereby facilitating subsequent exploration and innovation in this field and beyond.
Authors: Ruixin Li, Jin Liu, Yuling Shi, Stefano Lodi
Abstract: Most self-supervised learning (SSL) methods encourage invariance across augmentations, but strict flip invariance can suppress informative left--right correspondences in approximately bilateral data such as medical images and human faces. We propose Mirror-Fusion-Augmented Self-Supervised Learning (MFASSL), a Vision Transformer framework that injects a soft reflection prior into standard SSL without redesigning the backbone. MFASSL constructs mirror-paired views aligned to an estimated symmetry axis and introduces a lightweight Mirror-Fusion Attention (MFA) module for adaptive token-level interaction between mirrored regions while preserving asymmetric cues. The base SSL objective is further coupled with reflection-consistency and mid-layer token-alignment losses. Across CheXpert, BraTS, CelebA-HQ, and WFLW, MFASSL improves downstream performance, calibration, and reflection robustness over MoCo-v3, DINO, and MAE baselines under matched ViT-B/16 settings. It also achieves stronger and more consistent gains than recent equivariant SSL approaches with only approximately 2.7\% additional parameters. These results show that lightweight geometry-aware priors can effectively complement invariance-based SSL.
Authors: Peiyuan Zhu, Shaoan Xie, Zijian Li, Yifan Shen, Namrata Deka, Harsh Shrivastava, Guangyi Chen, Kun Zhang
Abstract: Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled representations. These challenges are severely exacerbated by two fundamental properties in the video domain: Temporal Misalignment, where textual descriptions often correlate only to specific, constrained temporal windows, leaving other frames text-irrelevant; and Semantic Asymmetry, which dictates a sparse, bidirectional, and non-equivalent relevance between frame-level visual details and caption-level concepts. This failure persists whether captions are short and temporally disjoint, creating ambiguity, or long and detailed, fostering entanglement between static objects and their temporal evolution. In this paper, we establish theoretical conditions that enable flexible alignment between video and text representations across the temporal dimension and at varying levels of granularity. Building on these theoretical insights, we introduce MoVA, Modular Long Video-Text Alignment, which learns dual asymmetric projections: a text-side projection that adaptively selects frame-aware subspaces of the caption, and a video-side projection that disentangles text-relevant visual concepts. Our framework ensures that the model can preserve global cross-modal semantics while disentangling evolving, frame-specific concepts and scale naturally to long captions and videos. Empirical evaluations show that MoVA outperforms existing methods in multiple video-text alignment tasks, demonstrating the effectiveness of our method.
Authors: Omer Sela, Inbar Huberman-Spiegelglas, Michael Rotman, Sagie Benaim, Avi Ben-Cohen
Abstract: Controlling the motion of multiple objects in image-to-video (I2V) generation requires preserving object identities while enforcing adherence to distinct target trajectories. This becomes particularly challenging as the number of objects increases and their paths intersect or occlude one another. Existing approaches entangle multiple trajectories within a shared, dense conditioning signal, making object-level correspondence difficult to preserve in crowded scenes. We depart from this paradigm and enforce a strict, per object spatial constraint that isolates instances independently. Our method, TrajLoc, achieves this directly within the attention layers by substituting the cross-attention weights of each object token with a Gaussian heatmap centered on its target location at every frame. The same per object token interface carries trajectory and depth through a learned embedding and preserves identity by encoding first frame appearance in place of an object token. Evaluations across six datasets, featuring up to 20 simultaneously controlled objects and out of distribution real world scenes, demonstrate that our method consistently improves both visual fidelity and trajectory adherence. Applied to two architecturally distinct backbones (CogVideoX 5B and WaN 2.1 14B), our approach achieves average gains of +4.3 dB PSNR and a 51% reduction in trajectory end point error compared to the strongest baselines. Project page: https://sela-omer.github.io/traj-loc/
Authors: Wenhao Zhang, Kuanwei Lin, Xuyi Yang, Wei Gao, Ge Li
Abstract: Long-video reasoning is fundamentally constrained by how models acquire and utilize visual evidence. Existing tool-augmented video frameworks often interleave temporal grounding and answer reasoning within a single trajectory, causing early semantic hypotheses to bias evidence localization. We term this failure mode premature semantic commitment, where biased grounding retrieves incomplete evidence and incomplete evidence further reinforces incorrect reasoning. To address this issue, we propose EFlow, an evidence-first video reasoning framework built upon Qwen3-VL. EFlow explicitly separates temporal grounding and logical reasoning through CoT for Temporal Grounding and CoT for Reasoning, enabling the model to retrieve relevant evidence before answer inference. In addition, EFlow introduces a confidence-aware reflection mechanism that re-evaluates the full video when retrieved evidence is potentially insufficient. We further construct dedicated trajectory datasets and train EFlow through supervised fine-tuning, reinforcement learning, and reinforcement fine-tuning. Extensive experiments across five video understanding benchmarks demonstrate that EFlow consistently improves long-video reasoning performance.
Authors: Xudong Li, Mengdan Zhang, Peixian Chen, Jiaxi Tan, Zihao Huang, Jingyuan Zheng, Yan Zhang, Xiawu Zheng, Xing Sun, Rongrong Ji
Abstract: Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognition. Existing methods typically build such representations through textual reasoning or 3D reconstruction. However, they often falter during multi-step reasoning, particularly when required to dynamically re-anchor evidence to the specific camera-, object-, or direction-centric reference frames demanded by complex queries. To address this, we propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence. Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps. Experiments on single- and multi-image spatial reasoning benchmarks show that OmniView-Space achieves state-of-the-art performance. Furthermore, the distilled model maintains this performance while reducing reliance on external geometry pipelines.
Authors: Kangmin Seo, Sangeek Hyun, MinKyu Lee, Jae-Pil Heo
Abstract: Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity. However, when supervision is limited to sparse input views, 3DGS tends to overfit to the observed images and generalize poorly to unseen viewpoints. We address this challenge from the perspective of flat minima (FM) optimization, which seeks solutions that remain stable under small parameter perturbations. Viewing Gaussian parameters as trainable weights, we adapt FM principles to the geometric and dynamic nature of 3DGS with a lightweight training framework. Our method regularizes optimization with controlled Gaussian perturbations that account for each Gaussian's anisotropy and the training progress, preserving fine details while improving robustness to sparse-view overfitting. To further stabilize this flat minima optimization process, we introduce periodic reinitialization, which temporarily returns non-positional parameters to their initial states for a short window. Together, these techniques integrate seamlessly into existing 3DGS pipelines without architectural changes. Experiments on LLFF and Mip-NeRF360 datasets demonstrate improved quantitative metrics and perceptual quality under sparse-view supervision, producing reconstructions that are sharper, more stable, and better generalized to novel viewpoints.
Authors: Youwei Pang, Xiaoqi Zhao
Abstract: Evaluation metrics are central to binary target segmentation because they determine how progress is measured, compared, and interpreted. In this paper, target denotes the task-defined positive region to be segmented rather than a generic foreground object. It may be salient, camouflaged, transparent, glass-like, mirror-like, shadow-like, lesion-like, or defined by other application-specific semantics. We treat existing metrics as compositions of modular design choices rather than isolated formulas. The proposed framework decomposes each metric into five stages covering prediction representation, target extraction, target matching, score computation, and metric reporting. We use this framework to analyze representative metrics and show how newer metrics address specific limits in earlier protocols. The stage choices keep each metric's assumptions visible. We then discuss the design space opened by the framework and its implications for task-aware evaluation protocols. Reference code is available at https://github.com/lartpang/PySODMetrics.
Authors: Zhihan Zeng, Amir Hussain, Yue Xiu, Phee Lep Yeoh, Lu Chen, Zhongpei Zhang, Guan Gui
Abstract: Low-altitude Unmanned Aerial Vehicles (UAVs) often need to infer channel knowledge across a range of heights from only sparse observations collected at a few altitude layers. To address this challenge, this paper studies height-conditioned cross-height channel knowledge map (CKM) prediction for UAV-assisted communications in geometry-rich urban environments. We develop a geometry-aware conditional prediction framework that combines urban scene priors, sparse multi-altitude observations, and target-height descriptors to reconstruct dense CKMs at unobserved target heights. An uncertainty head is further introduced to characterize prediction confidence and to support cost-aware online UAV sensing under motion and safety constraints. Experiments on a layered aerial CKM benchmark show that the proposed Feature Pyramid Network (FPN)-Transformer achieves the best overall performance under both unseen-scene zero-shot and legacy patch-random protocols, reducing the Root Mean Square Error (RMSE) to 5.347dB and 1.111dB, respectively, compared with 6.937dB and 1.221dB for the strongest baseline 3D-RadioDiff. Moreover, after applying our unseen-scene few-shot adaptation, the RMSE further decreases from 5.347dB in zero-shot prediction to 3.518dB with 10-shot two-height support, while the uncertainty-guided cost-aware sensing policy improves active reconstruction from 6.94dB at initialization to 4.79dB at sensing budget 40, outperforming uncertainty-only sensing at 5.08dB and random aerial sampling at 5.84dB.
Authors: Seok-Young Kim, Abdelrahman Elskhawy, Taewook Ha, Dooyoung Kim, Eunjae Shin, Benjamin Busam, Woontack Woo
Abstract: We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct reliable 3D scene graphs due to unstable 3D object representations and missing relations caused by frame-wise inference. DeWorldSG addresses these issues by estimating instance-level geometric 3D Gaussian distributions through depth-guided filtering and representing each object as a probabilistic 3D node rather than a single projected point. To mitigate relational sparsity from frame-wise inference, our framework further aggregates spatiotemporal evidence across object pairs and refines relations using contextual priors derived from a world model (V-JEPA 2). Experiments on the 3DSSG and ReplicaSSG datasets demonstrate state-of-the-art (SoTA) performance in both object and predicate prediction, while producing temporally consistent scene structures. In particular, our method improves triplet recall by 77.4% and predicate recall by 23.2% over prior SoTA approaches, making it suitable for robotic manipulation and AR applications. Our code and models are open-sourced.
Authors: Jingchen Ni, Cangjin Yu, Dan Jiang, Quan Zhang, Keyu Lv, Shannan Yan, Linyue Pan, Ke Zhang, Chun Yuan
Abstract: Driven by Artificial Intelligence-Generated Content (AIGC), the authenticity of audio-visual content is facing severe challenges. Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments within untrimmed sequences. However, existing methods are limited by CNNs' local receptive fields or Transformers' quadratic complexity, while emerging linear models often struggle to balance global authentic context compression with local abrupt forgery perception. To address this, we propose MG-RWKV, a multi-granularity framework that leverages the data-dependent state evolution of RWKV to achieve efficient full-sequence processing with O(T) complexity. Our framework features three core innovations: (1) a Bidirectional RWKV architecture that captures bidirectional temporal contexts without quadratic overhead; (2) a Multi-Granularity Mixture of Experts (MG-MoE) that performs dynamic routing over explicit temporal receptive fields, adaptively selecting granularities based on forgery duration to significantly enhance decision interpretability; and (3) Cross-Granularity Consistency (CGC), which aligns adjacent feature pyramid levels through hierarchical scale-wise pairing and spatial boundary-aware weighting, effectively reducing false positives in authentic regions. Extensive experiments on Lav-DF, TVIL, and Psynd datasets demonstrate that MG-RWKV achieves state-of-the-art performance with low computational cost.
Authors: Xinyi Shang, Peng Sun, Bei Shi, Zixuan Wang, Tao Lin
Abstract: Recent advancements in scaling dataset distillation rely heavily on decoupled information extraction pipelines, comprising SQUEEZE, RECOVER, and RELABEL stages. Despite their scalability to large-scale datasets, these methods suffer from prohibitive computational overhead and poor cross-architecture generalization. In this paper, we reveal the root cause of these bottlenecks: the implicit dual-compression process, from data to model and back to images, inherently induces severe information loss. Crucially, we empirically and theoretically demonstrate that this loss creates a distribution shift that fundamentally compromises the widely adopted RELABEL strategy, transforming the pre-trained model into an unreliable labeler that yields sub-optimal labels. To overcome these critical flaws, we propose CIM, a novel, metric-driven framework that abandons the flawed dual-compression paradigm. Instead, CIM explicitly quantifies and minimizes the information gap between the original and synthetic datasets. By directly aligning the data distributions, our approach ensures high-fidelity information condensation and inherently satisfies the prerequisites for effective relabeling. Extensive experiments demonstrate that CIM establishes a new state-of-the-art. Notably, it distills ImageNet-1K at an IPC=10 in merely 80 minutes on a single RTX-4090 GPU, achieving an unprecedented 48.7% Top-1 accuracy on ResNet-18 and significantly outperforming previous SOTA approaches, such as NRR-DD and DELT, by 2.6% and 2.9%, respectively. Our code is available at https://github.com/LINs-lab/CIM.
Authors: Zipeng Guo, Xiaoan Liu, Lichen Ma, Cheng Wang, Yu He, Xiaolong Fu, Jingling Fu, Xinyuan Shan, Shaojie Guo, Luohang Liu, Junshi Huang, Yan Li
Abstract: Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature poses a dual challenge: models must precisely apply all requested edits to the correct regions while preserving unmodified content, even under ambiguous instructions. Existing one-shot editors conflate intent resolution, spatial grounding, and synthesis into a single step, frequently resulting in partial execution failures, which is unacceptable for commercial scenarios. To address this, we introduce GMO-E$^2$DIT, an agentic editing framework that couples a Vision-Language Model (VLM) with a mask-conditioned image editor to tackle structured multi-turn task completion. Given an underspecified instruction, the VLM agent constructs a region-grounded edit agenda, effectively decoupling cognitive reasoning from generative rendering. The framework then executes sub-programs via operation-aware masks and references, utilizing a reflection-driven loop to inspect intermediate results and determine the subsequent state. This iterative mechanism reliably preserves safe partial progress, retries unfinished operations, and recovers from errors. Furthermore, we develop a unified data pipeline providing aligned supervision for planning, execution, and reflection, alongside EComEditBench, a comprehensive benchmark for instruction-driven evaluation. Extensive experiments demonstrate that GMO-E$^2$DIT achieves competitive performance compared to strong closed-source models, yielding superior instruction accuracy and edit fidelity over existing baselines.
Authors: Chengzhi Hu, Xuewen Liu, Jing Zhang, Mengjuan Chen, Zhikai Li, Qingyi Gu
Abstract: Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and parameter distribution, traditional pruning methods are inapplicable, leading to significant performance degradation. Specifically, prior methods developed for LLMs, which derive metrics through a series of approximations, amplify the relative contribution of weights in the saliency metric. In addition, weights in DiTs exhibit significantly larger magnitudes than those in LLMs. Moreover, existing pruning granularity overlooks variations in model structures. In this paper, we propose DiT-Pruning, which improves pruning performance by introducing customized saliency criteria and pruning granularity. We design a novel metric that balances the contributions of weights and activations from an energy-based perspective, enabling more effective identification of important elements. Furthermore, we observe distinct clustering patterns in the two-dimensional weight space. Accordingly, we adopt a clustering-aware pruning granularity, enabling effective sparse allocation. Extensive evaluations on various DiTs show that our method consistently preserves image quality, especially under high sparsity. For FLUX.1-dev at 512x512 resolution on MJHQ, DiT-Pruning achieves only a 0.001 loss in CLIP score at 50% sparsity, dramatically outperforming recent pruning methods.
Authors: Joren Michels, Lode Jorissen, Nick Michiels
Abstract: The visual quality of AI-generated videos has improved drastically in recent years, making it increasingly difficult for humans to distinguish between real and synthetic media. In this work, we evaluate the robustness and applicability of four state-of-the-art motion-based AI-generated video detectors. We identify significant preprocessing and sampling biases in these methods and demonstrate that they account for a substantial portion of their reported performance. Furthermore, we find that these detectors are highly sensitive to motion patterns specific to their evaluation datasets, where AI-generated videos generally exhibit less inter-frame movement than real videos. We show that for all detectors, performance collapses to near-random levels when evaluated on a dataset that does not contain this motion bias. Additionally, through dataset rebalancing and the application of simple spatial augmentations, we observe severe performance degradation across all evaluated models. In contrast, we find that an existing frequency-based detector maintains strong performance across all evaluated datasets, suggesting that frequency-based approaches may offer a more generalizable path forward for AI-generated video detection. We hope that our work raises awareness towards these vulnerabilities and encourages the development of more representative, unbiased datasets and more robust evaluation protocols.
Authors: Andrew Bell, George Webber, Andrew P King, Steffen E Petersen, Muhummad Sohaib Nazir, Alistair Young
Abstract: Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and sensitive to the optimisation trajectory. Learned priors can help guide optimisation towards plausible motion fields and enable faster adaptation, but learning priors for cardiac motion INRs remains under-explored. In this work, we compare four strategies for learning cardiac motion priors, including a population prior learned by joint optimisation, a consensus prior obtained by weight averaging, auto-decoders, and meta-learning. Using short-axis tagged cardiac magnetic resonance images from the UK Biobank, we evaluate their impact on tracking accuracy, motion behaviour, and adaptation trajectory. All learned priors substantially improved early adaptation performance compared with random initialisation. While the simple consensus prior was effective, auto-decoders recovered large deformations faster during early adaptation. Meta-learning achieved strong early performance and maintained the best adaptation trajectory over 50 iterations.
Authors: Haijie Yang, Zhenyu Zhang, Yixuan Dong, Jianjun Qian, Jian Yang
Abstract: Audio-driven talking head synthesis has achieved impressive progress in lip synchronization and visual quality, yet generating expressive emotional avatars with controllable intensity remains challenging, especially under real-time constraints. In this paper, we present GaussianEmoTalker, an audio-driven framework for real-time emotional talking head synthesis based on 3D Gaussian Splatting. Instead of directly predicting the final emotional avatar from speech, we formulate emotional animation as a neutral-to-emotional residual deformation problem. GaussianEmoTalker first constructs an identity-specific neutral talking space with GaussianBlendshapes, which provides high-fidelity Gaussian attributes and phoneme-synchronized neutral motion. It then predicts an emotion-conditioned residual deformation by combining mesh displacement cues, audio features, emotion categories, and intensity encodings. To fuse these heterogeneous signals, we introduce a spatial-audio-emotion attention module that estimates the offsets of Gaussian attributes for expressive and temporally stable rendering. Extensive experiments demonstrate that GaussianEmoTalker achieves competitive video quality, accurate lip synchronization, controllable emotional expression, and real-time rendering compared with recent emotional talking head methods. Our project page is available at https://njust-yang.github.io/GaussianEmoTalker.github.io/
URLs: https://njust-yang.github.io/GaussianEmoTalker.github.io/
Authors: Li Jin, Jian Huang, Junde Lu, Shuai Wang, Hao Sheng, Jie Wu
Abstract: Light Field Super-Resolution (LFSR) necessitates accurate modeling of spatial-angular correlations while preserving intrinsic 4D ray coherence. However, maintaining such high-dimensional consistency remains challenging, primarily due to two inherent limitations in prevailing modeling paradigms. First, spatial and angular dimensions are often modeled in a decoupled manner, restricting early cross-dimensional interaction and leading to geometric inconsistencies. Moreover, although continuous sequence modeling paradigms show promise in representing epipolar structures, their rigid scanning mechanisms fundamentally conflict with epipolar geometry, limiting geometry-aware feature aggregation. To address these challenges, we propose a hybrid light field super-resolution network, termed SMART, which integrates a Slope-Guided Mamba and an Angular-Refined Transformer to effectively overcome these limitations. Specifically, we introduce an angular-modulated spatial module to bridge the decoupling gap, incorporating angular priors to strengthen spatial-angular correlation modeling. To mitigate the scan-geometry mismatch, we propose a manifold-aligned trajectory module that enables geometry-consistent sequence modeling along epipolar structures. Experiments on five benchmarks demonstrate that SMART achieves state-of-the-art performance, surpassing previous methods by 0.42 dB (PSNR) with significantly reduced artifacts.
Authors: Tong Shao, Hongshun Ling, Li Zhang, Jinjing Wu, Junke Wang, Yuan Gao, Fang Wang
Abstract: Chest X-ray multi-label classification is a core task in intelligent medical imaging diagnosis. However, real clinical data often exhibit extreme long-tailed distributions, leading to degraded performance on rare diseases in tail classes. This issue is not only driven by data scarcity but also by two intrinsic factors:1) attenuation of tail-class lesion representations under complex anatomical backgrounds, and 2) dominance of head classes in modeling label co-occurrence relationships. To address these challenges, we propose TRCGL-Net. First, a learnable text-guided conditional diffusion model is employed to generate high-quality tail-class chest X-ray image samples under disease semantic constraints, improving data diversity and realism of rare disease patterns while alleviating class imbalance and preserving pathology-consistent semantics.Second, a channel reweighting mechanism is introduced to perform feature recalibration by emphasizing disease-relevant feature channels, thereby improving feature discriminability under long-tailed distributions.A class-aware attention mechanism is further applied to generate class-specific attention maps, enabling the model to localize disease-relevant regions and focus on fine-grained lesion areas.Finally, a graph convolution network based on label co occurrence is introduced to establish an information propagation mechanism among categories. Experiments on the PadChest dataset show that the proposed method achieves a tail-class mAP of 0.4904, an overall mAP of 0.4408, and an mAUC of 0.8989, outperforming state-of-the-art methods. TRCGL-Net effectively improves recognition performance for rare diseases under long-tailed distributions and mitigates the impact of extreme class imbalance in chest X-ray multi-label classification.
Authors: Xuying Huang, Sicong Pan, Maren Bennewitz
Abstract: Privacy-preserving perception is a critical requirement for deploying 3D scene understanding systems in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. Existing methods typically rely on obtaining rich semantic cues from RGB images, which may expose privacy-sensitive visual information. Depth-only 3D geometry provides a privacy-preserving alternative, but the absence of appearance-based semantic cues makes open-vocabulary predictions highly uncertain and less reliable. Under this setting, we propose to convert uncertainty into a guidance signal to identify unreliable semantic responses and use semantic priors from foundation models to regularize their refinement. We present UTTO, an uncertainty-guided test-time optimization framework for depth-only open-vocabulary 3D semantic segmentation. Without additional training, experiments on ScanNet20, ScanNet40, and ScanNet200 demonstrate that UTTO consistently improves depth-only open-vocabulary 3D segmentation and outperforms representative baselines under privacy-preserving conditions.
Authors: Jun Peng, Baiyang Song, Jie Li, Hui Li, Yiyi Zhou, Rongrong Ji, Yonghong Tian
Abstract: Video understanding is often plagued by severe temporal redundancy, where processing dense frame sequences is both semantically inefficient and computationally expensive. This challenge is further amplified when only a small subset of frames is truly relevant to the given query. In this paper, we propose a Query- and Content-Aware (QCA) keyframe selection framework that can select a compact yet information-rich set of frames from long videos. QCA first partitions the video into temporal segments and estimates the information contribution of each segment by jointly modeling query relevance and content deviation, and dynamically allocates keyframe budget to each segment. Within each segment, QCA anchors on the most query-relevant frame and iteratively incorporates additional frames to maximize diversity while maintaining high semantic relevance to the query. Crucially, our method requires no additional training and can be seamlessly integrated into existing Video-LLMs. Extensive experiments across multiple long video understanding benchmarks demonstrate that our proposed approach achieves state-of-the-art performance and has strong generalization ability. For instance, QCA achieves 67.8\% on LongVideoBench using 128 frames, while GPT-4o achieves 66.7\% using 256 frames. Our codes are available in \href{https://github.com/hktk07/QCA}{GitHub}.
Authors: Geunhyuk Youk, Jeonghyeok Do, Dayeon Kim, Jihyong Oh, Munchurl Kim
Abstract: Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales. Conversely, while coordinate-based arbitrary-scale VSR methods offer scale flexibility, they inherently suffer from severe over-smoothing at large scaling factors. Integrating generative priors with continuous decoding is promising but currently hindered by severe temporal flickering caused by the stochasticity of diffusion sampling. To address this, we propose AVSR-Diff (Arbitrary-scale Video Super-Resolution with Diffusion), a novel decoupled framework that separates scale-agnostic latent denoising from continuous coordinate rendering, effectively avoiding computationally heavy resolution-specific sampling. Our approach introduces a Temporally-Gated Feature Recurrence (TGFR) module to extract strictly aligned, temporally consistent latent priors. Furthermore, we design a continuous video VAE decoder incorporating a Scale-Aware Fourier Refinement (SAFR) module to dynamically adapt frequency components to any target scale. Extensive experiments demonstrate that AVSR-Diff consistently preserves high-frequency details and strong temporal stability across various scales, surpassing state-of-the-art arbitrary-scale baselines. Remarkably, our framework outperforms recent fixed-scale generative models even on their native resolution.
Authors: Nils Neukirch, Martin Maurer, Nils Strodthoff
Abstract: Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification head, and segmentation choice, or test cross-cohort robustness. We benchmark five feature extractors (Curia, Curia-2, DINOv3, Radiomics2D, Radiomics3D), seven classification heads (TabPFN, TabICL, XGBoost, CatBoost, Random Forest, logistic regression, Ridge), and three segmentation regimes on five tasks: tumor volume and stage classification, 2-year survival prediction, histology classification, and age prediction. Models are trained on LUNG1 (n=338) and evaluated on an internal test set (n=84) and the external LUNG2 cohort (n=211), with worst-case cross-cohort performance as the primary metric. The dominant design factor is task-dependent: segmentation drives volume and stage classification, while classifier choice drives survival, histology, and age prediction. Radiomics is competitive for tumor volume, tumor stage and survival (partly due to label-derivation effects for the former); Curia variants reach comparable peak scores for survival; DINOv3 falls slightly short across tasks. Patch and slice aggregation have negligible impact. We recommend Curia with tumor segmentation and a CatBoost head as a safe default, achieving the best mean rank across the three primary clinical tasks, though task-specific selection consistently outperforms any cross-task default. When tumor delineations are unavailable, Curia-2 with lung segmentation and logistic regression offers a competitive alternative. All pipelines use a two-stage design suited to small cohort sizes where end-to-end fine-tuning would risk overfitting.
Authors: Gabriel Tavernini, Elisabetta Fedele, Tiago Novello, Leonidas Guibas, Marc Pollefeys, Francis Engelmann
Abstract: Superquadrics have proven to provide a compact, geometrically meaningful representation for 3D objects. However, existing methods suffer from limited reconstruction accuracy, are restricted to rigid primitives, and lack robustness to partial point clouds. In this work, we present SuperFlex, an enhanced framework that expands the expressive power and applicability of superquadric decompositions. First, we introduce a novel loss formulation which significantly improves reconstruction accuracy. Second, we include bending and tapering deformations, enabling high-fidelity representation of curved and asymmetric geometries. Finally, we leverage these high-quality decompositions as supervision to train a model that is robust to partial real-world point clouds. Experiments demonstrate substantial improvements in reconstruction accuracy over both optimization- and learning-based baselines while maintaining a highly compact primitive representation.
Authors: Grigorios Kalliatakis, Georgia Karanasiou, Georgios Manikis, Manolis Tsiknakis, Dimitrios Fotiadis, Dorothea Tsekoura, Kalliopi Keramida, Vasileios Bouratzis, Lampros Lakkas, Katerina Naka, Andri Papakonstantinou, Anastasia Constantinidou, Kostas Marias
Abstract: Therapy-induced cardiotoxicity is the leading non-oncological cause of treatment interruption in breast cancer patients, yet early, automated risk stratification from routine cardiac imaging remains an unsolved problem. We present EchoRisk, the first curated, multicentre, longitudinal echocardiography dataset with explicit cardiotoxicity labels, released as the primary technical reference for the EchoRisk-MICCAI 2026 challenge. The dataset comprises 422 patients enrolled in the EU-funded CARDIOCARE prospective study across five European sites, yielding 2,159 echocardiography videos across 1,123 clinical exams acquired at up to five longitudinal timepoints, alongside a dedicated cohort of 280 patients with baseline imaging for early cardiotoxicity prediction. Three clinically grounded tasks are defined: automated estimation of left ventricular ejection fraction from cine video (Task 1), classification of LV dysfunction from longitudinal imaging (Task 2), and early prediction of therapy-induced cardiotoxicity from pre-therapy baseline echocardiography alone (Task 3). For each task we specify the evaluation protocol, primary and secondary metrics, and ranking procedure. We establish baseline performance using an R(2+1)D video backbone with LSTM aggregation trained from Kinetics-400 pretrained weights, demonstrating strong discriminative performance for cardiac functional assessment and LV dysfunction classification, while early cardiotoxicity prediction from a single pre-therapy video remains a significant open problem for the community. The dataset, evaluation code, and baseline implementations are publicly available to serve as a benchmark for further collaboration, comparison, and the creation of task-specific architectures in cardio-oncology.
Authors: Hongkuan Zhou, Tristan Rehm, Nadeem Nazer, Lavdim Halilaj, Jingcheng Wu, Steffen Staab
Abstract: Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect type, and provide interpretable visual evidence. Existing CLIP-based methods detect and localize anomalies well but offer limited language-level defect understanding, while instruction-tuned vision-language models can describe defects but do not natively produce pixel-level masks. We introduce GenAU, a Generalist vision-language framework for industrial Anomaly Understanding that unifies image-level detection, pixel-level segmentation, multi-type anomaly detection, and defect analysis in a single instruction-following model. GenAU augments a vision-language model with two segmentation tokens, [SEG_defect] and [SEG_normal], whose hidden states act as language-grounded queries over multi-scale visual features for pixel-level localization; the image-level score fuses this map with the decoder's textual normal/defect decision, while the language decoder produces structured defect-aware responses. Trained with a joint language-modeling and segmentation objective, GenAU covers all four tasks within one architecture and recipe, adding zero-shot multi-type detection and language-grounded defect analysis at a quantified cost to detection and segmentation. Across cross-dataset benchmarks, GenAU attains the strongest image-level detection among CLIP-based zero-shot methods on VisA and Real-IAD, with segmentation approaching but not surpassing specialized CLIP baselines.
Authors: Dianyu Wang, Yidan Zhang, Peirong Zhang, Xuyang Li, Xiaoxuan Liu, Lei Wang
Abstract: Recent multimodal large language models (MLLMs) have shown strong cross-modal understanding and coordinate generation abilities in visual grounding. However, transferring these abilities to remote sensing visual grounding (RSVG) remains challenging. High-resolution remote sensing images usually cover large-scale scenes, where targets are often extremely small and surrounded by numerous visually similar distractors. Meanwhile, queries often contain multiple clues, such as reference objects, spatial relations, and target attributes. Existing MLLM-based methods usually formulate RSVG as one-step coordinate generation, which may lead to unstable predictions for small-object localization and complex queries. To address these challenges, we propose GeoSearcher, which reformulates RSVG as an anchor-guided progressive reasoning process and realizes it through two coupled stages: Anchor-Centric Reasoning Supervised Fine-Tuning (ACR-SFT) and Process-Faithful Group Relative Policy Optimization (PF-GRPO). In ACR-SFT, anchor-centric reasoning data are used to teach the model to represent key visual clues as anchors and progressively integrate location, relational, and attribute clues around them. In PF-GRPO, Process-Aware Reward (PAR) and Reasoning-Informative Sample Selector (RISS) further optimize this reasoning behavior by jointly evaluating key reasoning steps and target localization, while focusing training on samples that are more beneficial for improving progressive reasoning. Through this design, GeoSearcher transforms large-scale visual search into a more constrained local reasoning process. Extensive experiments on DIOR-RSVG, OPT-RSVG, and VRS-Bench show that GeoSearcher outperforms existing state-of-the-art methods. The project will be released at https://github.com/wangdianyu954-xixi/GeoSearcher.
Authors: Arpita Nema, Hanwei Zhu, Xi Zhang, Weisi Lin
Abstract: The evaluation of long-term video quality understanding remains an open challenge for large vision-language models (LVLMs). Existing video quality benchmarks predominantly focus on short clips and isolated distortions, overlooking the temporal continuity, cumulative degradation, and reasoning complexity inherent in long-duration content. To address these limitations, we present LongVQUBench, a comprehensive benchmark for long-term video quality understanding. LongVQUBench contains over 1200 diverse videos spanning movies, documentaries, surveillance footage, egocentric recordings, and animated content, accompanied by 1500 multiple-choice and open-ended questions for validation and testing. To assess perceptual reasoning across different temporal scopes, we introduce three progressively complex evaluation levels: (i) local event quality understanding (LQU) for analyzing localized distortions; (ii) cross-event quality reasoning (CQR) for integrating multiple degraded events; and (iii) global quality understanding (GQU) for holistic perceptual evaluation over extended durations. Furthermore, a needle distortion question-answering (NDQA) paradigm is embedded across all three levels, where spatial or temporal artifacts are sparsely inserted to probe fine-grained detection and reasoning capabilities. Extensive experiments on 14 state-of-the-art LVLMs reveal significant performance degradation with increasing video length and reasoning depth, highlighting their limited capacity for long-range temporal integration and perceptual attribution. We envision LongVQUBench as a foundational step toward the systematic, hierarchical, and explainable evaluation of LVLMs' long-term video quality understanding.
Authors: Qihang Zhang, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi
Abstract: Color-polarization imaging using a color-polarization filter array (CPFA) sensor captures both texture (color intensity) and physical (polarization) information of the scene in a single shot, enabling various applications in computer vision. However, the raw mosaic output from a CPFA sensor often suffers from severe noise and resolution loss, especially under low-light conditions. Existing methods generally focus on either denoising or demosaicking tasks, failing to capture the coupling between them and neglecting shared low-level features. In this paper, we propose a color-polarization denoising and demosaicking network (CPDDNet), which is a joint framework that performs noise removal and CPFA interpolation using a feature fusion module that retains the features from the CPFA raw data at both the denoising and the demosaicking stages. Experimental results demonstrate that CPDDNet significantly enhances image quality and polarization parameter accuracy, outperforming existing approaches on a real dataset.
Authors: Jiale Li, Sihan Chen, Mengyuan Liu
Abstract: Video Large Language Models (VideoLLMs) have shown strong progress in video understanding, yet they still suffer from hallucinations that are inconsistent with visual evidence. Existing benchmarks mainly focus on object hallucination or coarse action perception, leaving a key video-specific problem underexplored: motion hallucination, in which models infer human motions that are absent from the video. We present MoHallBench, a benchmark for diagnosing motion hallucination in VideoLLMs. MoHallBench systematically evaluates three major sources of hallucination: co-occurrence priors, sequential inference, and similarity confusion. It contains 11,306 video clips and 40,493 question-answer pairs, covering binary-choice, multiple-choice, and generative settings. We further introduce a bi-directional questioning protocol with bias-aware metrics to reduce affirmation bias in binary evaluation. Experiments on ten recent open-source VideoLLMs reveal a clear decoupling between action recognition and hallucination resistance, as models that perform well on positive action recognition often fail on adversarial negatives. Among all settings, sequential inference hallucination is the most severe, showing that current models tend to over-infer expected outcomes from partial motion cues. Our analyses further confirm that stronger priors and finer-grained similarity substantially amplify hallucination. We hope MoHallBench can facilitate future evaluation and mitigation of motion hallucination in VideoLLMs.
Authors: Bingchen Zhao, Sara Beery, Oisin Mac Aodha
Abstract: Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry. Furthermore, while they generate hypotheses iteratively, they largely lack the ability to explicitly synthesize their own accumulated findings to uncover complex, interconnected phenomena. We introduce DiscoPER, an autonomous large language model-powered framework that conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives. To ensure rigorous scientific validity, every proposed discovery must pass statistical testing. To overcome the limitations of isolated search, our framework introduces a second-order reasoning mechanism that periodically analyzes its own accumulated discoveries. By treating prior discoveries as empirical data, DiscoPER identifies structural patterns, confounds, and epistemic gaps, actively redirecting hypothesis exploration toward uncharted regions of the search space. The search space is further expanded by incorporating tool use, enabling the system to explore hypotheses beyond structured metadata by seamlessly processing and extracting useful information from multimodal sources like images. Evaluated on iNatDisco, a new multimodal ecological knowledge benchmark with pattern-level ground truth obtained from peer-reviewed literature, DiscoPER recovers 8 of 9 known patterns with a 72.7% hypothesis support rate, outperforming both classical causal discovery and LLM-guided baselines. Ablations show that DiscoPER scales with more data, and confirms the benefits of second-order meta-reflection.
Authors: Markus Knoche, Daan de Geus, Bastian Leibe
Abstract: Accurate trajectory forecasting of surrounding traffic participants is a core capability for autonomous driving, enabling vehicles to anticipate behavior and plan safe maneuvers. We observe that current state-of-the-art forecasting models on Argoverse 2 and the Waymo Open Motion Dataset tailor their training objectives to the different benchmark metrics. Because these metrics encourage conflicting behavior, we propose a paradigm change for trajectory forecasting: training models with metric-agnostic probabilistic objectives and treating metric optimization as a downstream task applied to the predictive distribution. Concretely, we introduce Trajectory Distribution Evaluation (TraDiE) policies, metric-specific policies that map a predictive distribution to the set of $K$ trajectories and confidences required by trajectory forecasting metrics. We evaluate this framework by introducing DONUT-NLL, which adapts the training objective of the state-of-the-art trajectory forecasting model DONUT to directly optimize the predictive distribution. Using our policies, DONUT-NLL achieves state-of-the-art results on all metrics of the Waymo motion prediction benchmark.
Authors: Sviatoslav Voloshyn, Bruno K. W. Martens, Wangxin Liu, Jakob Vink{\aa}s, Junsheng Fu
Abstract: This paper presents SD-RouteFusion, a deployable end-to-end ego-trajectory prediction method that fuses a front-facing camera, vehicle kinematics, and a navigation route derived from a Standard Definition (SD) map. Unlike approaches that rely on High Definition (HD) map geometry, SD-RouteFusion aligns the learning objective with scalable and production-ready SD-map route inputs, enabling route-aware prediction without requiring HD-map infrastructure. First, we demonstrate that SD-map route prior provides a powerful long-horizon semantic prior. Through a comprehensive study on a large-scale real-world dataset comprising 480k driving scenarios across 10 European countries and the U.S., we quantify the value of SD-route conditioning: incorporating SD-map routes yields a 10.5% ADE improvement over an image-and-kinematics baseline, while our full fusion strategy achieves a 16.9% ADE reduction given a prediction horizon of 8 seconds. The fusion strategy consists of a dual-hypothesis design paired with a gated classifier, to ensure robustness under route corruption and visual uncertainty. Finally, to support broader evaluation, we release an SD-route generation toolkit that enables SD-route-conditioned ego-trajectory prediction on all datasets containing ego pose and future trajectories. Together, SD-RouteFusion establishes a practical path toward robust, route-aware ego-trajectory prediction at scale.
Authors: Eunsung Cha, Hyunjoon Lee, Jaesik Park
Abstract: Open-vocabulary 3D Gaussian segmentation is challenging because it requires language understanding for diverse queries and accurate separation of Gaussians along object boundaries. Prior approaches either embed language knowledge into individual Gaussians to improve query responsiveness or optimize per-Gaussian instance features to encode object identity. However, these strategies may produce noisy Gaussian segmentations or rely on cost-inefficient per-scene optimization. We propose PairGS, a framework that reframes Gaussian segmentation as modeling pairwise relations between Gaussians. 3D Gaussian representations provide rich signals for relation estimation, such as view contribution weights and multi-view mask evidence. By leveraging these cues, PairGS explicitly constructs a relation graph for segmentation without a heavy optimization process. PairGS first proposes sparse edge candidates using low-dimensional descriptors, computes precise pairwise affinities only on those candidates, and builds a hierarchical cluster tree for multi-granular querying. It achieves state-of-the-art results on open-vocabulary 3D Gaussian segmentation benchmarks, while the fast variant is 50x faster than optimization-based instance-feature approaches.
Authors: Tatiana Gaintseva, Akshit Achara, Gregory Slabaugh, Jiankang Deng, Ismail Elezi
Abstract: Text-to-image diffusion models power everyday creative tasks, but they still reproduce the demographic biases in their training data. On common prompts such as ``a photo of a nurse,'' ``a photo of a CEO'', they skew their outputs toward one gender, driven by the statistics of training data rather than anything in the text. Existing debiasing methods show promise in narrow settings but require retraining, batch-level control, or prompt-specific tuning, limiting their scalability. We propose \emph{EquiSteer}, a training-free method that works per sample by steering cross-attention (CA) activations at inference time. For each target attribute, EquiSteer precomputes steering vectors from contrastive prompts. Then at generation time, a prompt-aware gate leaves attribute-specific prompts untouched, while for neutral ones it clears existing attribute signals from the CA activations and injects a target attribute. Across SD-1.5, SD-2.1, SDXL, and SANA, EquiSteer reduces the average parity gap by up to $87\%$, with minimal effect on image quality and text-image alignment. Code is available at \href{https://github.com/Atmyre/EquiSteer}{https://github.com/Atmyre/EquiSteer}.%
URLs: https://github.com/Atmyre/EquiSteer, https://github.com/Atmyre/EquiSteer
Authors: Yu Guan, Tianjia Huang, Qinrong Cai, Qiuyun Fan, Dong Liang, Qiegen Liu
Abstract: Magnetic resonance imaging (MRI) reconstruction under realistic acquisition conditions can be fundamentally viewed as estimating the underlying k-space distribution from incomplete and noise-corrupted measurements. While diffusion models have recently shown strong potential as generative prior for inverse problems,existingapproachesstruggletohandlenoisyreconstruction settings, especially when operating directly in k-space domain. In this work, we propose a unified high-dimensional k-space reconstruction framework tailored for noisy inverse problems, whichenhancesdiffusion-based solversthroughrepresentation lifting.Ratherthanmodifyingthe underlying optimization procedures, the proposed framework augments the data representation space, enabling existing diffusion-based solvers to operate on enriched k-space embeddings with improved expressiveness. Extensive experiments on both in-house and public datasets across varying noise levels and undersampled factors demonstrate that the proposed frame work consistently improves reconstruction quality for multiple diffusion-based inverse solvers. Notably, the largest gains are observed in high-noise regimes, which is consistent with our theoretical analysis of error propagation under high-dimensional representation. These results suggest that high-dimensional representation provides a general and model-agnostic mechanism for improving diffusion-based MRI reconstruction in noisy settings, offering a new perspective on robust k-space generative modeling for practical inverse problems. The code will be available at https://github.com/yqx7150/HEP-MRIRec.
Authors: Hongxing Li, Xiufeng Huang, Dingming Li, Wenjing Jiang, Zixuan Wang, Haolei Xu, Hanrong Zhang, Haiwen Hong, Longtao Huang, Hui Xue, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
Abstract: Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typically do not explicitly distinguish perception from reasoning. In this paper, we propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process: the model first localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner based on the annotated image and cropped regions. To better align training with this decoupled formulation, we further introduce Perception-Reasoning Alternating GRPO (PRA-GRPO), a role-aware reinforcement learning strategy that alternates between perception-focused and reasoning-focused updates using only final-answer supervision. Built on top of Qwen3-VL-Instruct-2B/4B/8B, P2R consistently improves performance across model scales. In particular, P2R-4B achieves 93.2% on V-Star, 81.9% on HR-Bench-4K, and 80.5% on HR-Bench-8K, substantially outperforming its corresponding backbone. Further experiments show that the benefits of P2R extend beyond high-resolution benchmarks to broader multimodal reasoning tasks. These results suggest that explicitly decoupling perception from reasoning provides an effective framework for fine-grained visual reasoning.
Authors: Liyuan Zhu, Shengyu Huang, Amrita Mazumdar, Tianye Li, Zan Gojcic, Gordon Wetzstein, Iro Armeni, Shalini De Mello, Alex Trevithick
Abstract: We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, pixel-aligned renderings that encode appearance, geometry, and 3D scene motion along both input and target camera trajectories to correct rendering artifacts and fill in missing regions from an initial reconstruction. To train this model, we construct a dataset of aligned multiview video pairs and dynamic 3DGS representations, with simulated artifacts characteristic of monocular reconstruction. At test time, we distill the model's generations, including newly observed regions and motions, back into a single consistent, high-quality dynamic 3DGS, improving both novel-view synthesis and the underlying 3D motion. Our method sets a new state of the art in 4D reconstruction and seamlessly generalizes to in-the-wild videos with large viewpoint changes and dynamic motions.
Authors: Anushrut Jignasu, Daniele Grandi
Abstract: We present Linkify, a framework for learning from interface-augmented assembly graphs to enable context-aware part retrieval in mechanical assemblies. While recent generative AI methods for CAD have focused largely on isolated parts or monolithic assemblies, the rich geometric information at the interfaces between parts, where function is realized, remains underexplored. We address this gap by recomputing high-fidelity interface geometry for the Fusion 360 Gallery Assembly dataset, correcting missing and erroneous contacts, and generating point-cloud representations of local contact regions. Using this data, we construct assembly graphs whose nodes encode part geometry and whose edges encode interface geometry via a pretrained point-cloud encoder. On top of this representation, we train a Graph Attention Network based on GATv2 to solve a masked part prediction task: given an assembly with one part held out, the model predicts the class of the missing component from a large vocabulary of geometrically clustered parts, thereby approximating a realistic part-retrieval scenario. Compared to non-graph baselines such as logistic regression and k-nearest neighbors operating on aggregated node features, Linkify achieves higher Top-K accuracy and F1 scores. Ablation studies on graph connectivity, edge attributes, and attention mechanisms demonstrate that accurate contact computation and dynamic attention over interfaces are critical for performance. Our corrected interface dataset and training pipeline, released publicly, provide a foundation for future interface-aware models for assembly retrieval, validation, and generative design.
Authors: Yue Han, Chong Li, Zhening Liu, Cong Huang, Fang Deng, Yong Liu, Fangyun Wei, Yan Lu
Abstract: Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several orders of magnitude larger and excel at modeling complex visual patterns. Motivated by this gap, we introduce Ink3D, a framework that bridges 3D generation with large-scale video generative models to synthesize extremely complex textures. Ink3D first reconstructs a white-mesh geometry using an off-the-shelf 3D generation model. It then employs OrbitPainter, a conditional video generative model, to produce dense orbit-scan videos capturing object appearance across viewpoints. To convert these views into coherent textures, we introduce TextureOptimizer, a neural baking module that integrates dense multi-view observations while mitigating geometry inconsistencies arising from video generation. By decoupling geometry and texture synthesis and leveraging large-scale pretrained video priors, Ink3D enables significantly richer and more faithful texture generation than prior approaches.
Authors: Meng Chen, Akhil Iyer, Amy Pavel
Abstract: Multimodal large language models (MLLMs) provide new opportunities for blind and low vision (BLV) people to access visual information in their daily lives. However, these models often produce errors that are difficult to detect without sight, posing safety and social risks in scenarios from medication identification to outfit selection. While BLV MLLM users use creative workarounds such as cross-checking between tools and consulting sighted individuals, these approaches are often time-consuming and impractical. We explore how systematically surfacing variations across multiple MLLM responses can support BLV users to detect unreliable information without visually inspecting the image. We contribute a design space for eliciting and presenting variations in MLLM descriptions, a prototype system implementing three variation presentation styles, and findings from a user study with 15 BLV participants. Our results demonstrate that presenting variations significantly increases users' ability to identify unreliable claims (by 4.9x using our approach compared to single descriptions) and significantly decreases perceived reliability of MLLM responses. 14 of 15 participants preferred seeing variations of MLLM responses over a single description, and all expressed interest in using our system for tasks from understanding a tornado's path to posting an image on social media.
Authors: Subash Gautam, Debaditya Acharya, Alexandra Kleeman, Sarah Foster
Abstract: To improve residents' well-being in Australia's urban areas, governments have introduced policy reforms such as SEPP65, BADS, and SPP7.3 to enhance apartment design quality. These regulations require precise geometric and spatial analysis to evaluate health-related features, including daylight access, natural ventilation, privacy, and space efficiency. However, compliance checking remains challenging due to its manual, time-intensive nature. Additionally, evolving policies limit scalability for large-scale assessments across thousands of apartments. Existing automated floor plan analysis methods are fragmented and typically focus on single apartments, lacking a unified framework for multi-unit compliance checking. This article explores current advancements in automated floor plan analysis, particularly AI-driven approaches, and highlights key challenges in their practical adoption. To address these gaps, a conceptual framework is proposed for automated compliance checking in multi-apartment buildings. A Large Language Model (LLM) is used within a Rule Engine to convert textual building codes into executable, explainable rules. A Data Extraction Engine segments floor plan images into elements such as walls, rooms, fixtures, text, and symbols, and transforms them into a structured building graph with topological relationships. This structured representation is then evaluated by a Compliance Check Engine, which leverages LLM-generated rules for assessment. The proposed framework offers a scalable, consistent, and transparent approach to automated compliance checking across jurisdictions, supporting efficient enforcement of apartment design standards and promoting healthier, higher-density urban development.
Authors: Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Huihua Zhao, John Welsh, Michael Andres Lin, Wei Liu, Tingwu Wang, Xingye Da, Zhengyi Luo, Vishal Kulkarni, Naema Bhatti, Yuke Zhu, Linxi Fan, Bowen Wen, Danfei Xu, Soha Pouya, Yan Chang
Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions. This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation. We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos. Evaluated on 1,831 benchmark tasks, CHORD achieves an average success rate of 82.12%, demonstrating strong scalability. CHORD also generalizes to whole-body manipulation from hand-only and third-person demonstrations, achieving a 90.77% success rate, and the learned policies transfer to the real world in both open-loop and closed-loop settings.
Authors: Adam Cole, Mick Grierson
Abstract: Vertigo Vertigo is a scene-for-scene AI reconstruction of Hitchcock's Vertigo (1958), generated from only 2.78% of the original film's frames. Using this sparse set of keyframe anchors, we perform first-last frame interpolation via a large video diffusion model to predict the intervening sequences. Vertigo is itself a film about the obsessive reconstruction of an artificial ideal; Vertigo Vertigo extends this logic to the material of the film, treating the canonical text as a probe for the normative conventions of classical cinema encoded within generative systems. Evaluated through computational analysis and critical feedback from media theorists (Lev Manovich, Shane Denson, Kevin L. Ferguson), the artifact demonstrates remarkable structural fidelity: 73.1% of frames are recognizable as plausible renditions of Vertigo and only 3.6% fail catastrophically. This fidelity suggests that cinematic norms are deeply compressed within the model's latent priors. Aesthetically, the reconstruction is rendered as an unstable overlay between the original film and its predictive shadow, fueling a persistent doubt in the viewer's perception of authenticity -- a 21st-century vertigo. The work argues that generative media is not a paradigm shift from cinema but an acceleration of its logic of desire and false authenticity, extending from classical Hollywood through to the predictive media environments now reshaping contemporary perception.
Authors: Skand Peri, Hung Nguyen, Chanho Kim, Li Fuxin, Stefan Lee
Abstract: Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynamics models lack explicit 3D spatial structure and suffer from geometrically inconsistent long-term rollouts with compounding errors. Emerging 3D dynamics models based on partial point clouds improve geometric consistency but remain sensitive to occlusions and accumulated prediction drift. To address these challenges, we present 3D Point World Models (3DPWM) - a task-agnostic world model that operates entirely in 3D space by first completing partial point clouds and then learning action-conditioned dynamics in this completed 3D scene. By operating on completed geometry, 3DPWM enables reliable long-horizon rollouts and more accurate cost evaluation for model-based planning while supporting adaptation to new tasks. Experiments across different robotic embodiments and tabletop manipulation benchmarks demonstrate that 3DPWM achieves significantly more reliable long-horizon rollouts (100-300+ steps), supports both open-loop and closed-loop planning, and enables successful sim-to-real transfer.
Authors: Qian Ma, S M Rayeed, Charles V. Stewart, Qiong Wu, Yao Ma
Abstract: Knowledge-Based Visual Question Answering (KB-VQA) aims to evaluate whether Visual Language Models (VLMs) can retrieve, ground, and reason over external structured knowledge beyond visual evidence. In practice, answer accuracy is widely adopted as the primary evaluation metric, implicitly treating correctness as a proxy for knowledge-grounded reasoning. However, for existing KB-VQA benchmarks, this proxy relies on critical assumptions that are often overlooked and rendered unreliable by benchmark issues: annotated answer must be derivable from the associated knowledge base, question must be well-posed with sufficient constraints, and visual setting must meaningfully require grounded disambiguation. In this work, we show that these assumptions are systematically violated in existing KB-VQA benchmarks. Our audit reveals substantial instances with missing or contradicted answers and underspecified questions that render accuracy a misleading metric. Furthermore, we find that existing datasets rely on visually trivial, single-entity scenes that bypass the need for sophisticated visual-to-knowledge mapping. We demonstrate that even with controlled architectures, these flaws lead to distorted model rankings and overestimations of reasoning capabilities. To address this, we introduce (1) a principled audit-and-repair protocol that restores answer derivability and question clarity, and (2) a controlled multi-entity augmentation protocol that introduces visual ambiguity to challenge initial retrieval and grounded reasoning. Re-evaluation under corrected and augmented settings yields markedly different performance trends. Our findings call for rethinking evaluation protocols and designing more interaction-aware KB-VQA benchmarks that prioritize verifiable reasoning over simple matching.
Authors: Luke Chen, Cheng-Ju Wu, David R. Martin, Qilin Ye, Pramod Khargonekar, Mohammad Abdullah Al Faruque
Abstract: Collaborative-perception enables multi-robot systems to enhance situational awareness by sharing perceptual information. Existing collaborative-perception systems face an inherent trade-off between communication bandwidth requirements and perception accuracy, where methods that exchange more information achieve better perception results at the cost of increased communication overhead. However, real-world communication networks impose bandwidth constraints that require minimizing communication overhead without sacrificing perception performance. To address this challenge, we propose HydraCollab, an adaptive collaborative-perception framework that (i) selectively transmits the most informative sensor features and (ii) dynamically employs collaboration strategies (intermediate or late) based on spatial confidence maps. Extensive evaluations on the V2X-R, V2X-Radar and UAV3D-mini datasets demonstrate that HydraCollab achieves the best overall trade-off between accuracy and communication cost among existing collaborative-perception methods. Relative to SOTA Where2comm, HydraCollab uses only 41% of the bandwidth on V2X-R and 26% on V2X-Radar while improving performance by 0.78% and 0.75% respectively. Our code and models are available at https://github.com/AICPS/HydraCollab.
Authors: Adam Darmanin
Abstract: Maltese, although a low-resource language, has its own text corpora and pretrained language models, but we are aware of only one real labelled PDF corpus for OCR training, 57 pages, far below what paragraph-level training needs. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract ensemble voted under a lexicon-anchored, ROVER-style scheme adapted for a low-resource setting. We call the Maltese submission LV-ROVER-MLT: an engineered adaptation of LV-ROVER's voting algorithm, not a new one, submitted to the DocEng 2026 competition. All results below are dev-set figures from the competition's own benchmark; the held-out real test CER is unknown at the time of writing and this paper does not claim one. We report results on a 422-paragraph benchmark against a fine-tuned Tesseract baseline with a character error rate of 0.0234. Ensemble recognition alone, scored under the same label convention as the baseline, improves character error rate by 44 percent to 0.01317. A post-processing chain that aligns Tesseract's straight-quote and dash output to the benchmark's curly-quote convention, plus one stage that recovers misread diacritics, brings the full pipeline to a character error rate of 0.00700, a 70 percent reduction. We also tested the same method, unchanged, on Hungarian and Luxembourgish: a bootstrap and permutation audit confirms a 33.7 percent character error rate improvement on Luxembourgish, while the Hungarian margin, 0.8 percent, is not statistically significant.
Authors: Amirhosein Chahe, Tyler Naes, Jovin D'sa, Faizan M. Tariq, Sangjae Bae, Lifeng Zhou, David Isele
Abstract: Autonomous vehicles must safely navigate complex environments where planning-critical agents may be hidden from view. Current approaches often treat all occlusions with uniform conservatism, yielding needlessly defensive driving, or they infer hidden spaces without estimating the impact on the planner. This work bridges the critical gap between perception and planning by enabling Vision-Language Models (VLMs) to identify and reason about the specific hidden agents that are most critical to the ego-vehicle's trajectory. We introduce a novel framework that uses Planning KL-divergence (PKL), an information-theoretic metric, to systematically identify and rank occluded agents based on their impact on the ego vehicle's plan. Using this planning-aware ranking, we employ an expert VLM (GPT-5) to generate rich, structured annotations that capture the visual evidence and reasoning required for this task. We apply this framework to the nuScenes dataset to create a new benchmark focused on high-impact scenarios. We conduct comprehensive experiments on a wide range of general-purpose and domain-adapted VLMs, demonstrating that fine-tuning on our PKL-guided data yields dramatic performance improvements across all models. Notably, our results show that smaller, fine-tuned models significantly outperform their much larger zero-shot counterparts, and that our PKL-guided data selection strategy improves performance by approximately 30\% over random sampling. Our work presents the first systematic approach for training VLMs to focus on planning-critical occlusions, enabling more semantically grounded and efficient risk assessment in autonomous driving.
Authors: Runhao Li, Xiaoxu Ma, Zhenyu Weng, Yue Zhang, Guibo Luo, Huiping Zhuang, Zhiping Lin, Yap-Peng Tan
Abstract: Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, existing unsupervised methods rely heavily on large-scale image-text pairs. Collecting such data can be costly, particularly in scenarios where well-aligned pairs are scarce due to privacy and specialized constraints. More critically, existing methods tend to overfit to seen training data, restricting their generalization performance on unseen categories that the constrained training data cannot cover. To address these limitations, we propose Attribute-Prompted Kernel Hashing (APKH), a novel data-efficient approach that constructs a compact, modality-aligned Hamming space driven by the generalized attribute priors of vision-language foundation models. Specifically, APKH introduces two core modules: Context-optimized Attribute Kernel Mapping (CAKM) and Kernel-Smoothed Contrastive Alignment (KSCA). CAKM formulates cross-modal alignment through hyperspherical Radial Basis Function kernel mapping, optimizing dynamic attribute kernels via prompt learning to capture modality-invariant semantics. Furthermore, KSCA extends conventional point-to-point contrastive learning by modeling limited paired data as continuous kernel distributions. This explicit smoothing of the modality gap alleviates overfitting to sparse pairwise correlations. Extensive experiments demonstrate that APKH outperforms state-of-the-art hashing methods in the challenging cross-modal retrieval tasks from seen to unseen categories under data-constrained scenarios.
Authors: Kaysarul Anas Apurba, Md Hasibul Hasan, Mohammed Ali, Tanzilur Rahman
Abstract: Automated malaria diagnosis from blood smear microscopy is a critical challenge in global health AI; in resource-limited settings, the scarcity of expert microscopists remains the primary bottleneck to timely and accurate diagnosis. Three compounding failure modes prevent reliable clinical deployment of existing deep learning systems. First, end-to-end detectors treat unannotated cells as background during training, producing recall figures that are strongly influenced by annotation completeness rather than reflecting true cell recovery. Second, Non-Maximum Suppression tends to suppress valid detections in dense smear regions where infection counts matter most. Third, existing whole-slide detection pipelines lack per-cell spatial evidence for clinical audit, despite image-level explainability methods such as Grad-CAM having been applied to malaria image classification tasks. We present MalariAI, a two-stage decoupled framework that addresses all three failure modes in a unified pipeline. Stage 1 applies an annotation-agnostic distance-transform guided watershed algorithm to isolate every cell in a full 1600x1200 blood smear image, recovering 75.95% of ground-truth cells by centroid localisation across the 120-image NIH BBBC041 test set without any ground-truth input. Stage 2 fine-tunes EfficientNet-B0 with Focal Loss (gamma = 2.0, per-class inverse-frequency weights) on 64x64 crops, achieving 98.36% overall classification accuracy with 87.5% and 75.0% per-class accuracy on the rare schizont and gametocyte stages, compared to only 24.57% and 25.95% AP for a Faster R-CNN baseline on the same classes. Grad-CAM++ heatmaps generated per detected cell provide instance-level spatial evidence for clinical audit, enabling microscopists to verify model predictions at the individual parasite level without sacrificing classification performance.
Authors: Sagnik Ghosh
Abstract: Cardiovascular disease is still one of the main causes of death around the world. Acute myocardial infarction (MI), or heart attack, claims millions of lives each year. MI happens when blood flow to the coronary arteries is blocked or reduced, which causes permanent damage to the heart muscle. Without treatment, this can lead to cardiac arrest, where the heart stops pumping blood to the organs, resulting in organ failure and death. Even survivors often face serious problems like heart failure, pulmonary edema, and asystole. Research shows that 5 to 10 percent of survivors die within the first year after an MI, and nearly half need to be hospitalized again. Early thrombolytic treatment leads to better outcomes, so there is a clear need for faster and more accurate ways to diagnose MI. Right now, doctors usually review patient history and use their own experience to find the causes of MI. This process takes a lot of time and can be inconsistent. Detecting MI accurately and quickly can help patients take better care of themselves and prevent fatal events. In this study, we introduce an automated model to predict deadly outcomes of MI and help doctors understand important biomarkers linked to its complications. This approach aims to make diagnosis clearer, faster, and more affordable. The process includes preparing the data, filling in missing values, and handling imbalanced data using SVMSMOTE, ADASYN, and class-weighted methods. We use wrapper and embedded feature selection to find the most important variables, then scale the features for consistency. The model combines Logistic Regression, Random Forest, Light-GBM, and Bagging SVM, and is further improved with an artificial neural network to increase accuracy. We evaluate all models using precision, recall, and other key measures to find the best option for clinical use.
Authors: Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, Yevgeniy Vorobeychik
Abstract: Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific regions of the distribution that maximize user preferences-initially unknown but gradually uncovered through interactive feedback. This can naturally be framed as a reinforcement learning problem, where the goal is to fine-tune a diffusion model to maximize a reward function based on preferences. However, the main challenge lies in learning a parameterized reward model, which typically requires large-scale preference data-something that is often not feasible in practice. In this work, we introduce Personalized Active Preference Alignment PAPA, a novel method that bypasses the requirement for a parametrized reward model by directly optimizing the diffusion model using real-time user feedback. PAPA enables feedback-efficient preference alignment, drawing inspiration from the variational inference framework. We demonstrate PAPA's effectiveness through extensive experiments and ablation studies across diverse class-conditioned and fine-grained alignment tasks. Additionally, based on theoretical insights, we propose an enhanced fine-tuning strategy, referred to as EPAPA, that requires less computational budget and accelerates the fine-tuning process, further boosting PAPA's suitability for real-world deployment. Our code is made publicly available at https://github.com/NasikNafi/papa.
Authors: James Grover, Emily A. Hewson, Andrew Phair, Michael Ferraro, Hilary L. Byrne, Paul Keall, Michael G. Jameson, David E. J. Waddington
Abstract: Image-guided therapies, including radiotherapy, biopsy and deep brain stimulation, rely on real-time targeting of anatomical structures. However, in the presence of motion, imaging latencies create a temporal misalignment between observed and true anatomy, compromising treatment accuracy. Artificial intelligence-based frameworks have increasingly been presented to close this latency gap, but leading personalised models can fail due to a lack of stable anatomical grounding. Foundation models can provide grounded behaviour, but they do not adapt to real-time, individual patient dynamics. Here we introduce a closed-loop coupling framework that synergises patient-specific temporal prediction with continuous segmentation-based anatomical interpretation from a foundation model. A personalised model predicts future anatomy to compensate for system latency, while a streaming foundation model provides anatomical supervision used to continuously update the temporal predictor in real time during treatment. We validate the framework using a digital phantom and intrafraction magnetic resonance imaging (MRI) from patients undergoing MRI-guided radiotherapy. For a prediction horizon of 400 ms, the proposed method improves anatomical prediction and reduces dosimetric error compared with existing approaches, within clinically relevant latency constraints. These results establish closed-loop coupling as a general strategy for real-time image-guided intervention.
Authors: Zhiqi Li, Wen Zhang, Bo Zhu
Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data. However, these models are typically deterministic, which makes them difficult to optimize with reinforcement learning (RL) post-training methods that require stochastic trajectories and well-defined likelihood ratios. Existing SDE-based stochasticization techniques are designed for velocity-based samplers with infinitesimal or finely discretized transitions, and therefore do not directly apply to long-range flow maps. In this work, we propose Flow-Map GRPO, an online RL post-training framework for deterministic few-step flow-map generators. The key component is Anchored Stochastic Flow Map Composition (ASFMC), a path-preserving stochasticization mechanism that introduces randomness through anchor-based conditional resampling while preserving the original marginal probability path of the deterministic flow map. We derive GRPO objectives for both single-time and two-time flow-map parameterizations. Experiments on few-step FLUX-based text-to-image generators, including MeanFlow and sCM, show that Flow-Map GRPO improves pretrained deterministic flow-map models across reward-based, perceptual, and task-level evaluation metrics. Our results demonstrate that deterministic few-step flow-map generators can be effectively aligned with RL post-training without modifying their original model parameterization or retraining them as native stochastic models.
Authors: Taewook Kang, Taeheon Kim, Donghyun Shin, Jonghyun Choi
Abstract: Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but similar robot (e.g., from Panda to UR5e). Adapting these models to the shifted environment (i.e., target domain) often requires training on multiple demonstrations for each task, which are costly to collect. To reduce the burden of data curation and training, we propose an analogy-based method that adapts VLA models under environmental shifts through weight vector arithmetic with domain-specific information addition, named Domain ARiThmetic (DART). Unlike prior approaches, DART requires collecting only a single demonstration, enabling efficient adaptation. To accurately isolate domain-specific information for addition, DART performs subspace alignment between singular components in weight vectors to filter out noisy components. In both simulated and real-world experiments, DART outperforms existing VLA adaptation methods in one-shot scenarios across diverse visual and embodiment shifts. Code is available at https://github.com/snumprlab/dart.
Authors: Zhihan Zeng, Kaihe Wang, Zhongpei Zhang, Chongwen Huang
Abstract: Static radio maps provide location-dependent propagation priors, but they cannot capture short-term blockage caused by moving objects. Direct sensing-assisted beam prediction is also limited because a beam index discards SINR margins, MCS thresholds, BS alternatives, and communication-equivalent neighboring beams. This paper proposes QuaMoE-DRF, a quality-aware multimodal dynamic radio map forecasting framework for proactive beam and rate adaptation in ISAC networks. Its core representation is a future beam-SINR field. We show that the full multi-BS beam-SINR field is sufficient for finite-codebook threshold-rate BS, beam, MCS, goodput, and outage decisions. For tractability, the implemented model learns a compact reference-BS local field, complemented by BS-level supervision, joint BS--beam supervision, and latent network context; we also clarify that this compact projection alone is not sufficient for BS association. QuaMoE-DRF fuses static geometry, event-like motion observations, structured sensing states, and wireless history through a quality-aware mixture-of-experts module motivated by inverse-variance fusion under heteroscedastic modality errors. It jointly predicts communication-oriented map channels and proactive BS, beam, and MCS decisions. On a dynamic multi-BS and multi-UE urban benchmark, QuaMoE-DRF achieves 402.5 Mbps effective rate, 0.0417 outage probability, and 0.1836 map RMSE, improving the effective rate by 5.67% and reducing outage by 8.35% over the strongest completed effective-rate baseline. The current validation uses labels from a compact blockage/path-loss simulator, with ray tracing used only for calibration and sanity checking.
Authors: Iddo Hakim, Sharva Gogawale, Omer Ventura, Gal Grudka, Daria Vasyutinsky-Shapira, Berat Kurar-Barakat, Nachum Dershowitz
Abstract: Reading order inference remains a critical bottleneck in the digitization of complex historical manuscripts, where pages contain multiple spatially interleaved reading streams, the canonical example being the Glossa Ordinaria layout, in which a central text is surrounded by commentaries that wrap around it in non-rectangular, non-convex regions. We present a training-free, graph-based framework: each OCR text line becomes a node in a directed candidate-transition graph, edges are scored by a weighted additive ensemble of two lightweight language-model signals (causal language model conditional likelihood and BERT next-sentence prediction, NSP; a third sentence-embedding signal was evaluated but did not improve reading order), and the global reading order is recovered as a degree-constrained directed path cover. To avoid the cascading "edge-theft" failures of greedy edge selection, we propose a max-regret inference rule that prioritizes commitments with high opportunity cost. We evaluate on synthetic Glossa Ordinaria grid layouts, on 23 ALTO page geometries (10 historical source pages plus mirrored and flipped variants), and on a 140-page multi-column English subset of OmniDocBench, comparing our method against the canonical recursive XY-cut (PaddleOCR PP-StructureV3) and two LayoutReader variants (layout-only and text+layout) on identical inputs. On wrap-around Glossa layouts our method recovers 95% of ground-truth successor edges on average vs. XY-cut's 50%; on the OmniDocBench multi-column subset it reaches 88% macro edge accuracy versus XY-cut's 75% and LayoutReader's 25%. The LayoutReader baselines transfer poorly due to a word-level vs. line-level granularity mismatch. We additionally verify mirror-invariance under horizontal and vertical page reflections: Our method changes by less than 1 percentage point, classical XY-cut by 2 points, and LayoutReader-T by up to 8 points.
Authors: Chi Zhang, Penglin Cai, Ziheng Xi, Haoqi Yuan, Hao Luo, Wanpeng Zhang, Sipeng Zheng, Chaoyi Xu, Zongqing Lu
Abstract: As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by hardware and data collection systems, existing datasets with tactility remain small in scale and narrow in contact coverage. Meanwhile, Vision-Language-Action (VLA) models with tactile modality are constrained on dynamics-agnostic post-training, which limits the performance ceiling on downstream tasks. In this paper, we present H-Tac, a large-scale tactile-action dataset with 160-hour egocentric human videos containing more than 300 tasks and 135k episodes. Building upon this, we propose Transferable Tactile Pre-Training (TTP), a system of tactile-based pre-training on human data for fine-grained robotic tasks. To bridge the gap between humans and robots, we use unified tactile and action spaces throughout the pre-training and post-training phases, preserving prior knowledge during human-to-robot transfer. By leveraging a tactile expert for future tactile prediction, our framework explicitly models the contact dynamics and precise physical interactions. Extensive experiments in simulation and on real robots demonstrate that our model achieves superior performance, exhibiting robust generalization and fine-grained manipulation capabilities. TTP paves the way for scalable tactile pre-training via human-to-robot transfer.
Authors: Zhiyi Li, Peilin Wu, Xiaoshen Han, Ruojin Cai, Yilun Du
Abstract: Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making. However, prevailing approaches often operate on 2D video sequences, inherently lacking the 3D geometric understanding necessary for precise spatial reasoning and physical consistency. We introduce a Structured 4D Latent Predictive Model, which predicts the evolution of a scene's 3D structure in a structured latent space conditioned on observations and textual instructions. Our representation encodes the scene holistically and can be decoded into diverse 3D formats, enabling a more complete and 3D consistent scene understanding. This structured 4D latent predictive model serves as a planner, generating future scenes that are translated into executable actions by a goal-conditioned inverse dynamics module. Experiments demonstrate that our model generates futures with strong visual quality, substantially better 3D consistency and multi-view coherence compared to state-of-the-art video-based planners. Consequently, our full planning pipeline achieves superior performance on complex manipulation tasks, exhibits robust generalization to novel visual conditions, and proves effective on real-world robotic platforms. Our website is available at https://structured-4d-model.github.io/.
Authors: Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag
Abstract: The rapid advancement of diffusion models has enabled the generation of high-fidelity images from textual prompts, yet achieving precise, disentangled control over specific attributes remains a significant challenge. A fundamental limitation arises because visual differences between images are often far more descriptive and nuanced than what can be captured through human-crafted text descriptions, which frequently fail to convey fine-grained semantic details. To address this, we introduce ViDiT (Visual Direction Transfer for Diffusion), a framework that expands the editing vocabulary by capturing latent semantics directly from image-edit pairs. ViDiT learns the underlying transformation by optimizing a single, global, and continuous editing direction from a small set of ``before-and-after'' examples. This optimization process transfers visual changes into the diffusion model's conditioning space, allowing for detailed edits that text alone cannot easily describe. ViDiT operates on a ``Learn Once'' principle, which completely eliminates the need for model fine-tuning or expensive per-image optimization during inference. Once learned, these continuous directions enable ``Edit Anywhere'' capabilities, allowing users to apply highly disentangled manipulations, such as changes in facial features, animal attributes, or artistic styles, to any image in a zero-shot manner with granular control over the edit intensity. Quantitative and qualitative evaluations demonstrate that ViDiT outperforms existing text-based editing methods in maintaining input faithfulness while achieving precise, scalable attribute control.
Authors: Mahdi Naseri, Jiayan Qiu, Zhou Wang
Abstract: We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicit scene representation and then rendered into semantically richer visual content. Conventional image-generation systems can produce visually realistic outputs from limited scene descriptions, but the added content is usually implicit in the generator rather than represented as an inspectable intermediate structure. In contrast, GCE seeks to make scene enrichment explicit at the scene-representation level while examining its visual consequences during generation, with the goal of encouraging generated content that is visually plausible, structurally coherent, and semantically richer than the sparse input. To instantiate GCE, we propose a jointly trained adversarial framework that enriches scene graphs by modeling object semantics and inter-object relations. Our approach first represents the input description as a scene graph, where nodes model objects and edges capture inter-object relations. The framework uses graph convolutional networks to predict additional objects and their relations to the existing scene. Finally, the enriched scene graph is passed through the downstream image-generation pipeline to generate the corresponding visual content. We evaluate the framework with proxy scene graph enrichment metrics, image-quality comparisons, qualitative examples, and user studies on the Visual Genome dataset.
Authors: Ruihan Yu, Tianyu Huang, Jingwang Ling, Feng Xu
Abstract: 2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy and deformation ability leads to dim and vague edges at object silhouettes, limiting the reconstruction quality of current Gaussian splatting methods. To enhance the representation power, we draw inspiration from quantum physics and propose to use the Gaussian-Hermite kernel as the new primitive in Gaussian splatting. The new kernel takes a unified mathematical form and extends the Gaussian function, which serves as the zero-rank special case in the updated general formulation. Our experiments demonstrate that the proposed Gaussian-Hermite kernel achieves improved performance over traditional Gaussian Splatting kernels on both geometry reconstruction and novel-view synthesis tasks. Specifically, on the DTU dataset, our method yields more accurate geometry reconstruction, while on datasets such as MipNeRF360 and our customized Detail dataset, it achieves better results in novel-view synthesis. These results highlight the potential of the Gaussian-Hermite kernel for high-quality 3D reconstruction and rendering.
Authors: Zili Wang, Zheng Zhang, Kun Ding, Qi Yang, Fei Li, Shiming Xiang
Abstract: Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation, but their inherently sequential nature results in slow inference speed. Speculative decoding, a successful acceleration technique for large language models (LLMs), has effectively accelerated discrete visual AR models. However, the absence of an analogous theory for continuous distributions precludes its use in accelerating continuous AR models. To fill this gap, this work presents continuous speculative decoding, and addresses challenges from: 1) low acceptance rate, caused by inconsistent output distribution modeled by target and draft models, and 2) modified distribution without analytic expression, caused by a complex integral. For challenge 1), we address low acceptance rates through an approximated criterion, a novel denoising trajectory alignment strategy based on reparameterization proximity, and token pre-filling. For challenge 2), we introduce acceptance-rejection sampling algorithm with an appropriate upper bound, thereby avoiding explicitly calculating the integral. Furthermore, our denoising trajectory alignment is also reused in acceptance-rejection sampling, effectively avoiding repetitive diffusion model inference. Extensive experiments on various models at 256x256 and 512x512 resolutions demonstrate that our approach achieves over 2x wall-time speedup while preserving the image generation quality. Codes is available at: https://github.com/MarkXCloud/CSpD
Authors: Sangyun Chung, Youngjoon Yu, Se Yeon Kim, Youngchae Chee, Yong Man Ro
Abstract: Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA) optimization, which leverages minimal sensor-specific data to enable robust learning of non-RGB characteristics and overcome RGB-centric biases inherent in current VLMs. In addition, we present VS-TDX-the first comprehensive, public benchmark designed to rigorously evaluate VLMs' sensor-specific understanding across diverse and realistic scenarios. Through extensive experiments on VLMs and various sensor modalities, we validate that our method consistently delivers superior performance and generalization under resource-constrained and architecture-invariant settings. Our approach provides a practical advance towards scalable deployment of VLMs in increasingly sensor-diverse real-world environments.
Authors: Qifeng Zhou, Wenliang Zhong, Thao M. Dang, Hehuan Ma, Saiyang Na, Yuzhi Guo, Junzhou Huang
Abstract: To overcome the black-box nature of predictive AI and the hallucination risks of generative models, retrieval-based models offer an interpretable, evidence-based paradigm for pathology clinical workflow. However, real-world clinical queries are inherently interleaved (e.g., pathology images and text). Current dual-encoders suffer from an \textbf{Architectural Mismatch}, lacking the mechanism to fuse such composed queries. To address this, we formalize the task of Pathology Composed Retrieval (PCR). While Multimodal Large Language Models (MLLMs) offer deep-fusion capabilities, directly applying them exposes a \textbf{Task Mismatch} and a \textbf{Domain Mismatch}. To resolve these challenges, we propose HOMIE, a model-agnostic adaptation framework that transforms any generative MLLM into a specialized pathology retrieval expert. Evaluated on our newly introduced PCR Benchmark, a lightweight 2B-parameter HOMIE variant substantially outperforms existing paradigms, surpassing specialized 7B pathology MLLMs and dual-encoders by large margins on composed retrieval, while maintaining strong performance on traditional simple retrieval. The project page is available at https://qfchou.github.io/HOMIE_page/.
Authors: Tobias Christian Nauen, Brian Moser, Federico Raue, Stanislav Frolov, Andreas Dengel
Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context. By exploiting such biases, models attain high in-distribution accuracy but remain fragile under distribution shifts. To address this issue, we introduce ForAug, a controlled composition augmentation scheme that factorizes each training image into a foreground object and a background and recombines them to explicitly manipulate object position, object scale, and background identity. ForAug uses off-the-shelf segmentation and inpainting models to (i) extract the foreground and synthesize a neutral background, and (ii) paste the foreground onto diverse neutral backgrounds before applying standard strong augmentation policies. Compared to conventional augmentations and content-mixing methods, our factorization provides direct control knobs that break foreground-background correlations. Across 10 architectures, ForAug improves ImageNet top-1 accuracy by up to 6 percentage points (p.p.) and yields gains of up to 7.3 p.p. on fine-grained downstream datasets. Moreover, the same control knobs enable targeted diagnostic tests: we quantify background reliance, foreground focus, center bias, and size bias via controlled background swaps and position/scale sweeps, and show that training with ForAug substantially reduces these shortcut behaviors and significantly increases accuracy on standard distribution-shift benchmarks by up to $19$ p.p. Our code and dataset are publicly available at https://github.com/tobna/ForAug.
Authors: Tasnim Shahriar
Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to interpret. This study presents a controlled benchmark of seven established CNNs across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared fine tuning protocol. The evaluation reports top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 parameter storage, and multiply accumulate operations. EfficientNetV2-S records the highest observed top-1 accuracy on all three datasets, reaching 97.57%, 86.98%, and 78.73%. EfficientNet-B0 remains within 0.85 percentage points of EfficientNetV2-S across the three datasets while requiring only about 21% of its parameters and 14% of its multiply accumulate operations on Tiny ImageNet. It therefore offers a favorable general balance between predictive performance and computational demand. MobileNetV3-Small is a strong candidate for ultra low resource settings. It uses about 40% of the parameters and 15% of the multiply accumulate operations of EfficientNet-B0 while retaining competitive accuracy. A matched comparison of ImageNet pretrained and randomly initialized EfficientNet-B0 and MobileNetV3-Small models shows that the pretrained advantage is substantially larger on CIFAR-100 and Tiny ImageNet than on CIFAR-10 under the fixed protocol. The results provide a focused reference for selecting established lightweight CNNs when predictive quality, parameter storage, and theoretical computation must be considered together.
Authors: Mohamed Nagy, Naoufel Werghi, Bilal Hassan, Jorge Dias, Majid Khonji
Abstract: Precise 3D state estimation in multi-object tracking (MOT) is critical for self-driving cars, particularly for objects occluded. Motion modeling in the Kalman filter with a constant motion assumption is widely used in MOT methods, but it neglects the continuous changes in objects' motion caused by traffic in urban environments. Although recent research introduces a multimodel Kalman filter that incorporates multiple motion models, these approaches incur significant computational overhead from the simultaneous processing of multiple models. To this end, this work introduces a motion-dynamics Kalman filter (MD-KF) that overcomes the constant-motion assumption while preserving the singularity of the motion model. MD-KF models the changes in objects' motion over successive measurements as Gaussian distributions, and adaptively adjusts a weighted motion model to account for these variations. MD-KF consistently outperforms constant and multimodel KF across multiple datasets with a significant reduction in computation latency compared to multimodel approaches. The proposed approach demonstrates its superiority in trajectory estimation during occlusion and state estimation stability for stationary objects.
Authors: David Schneider, Zdravko Marinov, Moritz Mistol, Zeyun Zhong, Alexander Jaus, Rodi D\"uger, Rafael Baur, M. Saquib Sarfraz, Rainer Stiefelhagen
Abstract: Visual fall detection models are usually trained on small, staged datasets. Their real-world utility remains unclear; such data lacks diversity and evaluation protocols differ from paper to paper. We propose OmniFall, a unified benchmark of 15k videos (80 hours) with frame-level annotations in a single 16-class taxonomy. It spans three domains: OF-Staged unifies eight staged datasets with cross-subject and cross-view splits; OF-Synthetic adds 12k videos (17 h) with controlled demographic and environmental diversity; and OF-In-the-Wild provides a test-only set of genuine accident videos. We evaluate fine-tuned models as well as much larger zero-shot multimodal LLMs. On in-the-wild fall events, both do comparably well. The clinically critical fallen state is where they part: zero-shot models keep confusing fallen with lying, whereas models fine-tuned on synthetic data with explicit fallen-state scenes do substantially better. We release the unified annotations, the synthetic data, and the in-the-wild test set to foster the development of fall and fallen-state detectors for uncontrolled environments. Dataset: https://hf.co/datasets/simplexsigil2/omnifall
Authors: Juan C. Martinez-Sevilla, Joan Cerveto-Serrano, Noelia Luna, Greg Chapman, Craig Sapp, David Rizo, Jorge Calvo-Zaragoza
Abstract: In this work, we introduce the Sheet Music Benchmark (SMB), a dataset of six hundred and eighty-five pages specifically designed to benchmark Optical Music Recognition (OMR) research. SMB encompasses a diverse array of musical textures, including monophony, pianoform, quartet, and others, all encoded in Common Western Modern Notation using the Humdrum **kern format. Alongside SMB, we introduce the OMR Normalized Edit Distance (OMR-NED), a new metric tailored explicitly for evaluating OMR performance. OMR-NED builds upon the widely-used Symbol Error Rate (SER), offering a fine-grained and detailed error analysis that covers individual musical elements such as note heads, beams, pitches, accidentals, and other critical notation features. The resulting numeric score provided by OMR-NED facilitates clear comparisons, enabling researchers and end-users alike to identify optimal OMR approaches. Our work thus addresses a long-standing gap in OMR evaluation, and we support our contributions with baseline experiments using standardized SMB dataset splits for training and assessing state-of-the-art methods.
Authors: Junha Lee, Eunha Park, Chunghyun Park, Dahyun Kang, Minsu Cho
Abstract: Affordance grounding aims to localize where to interact with an object, a fundamental capability for embodied agents. Yet progress is bottlenecked by data: manual annotation is prohibitively expensive and confines existing datasets to a narrow set of predefined object and affordance categories. We introduce Affogato, a framework for open-vocabulary affordance grounding centered on Affogato-750K, a large-scale dataset of 750K 3D affordance heatmaps paired with natural language queries. We build it with a fully automated pipeline that orchestrates foundation models to generate them at scale without human labeling. It covers significantly more diverse categories than any existing dataset. For reliable evaluation, we further provide 5K human-verified test pairs. We also present Espresso-3D and Espresso-2D, simple yet effective models with a unified architecture across both modalities. Pretraining on Affogato-750K improves both Espresso and prior methods and yields the largest gains on unseen object and affordance categories, showing that it provides broadly transferable supervision across architectures.
Authors: Zixu Zhao, Yang Zhan, Yunhao Li, Yan Li
Abstract: Unmanned aerial vehicles (UAVs) have become powerful platforms for real-time, high-resolution data collection, producing massive volumes of aerial videos. Efficient retrieval of relevant content from these videos is crucial for applications in urban management, emergency response, security, and disaster relief. While text-video retrieval has advanced in natural video domains, the UAV domain remains underexplored due to limitations in existing datasets, such as coarse and redundant captions. Thus, in this work, we construct the Drone Video-Text Match Dataset (DVTMD), which contains 2,864 videos and 14,320 fine-grained, semantically diverse captions. The annotations capture multiple complementary aspects, including human actions, objects, background settings, environmental conditions, and visual style, thereby enhancing text-video correspondence and reducing redundancy. Building on this dataset, we propose the Text-Conditioned Multi-granularity Alignment (TCMA) framework, which integrates global video-sentence alignment, sentence-guided frame aggregation, and word-guided patch alignment. To further refine local alignment, we design a Word and Patch Selection module that filters irrelevant content, as well as a Text-Adaptive Dynamic Temperature Mechanism that adapts attention sharpness to text type. Extensive experiments on DVTMD and CapERA establish the first complete benchmark for drone text-video retrieval. Our TCMA achieves state-of-the-art performance, including 45.5% R@1 in text-to-video and 42.8% R@1 in video-to-text retrieval, demonstrating the effectiveness of our dataset and method. The code and dataset will be released.
Authors: Yuyao Zhang, Yu-Wing Tai
Abstract: Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined to sub 2MP (< $1K\times2K$) resolutions due to the quadratic complexity of attention mechanisms and the scarcity of high-quality high-resolution training data. We present UltraImageGen, a novel framework that introduces hierarchical local attention with low-resolution global guidance, enabling efficient, scalable, and semantically coherent image synthesis at ultra-high resolutions. Specifically, high-resolution latents are divided into hardware aligned fixed-size local windows to reduce attention complexity from quadratic to near-linear, while a low-resolution latent equipped with scaled positional embeddings injects global semantics as an anchor. A lightweight LoRA adaptation bridges global and local pathways during denoising, ensuring consistency across structure and detail. To maximize inference efficiency and achieve scalable ultra-high-resolution generation, we repermute token sequence in window-first order, so that the GPU-friendly dense local blocks in attention calculation equals to the fixed-size local window in 2D regardless of resolution. Together ourwork reliably scales the pretrained model to resolutions higher than $8K$ with more than $10\times$ speed up and significantly lower memory usage. Extensive experiments demonstrate that ourwork achieves superior quality while maintaining computational efficiency, establishing a practical paradigm for advancing ultra-high-resolution image generation.
Authors: Qinghong Yin, Yu Tian, Heming Yang, Xiang Chen, Xianlin Zhang, Yue Ming, Xueming Li, Yue Zhang
Abstract: Concept erasure methods aim to remove specific unsafe target concepts in diffusion models while preserving image generation utility. To address the vulnerability that erased concepts can be easily recovered under adversarial attacks, adversarial concept erasure methods integrate adversarial optimization into the concept erasure process. However, existing adversarial concept erasure methods face a trade-off between robustness and computational cost. We attribute this to adversarial optimization techniques that use random samples to approximate the adversarial objective function. Adversarial optimization that uses a small number of samples fails to produce adversarial embeddings that accurately capture the target concept space. To mitigate this limitation, we propose Semantic-Guided Adversarial Optimization, which uses a single sample to produce adversarial embeddings that better capture the target concept space. We also propose Semantic-Guided Concept Erasure, which automatically maps the target concept to a semantically similar surrogate. Extensive experiments on not-safe-for-work content, artistic styles, and object-related concepts demonstrate that our method, S-GRACE (Semantic-Guided Robust Adversarial Concept Erasure) achieves state-of-the-art erasure robustness and superior image generation utility, with significantly lower computational cost than existing methods. Our code is available at https://github.com/Qhong-522/S-GRACE.
Authors: Qinyue Tong, Ziqian Lu, Jun Liu, Rui Zuo, Zheming Lu, Yueming Jin
Abstract: Despite notable progress in text-guided medical image segmentation nowadays, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is important for medical education scenarios. In this work, we introduce Multi-Round Entity-Level Medical Reasoning Segmentation (MEMR-Seg), a new task that requires generating segmentation masks through multi-round queries with entity-level reasoning, helping learners progressively develop their understanding of medical knowledge. To support this task, we construct MR-MedSeg, a large-scale dataset of 177K multi-round medical segmentation dialogues, featuring entity-based reasoning across rounds. Furthermore, we propose MediRound, an effective baseline model designed for multi-round medical reasoning segmentation. To mitigate the inherent error propagation within the chain-like pipeline of multi-round segmentation, we introduce a lightweight yet effective Judgment & Correction Mechanism during model inference. Experimental results demonstrate that our method effectively addresses the MEMR-Seg task and outperforms conventional medical referring segmentation methods. The project is available at https://github.com/Edisonhimself/MediRound.
Authors: Mingi Kang, Jeov\'a Farias Sales Rocha Neto
Abstract: Convolutional Neural Networks and Vision Transformers are the two dominant architectural families in computer vision, defined by spatially local convolution and global self-attention respectively. Despite their apparent differences, we show that both operations are special cases of a single $k$-nearest neighbor aggregation framework: convolution selects neighbors by spatial proximity while attention selects by feature similarity, placing them at two ends of a shared operational spectrum. We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that exactly recovers standard and depthwise convolution, self-attention, and sparse attention variants including KVT-attention as special cases, and exposes the design space of neighbor-selection strategies between them through configurable similarity functions, positional encodings, and aggregation kernels. We validate ConvNN on ImageNet-1K classification across two complementary architectures: a hybrid branching layer in ResNet-50 that combines local and global feature learning, improving top-1 accuracy by 3.0% over the ResNet-50 baseline, and ConvNN-attention in ViT-Base that achieves 81.64% top-1 accuracy, surpassing standard multi-head self-attention by 0.7%. Together, these results demonstrate that ConvNN provides a principled foundation for designing operations that bridge convolutional and attention-based computation.
Authors: Seonghun Oh, Youngjung Uh, Jin-Hwa Kim
Abstract: Extracting an explicit surface that exactly matches the zero-level set of a neural signed distance function (SDF) remains challenging. Sampling-based isosurfacing methods such as Marching Cubes introduce discretization error. In contrast, continuous piecewise affine (CPWA) analytic approaches typically require plain ReLU MLPs, which limits the ability to learn high-frequency SDFs in practice. We present TetraSDF, an analytic isosurface extraction framework for SDFs that retains the expressiveness of grid-based encoders while enabling exact zero-level set extraction, by representing the SDF with a ReLU MLP composed with a multi-resolution tetrahedral positional encoder. Our positional encoder's barycentric interpolation preserves a global CPWA structure, allowing us to track ReLU linear regions within an encoder-induced polyhedral complex. We further introduce a fixed analytic input preconditioner derived from the encoder's metric to reduce directional bias, thereby stabilizing training. Across multiple benchmarks, TetraSDF matches or surpasses existing grid-based encoders in SDF reconstruction accuracy, while faithfully recovering the network's zero-level set as a triangle mesh.
Authors: Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang, Xiangyu Yue, Chenyu You
Abstract: Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence.
Authors: Jun Zhang, Xin Zhang, Jie Feng, Long Chen, Junhui Wang, Zhicheng Liu, Depeng Jin, Yong Li
Abstract: Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose \textbf{RoadBench}, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs.
Authors: Hui Shan, Ming Li, Haitao Yang, Kai Zheng, Sizhe Zheng, Yanwei Fu, Xiangru Huang
Abstract: Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wild images and project them back onto garment meshes. However, most image-conditioned texture generation approaches require strict topological consistency between the input image and the input 3D mesh, or rely on accurate mesh deformation to match to the image poses, which significantly constrains the texture generation quality and flexibility. To address the challenging problem of non-isometric image-based garment texture generation, we construct 3D Garment Videos, a physically simulated, garment-centric dataset that provides consistent geometry and material supervision across diverse deformations, enabling robust cross-pose texture learning. We further employ Nano Banana for high-quality non-isometric image editing, achieving reliable cross-topology texture generation between non-isometric image-geometry pairs. Finally, we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures. Through extensive experiments, we demonstrate that our feedforward dual-branch architecture generates versatile and spatially aligned PBR materials suitable for industry-level 3D garment design.
Authors: Farnoosh Koleini, Hongfei Xue, Ahmed Helmy, Pu Wang
Abstract: Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. While marker-based systems are lab-bound and slow, popular monocular methods use oversimplified, anatomically inaccurate models (e.g., SMPL) and ignore physics, fundamentally limiting their biomechanical fidelity. In this work, we introduce MonoMSK, a hybrid framework that bridges data-driven learning and physics-based simulation for biomechanically realistic 3D human motion estimation from monocular video. MonoMSK jointly recovers both kinematics (motions) and kinetics (forces and torques) through an anatomically accurate musculoskeletal model. By integrating transformer-based inverse dynamics with differentiable forward kinematics and dynamics layers governed by ODE-based simulation, MonoMSK establishes a physics-regulated inverse-forward loop that enforces biomechanical causality and physical plausibility. A novel forward-inverse consistency loss further aligns motion reconstruction with the underlying kinetic reasoning. Experiments on BML-MoVi, BEDLAM, and OpenCap show that MonoMSK significantly outperforms state-of-the-art methods in kinematic accuracy, while for the first time enabling precise monocular kinetics estimation.
Authors: Seungyeon Baek, Erqun Dong, Shadan Namazifard, Mark J. Matthews, Kwang Moo Yi
Abstract: We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting -- in practice their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue the missing ingredient for training-free generic model usage is proper optimization of the initial noise sample. We optimize the initial noise to approximately reproduce the unmasked image, in as few as tens of optimization steps, then use it with a conventional training-free inpainting method. Critically, we propose two core ideas that make this possible: (i) we perform linear approximation that avoids the costly and often impractical unrolling required to relate the initial noise sample to model output -- which potentially is why this relationship was previously overlooked; and (ii) perform spectral preconditioning by optimizing the initial noise sample in the spectral domain with Adam, which stabilizes the optimization. We demonstrate our method on various inpainting tasks, outperforming the state of the art. Project website: https://ubc-vision.github.io/sonic/
Authors: Fr\'ed\'eric Fortier-Chouinard, Yannick Hold-Geoffroy, Valentin Deschaintre, Matheus Gadelha, Jean-Fran\c{c}ois Lalonde
Abstract: Recent progress in text-to-video generation has achieved remarkable realism, yet fine-grained control over camera motion and orientation remains elusive, especially with extreme trajectories (e.g., a 180-degree turnaround, or looking directly up or down). Existing approaches typically encode camera trajectories using relative or ambiguous representations, limiting precise geometric control and offering limited support for large rotations. We introduce GimbalDiffusion, a framework that enables camera control grounded in physical-world coordinates, using gravity as a global reference. Instead of describing motion relative to previous frames, our method defines camera trajectories in an absolute coordinate system, allowing accurate, interpretable control over camera parameters. Using panoramic 360-degree videos for training, we cover the full sphere of possible viewpoints, including combinations of extreme pitch and roll that are out-of-distribution of conventional video data. To improve camera control, we introduce null-pitch conditioning, a strategy that prevents the model from overriding camera specifications in the presence of conflicting prompt content (e.g., generating grass while the camera points toward the sky). Finally, we propose new benchmarks to evaluate gravity-aware camera-controlled video generation, assessing models' ability to generate extreme camera angles and quantify their input prompt entanglement.
Authors: Daniel Adebi, Sagnik Majumder, Kristen Grauman
Abstract: Understanding camera motion is a fundamental problem in embodied perception and 3D scene understanding. While visual methods have advanced rapidly, they often struggle under visually degraded conditions such as motion blur or occlusions. In this work, we show that passive scene sounds provide cues complementary to vision for relative camera pose estimation for in-the-wild videos. We introduce a simple but effective audio-visual framework that integrates direction-of-arrival (DOA) spectra and binauralized embeddings into a state-of-the-art vision-only pose estimation model. Our results on two large datasets show consistent gains over strong visual baselines, plus robustness when the visual information is corrupted. To our knowledge, this represents the first work to successfully leverage audio for relative camera pose estimation in real-world videos, and it establishes incidental, everyday audio as an unexpected but promising signal for a classic spatial challenge. Project: http://vision.cs.utexas.edu/projects/av_camera_pose.
Authors: Yuwei Guo, Ceyuan Yang, Hao He, Yang Zhao, Meng Wei, Zhenheng Yang, Weilin Huang, Dahua Lin
Abstract: Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional teacher model or discriminator. To achieve an end-to-end solution, we introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models from scratch and at scale. Central to our approach is a self-resampling scheme that simulates inference-time model errors on history frames during training. Conditioned on these degraded histories, a sparse causal mask enforces temporal causality while enabling parallel training with frame-level diffusion loss. To facilitate efficient long-horizon generation, we further introduce history routing, a parameter-free mechanism that dynamically retrieves the top-k most relevant history frames for each query. Experiments demonstrate that our approach achieves performance comparable to distillation-based baselines while exhibiting superior temporal consistency on longer videos owing to native-length training.
Authors: Seongmin Jung, Seongho Choi, Gunwoo Jeon, Minsu Cho, Jongwoo Lim
Abstract: 3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose a generalizable 3DVG framework, PanoGrounder, that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3D semantic and geometric features, serve as an intermediate representation between 2D and 3D, and offer two major benefits: (i) they can be directly fed to VLMs with minimal adaptation and (ii) they retain long-range object-to-object relations thanks to their 360-degree field of view. We devise a three-stage pipeline that places a compact set of panoramic viewpoints considering the scene layout and geometry, grounds a text query on each panoramic rendering with a VLM, and fuses per-view predictions into a single 3D bounding box via lifting. Our approach achieves state-of-the-art results on ScanRefer and Nr3D, and demonstrates strong generalization to unseen 3D datasets and text rephrasings.
Authors: Kanghee Lee, Jungi Hong, Sion Lee, Injae Lee, Minseok Kwak, Kwonyoung Ryu, Jaesik Park
Abstract: Recent progress in Multimodal Large Language Models (MLLMs) has enabled 3D scene understanding and spatial reasoning directly from multi-view images, without requiring explicit 3D reconstructions. Nevertheless, key challenges that frequently arise in real-world environments, such as partial visibility, occlusion, and low-overlap conditions that require reasoning from fragmented visual cues, remain under-explored. To address these limitations, we propose a scalable multi-view data generation and annotation pipeline that constructs realistic spatial reasoning QAs, resulting in SpatialMosaic, a comprehensive instruction-tuning dataset with 2M QA pairs. We further introduce SpatialMosaic-Bench, a challenging benchmark for evaluating multi-view spatial reasoning under complex and diverse scenarios, consisting of 1M QA pairs across 11 tasks with both multiple-choice and numerical-answer formats. Our dataset spans both indoor and outdoor scenes, enabling comprehensive evaluation across diverse real-world scenarios. In addition, we provide a practical baseline for multi-view settings by integrating geometry encoders into VLMs for improved cross-view consistency and spatial grounding. Extensive experiments demonstrate that our dataset effectively enhances spatial reasoning under challenging multi-view conditions, validating the effectiveness of our data generation pipeline in constructing realistic and challenging QAs.
Authors: Zhexiao Xiong, Xin Ye, Burhan Yaman, Sheng Cheng, Yiren Lu, Jingru Luo, Nathan Jacobs, Liu Ren
Abstract: World models have become central to autonomous driving, where accurate scene understanding and future prediction are crucial for safe control. Recent work has explored using vision-language models (VLMs) for planning, yet existing approaches typically treat perception, prediction, and planning as separate modules. We propose UniDrive-WM, a unified VLM-based world model that jointly performs driving-scene understanding, trajectory planning, and trajectory-conditioned future image generation within a single architecture. UniDrive-WM's trajectory planner predicts a future trajectory, which conditions a VLM-based image generator to produce plausible future frames. These predictions provide additional supervisory signals that enhance scene understanding and iteratively refine trajectory generation. We further compare discrete and continuous output representations for future image prediction, analyzing their influence on downstream driving performance. Experiments on the challenging Bench2Drive benchmark show that UniDrive-WM produces high-fidelity future images and improves planning performance by 7.3% in L2 trajectory error and 10.4% in collision rate over the previous best method. These results demonstrate the advantages of tightly integrating VLM-driven reasoning, planning, and generative world modeling for autonomous driving. The project page is available at https://unidrive-wm.github.io/UniDrive-WM.
Authors: Mohamad Koohi-Moghadam, Mohammad-Ali Nikouei Mahani, Rex K. H. Au-Yeung, Raymond Yu O, Monalyn Marabi, Piyapharom Intarawichian, Fabian Z. X. Lean, Andrew Ferguson, Kyongtae Tyler Bae
Abstract: Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enabling controllable, high-fidelity lesion inpainting into benign histopathology images. We validate PathoGen across four datasets representing kidney, skin, breast, and prostate pathology. Quantitative assessment confirms PathoGen outperforms state-of-the-art baselines in image fidelity and distributional similarity. Evaluation by six expert pathologists revealed that synthetic images by PathoGen were only marginally distinguished from real tissue image slightly above chance (57.75% accuracy), demonstrating strong perceptual realism of PathoGen-generated lesions. PathoGen achieved the highest win rate (35.4%) when pathologists ranked generation quality against all baselines. Crucially, augmenting training sets with PathoGen-synthesized lesions improves segmentation Dice scores by up to 0.18 compared to traditional augmentations, with maximum benefit in data-scarce regimes. By simultaneously generating realistic morphology and pixel-level annotations, PathoGen effectively addresses both data scarcity and annotation cost, two critical bottlenecks in computational pathology development.
Authors: Takamichi Miyata, Sumiko Miyata, Andrew Morris
Abstract: Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods. Vision-language models (VLMs) enable strong zero-shot image classification, but existing VLM-based distracted driver detectors often underperform in real-world conditions. We identify subject-specific appearance variations (e.g., clothing, age, and gender) as a key bottleneck: VLMs entangle these factors with behavior cues, leading to decisions driven by who the driver is rather than what the driver is doing. To address this, we propose a subject decoupling framework that extracts a driver appearance embedding and removes its influence from the image embedding prior to zero-shot classification, thereby emphasizing distraction-relevant evidence. We further orthogonalize text embeddings via metric projection onto Stiefel manifold to improve separability while staying close to the original semantics. Experiments demonstrate consistent gains over prior baselines, indicating the promise of our approach for practical road-safety applications.
Authors: Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan
Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a \underline{\textbf{M}}ixture-\underline{\textbf{O}}f-\underline{\textbf{D}}istribution \textbf{DiT} (\textbf{MOD-DiT}), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a {distributed mixing approach} to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches.
Authors: Takaya Kawakatsu, Ryo Ishiyama
Abstract: Handwritten mathematical expression recognition (HMER) requires reasoning over diverse symbols and structures, yet autoregressive models struggle with exposure bias and syntax inconsistency. We present GryphOne, a discrete diffusion framework which reformulates HMER as iterative symbolic refinement instead of sequential generation. GryphOne progressively refines symbols and relations, removing autoregression and improving consistency. Symbol-aware tokenization and random-masking mutual learning further enhance robustness to handwriting diversity. On the MathWriting benchmark, GryphOne achieves 5.51% CER and 59.9% EM (ExpRate), outperforming all reimplemented models in the matched setting as well as the commercial HMER system. Held-out evaluation on CROHME 2014-2023 further shows strong cross-dataset generalization.
Authors: Qi Li, Yanzhe Zhao, Yongxin Zhou, Yameng Wang, Yandong Yang, Yuanjia Zhou, Jinxiang Liu
Abstract: Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. However, their practical application is often hindered by the substantial computational cost incurred from processing a large number of tokens from visual inputs. In this paper, we propose Magic-MM-Embedding, a series of novel models that achieve both high efficiency and state-of-the-art performance in universal multimodal embedding. Our approach is built on two synergistic pillars: (1) a highly efficient MLLM architecture incorporating visual token compression to drastically reduce inference latency and training time, and (2) a multi-stage progressive training strategy designed to not only recover but significantly boost performance. This coarse-to-fine training paradigm begins with extensive continued training to restore multimodal understanding and generation capabilities, progresses to large-scale contrastive pretraining and hard negative mining to enhance discriminative power, and culminates in a task-aware fine-tuning stage guided by an MLLM-as-a-Judge for precise data curation. Comprehensive experiments show that our model outperforms existing methods by a large margin while being more inference-efficient.
Authors: Chanhui Lee, Donggyu Choi, Seunghyun Shin, Hae-Gon Jeon, Jeany Son
Abstract: Diffusion model advances have enabled powerful text-guided image editing, but also raise ethical and legal risks such as deepfakes and unauthorized use. To prevent these risks, adversarial attack-based image immunization has emerged as a promising defense against AI-driven semantic manipulation. Yet, most existing approaches require image-specific optimization or additional neural networks at inference time, hindering scalability and practicality. In this paper, we propose the first universal adversarial perturbation-based image immunization framework that generates a single, image-agnostic adversarial perturbation specifically designed for diffusion-based editing pipelines. Inspired by UAP used in targeted attacks, our method aims to generate a UAP that induces diffusion models to misinterpret the input image as a specific semantic target. Simultaneously, it suppresses original content to misdirect the model's attention during editing, thereby effectively blocking unauthorized edits by overwriting the image's original semantics via the UAP. Extensive experiments show that our method, as the first universal immunization approach, significantly outperforms several baselines in the UAP setting. Notably, despite the inherent difficulty of universal perturbations, our method achieves competitive or superior performance compared to image-specific methods under a more restricted perturbation budget, while also exhibiting strong black-box transferability across diverse diffusion models.
Authors: David Smerkous, Zian Wang, Behzad Najafian
Abstract: Self-supervised pretraining has transformed computer vision by enabling data-efficient fine-tuning, yet high-resolution pretraining typically requires server-scale infrastructure, limiting custom in-domain training for many research laboratories. Masked Autoencoders (MAE) reduce computation by encoding only visible tokens, but combining MAE with hierarchical downsampling architectures has remained structurally challenging due to dense grid priors and mask-aware design compromises. We introduce AFFMAE, a masking-friendly hierarchical pretraining framework built on adaptive, off-grid token merging. AFFMAE removes dense-grid assumptions while preserving hierarchical scalability during pre-training and fine-tuning. To support this architecture, we developed numerically stable mixed-precision Triton kernels and a lightweight, point-based decoder that can be directly repurposed as a segmentation head. On high-resolution microscopy segmentation, AFFMAE matches MAE finetuning performance on foot process width estimation with ViT backbone at equal parameter counts while being 2x faster during pre-training and halving peak memory usage. Furthermore, AFFMAE achieves up to 5x throughput speedups fine-tuning at the 1024px resolution, providing high-resolution model training on desktop hardware. Code available at https://github.com/najafian-lab/affmae.
Authors: Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani
Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes prompt tuning attractive. In this work, we propose MMLoP (Multi-Modal Low-Rank Prompting), a framework that achieves deep multi-modal prompting with only 11.5K trainable parameters, comparable to early text-only methods like CoOp. MMLoP parameterizes vision and text prompts at each transformer layer through a low-rank factorization that constrains prompts to a compact subspace, providing parameter efficiency while motivating the need for our complementary regularization components. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global embedding shift induced by prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples vision and text prompts through a common low-rank factor to enforce cross-modal alignment. Extensive experiments across three benchmarks and 11 diverse datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70\% on base-to-novel generalization. Code is available at https://github.com/sajjad-ucsb/MMLoP.
Authors: Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon
Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning. We study token reduction in hybrid Mamba--Transformer VLMs and find that it is \emph{stateful}: Mamba layers maintain a recurrent state that accumulates information from earlier tokens, allowing discarded tokens to persist, so reduction behaves more like compression than dropping.We support this view with a representation-based probing method measuring how much information from discarded tokens is retained, and analyze layer-wise sparsity and cross-layer importance stability. Our findings show importance is sparse within layers but unstable across layers, making aggressive early pruning unreliable while hybrids remain robust to later reduction.Motivated by this, we propose a hybrid-aware token reduction framework with a low-to-high progressive schedule and a unified query-conditioned importance score for attention and Mamba layers. For Mamba, excluding the position-dependent decay from the recurrence produces a stronger selection signal. Across long-video benchmarks, our method achieves $3.8{\times}$--$4.2{\times}$ prefilling speedups at a 25% token budget while maintaining near-baseline accuracy and improving with light finetuning. Hybrid models benefit from aggressive reduction, improving both efficiency and accuracy, whereas Transformers exhibit the standard trade-off. Our method also outperforms prior baselines on the same hybrid backbone and combines effectively with visual redundancy reduction methods.
Authors: Xiaokai Bai, Lianqing Zheng, Runwei Guan, Siyuan Cao, Songkai Wang, Huiliang Shen
Abstract: Collaborative perception (CP) improves scene understanding through multi-agent information sharing, yet LiDAR-centric systems remain costly and vulnerable in adverse weather. Camera--4D radar offers a practical alternative, but their synergy is still underexplored in CP. We introduce RC-GeoCP, which promotes low-cost, weather-resilient, and geometrically stable radar from an ego-level auxiliary cue to a cross-agent collaboration anchor. To resolve misalignment caused by depth ambiguity and spatial dispersion across agents, RC-GeoCP establishes an ego-normalized geometric consensus: the same radar-derived reliability prior is reused to ground local BEV features, select complementary messages, and weight received evidence. Specifically, Geometric Structure Rectification (GSR) aligns visual semantics with geometry derived from radar to generate spatially grounded, geometry-consistent representations. Uncertainty-Aware Communication (UAC) then serves as an information filter that inherits rectified features from GSR, leveraging inter agent disagreement to steer selective communication toward the most informative regions. Finally, the Consensus-Driven Assembler (CDA) aggregates multi-agent information via ego-normalized geometric anchors to form a spatially coherent representation. We establish a unified radar-camera CP evaluation protocol on V2X-Radar and V2X-R, demonstrating a strong accuracy--communication trade-off. Code will be released soon.
Authors: Kai Luo, Xu Wang, Rui Fan, Kailun Yang
Abstract: Generalizing across unknown targets is critical for open-world perception, yet existing 3D Multi-Object Tracking (3D MOT) pipelines remain limited by closed-set assumptions and ``semantic-blind'' heuristics. To address this, we propose Next-step Open-Vocabulary Autoregression (NOVA), an autoregressive association formulation that shifts the data association stage from fragmented distance-based matching toward trajectory-conditioned spatio-semantic modeling. NOVA reformulates 3D trajectories as structured spatio-temporal semantic sequences, enabling the simultaneous encoding of physical motion continuity and deep linguistic priors. By leveraging the autoregressive capabilities of Large Language Models (LLMs), we transform the tracking task into a principled process of next-step sequence completion. This mechanism allows the model to explicitly utilize the hierarchical structure of language space to resolve fine-grained semantic ambiguities and maintain identity consistency across complex long-range sequences through high-level commonsense reasoning. Extensive experiments on nuScenes, V2X-Seq-SPD, and KITTI demonstrate the superior performance of NOVA. Notably, on the nuScenes dataset, NOVA achieves an AMOTA of 22.41% for Novel categories, yielding a significant 20.21% absolute improvement over the baseline. These gains are realized through a compact 0.5B autoregressive model. Code will be available at https://github.com/xifen523/NOVA.
Authors: Jingkai Wang, Yixin Tang, Jue Gong, Jiatong Li, Shu Li, Libo Liu, Jianliang Lan, Yutong Liu, Yulun Zhang
Abstract: Diffusion transformer (DiT) architectures show great potential for real-world image super-resolution (Real-ISR). However, their computationally expensive iterative sampling necessitates one-step distillation. Existing one-step distillation methods struggle with Real-ISR on DiT. They suffer from fundamental trajectory mismatch and generate severe grid-like periodic artifacts. To tackle these challenges, we propose StrSR, a novel one-step adversarial distillation framework featuring spectral and trajectory regularization. Specifically, we propose an asymmetric discriminative distillation architecture to bridge the trajectory gap. Additionally, we design a frequency distribution matching strategy to effectively suppress DiT-specific periodic artifacts caused by high-frequency spectral leakage. Extensive experiments demonstrate that StrSR achieves state-of-the-art performance in Real-ISR, across both quantitative metrics and visual perception. The code and models will be released at https://github.com/jkwang28/StrSR .
Authors: Yulun Wu, Ruyi Zha, Wei Cao, Yingying Li, Yuanhao Cai, Yaoyao Liu
Abstract: Sparse-view computed tomography (CT) is critical for reducing radiation exposure to patients. Recent advances in radiative 3D Gaussian Splatting (3DGS) have enabled fast and accurate sparse-view CT reconstruction. Despite these algorithmic advancements, practical reconstruction fidelity remains fundamentally bounded by the quality of the captured data, raising the crucial yet underexplored problem of X-ray active view selection. Existing active view selection methods are primarily designed for natural-light scenes and fail to capture the unique geometric ambiguities and physical attenuation properties inherent in X-ray imaging. In this paper, we present Perturbed Gaussian Ensemble, an active view selection framework that integrates uncertainty modeling with sequential decision-making, tailored for X-ray Gaussian Splatting. Specifically, we identify low-density Gaussian primitives that are likely to be uncertain and apply stochastic density scaling to construct an ensemble of plausible Gaussian density fields. For each candidate projection, we measure the structural variance of the ensemble predictions and select the one with the highest variance as the next best view. Extensive experimental results on arbitrary-trajectory CT benchmarks demonstrate that our density-guided perturbation strategy effectively eliminates geometric artifacts and consistently outperforms existing baselines in progressive tomographic reconstruction under unified view selection protocols.
Authors: Magdalena Wysocki, Kadir Burak Buldu, Miruna-Alexandra Gafencu, Mohammad Farid Azampour, Nassir Navab
Abstract: Accurate 3D reconstruction of vertebral anatomy from ultrasound is important for guiding minimally invasive spine interventions, but it remains challenging due to acoustic shadowing and view-dependent signal variations. We propose an occupancy-based shape completion method that reconstructs complete 3D anatomical geometry from partial ultrasound observations. Crucially for intra-operative applications, our approach extracts the anatomical surface directly from the image, avoiding the need for anatomical labels during inference. This label-free completion relies on a coupled latent space representing both the image appearance and the underlying anatomical shape. By leveraging a Neural Implicit Representation (NIR) that jointly models both spatial occupancy and acoustic interactions, the method uses acoustic parameters to become implicitly aware of the unseen regions without explicit shadowing labels through tracking acoustic signal transmission. We show that this method outperforms state-of-the-art shape completion for B-mode ultrasound by 80% in HD95 score. We validate our approach both in-silico and on phantom US images with registered mesh models from CT labels, demonstrating accurate reconstruction of occluded anatomy and robust generalization across diverse imaging conditions. Code and data will be released on publication.
Authors: Jingxing Li, Yongjae Lee, Deliang Fan
Abstract: 3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians, yet its training remains expensive, with the backward pass dominating runtime in the post-densification refinement phase. We observe substantial update redundancy in this phase: many sampled views have near-plateaued losses and provide diminishing gradient benefits, but standard training still runs full backpropagation. We propose SkipGS with a novel view-adaptive backward gating mechanism for efficient post-densification training. SkipGS always performs the forward pass to update per-view loss statistics, and selectively skips backward passes when the sampled view's loss is consistent with its recent per-view baseline, while enforcing a minimum backward budget for stable optimization. On Mip-NeRF 360, compared to 3DGS, SkipGS reduces end-to-end training time by 23.1%, driven by a 42.0% reduction in post-densification time, with comparable reconstruction quality. Because it only changes when to backpropagate without modifying the renderer, representation, or loss, SkipGS is plug-and-play and compatible with other complementary efficiency strategies, enabling additive speedups. Code is available at https://github.com/ASU-ESIC-FAN-Lab/SkipGS.
Authors: Pum Jun Kim, Seung-Ah Lee, Seongho Park, Dongyoon Han, Jaejun Yoo
Abstract: Understanding how neural networks rely on visual cues offers a human-interpretable view of their internal decision processes. The cue-conflict benchmark has been influential in probing shape-texture preference and in motivating the insight that stronger, human-like shape bias is often associated with improved in-domain performance. However, we find that the current stylization-based instantiation can yield unstable and ambiguous bias estimates. Specifically, stylization may not reliably instantiate perceptually valid and separable cues nor control their relative informativeness, ratio-based bias can obscure absolute cue sensitivity, and restricting evaluation to preselected classes can distort model predictions by ignoring the full decision space. Together, these factors can confound preference with cue validity, cue balance, and recognizability artifacts. We introduce REFINED-BIAS, an integrated dataset and evaluation framework for reliable and interpretable shape-texture bias diagnosis. REFINED-BIAS constructs balanced, human- and model- recognizable cue pairs using explicit definitions of shape and texture, and measures cue-specific sensitivity over the full label space via a ranking-based metric, enabling fairer cross-model comparisons. Across diverse training regimes and architectures, REFINED-BIAS enables fairer cross-model comparison, more faithful diagnosis of shape and texture biases, and clearer empirical conclusions, resolving inconsistencies that prior cue-conflict evaluations could not reliably disambiguate.
Authors: Alara Dirik, Stefanos Zafeiriou
Abstract: Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to multiple views of the same scene often yields inconsistent estimates, limiting their use in downstream applications such as editable neural scenes and 3D reconstruction. Video-based models can improve cross-frame consistency but require dense, ordered sequences and substantial compute, limiting their applicability to sparse, unordered image collections. We propose Geo-ID, a novel test-time framework that repurposes pretrained single-view intrinsic predictors to produce cross-view consistent decompositions by coupling independent per-view predictions through sparse geometric correspondences that form uncertainty-aware consensus targets. Geo-ID is model-agnostic, requires no retraining or inverse rendering, and applies directly to off-the-shelf intrinsic predictors. Experiments on synthetic benchmarks and real-world scenes demonstrate substantial improvements in cross-view intrinsic consistency as the number of views increases, while maintaining comparable single-view decomposition performance. We further show that the resulting consistent intrinsics enable coherent appearance editing and relighting in downstream neural scene representations.
Authors: Yunuo Chen, Chuqin Zhou, Jiangchuan Li, Xiaoyue Ling, Bing He, Jincheng Dai, Li Song, Guo Lu
Abstract: We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a compact anchor frame, which preserves the scene geometry and semantic layout while discarding high-frequency details. We then reinterpret generative decoding as a virtual temporal transition from this anchor to the final reconstructed image. To model this progression, we leverage a pretrained video diffusion model (VDM) as a temporal prior: the anchor frame serves as the initial frame and the original image as the target frame, transforming the decoding process into a next-frame prediction task. In contrast to image diffusion-based ULB-IC models, our decoding proceeds from a visible, semantically faithful anchor, which improves both fidelity and realism for perceptual image compression. Extensive experiments demonstrate that our method achieves superior rate-distortion performance. On the CLIC2020 test set, our method achieves over 50% bitrate savings across LPIPS, DISTS, FID, and KID compared to DiffC, while also delivering a significant decoding speedup of up to $\times$5. Code will be released at https://github.com/UnoC-727/NeFIC.
Authors: Kim Ouan, No\'emie Moreau, Katarzyna Bozek
Abstract: The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity heavily rely on expensive segmentation maps of these nerve fibers. In this paper, we demonstrate that self-supervised pretrained features from ImageNet are transferable to the domain of in vivo confocal microscopy. We show that DINO should not be disregarded as a deep learning model for medical imaging, although it was superseded by two later versions. After careful fine-tuning, DINO improves upon the state-of-the-art in terms of accuracy (84,25%) and sensitivity (77,97%). Our fine-tuned model focuses on the key morphological elements in grading without the use of segmentation maps.
Authors: Hui Shan, Keyang Luo, Ming Li, Sizhe Zheng, Yanwei Fu, Zhen Chen, Xiangru Huang
Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often degrade geometric details in hidden regions and fail to preserve the underlying object-object spatial relationships (OOR). We present a novel framework Interact3D designed to generate physically plausible interacting 3D compositional objects. Our approach first leverages advanced generative priors to curate high-quality individual assets with a unified 3D guidance scene. To physically compose these assets, we then introduce a robust two-stage composition pipeline. Based on the 3D guidance scene, the primary object is anchored through precise global-to-local geometric alignment (registration), while subsequent geometries are integrated using a differentiable Signed Distance Field (SDF)-based optimization that explicitly penalizes geometry intersections. To reduce challenging collisions, we further deploy a closed-loop, agentic refinement strategy. A Vision-Language Model (VLM) autonomously analyzes multi-view renderings of the composed scene, formulates targeted corrective prompts, and guides an image editing module to iteratively self-correct the generation pipeline. Extensive experiments demonstrate that Interact3D successfully produces promising collsion-aware compositions with improved geometric fidelity and consistent spatial relationships.
Authors: Rasul Khanbayov, Mohamed Rayan Barhdadi, Erchin Serpedin, Hasan Kurban
Abstract: Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 240 real-world videos captured at 4K resolution and 60fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released.
Authors: Yuhan Chen, Yicui Shi, Guofa Li, Liping Zhang, Jie Li, Jiaxin Gao, Wenbo Chu
Abstract: Skeleton-based action recognition is widely applied in sensor-based systems, including human-computer interaction and intelligent surveillance. However, typical sensors produce sparse and discrete joint coordinates, often leading to the loss of fine-grained spatiotemporal information during dynamic movements. Furthermore, predefined physical topologies restrict modeling potential long-range dependencies. To address these challenges, we propose KGS-GCN, which integrates kinematics-driven Gaussian splatting and probabilistic topology within a graph convolutional network. A Gaussian splatting module constructs anisotropic covariance matrices by extracting instantaneous joint velocity vectors, rendering sparse skeleton sequences into multi-view continuous heatmaps rich in spatiotemporal semantics. Additionally, a probabilistic topology construction strategy transcends physical connectivity limitations by utilizing the Bhattacharyya distance to quantify statistical correlations between joint Gaussian distributions, generating an adaptive prior adjacency matrix. Finally, the lightweight multi-view rendering branch and topological GCN backbone are unified through a visual context gating mechanism, enabling seamless fusion of continuous dynamic cues with structural priors while maintaining high computational efficiency, requiring only 1.4M parameters and 1.3 GFLOPs. Extensive experiments on multiple benchmark datasets demonstrate that KGS-GCN significantly enhances the modeling of complex spatiotemporal dynamics and achieves competitive performance at low computational cost, establishing an efficient paradigm for improving the perceptual robustness of low-fidelity sensor data.
Authors: Markus Gross, Sai Bharadhwaj Matha, Rui Song, Viswanathan Muthuveerappan, Conrad Christoph, Julius Huber, Daniel Cremers
Abstract: Semantic segmentation for uncrewed aerial vehicles (UAVs) is fundamental for aerial scene understanding, yet existing RGB and RGB-T datasets remain limited in scale, diversity, and annotation efficiency due to the high cost of manual labeling and the difficulties of accurate RGB-T alignment on off-the-shelf UAVs. To address these challenges, we propose a scalable geometry-driven 2D-3D-2D paradigm that leverages multi-view redundancy in high-overlap aerial imagery to automatically propagate labels from a small subset of manually annotated RGB images to both RGB and thermal modalities within a unified framework. By lifting less than 3% of RGB images into a semantic 3D point cloud and rendering it into all views, our approach enables dense pseudo ground-truth generation across large image collections, automatically producing 97% of RGB labels and 100% of thermal labels while achieving 91% and 88% annotation accuracy without any 2D manual refinement. We further extend this 2D-3D-2D paradigm to cross-modal image registration, using 3D geometry as an intermediate alignment space to obtain fully automatic, strong pixel-level RGB-T alignment with 87% registration accuracy and no hardware-level synchronization. Applying our framework to existing geo-referenced aerial imagery, we construct SegFly, a large-scale benchmark with over 20,000 high-resolution RGB images and more than 15,000 geometrically aligned RGB-T pairs spanning diverse urban, industrial, and rural environments across multiple altitudes and seasons. On SegFly, we establish the Firefly baseline for RGB and thermal semantic segmentation and show that both conventional architectures and vision foundation models benefit substantially from SegFly supervision, highlighting the potential of geometry-driven 2D-3D-2D pipelines for scalable multi-modal aerial scene understanding. Data and Code available at https://github.com/markus-42/SegFly.
Authors: Telang Xu, Chaoyang Zhang, Guangtao Zhai, Xiaohong Liu
Abstract: Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit priors for spatially adaptive conditioning and structurally faithful restoration. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO.
Authors: Ilia Sudakov, Artem Babenko, Dmitry Baranchuk
Abstract: Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit visual AR-based generative classifiers and identify an important limitation of prior approaches: their reliance on a fixed token order, which imposes a restrictive inductive bias for image understanding. We observe that single-order predictions rely more on partial discriminative cues, while averaging over multiple token orders provides a more comprehensive signal. Based on this insight, we leverage recent any-order AR models to estimate order-marginalized predictions, unlocking the high classification potential of AR models. Our approach consistently outperforms diffusion-based classifiers across diverse image classification benchmarks, while being up to 25x more efficient. Compared to state-of-the-art self-supervised discriminative models, our method delivers competitive classification performance - a notable achievement for generative classifiers.
Authors: Gia-Bao Doan, Nam-Khoa Huynh, Minh-Nhat-Huy Ho, Khanh-Thanh-Khoa Nguyen, Thi-Thu-Hien Pham, Thanh-Hai Le
Abstract: The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization techniques often struggle to balance accuracy with computational efficiency. In this work, we develop and evaluate a temporal action localization framework tailored for driver monitoring scenarios, particularly suitable for periodic inspection settings such as transportation safety checkpoints or fleet management assessment systems. Our approach follows a two-stage pipeline that combines VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector, enhanced by a Spatial Pyramid Pooling-Fast (SPPF) module to capture multi-scale temporal features. Experimental results reveal a distinct trade-off between model capacity and efficiency. At the feature extraction stage, the ViT-Giant backbone delivers higher representations with 88.09% Top-1 test accuracy, while the ViT-based variant proves to be a practical alternative, achieving 82.55% accuracy with significantly lower computational fine-tuning costs (101.85 GFLOPs/segment compared to 1584.06 GFLOPs/segment for Giant). In the downstream localization task, the integration of SPPF consistently improves performance across all configurations. Notably, the ViT-Giant + SPPF model achieves a peak mAP of 92.67%, while the lightweight ViT-based configuration maintains robust results.
Authors: Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna, Sai Praneeth Karimireddy, Rahul Gupta, Shrikanth Narayanan
Abstract: Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations. We introduce the Compositional Privacy Risk Taxonomy (CPRT), a regulation-aware framework that organizes visual attributes according to standalone identifiability and compositional harm potential. CPRT defines four graded severity levels and is paired with an interpretable scoring function that assigns continuous privacy severity scores. We further construct a taxonomy-aligned dataset of 6.7K images and derive compositional risk scores. By evaluating frontier and open-weight VLMs we find that frontier models align well with compositional severity when provided structured guidance, but systematically underestimate composition-driven risks. Smaller models struggle to internalize graded privacy reasoning. To bridge this gap, we introduce a deployable 8B SFT model that closely matches frontier-level performance on compositional privacy assessment
Authors: Fulvio Sanguigni, Davide Lobba, Bin Ren, Marcella Cornia, Nicu Sebe, Rita Cucchiara
Abstract: Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, existing datasets remain static, lacking instruction-driven editing for controllable and interactive fashion generation. In this work, we introduce the Dress Editing Dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing within a single framework. Each sample in Dress-ED includes an in-shop garment image, the corresponding person image wearing the garment, their edited counterparts, and a natural-language instruction of the desired modification. Built through a fully automated multimodal pipeline that integrates MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification, Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types, including both appearance (e.g., color, pattern, material) and structural (e.g., sleeve length, neckline) modifications. Based on this benchmark, we further propose a unified multimodal diffusion framework that jointly reasons over linguistic instructions and visual garment cues, serving as a strong baseline for instruction-driven VTON and VTOFF. Dataset and code available at this link: https://github.com/aimagelab/Dress-ED
Authors: Jingchen Ni, Quan Zhang, Dan Jiang, Keyu Lv, Ke Zhang, Chun Yuan
Abstract: Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods, existing weakly-supervised COD methods exhibit significantly poorer performance. Even for the Segment Anything Model (SAM), there are still challenges in handling weakly-supervised camouflage object detection (WSCOD), such as: a. non-camouflage target responses, b. local responses, c. extreme responses, and d. lack of refined boundary awareness, which leads to unsatisfactory results in camouflage scenes. To alleviate these issues, we propose a frequency-aware and contrastive learning-based WSCOD framework in this paper, named FCL-COD. To mitigate the problem of non-camouflaged object responses, we propose the Frequency-aware Low-rank Adaptation (FoRA) method, which incorporates frequency-aware camouflage scene knowledge into SAM. To overcome the challenges of local and extreme responses, we introduce a gradient-aware contrastive learning approach that effectively delineates precise foreground-background boundaries. Additionally, to address the lack of refined boundary perception, we present a multi-scale frequency-aware representation learning strategy that facilitates the modeling of more refined boundaries. We validate the effectiveness of our approach through extensive empirical experiments on three widely recognized COD benchmarks. The results confirm that our method surpasses both state-of-the-art weakly supervised and even fully supervised techniques.
Authors: Nicolas von L\"utzow, Barbara R\"ossle, Katharina Schmid, Matthias Nie{\ss}ner
Abstract: Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial structure and appearance. Unlike diffusion-based methods that refine scenes holistically, our formulation constructs scenes step-by-step, naturally supporting completion, outpainting, controllable sampling via temperature, and flexible generation horizons. This formulation leverages the compositional inductive biases and scalability of autoregressive modeling while operating on explicit representations compatible with modern neural rendering pipelines, positioning autoregressive transformers as a complementary paradigm for controllable and context-aware 3D generation.
Authors: Biswadeep Sen, Benoit R. Cottereau, Nicolas Cuperlier, Terence Sim
Abstract: Event-based cameras capture visual information as asynchronous streams of per-pixel brightness changes, generating sparse, temporally precise data. Compared to conventional frame-based sensors, they offer significant advantages in capturing high-speed dynamics while consuming substantially less power. Predicting future event representations from past observations is an important problem, enabling downstream tasks such as future semantic segmentation or object tracking without requiring access to future sensor measurements. While recent state-of-the-art approaches achieve strong performance, they often rely on computationally heavy backbones and, in some cases, large-scale pretraining, limiting their applicability in resource-constrained scenarios. In this work, we introduce E-TIDE, a lightweight, end-to-end trainable architecture for event-tensor prediction that is designed to operate efficiently without large-scale pretraining. Our approach employs the TIDE module (Temporal Interaction for Dynamic Events), motivated by efficient spatiotemporal interaction design for sparse event tensors, to capture temporal dependencies via large-kernel mixing and activity-aware gating while maintaining low computational complexity. Experiments on standard event-based datasets demonstrate that our method achieves competitive performance with significantly reduced model size and training requirements, making it well-suited for real-time deployment under tight latency and memory budgets.
Authors: Jinkun Hao, Mingda Jia, Ruiyan Wang, Hongrui Zhu, Jiafei Cao, Xihui Liu, Ran Yi, Lizhuang Ma, Jiangmiao Pang, Xudong Xu
Abstract: We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either lack explicit 3D grounding, causing structural drift under viewpoint changes, or treat the scene as static, failing to update world states across multi-stage interactions. EgoSim addresses both limitations by modeling 3D scenes as updatable world states. We generate embodiment interactions via a Geometry-action-aware Observation Simulation model, with spatial consistency from an Interaction-aware State Updating module. To overcome the critical data bottleneck posed by the difficulty in acquiring densely aligned scene-interaction training pairs, we design a scalable pipeline that extracts static point clouds, camera trajectories, and embodiment actions from in-the-wild large-scale monocular egocentric videos. We further introduce EgoCap, a capture system that enables low-cost real-world data collection with uncalibrated smartphones. Extensive experiments demonstrate that EgoSim significantly outperforms existing methods in terms of visual quality, spatial consistency, and generalization to complex scenes and in-the-wild dexterous interactions, while supporting cross-embodiment transfer to robotic manipulation. Codes and datasets will be open soon. The project page is at egosimulator.github.io.
Authors: Yuan Qing, Kunyu Zheng, Lingxiao Li, Boqing Gong, Chang Xiao
Abstract: Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a physics-based authentication signature that real cameras produce naturally, but that generative models cannot faithfully reproduce. Our approach exploits the Moir\'e effect: the interference fringes formed when a camera views a compact two-layer grating structure. We derive the Moir\'e motion invariant, showing that fringe phase and grating image displacement are linearly coupled by optical geometry, independent of viewing distance and grating structure. A verifier extracts both signals from video and tests their correlation. We validate the invariant on both real-captured and AI-generated videos from multiple state-of-the-art generators, and find that real and AI-generated videos produce significantly different correlation signatures, suggesting a robust means of differentiating them. Our work demonstrates that deterministic optical phenomena can serve as physically grounded, verifiable signatures against AI-generated video.
Authors: Xingtong Ge, Yi Zhang, Yushi Huang, Dailan He, Xiahong Wang, Bingqi Ma, Guanglu Song, Yu Liu, Jun Zhang
Abstract: Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency distillation often becomes conservative under complex video dynamics, yielding an over-smoothed appearance and weak motion. Distribution matching distillation (DMD) can recover sharp, mode-seeking samples, but its local training signals do not explicitly regularize how denoising updates compose across timesteps, making composed rollouts prone to drift. To overcome this challenge, we propose Self-Consistent Distribution Matching Distillation (SC-DMD), which explicitly regularizes the endpoint-consistent composition of consecutive denoising updates. For real-time autoregressive video generation, we further treat the KV cache as a quality parameterized condition and propose Cache-Distribution-Aware training. This training scheme applies SC-DMD over multi-step rollouts and introduces a cache-conditioned feature alignment objective that steers low-quality outputs toward high-quality references. Across extensive experiments on both non-autoregressive backbones (e.g., Wan~2.1) and autoregressive real-time paradigms (e.g., Self Forcing), our method, dubbed \textbf{Salt}, consistently improves low-NFE video generation quality while remaining compatible with diverse KV-cache memory mechanisms. Project page: https://xingtongge.github.io/Salt
Authors: Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui, Hongwei Xie, Guang Chen, Hangjun Ye, Michael Ying Yang, Francesco Nex, Hao Cheng
Abstract: Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor domains, and environmental conditions. Recent world-model-based planning methods have shown strong capabilities in scene understanding and multi-modal future prediction, yet their generalization across datasets and sensor configurations remains limited. In addition, their loosely coupled planning paradigm often leads to poor video-trajectory consistency during visual imagination. To overcome these limitations, we propose DriveVA, a novel autonomous driving world model that jointly decodes future visual forecasts and action sequences in a shared latent generative process. DriveVA inherits rich priors on motion dynamics and physical plausibility from well-pretrained large-scale video generation models to capture continuous spatiotemporal evolution and causal interaction patterns. To this end, DriveVA employs a DiT-based decoder to jointly predict future action sequences (trajectories) and videos, enabling tighter alignment between planning and scene evolution. We also introduce a video continuation strategy to strengthen long-duration rollout consistency. DriveVA achieves an impressive PDM-based planning performance of 90.9 PDM score on the NAVSIM benchmark. Extensive experiments also demonstrate the zero-shot capability and cross-domain generalization of DriveVA, which reduces average L2 error and collision rate by 78.9% and 83.3% on nuScenes and 52.5% and 52.4% on the Bench2Drive built on CARLA v2 compared with the state-of-the-art world-model-based planner.
Authors: Hina Kogure, Kei Katsumata, Taiki Miyanishi, Komei Sugiura
Abstract: Dynamic urban environments are often captured by cameras placed at spatially separated locations with little or no view overlap. However, most existing 4D reconstruction methods assume densely overlapping views and struggle under sparse multi-location observations, producing unstable reconstructions in unobserved intermediate regions. To address this practical yet underexplored setting, we propose Stitch4D, a unified 4D reconstruction framework that compensates for missing spatial coverage in sparsely observed urban environments. Stitch4D synthesizes intermediate bridge views between distant camera locations and jointly optimizes real and synthesized observations in a unified coordinate frame with inter-location consistency constraints. By recovering intermediate spatial coverage before optimization, Stitch4D mitigates geometric collapse and improves reconstruction stability in sparse regions. To evaluate this setting, we introduce Urban Sparse 4D (U-S4D), a controlled CARLA-based benchmark for free-viewpoint reconstruction under sparse multi-location configurations. Experiments on U-S4D show that Stitch4D consistently outperforms representative 4D reconstruction baselines in image-quality metrics. These results suggest that recovering intermediate spatial coverage is an effective strategy for stabilizing 4D reconstruction in sparse urban environments. The project page is provided in https://stitch4d-project-page.vercel.app/.
Authors: Mohammad Mahdi, Nedko Savov, Danda Pani Paudel, Luc Van Gool
Abstract: Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired supervision is available, synchronized exo-ego data inherently introduces substantial spatio-temporal and geometric discontinuities, violating the smooth-motion assumptions of standard video generation benchmarks. We identify this synchronization-induced jump as the central challenge and propose Syn2Seq-Forcing, a sequential formulation that interpolates between the source and target videos to form a single continuous signal. By reframing Exo2Ego as sequential signal modeling rather than a conventional condition-output task, our approach enables diffusion-based sequence models, e.g. Diffusion Forcing Transformers (DFoT), to capture coherent transitions across frames more effectively. Empirically, we show that interpolating only the videos, without performing pose interpolation already produces significant improvements, emphasizing that the dominant difficulty arises from spatio-temporal discontinuities. Beyond immediate performance gains, this formulation establishes a general and flexible framework capable of unifying both Exo2Ego and Ego2Exo generation within a single continuous sequence model, providing a principled foundation for future research in cross-view video synthesis.
Authors: Ahmed Marouane Djouamaa, Abir Belaala, Abdellah Zakaria Sellam, Salah Eddine Bekhouche, Cosimo Distante, Abdenour Hadid
Abstract: Accurate medical image segmentation requires both long-range contextual reasoning and precise boundary delineation, a task where existing transformer- and diffusion-based paradigms are frequently bottlenecked by quadratic computational complexity and prohibitive inference latency. We propose RF-HiT, a Rectified Flow Hierarchical Transformer that integrates an Hourglass Transformer backbone with a multi-scale hierarchical encoder for anatomically guided feature conditioning. Unlike prior diffusion-based approaches that rely on hundreds of denoising steps, RF-HiT leverages rectified flow with efficient transformer blocks, achieving linear complexity and requiring only a few discretization steps. The model further fuses conditioning features at each resolution via learnable interpolation, enabling effective multi-scale feature integration with minimal computational overhead. As a result, RF-HiT achieves a strong efficiency-performance trade-off, requiring only 10.14 GFLOPs, 13.6M parameters, and inference in as few as 3 steps. Despite its compact design, RF-HiT attains 91.27% mean Dice on ACDC and 87.40% on BraTS 2021, achieving performance comparable to or exceeding that of significantly more intensive architectures. These results suggest that RF-HiT is a promising, computationally efficient foundation for clinical image segmentation.
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 performs downstream tasks, such as 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 at https://papers.starslab.ca/realm/.
Authors: Junyuan Xiao, Dingkang Liang, Xin Zhou, Yixuan Ye, Tongtong Su, Guangmo Yi, Bin Xia, Qiang Lyu, Shurui Shi, Jun Huang, Jianlou Si, Wenming Yang
Abstract: Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose $M^2$-REPA, the first representation alignment method tailored for multi-modal video generation. Our key insight is that foundation models trained on different modality spaces naturally capture distinct domain-specific priors, acting as complementary "experts." Specifically, we first decouple modality-specific features from the diffusion model's intermediate representations, then align each with its corresponding expert foundation model. To this end, we design two synergistic objectives: a multi-modal representation alignment loss that enforces feature-to-expert matching, and a modality-specific decoupling regularization that encourages complementarity across different modalities. This design enables joint optimization, fully exploiting priors from multiple foundation models. Extensive experiments demonstrate that our method significantly outperforms baselines in visual quality and long-term consistency.
Authors: Lucas Yunkyu Lee, Soonho Kim, Youngwook Kim, Sangmin Kim, Jaesik Park
Abstract: Recent progress in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction results. While these methods demonstrate remarkable performance, the specific factors behind their gains remain underexplored, making a systematic understanding of the underlying principles challenging. In this paper, we perform a comprehensive analysis of these hidden factors to provide a clearer perspective on the 4DGS framework. We first establish a controlled baseline, FreeTimeGS_ours, by formalizing and reproducing the heuristics of the state-of-the-art FreeTimeGS. Using this framework, we examine 4DGS along its fundamental axes and identify practical secrets, including the emergent temporal partitioning driven by Gaussian durations and the decoupling between photometric fidelity and motion behavior. Based on these insights, we propose FreeTimeGS++, a principled method that employs gated marginalization, UFM-guided initialization, and color correction to improve stability and reproducibility. Our approach yields reproducible results with reduced run-to-run variance.
Authors: Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi, Fabio Maninchedda, Dmitry Kostiaev, Artem Sevastopolsky, Vittorio Megaro, Trevor Phillips, Alejandro Blumentals, Shridhar Ravikumar, Mehak Gupta, Reinhard Knothe, Jeronimo Bayer, Matthias Vestner, Simon Schaefer, Thomas Etterlin, Christian Zimmermann, Alexey Artemov, Mathias Deschler, Peter Kaufmann, Stefan Brugger, Sebastian Martin, Brian Amberg, Tom Runia
Abstract: We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.
Authors: Francisco Chen, Yiran Wang, Yunpeng Shi
Abstract: Pairwise translation directions are a key input to camera location estimation in global structure-from-motion. Existing estimators usually process each image pair independently, producing directions that may be locally plausible but inconsistent with the other relative directions in the viewing graph. To jointly estimate the direction, we propose TriDE, which exploits camera-triangle consistency as an efficient higher-order verification signal. Instead of solving a costly global nonlinear optimization problem that is sensitive to initialization, TriDE refines unreliable pairwise directions through message passing between directions and their incident weighted triangles. This information propagation strategy enables us to establish a strong phase-transition bound for exact recovery under a realistic random corruption model. Experiments on real image graphs show that TriDE improves direction accuracy by a large margin and yields better downstream camera locations, providing a practical link between local pairwise estimation and global camera pose geometry.
Authors: Johnny Corbino
Abstract: Adversarial attacks fool deep image classifiers by adding tiny, almost invisible noise patterns to a clean image. The standard $\ell^\infty$-bounded attacks (FGSM and PGD) produce high-frequency, near-random sign patterns at the pixel level: small in $\ell^2$, but carrying disproportionate gradient energy. We exploit this with a single-shot, training-free detector using the high-order Corbino-Castillo mimetic operators from the open-source MOLE library. No retraining, no surrogate classifier, no access to the network under attack: the verdict is a property of the input alone, computed in $O(HW)$ time. We illustrate the detector on the standard "peppers" test image: untargeted FGSM and PGD attacks at the $\ell^\infty$ budget $\varepsilon = 16/255$ flip SqueezeNet's prediction from "bell pepper" to "doormat" (FGSM) and "maraca" (PGD), and the detector separates these adversarial inputs from the clean image by $4.1\times$-$5.0\times$ (FGSM) and $1.9\times$-$2.2\times$ (PGD). The margin grows monotonically with the operator order $k$, while an equal-amplitude smooth perturbation leaves the statistic within 1% of its clean value.
Authors: Mohamed Ahmed Mohamed, Xiaowei Huang
Abstract: Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In this paper, we propose Clear2Fog (C2F), an end-to-end, physics-based pipeline that simulates fog on clear-weather datasets while ensuring cross-modal consistency across camera and LiDAR. C2F combines monocular depth estimation with a novel atmospheric light estimation method to improve the physical consistency of synthetic fog generation while reducing structural artifacts and chromatic biases observed in existing frameworks. Utilising a training set of 270,000 images from the Waymo Open Dataset, we conduct an extensive data efficiency study to investigate whether environmental diversity can reduce dataset scale requirements and improve model generalisation under varying fog conditions. Our findings reveal that models trained on mixed-density fog datasets at 75% scale achieve comparable detection performance to those trained on fixed-density datasets at 100% scale, reducing synthetic training data requirements by 25%. We observe that this efficiency trend is consistent across two representative detector architectures. Furthermore, we investigate the sim-to-real transfer by using C2F-generated data as a pre-training foundation before fine-tuning on real-world fog data. We demonstrate that, within the evaluated settings, a relative 10x increase in the default fine-tuning learning rate reduces the negative transfer caused by standard fine-tuning, achieving up to a 1.17 mAP point improvement beyond the real-only baseline. Overall, this work demonstrates the value of diverse synthetic fog as a pre-training tool for real-world adaptation.
Authors: Li Pang, Heng Zhao, Yijia Zhang, Deyu Meng, Xiangyong Cao
Abstract: Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real-world HSIs suffer from noise, blur, and resolution loss. However, existing models trained on source data often fail on target domains lacking clean references, a common real-world scenario. To address this, we present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances HSI restoration by augmenting limited training images with synthetic data matching the target distribution, without extra clean target-domain HSI data. It has three stages: (i) proxy generation, where off-the-shelf restoration models are applied to degraded target observations to produce semantics-preserving proxy HSIs that approximate clean target-domain images; (ii) distribution-adaptive synthesis, where a blur-robust unCLIP diffusion model generates target-aligned RGBs from proxy RGBs with prompt conditioning and embedding-space noise initialization. The warp-based spectral transfer module then synthesizes HSIs by aligning each generated RGB with its proxy RGB, estimating soft patch-wise transport weights, and applying these weights and learnable local interpolation kernels to the proxy HSI; and (iii) aligned supervised finetuning, where restoration networks pretrained on the source distribution are finetuned with proxy HSIs and synthesized target-aligned HSIs, then deployed on degraded target images. We also provide theoretical analysis showing that, under stated assumptions, the proposed augmentation-based finetuning obtains a tighter target-domain restoration-risk upper bound by jointly improving target-distribution coverage and controlling spectral bias. Experiments on simulated and real datasets across denoising, super-resolution, and other restoration tasks demonstrate that HIR-ALIGN is superior to proxy-only target-adaptation baselines and outperforms representative unsupervised methods in most cases.
Authors: Yulu Pan, Han Yi, Seongsu Ha, Md Mohaiminul Islam, Benjamin Zhang, Lorenzo Torresani, Gedas Bertasius
Abstract: True video intelligence demands more than recognizing what is visible: it requires reasoning about why events unfold, predicting what would change under different conditions, and deciding what to do next. We refer to this progression, from perception through causal reasoning and simulation to strategic planning, as Strategic Video Intelligence (SVI). No existing benchmark evaluates this capability stack: in-the-wild videos lack verifiable ground truth for causal and strategic questions, while synthetic environments sacrifice the complexity of real multi-agent systems. To bridge this gap, we introduce SVI-Bench, a large-scale benchmark that leverages team sports as a dynamic microworld, combining the complexity of real-world multi-agent interaction (10-22 agents making coordinated decisions under adversarial pressure) with the verifiability of explicit rules and definitive outcomes. SVI-Bench comprises approximately 35K hours of broadcast video, 15M annotated actions, 15K hours of expert commentary, 23K game reports, and 103K structured statistical records across basketball, soccer, and hockey, all constructed via a data engine that transforms raw game data into a dense, cross-referenced corpus. We organize evaluation into 9 tasks spanning a progressive four-pillar hierarchy: Dynamic Scene Understanding, Causal Reasoning, Strategic Simulation, and Agentic Synthesis. Evaluating strong multimodal and agentic baselines, we find a capability cliff: models perform competently on perceptual tasks, achieving approximately 74% on fine-grained action QA, but degrade sharply at each successive cognitive level. Agentic tasks prove hardest: the strongest model achieves only 5% accuracy when required to autonomously gather and integrate evidence across a corpus of 1.8M clips.
Authors: Olaf D\"unkel, Basavaraj Sunagad, Haoran Wang, David T. Hoffmann, Christian Theobalt, Adam Kortylewski
Abstract: Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-level supervision. Semantic correspondence (SC) evaluates this capability by testing whether object parts can be matched across instances and categories under large variations in appearance, viewpoint, and geometry. To enable a systematic SC evaluation, we introduce SOCO, a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. In addition, SOCO includes keypoint language descriptions, enabling the evaluation of large vision-language models (LVLMs) and their fine-grained part-level understanding. Comprehensive experiments reveal that (i) vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories and only partially capture object-part position, (ii) LVLMs are stronger at text-prompted part localization than at visual-reference cross-image matching, exposing a gap between language-grounded localization and fine-grained visual correspondence, and (iii) correspondence performance predicts performance on dense downstream tasks, including segmentation, tracking, 3D pose estimation, and 3D detection, more strongly than ImageNet classification. Together, these findings position SOCO as a benchmark for structured, part-level representation quality in vision and multimodal foundation models.
Authors: Duoduo Xue, Zhiyu Zhu, Junhui Hou
Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterization space. To achieve this, we propose the Data Manifold-aware Image diffusioN moDel (MIND), a novel framework that explicitly models manifold geometry by integrating discrete patch tokenization into the score function of a continuous diffusion model. This approach successfully leverages both the structural quantification capabilities of discrete tokens and the parallel generation flexibility of continuous diffusion. Moreover, we enable end-to-end differentiable training via a novel soft top-$k$ aggregation mechanism and introduce dual-branch high-frequency feature embedding layers to alleviate the spectral bias of transformer backbones on low-dimensional inputs. Furthermore, for inference, we design a multi-stage transition sampling scheme that dynamically adjusts the sampling scheme based on timestep. Extensive experiments on ImageNet 256$\times$256 demonstrate the effectiveness of MIND. After 80-epoch training, our base model achieves an FID of 22.73 without guidance, nearly halving the 43.47 FID of the vanilla DiT-B/2 baseline. The proposed method reduces FID by 15.95 and 9.06 on average compared with the baselines DiT and SiT, respectively. For image generation on ImageNet-256$\times$256 with guidance, the proposed MIND-B with only 130M parameters achieves an FID of 2.06, superpassing the LlamaGen-3B with 3.1B parameters. The proposed MIND-XL with 715M parameters further reduces the FID to 1.95. Our MIND introduces a fresh perspective on diffusion-based image generation, paving the way for future research and innovation in this community. The code will be publicly available.
Authors: Chaodong Jia, Zequn Xie, Xibei Jia, Sihang Cai, Shulei Wang, Tao Jin
Abstract: Text-Based Person Search (TBPS) aims to retrieve pedestrian images using natural language queries. However, existing TBPS models, especially those based on CLIP, struggle with fine-grained understanding due to global representational bias and semantic sparsity inherited from training on short captions. This results in weak fine-grained alignment, exacerbated by the scarcity of region-level annotations. To address this, we propose ROGLE (Robust Global-Local Embedding), a unified framework that overcomes reliance on costly manual annotations through an automated Region-to-Sentence Matching (RSM) strategy. RSM automatically mines pseudo region-sentence pairs for scalable fine-grained supervision. Furthermore, ROGLE employs a multi-granular learning strategy that fuses global contrastive learning with region-level local alignment. We also introduce the P-VLG Benchmark, a large-scale dataset constructed by curating and enriching images from established public benchmarks. It features over 100,000 annotated regions and rich long-form captions, making it the first TBPS benchmark to support both global and local assessment protocols. Extensive experiments show that ROGLE significantly outperforms existing approaches, particularly on challenging long-form queries. Code and the P-VLG benchmark will be made publicly available.
Authors: Qian Zhang, Michal Golovanevsky, Fulvio Domini, James Tompkin
Abstract: Human perception of surface slant from texture exhibits systematic, graded biases that emerge reliably in psychophysical experiments. Prior work showed that unsupervised CNNs reproduce several human-like biases, while supervised CNNs do not. Do Vision-Language Models (VLMs) exhibit similar competences? Across multiple VLM families and model scales, zero-shot and in-context prompting both produce distinctive failures: slant is predicted at only a small set of anchors (e.g., 0\degree, $\pm$25\degree, $\pm$45\degree) with little dependence on stimulus field of view, optical slant, or surface curvature. Supervised fine-tuning partially remediates the failure, but residual anchoring persists. While success in high-level vision-language benchmarks might not require sensitivity to low-level geometric cues, we interpret anchoring as a failure at the representation-to-output language interface: not necessarily an absence of geometric encoding, but a failure to express it in a graded form.
Authors: Xuanyi Liu, Deyi Ji, Junyu Lu, Jing Wang, Lanyun Zhu, Qianxiong Xu, Xuhang Chen, Tianrun Chen, Siwei Ma
Abstract: Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As a result, the rewriter may over-infer missing details, causing an intent-generation gap. To address this limitation, we propose FaithRewriter, a novel prompt-enhancement framework for T2I generation. Specifically, FaithRewriter first leverages a multimodal MLLM to generate an image from the original prompt as an intermediate visual cue. This cue is then combined with the prompt and fed into a large-scale LLM to produce visually grounded augmentations that better reflect how the intended content should appear in images. Finally, these augmentations are distilled into a small-scale LLM for efficient deployment, enhancing its ability to generate effective T2I prompts. Experiments show that FaithRewriter yields prompts that are more faithful to the user intent and more visually plausible than strong baselines, helping narrow the intent-generation gap.
Authors: Xiaomeng Yang, Yanyu Li, Gordon Guocheng Qian, Ivan Skorokhodov, Viacheslav Ivanov, Avalon Vinella, Xuan Zhang, Yanzhi Wang, Sergey Tulyakov, Anil Kag
Abstract: While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring substantial data curation and iterative optimization costs that hinder interactive control. We present Prompt2Effect, a weight-driven hypernetwork that amortizes per-effect training by directly synthesizing effect-specific LoRA weights in a single forward pass. Unlike prior hypernetworks that regress adapter weights purely from semantics, Prompt2Effect is explicitly conditioned on the frozen base model weights, grounding prediction in the structural geometry of each layer. Furthermore, instead of predicting raw LoRA matrices, we introduce an SVD-canonicalized parameterization that resolves factorization ambiguity and stabilizes large-scale synthesis. Extensive experiments demonstrate that Prompt2Effect achieves on-par or superior video quality and effect alignment compared to conventional LoRA fine-tuning, while reducing the computational cost from 56 GPU training hours to 3.3 seconds of hypernetwork inference. When used as initialization for subsequent fine-tuning, our predicted weights further improve final performance and accelerate optimization by approximately 10x.
Authors: Jo\~ao Cardeira, Diogo Gl\'oria-Silva, Manuel Letras da Luz, Rafael Ferreira, Diogo Tavares, David Semedo, Jo\~ao Magalh\~aes
Abstract: European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT focus on historical artifacts and literature. This work addresses modern OCR applications, introducing PorTEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction. To ascertain quality, we employ an annotation pipeline combining transcriptions from a frontier LVLM with exhaustive review by native speakers. We observe a sharp performance drop from synthetic to real world samples in most models, and find that, currently, specialized multilingual data is a better driver for pt-PT performance than model size or resolution budget, motivating the release of open pt-PT OCR resources.
Authors: Diogo Gl\'oria-Silva, Jo\~ao Cardeira, Manuel Letras da Luz, Afonso Simpl\'icio, Gon\c{c}alo Vinagre, Diogo Tavares, Rafael Ferreira, In\^es Calvo, In\^es Vieira, David Semedo, Jo\~ao Magalh\~aes
Abstract: Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open-source multimodal models, which either conflate it with Brazilian Portuguese or severely under-represent it in their training data mixes. We introduce AMALIA-VL, the first open-source instruction-tuned LVLM built natively for pt-PT, pairing a high-resolution vision encoder with dynamic image tiling and a fully open pt-PT-optimized language model via a learned connector. We contribute with a purposefully designed three-stage training process - vision-language alignment, general visual instruction tuning, and preference optimization - together with a pt-PT-centric multimodal data mix combining curated and translated public datasets with novel datasets that address the near-total absence of European Portuguese multimodal resources. Our evaluation shows that AMALIA-VL establishes a strong baseline for open-source pt-PT LVLMs. We will release model weights, training data, and construction pipelines along with machine-translated pt-PT evaluation benchmarks to help democratize pt-PT LVLM development.
Authors: Dong Yeong Kim, Jaewon Choi, Youmin Shin, JunGyu Lee, Myeongseop Kim, Jinwook Choi, Joo Whan Kim, Young-Gon Kim
Abstract: Computed Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused datasets.
Authors: Yi Xiao, Carlos Rodriguez Coronel, Jing Zhan, Haniyeh Ehsani Oskouie, Alex Wong, Dong Lao
Abstract: We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.
Authors: Xiangchen Yin, Wenzhang Sun, Jiahui Yuan, Zijie Liu, Yinda Chen, Wei Li, Dachun Kai, Chunfeng Wang, Xiaoyan Sun
Abstract: Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state video dataset that turns diverse videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable video world model that jointly controls the scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object controls with consistent scene structure while transferring scenes into diverse target weather states, outperforming video-to-video weather editing baselines on weather-state generation. Our project page is available at https://xiangchenyin.github.io/Holo-World/
Authors: Yubo Zhou, Jianghao Wu, Ping Ye, Shaoting Zhang, Guotai Wang
Abstract: Concept segmentation models like Segment Anything Model 3 (SAM3) show strong generalization on natural images, yet their performance degrades in medical imaging due to the domain gap caused by different imaging principles and styles. Test-Time Adaptation (TTA) is essential for improving the testing performance by updating the model on the fly without annotations. However, existing vision-language TTA methods are mainly driven by image-level uncertainty minimization, which does not necessarily reflect region-level semantic correctness in medical segmentation. Moreover, they often lack mechanisms to maintain stability in continual one-pass adaptation, leading to limited performance when reliable dense supervision is missing for segmentation. To address these issues, we propose Concept Alignment Contrast and LongShort Prompt Memory for Test-Time Adaptation (CM-TTA) of SAM3 for medical images. First, for a test sample with multiple augmentations, we introduce a novel Concept Alignment Contrast (CAC) metric, which leverages textual-visual semantic consistency to robustly evaluate prediction quality to select the best augmented view as the supervision. Second, to balance rapid and stable adaptation, we design a Long-Short Prompt Memory (LSPM) module. The short memory dynamically fuses recent prompts based on CAC scores for agile local adaptation, while the long memory maintains a stable global prompt to generate enhanced pseudo-labels. Finally, a Densely Supervised Prompt Update (DSPU) strategy is proposed to optimize the prompt embeddings with enhanced pseudo labels as dense supervision. Extensive experiments on prostate and skin lesion segmentation demonstrate that our CM-TTA framework significantly outperforms existing methods for TTA of SAM3. The code is available at https://github.com/SherlockZYB/CM-TTA.
Authors: Jiayi Lei, Yuandong Pu, Xingyu Han, Rongpeng Zhu, Jing Xu, Jinyao Wang, Zijian Zhou, Bin Fu, Yuewen Cao, Yihao Liu, Hongsheng Li
Abstract: Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspired by Russell's inductivist turkey, we introduce Counterfactual-World (CF-World), a counterfactual benchmark designed to investigate whether text-to-image models can generate images under rules that systematically contradict real-world priors. CF-World organizes each scenario into three progressive levels: factual generation under ordinary world knowledge, explicit counterfactual generation with direct visual instructions, and implicit counterfactual generation requiring causal deduction from altered rules. We evaluate both open-source and closed-source T2I models using a Vision Language Model (VLM)-based evaluator (CF-Eval). Furthermore, we introduce two metrics: Prior Resistance Rate (PRR), which measures a models' ability to overcome entrenched real-world priors, and Reasoning Retention Rate (RRR), which assesses whether models can maintain reasoning-dependent counterfactual generation without explicit visual cues. Experiments show that all models exhibit sharp degradation from factual to counterfactual settings. Further analyses suggest that these failures arise because current T2I models encode world knowledge and visual appearances as tightly coupled patterns. Consequently, their heavy reliance on frequent visual co-occurrences within the training data forces them to default to familiar commonsense priors when tasked with rendering counterfactual worlds.
Authors: Zhenyang Li, Lutao Jiang, Yizhou Zhao, Ying-Cong Chen, Xin Wang, Weikai Chen, Yifan Peng
Abstract: Reconstructing realistic, physically plausible garments from a single image remains a fundamental challenge. Template-free methods capture surface geometry but lack explicit sewing structure for simulation; while programmatic systems are simulation-ready but constrained by predefined templates. This reveals a fundamental representation gap between geometric reconstruction and structured garment construction. We present PatternGSL, a structured garment representation in the form of a template-free and learnable specification language that encodes complete sewing patterns, including panel boundaries, parameterized seams, and explicit stitch topology, in a compact and standardized form. PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling. We further propose a vision-language framework that predicts PatternGSL specifications directly from a single image and decodes them into garments using lightweight deterministic validity handling, without optimization-based refinement or manual cleanup. In addition, we introduce PatternGSLData, the first large-scale image-to-GSL paired dataset comprising 300K samples with complete sewing pattern annotations, enabling supervised VLM training for structured garment reconstruction. Experiments demonstrate improved pattern accuracy over prior baselines, explicit sewing-structure recovery, reliable cloth simulation, and pattern-level editing through the same deterministic decoding pipeline. Code and data-processing scripts will be released at https://lagrangeli.github.io/PatternGSL/.
Authors: Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu, Xueyang Li, Pin-Yu Chen, John Kheir, Meysam Ghaffari, Carlos Morato, Ahmed Abbasi, Yiyu Shi
Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation. In clinical practice, however, images are interpreted alongside structured records and metadata, and VLMs are increasingly deployed under joint image-record inputs. We uncover a previously underexamined multimodal vulnerability: when given both modalities, VLMs may overweight record context in authenticity judgments, such that the same image receives different predictions solely due to changes in its accompanying text. This raises concerns about robustness in real-world deployment. To systematically characterize this effect, we reformulate synthetic medical image detection as an audit of multimodal robustness at the image-record interface and introduce a paired benchmark that holds the image fixed while swapping controlled metadata variants. Across multiple imaging modalities, we evaluate diverse open-weight and frontier API VLMs and find that changing the metadata context alone can flip authenticity judgments, with accuracy on authentic images dropping by 61.1% on average under an explicit AI-origin tag. We further propose an inference-time mitigation pipeline that detects and neutralizes provenance shortcuts without model retraining, substantially outperforming direct prompt-based suppression on the affected subset. Our benchmark provides a standardized tool for assessing and improving multimodal robustness beyond image-only settings. Code and data will be released upon acceptance.
Authors: Haoyu Chen, Kaichen Zhou, Hang Hua, Kaile Zhang, Jingwen Qian, Wufei Ma, Haonan Chen, Chunjiang Liu, Yizhou Zhao, Xiaoyuan Wang, Weiyue Li, Alan Yuille, Paul Pu Liang, Yilun Du
Abstract: Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in view, and the few that force objects out of view evaluate static scenes where nothing changes during occlusion. To bridge this gap, we introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments: a target object undergoes a physical process, disappears from view, and must be correctly recovered in its updated state upon reappearance. We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment across four diagnostic pillars. Evaluation of eight state-of-the-art models reveals key insights and open challenges regarding memory consistency under the disappear-and-reappear paradigm.
Authors: Nan Yang, Zhanwen Liu, Linfeng Zhang, Shangyu Xie, Yang Wang, Wenzhuo Zhou, Xiangmo Zhao
Abstract: Vision-Language Models (VLMs) improve generalization and interpretability in autonomous driving but suffer from efficiency issues due to long visual token sequences, particularly in standard multi-view settings. Existing token pruning methods employ fixed pruning rate allocation and static importance metrics, ignoring dynamic inter-view importance differences and the evolving information importance during inference. Our analysis reveals that multi-view VLMs inherently encode task-related view priors in deeper layers and exhibit dynamic information requirements. Motivated by these findings, we propose MVPruner, a two-stage adaptive token pruning method that aligns pruning behavior with the model's dynamic information requirements. The first stage allocates pruning budgets based on the information diversity of each view, and retains tokens with consistent contribution across stages, ensuring semantic representational capacity. The second stage allocates budgets and selects tokens guided by instruction text to guarantee task alignment. Experimental results on four benchmarks demonstrate the superior performance of our method. For example, DriveMM equipped with MVPruner achieves 87.3% reduction in FLOPs, 4.97* speedup in prefilling phase while retaining 98.5% accuracy on DriveLM benchmark.
Authors: Matteo Farina, Vishaal Udandarao, Thao Nguyen, Selim Kuzucu, Maximilian B\"other, Andreas Hochlehnert, Adhiraj Ghosh, Marianna Nezhurina, Karsten Roth, Joschka Struber, Yuhui Zhang, Sebastian Dziadzio, Elaine Sui, Soumya Jahagirdar, Dhruba Ghosh, Hasan Hammoud, Thomas De Min, Simone Caldarella, Jehanzeb Mirza, Sedrick Keh, Mehdi Cherti, Hilde Kuehne, Bernt Schiele, Serena Yeung-Levy, Muhammad Ferjad Naeem, Federico Tombari, Ana Klimovic, Elisa Ricci, Matthias Bethge, Sewoong Oh, Ameya Prabhu, Alessio Tonioni, Jenia Jitsev, Massimiliano Mancini, Ludwig Schmidt, Nikhil Parthasarathy
Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies. We introduce DataComp for VLMs (DCVLM), a benchmark for controlled data-centric experiments to improve VLM training. As part of DCVLM, we collect 160 datasets spanning four data types -- image-caption pairs, multimodal interleaved documents, text-only, and instruction-tuning data -- into a corpus of 6T multimodal tokens. DCVLM allows participants to test curation strategies (filtering, mixing, formatting, sampling) across 1B-8B models and 6.25B-200B token budgets. Models are then evaluated on a carefully selected suite of up to 52 downstream benchmarks across 9 domains. We conduct extensive experiments on DCVLM and find that data mixing, not filtering, is key to a high-quality training dataset: instruction-heavy mixtures scale better than caption-heavy ones, with gains widening at larger scales. The resulting dataset, DCVLM-Baseline, enables training an 8B VLM to 63.6% accuracy on our 33-task core suite with 200B training tokens. Compared to FineVision, the state-of-the-art open VLM training dataset, this represents an improvement of +5.4pp. DCVLM and all accompanying artifacts will be made publicly available at https://www.datacomp.ai/dcvlm/.
Authors: Zhengyuan Li, Zeyun Deng, Yifan Shen, Liangyan Gui, Miaolan Xie, Joseph Campbell, Xifeng Gao, Kui Wu, Zherong Pan, Aniket Bera
Abstract: Self-collision remains a persistent challenge in SMPL-based human pose estimation and motion generation. Under extreme articulations or stochastic motion synthesis, generated meshes frequently exhibit self-penetrations, leading to physically implausible results. We propose PoseShield, a neural collision constraint defined directly in SMPL pose space. We formulate collision correction as a constrained optimization problem and connect the learned constraint with the Eikonal equation. Enforcing Eikonal regularization ensures non-vanishing gradients near the collision boundary, improving numerical stability and robustness of the optimization process. Unlike prior methods that operate in the mesh space or rely on heuristic penalties, our approach operates directly in the low-dimensional space of human poses and is theoretically grounded. The same learned constraint extends to human motion sequences, providing a generator-agnostic post-hoc collision corrector without retraining the underlying motion model. Experiments on a newly constructed SMPL pose benchmark show that our method achieves a 95.8% success rate and outperforms state-of-the-art baselines.
Authors: Chengzeng You, Binbin Xu, Soteris Demetriou
Abstract: The structural vulnerabilities of point cloud-based 3D object detectors remain poorly understood. Prior work has studied adversarial robustness primarily on isolated 3D object models, while recent LiDAR spoofing attacks target richer and more realistic driving scenes but focus mainly on physical realizability rather than understanding detector behavior or attack efficiency. In this work, we investigate how LiDAR-based detectors rely on spatial evidence in complex scenes and whether these reliance patterns can be exploited to induce failures more efficiently. To this end, we propose an explainability-guided adversarial analysis methodology. We introduce the Saliency-LiDAR (SALL) method, which aggregates Integrated Gradient attributions across scenes to produce universal saliency maps for LiDAR-based 3D object detectors. Guided by these maps, we design the Explainability-aware Frustum Attack (EFA), which selectively perturbs only the most influential frustums rather than uniformly attacking entire object regions. Experiments on KITTI and nuScenes, across detectors such as PointPillars and SECOND, show that EFA reduces detection recall by more than 15 percentage points while requiring 25-50% fewer perturbed frustums than the state-of-the-art non-saliency-aware baseline. These findings reveal that modern 3D detectors concentrate discriminative evidence in a small subset of spatial regions, exposing a structural robustness vulnerability in current LiDAR perception systems. Our code is released at https://github.com/SecMindLab/Saliency_LiDAR.
Authors: Deyin Liu, Jicheng Xu, Lin Yuanbo Wu, Xiaowei Zhao, Xiatian Zhu, Zhe Jin, Anjan Dutta
Abstract: Human image animation, which aims to generate a video of a reference subject following a provided action sequence, has received increasing research interest. With the development of diffusion-based/flow-based video foundation models, existing animation works have began to upgrade the guidance information from 2D skeleton/pose to 3D modeling conditions. Despite achieving reasonable results, these approaches face challenges in synthesizing trajectory-controllable human motion within natural scene under changed camera views. In this work, we present a scene-adaptive human image animation framework that controls both human motion and camera trajectories within a reconstructed 3D environment for video generation. To achieve this, we first develop a ground-adaptive 3D motion retargeting approach to enable user-friendly motion trajectory control adapting to the changes of elevations of ground and orientations automatically. Then we design a viewpoint-adaptive latent fusion mechanism to inject point-cloud geometric priors through scene-visibility masking into the generative process, providing precise guidance of viewpoint changes under camera control. Experiments on two standard human image animation benchmark datasets demonstrate remarkable improvements of our method over the state of the arts in related video generation metics. Project page: https://robinhood256100.github.io/web-disp
Authors: Rasul Khanbayov, Erchin Serpedin, Hasan Kurban
Abstract: Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that addresses all three challenges. First, a Graph Attention Task Head models anatomical concept co-occurrence, boosting macro-F1 by +13.8,pp over the prototype baseline on TBX11K. Second, a Concept-Mismatch Safety Check - the first such mechanism in prototype-based medical classifiers - warns when the model's dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of erroneous annotations versus 51% for MC-Dropout with no extra inference cost. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component. On NIH ChestX-ray14, one Effusion example recovers full-supervision localization accuracy; on TBX11K, prototype maps achieve 2.6x better lesion localization than end-to-end baselines. All three capabilities add only +1~ms latency at interactive batch size. The project page is https://github.com/KurbanIntelligenceLab/GRAPE.
Authors: Meng Yang, Zizhuo Li, Linfeng Tang, Fan Fan, Jiayi Ma
Abstract: Multi-modal image matching is essential for visual localization and multi-sensor fusion, but it is hindered by the scarcity of large-scale training data with precise geometric annotations. Existing real-world datasets suffer from prohibitive costs, limited scene diversity, and errors in SfM-MVS pipelines, while synthetic methods struggle to maintain 3D geometric consistency or achieve photorealistic appearance. To address this, we propose AnyMatch, a novel framework that leverages abundant, easily accessible single-view images at minimal cost to generate rich multi-modal training data. AnyMatch integrates monocular depth estimation, 3D reprojection, diffusion-based inpainting, and crossmodal image translation to synthesize multi-view, multi-modal image pairs with 3D geometric fidelity. Crucially, our method provides annotations that strictly adhere to 3D geometric consistency through explicit 3D reprojection, avoiding SfM-MVS error accumulation. Furthermore, AnyMatch offers strong scalability, enabling controllable scene diversity and annotation difficulty via adjustable input and camera parameters. We construct Any-syn, a large-scale synthetic multi-modal dataset using AnyMatch. Experimental results show that matching networks (e.g., LoFTR, EDM, RoMa) fine-tuned on Any-syn achieve substantial performance gains on multi-modal benchmarks, exhibiting superior generalization and robustness compared to models trained on existing data.
Authors: Wenjie Xue, Jun Yang, Jingmin Wang, Limin Shang
Abstract: Rolling-shutter cameras introduce characteristic distortions when imaging fast moving objects, and these effects are typically treated as artifacts to be corrected. In this work, we instead leverage rolling-shutter distortions as a valuable source of temporal information to estimate the 3D translational and angular velocities of rapidly moving spherical objects from a single rolling-shutter frame. We design a robust and easily detectable spherical pattern and propose a correspondence-free formulation that recovers motion by enforcing geometric consistency in a back-projection framework. By exploiting the geometry of the sphere, translational and rotational motions are decoupled and estimated through a two-stage optimization process, enabling reliable velocity recovery even for textureless objects. Extensive experiments on both synthetic and real datasets demonstrate accurate and robust estimation of motion parameters under challenging high-speed conditions.
Authors: Gabi Pragier, Matan Karklinsky, David Ungarish, Avi Ben-Cohen
Abstract: Structure from Motion (SfM) systems traditionally struggle with planar scenes, where standard epipolar geometry-based methods become degenerate. Rather than viewing planar surfaces as a limitation, we propose a unified framework that leverages them as a source of geometric constraints. Our key insight is that each planar surface visible across multiple views provides an independent estimate of relative camera poses through homography decomposition. By aggregating estimates from multiple planes or even from a single dominant plane we achieve robust pose recovery in scenarios where traditional methods fail. We introduce a novel graph-based approach that constructs a pose-graph from homography estimates and employs spectral embedding to identify and filter unreliable edges. Our method maps homography-based pose estimates onto the real line based on their geometric and visual consistency, enabling efficient extraction of a maximally consistent spanning tree for pose recovery. This approach naturally handles both highly planar scenes, such as indoor sports arenas, and general $3$D environments. We demonstrate superior performance on basketball court imagery where existing methods struggle, while matching or exceeding state-of-the-art results on unconstrained outdoor scenes from the IMC Phototourism benchmark.
Authors: Lisa Herzog, Jonas Br\"andli, Maurice Schneeberger, Loran Avci, Nordin Dari, Martin H\"ansel, Hakim Baazaoui, Pascal B\"uhler, Susanne Wegener, Beate Sick
Abstract: Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretability remains limited. We present multimodal Deep Transformation Models (DTMs) combining statistical approaches and neural networks to achieve strong predictive performance while preserving interpretability for tabular data. A key contribution of this work is the adaption of the xAI methods Grad-CAM and Occlusion to DTMs relying on 3D CNNs, enabling interpretation of the image branch through the generation of explanation maps. We developed DTMs to predict functional independence three months after stroke using diffusion-weighted imaging and clinical data from 407 patients. In a ten-fold cross-validation, the models achieved state-of-the-art predictive performance (AUC 0.81 [0.75, 0.87]) while maintaining interpretability for tabular features, with functional independence before stroke and stroke severity on admission emerging as the strongest predictors. Explanation maps from both xAI methods highlighted consistent regions, including frontal lobe areas which are known to be associated with age, a strong predictor of functional outcome. Notably, these regions disappeared once age was included as an explicit tabular predictor. Similarity analyses of explanation maps revealed distinct spatial patterns, providing meaningful insights into stroke pathophysiology, systematic error analysis and hypothesis generation.
Authors: Sanghyuk Chun, Olga Russakovsky
Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities. Most current approaches are built on the assumption of a deterministic one-to-one alignment between modalities. However, this oversimplifies real-world multimodal relationships, where their nature is inherently many-to-many. The many-to-many property, or multiplicity, is not a side-effect of noise or annotation error, but an inevitable outcome of intra-modal variability, representational asymmetry, and task-dependent ambiguity in multimodal tasks. We argue that multiplicity is a fundamental bottleneck that affects all stages of the multimodal learning pipeline: from data construction to model training and evaluation benchmarks. By formalizing its causes and consequences, we demonstrate how ignoring multiplicity leads to training uncertainty, unreliable evaluation, and degraded dataset quality. This position paper calls for new research directions on multimodal learning, including multiplicity-aware learning frameworks and dataset construction and evaluation protocols.
Authors: Tuan Nguyen, Sze Jue Yang, Khoa D. Doan, Chee Seng Chan, Kok-Seng Wong
Abstract: Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test. Such summaries can hide a different failure mode, in which one target label is activated by many trigger realizations. We study this failure mode with FLAT, a latent-conditioned reliability stress test for HFL backdoors. In FLAT, compromised clients still submit ordinary classifier updates to the server, while an attacker-side generator $G(x,t,z)$ separates target intent $t$ from trigger realization $z$. This separation shifts the audit question from whether one known trigger succeeds to how the hidden behavior varies across targets, latent samples, defenses, and post-stop rounds. On CIFAR-10, CIFAR-100, and Tiny-ImageNet, FLAT preserves clean utility while reaching 99.49%, 99.66%, and 94.10% single-target FedAvg ASR. The evaluation also reveals non-uniform defense responses, where a server rule can suppress one target mode while leaving another active. These observations motivate HFL backdoor audits that report target-wise ASR, worst-target ASR, target coverage, latent-sampled behavior, post-stop persistence, and defense response.
Authors: Po-Heng Chou, Wei-Lung Mao, Ru-Ping Lin, Jen-Yu Chiu, Chun-Yu Yeh
Abstract: This letter presents a CWT-enhanced vibration sensing framework for bearing fault monitoring through localized time-frequency region detection on continuous wavelet transform (CWT) spectrograms. Vibration signals are transformed into CWT spectrograms to improve the observability of weak and non-stationary fault signatures, and YOLOv9, YOLOv10, and YOLOv11 are employed to detect and identify localized fault-related energy regions in the time-frequency domain. Experiments on the CWRU, PU, and IMS datasets show that the proposed framework improves the detectability and robustness of fault-related sensing patterns compared with conventional time-series models, modern vision backbones, and short-time Fourier transform (STFT)-based representations, achieving mean average precision (mAP) values up to 99.4%, 97.8%, and 99.5%, respectively. In addition, the localized region detection framework provides a more interpretable relationship between time-frequency energy distributions and characteristic bearing fault frequencies. These results demonstrate an effective and generalizable approach for interpretable vibration sensing in noisy industrial environments.
Authors: Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov
Abstract: Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis. We introduce KAGE-Env, a JAX-native 2D platformer that factorizes the observation process into independently controllable visual axes while keeping the underlying control problem fixed. By construction, varying a visual axis affects performance only through the induced state-conditional action distribution of a pixel policy, providing a clean abstraction for visual generalization. Building on this environment, we define KAGE-Bench, a benchmark of six known-axis suites comprising 34 train-evaluation configuration pairs that isolate individual visual shifts. Using a standard PPO-CNN baseline, we observe strong axis-dependent failures, with background and photometric shifts often collapsing success, while agent-appearance shifts are comparatively benign. Several shifts preserve forward motion while breaking task completion, showing that return alone can obscure generalization failures. Finally, the fully vectorized JAX implementation enables up to 33M environment steps per second on a single GPU, enabling fast and reproducible sweeps over visual factors. Code: https://avanturist322.github.io/KAGEBench/.
Authors: Junxian Li, Tu Lan, Haozhen Tan, Yan Meng, Haojin Zhu
Abstract: Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security risks related to response efficiency remain largely unexplored. In this paper, we introduce SlowBA, a novel backdoor attack that targets the responsiveness of VLM-based GUI agents. The key idea is to manipulate response latency by inducing excessively long reasoning chains under specific trigger patterns. To achieve this, we propose a two-stage reward-level backdoor injection (RBI) strategy that first aligns the long-response format and then learns trigger-aware activation through reinforcement learning. In addition, we design realistic pop-up windows as triggers that naturally appear in GUI environments, improving the stealthiness of the attack. Extensive experiments across multiple datasets and baselines demonstrate that SlowBA can significantly increase response length and latency while largely preserving task accuracy. The attack remains effective even with a small poisoning ratio and under several defense settings. These findings reveal a previously overlooked security vulnerability in GUI agents and highlight the need for defenses that consider both action correctness and response efficiency. Code can be found in https://github.com/tu-tuing/SlowBA.
Authors: Jiawen Wen, Penglei Sun, Wenjie Zhang, Suixuan Qiu, Weisheng Xu, Xiaofei Yang, Xiaowen Chu
Abstract: As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a "goal-driven trap", prioritizing physical geometry ("can I go?") over semantic rules ("may I go?"), frequently overlooking subtle regulatory constraints. To bridge this gap, we establish Rule-VLN, the first large-scale urban benchmark for rule-compliant navigation. Spanning a massive 29k-node environment, it injects 177 diverse regulatory categories into 8k constrained nodes across four curriculum levels, challenging agents with fine-grained visual and behavioral constraints. We further propose the Semantic Navigation Rectification Module (SNRM), a universal, zero-shot module designed to equip pre-trained agents with safety awareness. SNRM integrates a coarse-to-fine visual perception VLM framework with an epistemic mental map for dynamic detour planning. Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%.
Authors: Yiheng Zhang, Zhe Zhu, Tingrui Shen, Zhuojiang Cai, Tianxiao Li, Zixing Zhao, Qiujie Dong, Zhiyang Dou, Jiepeng Wang, Le Wan, Yuwang Wang, Wenping Wang, Yuan Liu, Cheng Lin
Abstract: The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging, as existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities. In this paper, we present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces. QuadLink formulates polygonal mesh generation as a hybrid centroid-conditioned vertex linking model: it first predicts a unified set of anchors (vertices and face centroids), then learns centroid-conditioned links that associate vertices with face centroids, and finally assembles polygonal faces with a quad-first strategy guided by robust geometric verification strategies. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology. To construct training data for this model, we further introduce a Tri-to-Quad Operator that converts artistic triangle meshes into quad-dominant training data via global merge selection. Extensive experiments show that QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. Our method natively supports hybrid polygonal topology, generalizing to arbitrary n-gon meshes without architectural changes.
Authors: Hasan Moughnieh, Ibrahim Ghaddar, Hadi Elham, Imad H. Elhajj, Daniel Asmar
Abstract: Robust multi-sensor fusion is essential for reliable autonomy in diverse and degraded environments, where sensor reliability can fluctuate rapidly. Because different modalities fail in distinct ways, effective fusion should adaptively balance complementary cues rather than rely on fixed weighting. This adaptability is particularly important for ego-motion estimation, since accurate updates depend on the consistent integration of complementary sensor information. We propose ADM-Fusion, an end-to-end deep learning based multi-sensor fusion method designed to adapt to environmental changes and sensor degradation. ADM-Fusion employs an adaptive sensor mixture-of-experts framework with content-aware routing to dynamically assign weights to sensor inputs in real time. The system further incorporates separate translation and rotation branches, coupled through a cross-task attention mechanism to preserve task-specific specialization while enabling information sharing. ADM-Fusion is trained on the CARLA-LOC simulated dataset and subsequently fine-tuned on KITTI real-world data, demonstrating effective simulation-to-real transfer. Experiments show that ADM-Fusion remains robust under degraded conditions while maintaining competitive performance against existing methods.
Authors: Haoyang Li, Guanlin Li, Youhe Feng, Chen Zhao, Zhuoran Wang, Yang Li, Qizhe Wei, Shifeng Bao, Haitao Shen, Yihan Zhao, Tong Yang, Jing Zhang
Abstract: Cross-embodiment transfer in vision-language-action (VLA) models remains challenging because low-level state and action spaces differ fundamentally across robot platforms. We observe that the high-level cognitive process underlying manipulation, including scene perception, object identification, task planning, and sub-task decomposition, is largely shared across embodiments. Based on this observation, we present ZR-0, a 2.6 billion parameter end-to-end VLA model that uses dense Embodied Chain-of-Thought (ECoT) supervision to align cross-embodiment representations within the vision-language model (VLM). ZR-0 adopts a dual-stream architecture: a pre-trained VLM (System 2) generates structured ECoT reasoning during training, while a Diffusion Transformer-based action expert (System 1) produces continuous action chunks via flow matching. The two components are coupled through cross-attention, with an attention mask that restricts the action expert to input prompt features only, enabling ECoT generation to be entirely skipped at inference without any performance loss. ZR-0 is pre-trained on ProcCorpus-60M, a large-scale dataset comprising approximately 60 million frames (approximately 1,000 hours) from over 400K trajectories, with dense ECoT annotations covering 96.8% of all frames. We evaluate ZR-0 on three simulation benchmarks spanning single-arm (LIBERO), bimanual (RoboTwin 2.0), and humanoid (RoboCasa GR-1 Tabletop) embodiments, as well as real-world experiments on the xArm platform, demonstrating strong performance across all settings. Code and model checkpoints are available at https://github.com/RUCKBReasoning/ZR-0.