Authors: Hairui Zhu, Yiying Yang, Tengjin Weng, Ziyu Lu, Xiao Yao, Xiaoyang Ye, Lin Ma, Wenhao Jiang
Abstract: Complex image creation and editing often require more than a single generation or editing model. A user request may involve synthesizing images, localizing objects, segmenting regions, editing selected content, compositing intermediate assets, reading text, and enhancing the final result. Such tasks shift multimodal agents from perception-augmented reasoning to manipulation-centered visual creation, where tools must actively transform visual states rather than merely inspect them. However, existing multimodal tool-use agents are mostly optimized for perception, search, or domain-specific editing, and lack large-scale supervision for executable image-creation trajectories. In this paper, we introduce CanvasCraft, a large-scale multimodal tool-use dataset for complex image creation and editing, and \textbf{CanvasAgent}, a tool-augmented multimodal agent that learns to orchestrate heterogeneous visual tools through multi-turn interaction. CanvasCraft contains 140K fully annotated executable trajectories and 10K RL task specifications. CanvasAgent is first trained with SFT to learn executable reasoning-action trajectories, and is then optimized with GRPO using a hybrid reward that combines outcome- and process-level signals. During rollout, CanvasAgent inspects intermediate results, tracks visual assets, and adapts tool decisions to the evolving visual state. Experiments evaluate both final image quality and trajectory behavior, demonstrating the effectiveness of CanvasAgent and the proposed dataset for complex multi-tool image creation workflows.
Authors: Amir Pouladi, Vesal Ahsani, Haijun Li, Homayoun Najjaran, Afzal Suleman
Abstract: Fog severely degrades the visibility of small unmanned aerial vehicles (UAVs) in skydominant, long-range imagery, reducing the reliability of downstream detection and tracking. This paper presents a task-driven evaluation framework that links depth-aware synthetic fog generation, image restoration, object detection, and tracking within a unified pipeline. Given the practical difficulty of collecting and annotating foggy UAV scenes, synthetic fog is generated from real clear-weather outdoor images containing UAV targets using monocular depth estimation and the atmospheric scattering model. Representative restoration methods from classical, convolutional neural network (CNN)-based, and transformer-based families are first compared, after which the selected restoration model is integrated into the downstream perception pipeline. Detection is evaluated under both clean-only and fog-inclusive training regimes using multiple detector variants, while tracking-by-detection is assessed on clean, foggy, and restored video sequences. Beyond image-level restoration metrics, the study evaluates how fog and restoration affect detection robustness and tracking performance. The results show that fog substantially degrades both detection and tracking, primarily through increased missed detections. Fog-inclusive training provides the most consistent improvement in robustness, whereas test-time restoration is most beneficial when the detector has been trained only on clean imagery. These findings show that restoration quality does not necessarily translate into proportional gains in downstream perception and therefore should be evaluated jointly with detection and tracking performance.
Authors: Tongbing Huang, Yang Fu, Yunfei Wang, Zhaocan Wang
Abstract: According to commonly consented theories, the minimum hardware requirement for gaze tracker is one camera and two light sources to realize gaze estimation with free head movements. However, in some scenarios such as eye tracking on mobile devices, it is preferable to use less components, especially light sources. We propose a gaze estimation method with one camera and one light source. A "virtual light source" is introduced, which is geometrically placed symmetrically to the real light source with respect to the camera, and generates a "virtual glint" in the acquired image. We estimate the "virtual glint" by exploiting the relationship between the distance between two pupils and two glints in the captured image, and estimate the gaze with polynomial regression assuming two light sources are available. A new normalization factor for regression method is verified, which turns out to be practical for one-glint system. The performance is proved to be acceptable, while degradation is noticed compared to system with two actual light sources.
Authors: Amol Harsh, Zongyan Han, Jean Lahoud, Ye Liu, Rao Muhammad Anwer, Hisham Cholakkal, Salman Khan, Fahad Khan
Abstract: Natural-language queries about 3D environments become actionable when responses are verifiable and metric. Verifiability requires explicit grounding to the referred 3D region, while metric answers report physical measurements in real-world units (e.g., size, thickness, clearance, and distance). Existing 3D large multimodal models (LMMs) approaches remain limited: conversational systems typically respond without explicit 3D grounding, while 3D grounding models are not designed for interactive, metric-aware dialogue. In this paper, we present Ground3D-LMM, a unified model that takes a point cloud and an optional RGB image as input and supports 3D spatial conversation with (i) point-grounded responses and (ii) metric numeric outputs at both object and part granularity, including multi-object queries. To evaluate this intersection of grounding and measurement, we define the 3D Grounded Measurement task, which requires predicting the referred 3D region and the corresponding metric quantities in real-world units. We introduce a large-scale dataset built on ScanNet and ScanNet++ datasets with dense object and part annotations and roughly 2.5M question-answer pairs spanning eight tasks, along with a manually verified test set. Extensive experiments on multiple datasets and tasks show that our proposed Ground3D-LMM model provides a strong baseline for grounded, metric-aware 3D conversational understanding. Our dataset and model are publicly available.
Authors: Chang Nie, Jiaju Wei, Junlan Feng, Chaoyou Fu, Caifeng Shan
Abstract: Agentic video understanding equips models with long-term memory to autonomously process and respond to continuous, long-horizon multimodal streams. However, advanced video agents often rely on ``detective-style'' iterative reasoning for action control (e.g., $\mathtt{search}$) and evidence aggregation, incurring prohibitive costs and latency. We argue that such heavy reasoning primarily compensates for the lack of global context and semantic misalignment in retrieval. This paper introduces Light-Omni, a multimodal agent framework for reflexive and lightweight video understanding. It achieves this through dual contextual states that instantly build the required context in a single forward pass. First, we maintain a global state, a finite-sized multimodal script continuously consolidated from episodic memory, serving as the global context for Light-Omni. Through hierarchical merging, it preserves recent details while summarizing past events. Second, conditioned on this global context, we generate a parametric latent state that directly drives autonomous actions and produces retrieval embeddings, with minimal latency. Benefiting from this coupled design, Light-Omni achieves semantically aligned retrieval and reflexive responses while avoiding iterative reasoning. Extensive experiments validate the effectiveness of Light-Omni across multiple video benchmarks. Notably, it outperforms M3-Agent with an average 2.4% accuracy gain, a 12.1$\times$ speedup, and a 2.6$\times$ improvement in GPU memory efficiency. Furthermore, it serves as a memory system to enhance both the performance and efficiency of existing MLLMs. Project page: https://clare-nie.github.io/Light-Omni.
Authors: Paul K. Mandal, Pavan Reddy, Tristan Malatynski
Abstract: Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted. We call these signals statistical adversaries. We analyse Imagenet to find patterns that are strongly linked to certain labels. We then use statistical controls to remove random correlations from our candidate signals. Finally, we demonstrate that these signals directly and predictably alter model predictions. These statistical adversaries are more targeted than generic corruptions and transfer across different model architectures. This suggests that some vulnerabilities are driven by dataset structure and distribution rather than a single model's idiosyncrasies. We conclude that ordinary datasets can contain exploitable adversarial surfaces even in the absence of poisoning, and suggest that dataset audits should treat spurious structure not only as a source of bias or interpretability failure, but also as a latent attack surface for vision models.
Authors: Gaoxiang Jia, Vikram Appia, Junzhou Huang, Xinlei Wang
Abstract: 3D Gaussian splatting (3DGS) is a strong representation for real-time novel-view synthesis, but its standard training pipeline relies on point estimates and hand-tuned heuristics, providing no native uncertainty or principled complexity control. This is most limiting under sparse views or fixed acquisition budgets, where a model must identify weakly supported geometry and select informative views. We introduce a rendering-aware Bayesian 3DGS framework that tracks Gaussian geometry with a Normal-Inverse-Wishart posterior over means and covariances using renderer-derived surrogate summaries. An optional Dirichlet-process extension adds a probabilistic component-usage signal, and the training schedule makes the closed-form versus approximate inference boundary explicit. Re-rendering posterior geometry samples yields native predictive uncertainty for interval calibration and active view selection. In a fixed-budget 16-to-32 active-view task, native NIW acquisition improves PSNR by +0.453 dB and LPIPS by -0.0146 over a scoring-only 3-member standard-ensemble baseline, winning 29/39 scene-seed pairs and 10/13 scene means; it also improves over PPU-style (+0.355 dB) and NIW-proxy (+0.401 dB) acquisition. NIW native intervals reduce 95% coverage error by about 17x relative to a shared proxy (0.046 vs. 0.796) and are about 10x closer to nominal coverage than a 3-member deep ensemble (0.047 vs. 0.454) at roughly one-third the training cost. As a reconstruction compatibility check, paired NIW-vs-standard analysis over 39 scene-seed runs yields +0.030 dB PSNR with 1.6% additional training time. These results position Bayesian 3DGS as a practical probabilistic scene representation for decision-facing tasks such as active view selection.
Authors: Tim Lenz, Maurice Heide, Marco Gustav, Nic G. Reitsam, Jakob Nikolas Kather
Abstract: Computational pathology foundation models (PFMs) have advanced whole-slide image analysis. However, their size and inference cost hinder local deployment in pathology departments. We propose MuCoDi, a pretraining framework that distills frozen tile embeddings from multiple PFMs into compact edge-oriented encoders. Instead of regressing individual teacher features, MuCoDi trains lightweight MobileOne and RepViT students with a contrastive distillation objective adapted from MoCo v3, where cached Virchow2, UNI2, and H-Optimus-1 embeddings replace momentum-encoder keys. We pretrain students on 14.3M TCGA tiles from only 11.8K WSIs and evaluate frozen encoders on 23 clinically curated downstream classification tasks. RepViT-based MuCoEdge students retain near-teacher performance while reducing model size by orders of magnitude: MuCoEdge-R2.3 and MuCoEdge-R1.5 reach 71.0% external AUROC, within 0.8 percentage points of the best teacher (Virchow2, 71.8%), while MuCoEdge-R2.3 obtains the best external F1 and the second-best AUPRC (51.8% and 53.3%). MuCoEdge-R1.0 reaches 70.9% AUROC with only 6.4M parameters and 1.12 GFLOPs. On a Raspberry Pi 5, sub-million-parameter MobileOne students achieve up to 605-fold single-tile speedup over Virchow2 while retaining 66.5% to 66.9% external AUROC, demonstrating that PFM-quality pathology representations can be moved toward practical edge deployment. Code is available at https://anonymous.4open.science/r/mucodi-6243.
Authors: Gregor Kobsik, Tim Elsner, Leif Kobbelt
Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding. Generative image models trained at scale have recently emerged as generalist visual learners that can identify and segment object parts directly in the image domain, across arbitrary categories and without task-specific training. Adapting such models to downstream tasks typically requires fine-tuning; we ask whether their pretrained capability can instead be harnessed directly, without any training, and answer affirmatively with a training-free harness. Our pipeline renders multi-view images of a 3D object, uses a vision-language model to analyze its semantic parts, prompts a generative image model to paint a color-coded part segmentation mask, reprojects it onto the geometry, and fits a superquadric primitive to each part via parameter optimization. The approach contains no learned parameters: it is category-agnostic and orientation-invariant, properties that previous learning-based models struggled with. Its accuracy ceiling rises with future generative-model improvements, which we confirm with a ground-truth segmentation study showing that part segmentation, not primitive fitting, is the current accuracy bottleneck. On HumanPrim and Toys4K, our method achieves the lowest Chamfer distance among all evaluated methods, using 5--9 primitives per object on average.
Authors: Fabio Hellmann, Alexander Hustinx, Benjamin D. Solomon, GestaltMatcher Database Consortium, Tzung-Chien Hsieh, Peter Krawitz, Elisabeth Andr\'e
Abstract: FaceMesh2HPO is a framework for classifying facial phenotypic descriptors aligned with the Human Phenotype Ontology (HPO) to support clinical diagnosis. Using annotations from 124 clinicians across 10 disorders (107 HPO terms) combined with non-syndromic controls, we generated 3D facial meshes (478 landmarks) from 2D images and trained a hierarchical PointNet-based pipeline with cascading classification and feature elimination. The best models, incorporating 3D meshes, facial outline, and demographic metadata, achieved AUROCs between ~0.55 and ~0.89, with higher performance at parent nodes than leaf terms. External validation showed variable generalizability across disorders. Results demonstrate that hierarchical modeling of 3D facial geometry enables interpretable, ontology-linked phenotype classification, though performance on rare leaf terms remains limited. Improved data diversity and feature selection strategies are needed to enhance robustness and clinical utility.
Authors: Jiquan Yuan
Abstract: With the rapid advancement of image generation technologies, perceptual quality assessment of AI-generated images has emerged as a crucial research direction in computer vision. The core challenge of this task lies in achieving efficient quality assessment for massive generated images. Current mainstream approaches exhibit two key limitations: 1) Methods employing complex feature extraction strategies, while improving performance, incur prohibitive computational costs that hinder real-time inference; 2) Simple image scaling-based solutions, despite their computational efficiency, demonstrate significantly inferior assessment accuracy. To address this critical issue, we propose Patch Knowledge Transfer (PKT), a knowledge distillation-based optimization framework that achieves synergistic optimization of visual representation capability and inference efficiency through an innovative multi-level knowledge transfer mechanism. Specifically, we design a dual-model architecture: a teacher model with local-global hybrid processing provides high-quality supervision signals, while a student model relying solely on global processing efficiently inherits the teacher's representation capacity through multi-level supervision. Extensive experiments conducted on 4 AIGIQA databases demonstrate that the PKT framework enables the student model to maintain performance comparable to the teacher while reducing computational costs by 67.7\%. Furthermore, compared to existing methods, our approach achieves a superior balance between model efficiency and assessment accuracy.
Authors: Aditi Naiknaware, Jian Sun, Aminreza Khandan, Shengyang Huang, Sean Dow, Bijan Najafi, Salimeh Sekeh
Abstract: Wound monitoring is a critical yet underserved clinical challenge, where timely identification of severe adverse events (SAEs) such as infection, tissue deterioration, and delayed healing can significantly impact patient outcomes. While vision-language models (VLMs) show strong multimodal reasoning, they often lack domain-specific grounding to integrate wound imagery with heterogeneous clinical information, and provide limited mechanisms for detecting cases that diverge from the training distribution. We present a multimodal framework for automated wound monitoring and SAE detection. Our approach leverages paired clinical notes and wound descriptions capturing visual characteristics such as appearance, surrounding skin condition, color changes, and signs of inflammation or healing progression, encoded through a dual-stream Low-Rank Adaptation (LoRA) framework built on a frozen BiomedCLIP backbone. We introduce a cross-contextual LoRA fusion mechanism enabling information exchange between clinical semantics and visual wound descriptors, producing context-aware multimodal representations without full model fine-tuning. To identify personalized SAEs, we propose a wound-specific out-of-distribution (OOD) detection framework combining semantic matching, visual typicality, caption-text alignment, and caption-visual alignment into a unified SAE (OOD) score. To capture healing dynamics, we incorporate covariate consistency and temporal drift penalties that leverage changes in wound characteristics across visits. Experiments on a longitudinal wound dataset collected through clinical visits show promising performance on both wound healing assessment and SAE detection, highlighting the potential of semantically enriched, temporally aware vision-language systems for clinical wound monitoring and early risk identification.
Authors: Mohammad S. Majdi, Jeffrey J. Rodriguez
Abstract: Accurate and efficient classification of thoracic diseases in chest X-ray (CXR) images is crucial for timely diagnosis and treatment. However, the presence of multiple pathologies with overlapping visual characteristics poses significant challenges for automated classification systems. In this study, we propose two novel hierarchical multi-label classification techniques, namely the loss-based and logit-based methods, to address these challenges by leveraging the hierarchical relationships among different thoracic pathologies. The loss-based technique integrates hierarchical information directly into the optimization process, while the logit-based method adjusts the predicted probabilities of each class based on its parent class in the disease taxonomy. We evaluate the performance of both techniques using three large-scale CXR datasets: CheXpert (224,316 CXRs), PADCHEST (160,000 CXRs), and NIH (112,120 CXRs). The experimental results demonstrate significant improvements in accuracy, AUC, and F1 scores compared to the baseline method across various pathologies. The logit-based and loss-based methods improve accuracy by 12\% and 11\%, AUC by 13\% and 10\%, and F1 scores by 24\% and 12\%, respectively compared to the baseline. These results represent a substantial improvement over the baseline method. Furthermore, we conduct a comprehensive statistical analysis to validate the robustness and reliability of the proposed techniques. The integration of domain-specific hierarchical knowledge not only enhances the classification performance but also provides a more interpretable output for clinical decision support. Our findings highlight the potential of hierarchical multi-label classification in advancing computer-aided diagnosis systems for chest radiography.
Authors: Hanan Gani, Guy Pulik, Daniel Rosenfeld, Duncan Watson-Parris, Salman Khan
Abstract: High-resolution satellite imagery is critical for observing fine-scale cloud structures that inform weather modification strategies like cloud seeding for rain-enhancement. However, the spatial resolution of current geostationary and polar-orbiting satellites is often insufficient for capturing small cloud features. Current super-resolution methodologies are suited for natural images and, therefore, struggle to generalize to satellite-captured spectral images of cloud cover. To address this, we propose a two-stage diffusion-based super-resolution framework to enhance the resolution of multi-spectral cloud microstructures by a factor of $4\times$. Specifically, we use inverse diffusion to recover the high resolution properties from low resolution. Stage 1 utilizes real-world paired data to learn robust degradation handling and inter-sensor alignment, while Stage 2 employs a self-supervised internal downgrading of high resolution data to refine structural learning and texture synthesis. Our approach outperforms the state-of-the-art transformer and diffusion-based baselines in both reconstruction accuracy and visual quality. We demonstrate that the two-stage method better captures fine cloud microstructures (e.g. convective turrets and cloud gaps) that are crucial for effective cloud seeding decisions. Ablation studies confirm the complementary benefits of the two stages: Stage 1 excels in coarse structural fidelity, while Stage 2 contributes enhanced detail and realism. These results highlight a practical path toward improving cloud microphysics analysis and as a step towards utilizing AI for climate and sustainability. Our code and models are publicly available at: https://github.com/hananshafi/superresolution-cloud-microphysics.
URLs: https://github.com/hananshafi/superresolution-cloud-microphysics.
Authors: Suranjana Sooraj, Xuyang Chen, Madhumitha Venkatesan, Dongyu Liu
Abstract: Rendering time series as chart images for CNN-based classification has become increasingly common in time-series classification (TSC). However, it remains unclear whether models learn underlying temporal patterns or rely on encoding-specific visual cues introduced by chart design. We present VEIL: a systematic study examining how chart encodings influence learned representations through complementary analyses of similarity, transferability, and attribution. Attention-guided training appears to mitigate this effect when encoding sensitivity is consistently identified across diagnostics, but provides limited or negative benefit when such signals are absent. These findings position VEIL within the broader question of how machines perceive visualizations -- extending graphical perception from human readers to vision models -- and show that visualization design choices shape learned representations in ways that warrant treating chart-based TSC as a representation and measurement problem rather than a simple modeling decision.
Authors: Abdullah Tariq Choudhry, Tapadhir Das
Abstract: Autonomous vehicles (AVs) face increasing threats from vandalism-induced occlusion attacks (VOAs) that compromise camera-based perception. While detection frameworks can identify vandalized images, restoring camera-stream utility after physical occlusion remains underexplored. This paper presents present the Recovery and Enhancement of Vandalized Images for Vision Excellence (REVIVE) framework, a vandalism recovery pipeline integrating: (1) binary VOA detection, (2) multi-class VOA pattern identification, (3) EfficientNet-based U-Net segmentation, and (4) type-aware recovery using Bootstrapping Language-Image Pre-training (BLIP)-guided Stable Diffusion inpainting, direct pixel replacement, or adaptive median filtering. Stable Diffusion shows variable reconstruction performance (per-pattern SSIM 0.667-0.867, PSNR 15.4-26.7dB) across VOA patterns, while aligned direct pixel replacement achieves near-identical reconstruction under the aligned-reference condition. On 500 tracked clean/vandalized image pairs, unrecovered VOAs reduce YOLOv8l object-detection recall to 0.588, while direct pixel replacement restores recall to 0.967 and F1-score to 0.970 under that aligned-reference condition. LaMa, Telea, and Navier-Stokes baselines improve image similarity but provide more limited downstream detection recovery, and Stable Diffusion is treated as an asynchronous recovery branch subject to a quality gate rather than a blocking real-time perception step. We evaluate a reference-available quality gate that filters recovered candidates before downstream use: without it, type-aware routing degrades per-image recall to 0.304, whereas with it, recall returns to 0.608, at or above the unrecovered baseline, ensuring the forwarded stream is never worse than the unrecovered frame. REVIVE therefore, provides a structured recovery framework from VOAs in AVs.
Authors: Runze Cheng, Yicheng Zhan, Josef Spjut, Kaan Ak\c{s}it
Abstract: Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality
Authors: Marcelo dos Santos, Rayson Laroca, Jo\~ao Carlos Raposo Neves, David Menotti
Abstract: Images acquired in surveillance environments often suffer from conditions such as low resolution, variations in pose, irregular illumination, and occlusions. Due to the low quality of these images, face recognition algorithms often struggle. This major limitation can be addressed by employing super-resolution techniques that enhance the details of the image. However, due to the high degree of difficulty of the problem, most super-resolution algorithms tend to cause distortions in the image and in the individual's identity. Thus, additional information must be incorporated into the processing to improve recognition robustness. In this regard, surveillance cameras can capture multiple images, even at low quality, and the data extracted from these images, such as consecutive video frames, can significantly enhance both super-resolution and facial recognition. In this work, we introduce FASR++, a diffusion-model-based super-resolution algorithm. It leverages a reference low-resolution image and features extracted from multiple auxiliary low-quality images to generate a super-resolved output, minimizing distortions in the individual's identity. Our approach recovers facial features without explicitly providing soft attributes or computing a function gradient to guide the reconstruction process. FASR++ generates high-quality images that can considerably improve performance in face recognition tasks when used as a pre-processing step. We validate our approach on two standard face recognition datasets and attain state-of-the-art results for verification, face recognition, and image quality metrics such as PSNR, SSIM, and LPIPS.
Authors: Zhiwei Yang, Yuanchen Wu, Nan Zhang, Yucong Meng, Ke Yan, Shouhong Ding
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then, two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks. Code is available at https://github.com/zwyang6/SaGe.
Authors: Amy Lu, Changxiu Ji
Abstract: Association unlearning aims to disable learned label-attribute shortcuts while preserving task performance. Existing evaluations mainly measure output-level robustness or probe whether shortcut attributes remain readable in frozen features, but neither test determines whether a retained association remains functionally usable by the original classifier. We propose the Association Restoration Test (ART), a post-hoc diagnostic for functional shortcut restorability. ART estimates class-conditional association directions, amplifies residual components, and evaluates the modified features with the original classifier head. Across Waterbirds, CelebA, SpuCoDogs, and an ISIC timestamp-artifact extension, we show that output metrics, representation probes, and ART characterize distinct aspects of shortcut mitigation. These findings motivate restoration-aware evaluation for unlearning and shortcut-mitigation methods that target learned associations rather than individual classes or concepts.
Authors: Hossein Rajoli, Fatemeh Lotfi, Niloufar Alipour Talemi, Hossein Kashiani, Xiaolong Ma, Fatemeh Afghah
Abstract: Pre-trained Vision-Language Models (VLMs) like CLIP have proven highly effective as foundation models for various downstream applications. However, prompt learning in VLMs encounters a performance-generalization dilemma: while prompts can be tuned to achieve high accuracy on seen distributions, this tuning process often undermines their generalizability to unseen data. The limited set of learnable prompts, which contextualize and condition the input to steer it toward the task within the pretrained VLM, tends to overfit the training data, leading to a trade-off between task-specific performance and preserving generalization. To address this dilemma, we introduce SAMPLe (Sharpness-Aware Minimization Prompt Learning), a plug-in sharpness-aware optimizer that enhances prompt generalizability by accounting for loss landscape sharpness. Unlike conventional methods, SAMPLe balances exploration and exploitation by satisfying objective function constraints at each step, dynamically adapting to the current optimization state based on the local curvature and gradient properties. This approach reduces overfitting on seen distributions and improves adaptability to unseen data, preserving the generalization potential of pre-trained VLM models. We integrate SAMPLe into multiple prompt learning frameworks, including CoOp, CoCoOp, MaPLe, TCP, and Co-Prompt, demonstrating its effectiveness across diverse methods. Experiments show that SAMPLe elevates prompt learning frameworks and consistently outperforms existing optimizers across diverse settings, establishing itself as a robust, model-agnostic solution for prompt learning.
Authors: Huakun Liu, Qing Yu, Kent Fujiwara, Hideaki Uchiyama, Kiyoshi Kiyokawa
Abstract: Generating temporally continuous and socially coherent human motion from text remains a fundamental challenge, particularly in realistic streams where people act alone, enter interactions, and later disengage. Most existing methods generate fixed-length motion clips under static agent configurations, which makes them brittle to solo-social transitions and unsuitable for incremental generation over long horizons. We propose ARMS, an Anchor-Relational Motion Streaming framework that unifies solo motion and human-human interaction within a single causal generative process. ARMS introduces a dynamics-asymmetric representation that decouples per-person temporal evolution from inter-person alignment via a partner-referenced relative-translation term, enabling seamless switching of social coupling without sacrificing long-horizon stability or spatial consistency between agents. On top of a causal latent space, a causal relational diffusion model progressively refines motion segment by segment using only past context, capturing both intra-person temporal dependencies and inter-person relations. Mode-aware relational gating activates or masks cross-agent connections, allowing the same model to support both solo and interaction generation. Experiments show that ARMS improves transition smoothness and social coherence compared to interaction-centric baselines, while also achieving competitive results on human-human interaction benchmarks.
Authors: Xuewei Meng, Jiaqi Zhang, Chuanmin Jia, Xinfeng Zhang, Shanshe Wang, Siwei Ma
Abstract: In the Versatile Video Coding~(VVC) standard, adaptive loop filter~(ALF), including Geometry transformation-based Adaptive Loop Filter~(GALF) and Cross Component Adaptive Loop Filter~(CCALF), plays an essential role in reducing compression artifacts. However, it also has high coding complexity and requires many picture buffer accesses in the encoder that will increase external memory access and is unfriendly to the software and hardware design. Therefore, we propose an optimized ALF framework, including the parallel design of GALF and CCALF, the adaptive parameter decision of GALF, and one-pass CCALF scheme by effectively estimating the CCALF filtering distortion without conducting filter operation. Compared to VTM-8.0, the proposed method can reduce the picture buffer access from 152 to 1 and achieve roughly 25\% time-savings of the ALF module with negligible coding performance change under RA configuration. Some of the proposed methods have been adopted in the VVC reference software.
Authors: Zihan Wang, Seungjun Lee, Yinghao Xu, Gim Hee Lee
Abstract: Embodied navigation aims to build agents that interpret multimodal goals, reason in 3D space, and reach target destinations reliably in the real world. However, progress remains constrained by the lack of scalable, high-fidelity, and physically grounded interactive environments. Although real-world scanned datasets offer visual realism, they are limited by scale. In contrast, synthetic simulators scale more easily but often exhibit large sim-to-real gaps. We introduce Image2Sim, a real-time neural simulation framework that constructs high-quality interactive environments from posed RGB-D image sequences. The central idea is to decouple 3D spatial anchoring from photorealistic observation synthesis. For scene construction, Image2Sim uses a feed-forward feature Gaussian model that lifts posed RGB-D observations into a 3D feature-Gaussian representation in a single pass. For rendering, we propose a Geometry-Aware One-Step Pixel Flow model that transforms sparse and noisy Gaussian projections into high-quality panoramic RGB-D observations. Image2Sim also serves as a fully automated embodied data engine that generates high-fidelity observations, executable actions, and diverse navigation instructions at scale. It converts large collections of videos and images into nearly 20K interactive scenes and synthesizes more than 10 million navigation training samples. Navigation models trained entirely in these neural environments achieve strong improvements on major benchmarks and transfer effectively to real-world zero-shot settings. These results suggest that scalable neural simulation can serve as a practical training substrate for embodied navigation at scale.
Authors: Guang Yang, Brian Siyuan Zheng, Victoria Ebert, Noah A. Smith
Abstract: We propose a novel pipeline, Legato 2, for extracting symbolic notation and semantic knowledge from images of sheet music. Legato 2 features the first large-scale neural model for optical music recognition (OMR) to operate sequentially on a system-by-system basis, following the horizontal lines of notation as they are read on the page, rather than treating the page as an undifferentiated image, enabling better scaling to arbitrarily long inputs. It is also the first OMR model capable of generating symbolic transcriptions that include embedded textual content, such as titles and annotations. The pipeline combines system-level segmentation with an autoregressive vision-LM to capture both local notation details and score structure. Across multiple datasets, Legato 2 consistently outperforms prior state of the art. We also show that symbolic transcriptions complement visual inputs for frontier language models, improving their interpretation of dense musical documents. Legato 2 establishes new state-of-the-art performance in both OMR and downstream sheet music understanding.
Authors: Tianyuan Zhang, Xianglong Liu, Aishan Liu, Lu Wang, Yitong Zhang, Peng Yue, Mingchuan Zhang, Siyuan Liang, Dacheng Tao
Abstract: Environmental illusions (eg., shadows, reflections, and tire marks) are naturally existing yet overlooked phenomena in real-world driving environments. They can disturb visual perception, leading to misinterpretation of the scene and posing serious safety risks to autonomous driving (AD) systems. However, existing researches largely overlook these phenomena, leaving a critical gap. To address this issue, we study AD robustness through the lane perception perspective, a fundamental task supporting core functions like cruise control and lane centering. We focus on two representative models: conventional lane detection (LD) and vision-language model-based systems (ADVLMs). In this work, we introduce the first benchmark, LanEvil++, for evaluating the robustness of lane perception under environmental illusions. LanEvil++ encompasses 14 types of illusions and leverages the CARLA simulator to generate 94 high-fidelity, fully controllable 3D scenes, yielding a dataset of 90,292 annotated images, 1,596 video clips, and 41,855 visual question answering pairs. Extensive evaluations demonstrate that environmental illusions substantially degrade the performance of state-of-the-art LD methods. On average, LD models experience a 5.27% drop in Accuracy and a 10.49% decline in F1-score, while ADVLMs show a 2.03% reduction in GPT-score and a 0.75% drop in Language-score. Among all illusions, shadows emerge as the most disruptive factor, reducing accuracy by up to 7.20%. Furthermore, closed-loop simulations reveal that these illusions can lead to incorrect driving decisions. Complementary real-world case studies highlight safety-critical failures in actual traffic scenes. To enhance robustness, we propose the Multimodal Illusion Defense Approach (MIDA). MIDA achieves substantial gains under challenging conditions, boosting robustness by 4.23% on LD models and 3.82% on ADVLMs.
Authors: Jiakun Li, Zhe Li, Wenqiang Wu, Zheng Chang, Mingqi Gao, Jinyu Yang, Feng Zheng
Abstract: Synthesizing physically plausible human-scene interactions (HSI) remains a critical challenge in computer vision and the development of human avatars. Although recent generative models enable diverse motion synthesis, they suffer from an inductive bias referred to as semantic-geometric entanglement. Because spatial constraints often strongly correlate with specific actions in training data, monolithic models will learn the shortcut bias, aggressively overriding the semantic intent when faced with strict geometric cues. Furthermore, this entanglement exacerbates physical hallucinations, such as body-scene penetrations. To address these limitations, we propose DeSeG, a hierarchical framework that explicitly decouples semantic intent from geometric constraints. First, we introduce a Residual Semantic Planner that encodes textual instructions and canonicalized goal voxels into a compact latent space, enabling fine-grained semantic control independent of spatial trajectories. Second, we propose a physics regularized diffusion executor that incorporates differentiable repulsive potential fields directly into the diffusion objective, enforcing collision-aware motion generation. Extensive experiments on the Lingo dataset demonstrate that DeSeG achieves state-of-the-art performance, reducing mean scene penetration by 47% and improving semantic alignment by 29% over the SOTA baselines.
Authors: Yake Wei, Yuan Wang, Fengyun Rao, Jing Lyu, Di Hu
Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''. A basic operation in this reasoning process is to zoom in on regions of interest (often represented with bounding boxes) to acquire finer visual details. In this paper, we propose \textbf{Seg}mentation before \textbf{Answer}ing (SegAnswer), which shifts the unit of zoom-in from the popular bounding box to pixel-level segmentation mask. By employing fine-grained masks to isolate the target area from cluttered environments, segmented visual input yields a more precise region of interest, effectively filtering out redundant background and interfering objects. Furthermore, the discrete patches of segmented visual input align more seamlessly with how MLLMs structure visual tokens via positional embeddings. In experiments, we evaluate SegAnswer across diverse benchmarks, including high-resolution perception, general perception, and hallucination. It achieves consistent improvements and also exhibits considerable performance on segmentation tasks, validating its capability for reliable pixel grounding.
Authors: Lizhou Liao, Wentao Xu, Handong Wang, Lirong Yang, Shuai Yang, Weiwei Liu, Chang Huang
Abstract: Vision-centric autonomous driving requires accurate metric geometry and ego-motion estimation from synchronized multi-camera observations. Recent visual geometry models show strong performance in pose estimation, depth prediction, and 3D reconstruction, but are not tailored to rigid multi-camera driving systems. They often encode camera poses as entangled representations, in which time-varying ego-motion and static camera-rig geometry are jointly modeled, limiting the utilization of vehicle-side geometric priors. We propose Trajectory-Rig Decoupled Metric Geometry Learning (TRIG), a geometry perception framework for autonomous driving. TRIG factorizes camera poses into ego-trajectory and camera-rig components, enabling separate modeling of ego-motion and static multi-camera topology. We introduce decoupled pose encoding and supervision, which separately constrain trajectory evolution and rig geometry for metric-consistent learning. Moreover, sparse Temporal--Spatial attention separates cross-camera interaction from temporal aggregation, reducing global attention cost while preserving geometric reasoning. Experiments on five autonomous driving benchmarks show that TRIG achieves state-of-the-art performance in pose estimation, metric depth prediction, and 3D reconstruction.
Authors: Fred Mutisya, Oscar Onyango, Sarah Sitati, Syokau Ilovi, Aeesha NJ Malik, Brenda W'mosi, Brian Makini, Jalemba Aluuvala, Josiah Onyango, Rachael Kanguha Mmene, Steven Wanyee
Abstract: Background. Retinopathy of prematurity (ROP) is a preventable cause of childhood blindness, with rising burden in low- and middle-income countries where ROP-trained ophthalmologists are scarce. Plus disease, marked by retinal vessel dilation and tortuosity, triggers treatment but is subjective and variable. Automated screening could extend specialist reach, but African evidence remains limited. Methods. We analysed 121 Kenyan preterm infants, covering 237 eyes and 1,635 fundus images graded as No Plus, Pre-Plus or Plus. Vessel annotations from two graders supported segmentation training. Eleven configurations were evaluated for eye-level Plus detection using patient-grouped nested cross-validation, including image classifiers, multiple-instance learning, multi-task segmentation-classification, and segment-then-classify pipelines. Results. Vessel segmentation was feasible, achieving pooled Dice 0.533, IoU 0.368, sensitivity 0.623 and specificity 0.979 on held-out images. RGB classifiers were highly sensitive but over-referred, while segmentation-coupled models were more specific. Combining approaches improved performance: an OR-based screen achieved the highest sensitivity, an AND-based confirmation achieved the highest specificity, and a probability ensemble gave the best balanced performance, with sensitivity 0.692, specificity 0.914 and balanced accuracy 0.803, outperforming the vision classifier alone. Conclusions. Classification and vessel segmentation are complementary for ROP Plus detection in Kenyan data. Classifiers support sensitive case-finding, while segmentation improves specificity and reduces over-referral. African ROP AI systems should use combined workflows and undergo prospective multi-site validation.
Authors: Yunkyu Lee, Woohyeok Kim, Sunghyun Cho
Abstract: Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets. In this paper, we propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses. It integrates efficient wave-optics PSF computation via Debye CZT propagation, depth-aware defocus rendering with occlusion handling, and blur synthesis in the radiometrically linear space with camera ISP simulation. This unified pipeline enables the scalable generation of photorealistic defocus datasets with diverse lens characteristics. Using our pipeline, we generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs. We further analyze the limitations of real-captured defocus datasets and show that such imperfections can bias full-reference evaluation. Extensive experiments demonstrate that models trained on CLDefocus achieve improved cross-device generalization compared to models trained on existing real and synthetic datasets.
Authors: Suraj Yadav, Anjaneya Sharma, Siddharth Yadav
Abstract: Deep neural networks trained with Empirical Risk Minimization (ERM) often fail under distribution shifts because they exploit spurious correlations between object labels and background context. Recent generative approaches address this issue by creating counterfactual images with altered contexts, but typically use these samples as standard data augmentation, leaving the model free to retain background-sensitive representations. We propose a two-stage framework that uses generative intervention to explicitly learn background-invariant visual representations. First, we isolate the foreground object using zero-shot segmentation and generate context-shifted variants with a structure-preserving diffusion model, preserving object identity while varying the surrounding environment. We then introduce Cross-Variant Self-Supervised Learning, where variants of the same object under different backgrounds form positive pairs in a contrastive objective. This encourages the encoder to align object-centric representations while suppressing background-specific cues. Then, we fine-tune the pretrained encoder using an ERM warm-up followed by GroupDRO with layer-wise learning rates. Experiments on distribution-shift benchmarks demonstrate best worst-group performance, achieving 92.5% on Waterbirds, 81.7% on MetaShift, and 87.4% on NICO++. Code: https://github.com/surajyadav-research/GRSSL
Authors: Younggun Kim, Taeheon Kim, Youngseo Kim, Seunghee Park
Abstract: Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image. We argue that this direct paradigm remains limited for in-the-wild deployment in terms of operational range, reliability under reduced-resolution inputs, and inference efficiency. To address these challenges, we propose AVA-VLM, an Adaptive Visual Attention-Vision Language Model that follows a human-inspired coarse-to-fine reasoning strategy. AVA-VLM first reasons over a low-resolution global image and selectively requests a high-resolution local crop only when detailed inspection is needed, similar to how a human inspector zooms in on hard-to-see yet important areas. We further introduce a region-aware Chain-of-Thought dataset that teaches the model when to inspect, where to crop, and how to use local evidence. Experiments show that AVA-VLM improves reliability under long-distance and reduced-resolution conditions while substantially reducing visual-token usage.
Authors: Suneeta Mall, Vladimir Nekrasov, Ashnil Kumar, Sajith Karunasena, Aiden Nibali, Alix Bird, Mateo Diaz Shine, Jarrel Seah
Abstract: Imaging demand is growing faster than the radiology workforce can expand, and reporting backlogs cannot be resolved through training and recruitment alone. The most direct opportunity is reducing the time and effort radiologists spend producing reports, a task that requires interpreting images, integrating clinical history and prior studies, and drafting structured findings. We present Harrison.Rad 1.5 (HR1.5), a radiology-specific multimodal large language model that accepts interleaved text and visual inputs and generates structured and unstructured text across plain-film radiology, spanning computed radiography, chest, musculoskeletal, abdominal, spine, and pelvic x-rays, and mammography. HR1.5 is trained through a three-stage pipeline: domain adaptation of a base language model on radiology reports, contrastive vision-encoder training with curriculum-based hard negatives on ~6 million image-report instances, and visual-question-answering fine-tuning on multi-turn conversations. We evaluate it with a Findings-Diagnosis scoring framework that extends RadGraph-XL entity extraction with ontology-based synonym matching and polarity-contradiction detection, benchmarked on RadBench, a simulated FRCR 2B Short Case examination scored against Angoff-method thresholds, ReXGradient, and internal multi-modality datasets. HR1.5 is the only system evaluated to meet the simulated FRCR passing standard and achieves the highest accuracy on closed-format clinical questions, across anatomical regions, on internal multi-body-part and mammography reporting, and on the primary clinically-aligned score for public chest reporting. We further examine explainability and model behaviour, including question-sensitive Grad-CAM heatmaps, attention analysis, and confidence estimation, to support responsible future evaluation toward clinical use, and a framework for clinically grounded assessment of report quality.
Authors: Cemil-Andrei Dilmac, Florinel-Alin Croitoru, Radu Tudor Ionescu
Abstract: Coreset selection aims to identify a small and highly representative subset of a massive dataset for efficient model training. The problem remains challenging even in the few-shot knowledge distillation (KD) setup, where a full-scale pre-trained teacher informs the student network. Typical sample selection strategies often struggle to surpass the random selection baseline. In this paper, we showcase few-medoids, an embarrassingly simple coreset selection strategy that chooses the samples closest to the centroid (average image) of each class. We present extensive KD experiments on four datasets, covering a wide range of image classification problems, and three teacher-student model pairs, comprising both convolutional and transformer networks. Although the proposed method is embarrassingly simple, our empirical results indicate that few-medoids is able to consistently surpass the random selection baseline, as well as the other coreset selection strategies. We therefore consider that few-medoids can be used as a drop-in replacement for commonly-used baselines (e.g. herding or k-center Greedy), in future research on coreset selection. To reproduce the reported results, we publicly release our code at https://github.com/CemilAndreiDilmac/Few-Shot-KD-Coreset.
URLs: https://github.com/CemilAndreiDilmac/Few-Shot-KD-Coreset.
Authors: Zhixuan You, Jihua Zhu, Yiding Sun, Zihao Guo, Haozhe Cheng, Dongxu Zhang, Lin Chen, Hainan Luo
Abstract: 3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited semantic supervision. In this paper, we propose GaussFusion, a multimodal pre-training framework for 3D Gaussian representations. GaussFusion integrates image and text supervision into masked Gaussian modeling through cross-modal semantic alignment, enabling the Gaussian encoder to learn both visual and language-level semantic information during pre-training. To better adapt masked modeling to the non-uniform distribution of Gaussian primitives, we further propose Gaussian Salience-guided Multi-scale Hole Masking (GSHM). GSHM constructs spatially continuous masked regions based on Gaussian salience. By applying hole masks at multiple scales, GSHM encourages the encoder to capture both fine-grained local patterns and broader structural dependencies. Extensive experiments on downstream tasks demonstrate that GaussFusion improves the transferability of Gaussian representations. Notably, GaussFusion outperforms Gaussian-MAE on ModelNet40 and ScanObjectNN (PB-T50-RS) by 0.61\% and 3.85\%, respectively.
Authors: Mingyang Song, Luxin Xu, Haoyu Sun, Minzhou Pan, Yu Cheng, Bo Li
Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Real deployments are different: the same image may be allowed in one product, restricted in another, and newly disallowed when a policy boundary changes. We study policy-adaptive image guardrailing, where a model must decide whether an image violates the currently supplied policy and generalize to held-out policy definitions. We introduce PolicyShiftBench, a comprehensive benchmark with 2,000 policy-discriminative instances over 265 images, where each image is paired with 7.55 policy-conditioned prompts on average to test whether models adapt to the active policy rather than relying on image-level safety priors. We then propose PolicyShiftGuard, a compact policy-conditioned guardrail trained with a two-stage training recipe that combines Randomized Policy SFT (RP-SFT) with Boundary-Pair Policy Adaptation (BP-Adapt). BP-Adapt trains matched prompts for the same image and risk category using standard label supervision and a pairwise comparison loss that separates blocking policies from passing policies. Experiments show that existing VLMs and specialized guardrails remain brittle under policy shifts, while PolicyShiftGuard substantially improves policy-sensitive performance. The 7B model achieves SOTA performance of 76.9 Avg. F1 and 72.1 Avg. PSS on PolicyShiftBench, transfers well to UnSafeBench and SafeEditBench, and improves the latency-performance trade-off with a concise output format. Ablations confirm that matched pass/block boundary pairs are essential for stable policy adaptation.
Authors: Ziyi Chen, Haoyan Shi, Sunhan Xu, Congyan Lang
Abstract: Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.g., object-guided attribute prediction), which is prone to error propagation. We propose PRPC, a Progressive Reasoning framework with Primitive Correction, which explicitly models the bidirectional dependency between attributes and objects via step-wise inference. PRPC performs mutual correction of primitives to suppress prediction errors in earlier steps. Specifically, we formulate CZSL as structured, Q&A-style Chain-of-Thought reasoning process and constrain the MLLM to follow predefined semantic steps to generate intermediate decisions. To further enhance the reliability and logical consistency of intermediate reasoning, we introduce reinforcement learning post-training with a GRPO-based objective, providing step-level rewards aligned with the progressive inference procedure. Extensive experiments on three CZSL benchmarks demonstrate that PRPC achieves state-of-the-art performance, validating the effectiveness of progressive reasoning and bidirectional correction for robust compositional generalization.
Authors: Shuheng Zhang, Feng Wu
Abstract: Interactive 3D segmentation aims to extract object masks in point clouds with minimal user clicks. Despite recent progress, most existing approaches still struggle with (i) coarse voxel resolution that blurs fine boundaries under limited clicks and (ii) hard false positives caused by confusing background structures. These issues are exacerbated by density and scale shifts across datasets (e.g., dense RGB-D reconstructions vs. sparse LiDAR scans), where fixed refinement heuristics and purely click-driven decoding generalize poorly. To address them, we propose NegROI -- a novel transformer-based interactive framework that couples click-centric multi-resolution refinement with scene-conditioned negative prompts. Given a coarse voxel prediction, it refines only a local Region Of Interest (ROI) around the current click on a finer grid and fuses refined logits back to the coarse mask. To improve robustness and efficiency, we introduce uncertainty-driven selective refinement that prioritizes ambiguous regions. Meanwhile, we model hard background patterns via a set of scene-conditioned negative prompts obtained by cross-attention over scene tokens. We further stabilize these prompts with a diversity regularizer. Finally, we propose boundary-aware hard negative mining to supervise negative-prompt attention toward boundary-proximal, high-confidence false positives. Our experiments on common benchmark datasets (i.e., ScanNet, S3DIS, and KITTI) demonstrate improved click efficiency and reduced false positives, with stronger cross-dataset robustness than the state-of-the-art baselines.
Authors: Yinheng Zhu, Xiaowei Xu
Abstract: Vascular computed tomography datasets are commonly annotated only once per scan, yielding the pervasive yet under addressed problem of single mask annotation noise. Existing solutions either require costly multirater fusion or are coupled with network training, preventing explicit auditing of where and why labels fail. We introduce a decoupled framework for single-mask annotation noise detection that leverages cross-sectional patch self-consistency to produce interpretable and auditable noise evidence. Tubular anatomy exhibits strong cross-sectional recurrence: patches extracted orthogonally along vessel centrelines recur in appearance across locations and subjects. Thus, anatomically similar patches should have consistent masks, and disagreement signals unreliable annotation. Our method samples cross-sectional patches, retrieves intensity-equivalent neighbours via scalable vector search, and computes a patch-level noise score from statistical mask disagreement, yielding explicit image-mask evidence for every flagged region. Aggregating scores produces scan-level quality maps for dataset quality assessment or quality-weighted training. Experiments on the coronary CT dataset validate the detected noise for improving training robustness and reveal systematic annotation biases. Specifically, transverse and oblique vessels exhibit 5.1 times higher error rates than axis-aligned structures, with additional correlations to cross-sectional area and intensity. Code is available here.
Authors: Daniel Shalam, Emanuel Ben Baruch, Avi Ben Cohen, Tal Remez
Abstract: Multimodal large language models can emit localized predictions, bounding boxes for objects and temporal windows for video and audio events, but they hallucinate these regions prolifically. The model's own token log-probabilities are nearly uninformative: they conflate grounding quality with input ambiguity, and coordinate tokens become near-deterministic once the model commits. We propose Multi-Token Localized Attention (MTLA): a training-free, post-hoc score that measures how strongly a prediction's tokens attend to the region they claim. Prior attention-based detectors, which sum attention over the entire input modality and read a single response token, are weaker special cases; we show that summing only within the claimed region and aggregating across all prediction tokens recovers a stronger grounding signal. The same recipe applies almost trivially to other modalities and tasks: object detection in images and temporal localization in video and audio. Across multiple MLLM families and three modalities, MTLA improves hallucination AUROC by +7 to +38 over the best prior training-free baseline. Used as a confidence score for re-ranking, it nearly doubles the zero-shot COCO detection AP of an open-source 8B generalist (from 20.4 to 37.0), narrowing the gap to supervised detectors without any task-specific training.
Authors: Xingyu Tan, Yunrong Qin, Mengjie Hu
Abstract: Multispectral image(MSI) and hyperspectral image(HSI) object tracking object tracking exploits recorded band-wise observations to improve target--background discrimination under similar RGB appearance, mixed pixels, illumination variation, occlusion, and clutter. However, existing trackers commonly process all search regions through a fixed capacity spectral--spatial path, ignoring that tracking difficulty varies substantially across frames and target states. Clear regions may require only lightweight local discrimination, whereas ambiguous boundaries and spectrally similar distractors often demand stronger contextual reasoning. To address this limitation, we propose SpecTrack, a spectral--spatial complexity-aware tracker that formulates MSI tracking as search-region-level adaptive capacity allocation. Its core component, the Spectral Adaptive Mixture-of-Experts (SAMoE) module, provides a capacity-ordered expert pool with progressively increasing latent rank, receptive field, and depth. Expert selection is guided by a Spectral Prompt Router, which fuses semantic context, spatial boundary cues, and a latent channel-variation cue computed after multispectral patch embedding to activate a sparse subset of SAMoE experts for each search region. In parallel, a Shared Global Expert supplies common latent spectral--spatial context to reduce fragmented sparse-routing decisions. Experiments on MUST, MSITrack, and HOTC20 demonstrate a favorable accuracy--efficiency trade-off. The accuracy-oriented SpecTrack-L384 achieves state-of-the-art or highly competitive AUCs of 65.2\%, 51.9\%, and 72.6\% on the three benchmarks, while the balanced SpecTrack-B224 reaches 62.4\% AUC at 43.7 FPS on MUST. An additional GOT-10k evaluation indicates RGB-domain architectural generalization, with SpecTrack-L384 achieving 79.3\% AO.
Authors: Shenbo Xie, Mingrui Cai, Xu Yang, Yifei Liu, Changxing Ding
Abstract: Human-Object Interaction (HOI) video generation aims to synthesize realistic videos of humans manipulating diverse objects, serving as a promising avenue for AI-driven live streaming e-commerce. A primary obstacle in this domain lies in the complexity of modeling fine-grained physical dynamics and the intricate spatial-temporal coordination between human hands and objects. Existing approaches to this problem typically rely on dense temporal guidance, e.g., frame-wise hand-object pose sequences, to strictly control the interaction process. However, such dense guidance incurs high annotation costs and affects motion synthesis diversity. To overcome these limitations, we introduce SparseCtrl-HOI, a novel sparse temporal control framework for HOI video generation. It requires only a few keyframes that capture interaction states at designated timestamps. Specifically, we employ a Time-Controlled Rotary Positional Embedding (TiRoPE) mechanism to temporally anchor these keyframes while preserving their spatial integrity. Subsequently, to govern the dynamics across intermediate frames, we propose a Motion Prior Injection Module that leverages Multimodal Large Language Models (MLLMs) to extract high-level motion priors. This empowers the model to hallucinate logically and physically plausible transitions. Furthermore, we build SparseHOI-5K, a high-quality and richly annotated dataset for HOI video generation with sparse temporal control. Comprehensive evaluations confirm that our method substantially reduces annotation overhead while synthesizing superior live-streaming e-commerce videos. Both our code and dataset are publicly available at https://mpi-lab.github.io/SparseCtrl-HOI.
Authors: Byunghoon Oh, Sunghwan Park, Jaewoo Lee
Abstract: Unlearnable examples keep publicly shared photos from being learned by unauthorized face-recognition models. An imperceptible perturbation, added before sharing, makes any model trained on the protected photos fail on clean faces. The perturbation is crafted on the shared image, however the attacker trains on the face it extracts, cropped and resized to the recognizer input, and under this extraction the protection collapses. We propose LPID, which builds the extraction into the unlearnable-example objective. LPID confines the perturbation to the extracted face region and optimizes it through a differentiable model of the extraction, concentrating its energy in the frequency band the extraction preserves. Because this robustness is a property of the transform rather than of any identity, LPID is re-optimized per album and protects even users it has never seen. LPID attains the lowest attacker accuracy of all methods in every setting we evaluate, holding the attacker below $10\%$ under crop+resize extraction on identities unseen at protection time, while remaining imperceptible at $32.7$\,dB PSNR and $0.161$ LPIPS.
Authors: Jun Wei, Xinchang Liu, Yu Liu, Chuhua Yang, Shuhui Wang, Hui Huang
Abstract: Pixel-level annotation remains a major bottleneck in medical image segmentation, making weak supervision an attractive yet under-constrained alternative. We propose OBBSeg, an intermediate supervision paradigm guided by Oriented Bounding Boxes (OBBs) that bridges the gap between full and weak supervision. By jointly encoding spatial extent and orientation, OBBs provide compact geometric supervision that better aligns with elongated or anisotropic lesions, reducing the ambiguity of coarse box annotations. To mitigate the inherent rectangular bias of OBBs, we introduce a Mask-to-OBB loss, a differentiable formulation that enforces geometric consistency between predicted masks and OBB regions. Furthermore, we incorporate prompt-driven semantic guidance through two complementary modules-PAFE and DBFE-which enhance foreground representation and suppress background interference. Extensive experiments on 13 datasets across 5 imaging modalities show that OBBSeg not only outperforms existing weakly supervised methods but also achieves performance comparable to fully supervised approaches, demonstrating its potential for efficient and scalable medical image segmentation. The code is available at https://github.com/StarLxc3/OBBSeg.
Authors: Muhammad Assad Shehbaz, Carlos Francisco Moreno-Garc\'ia
Abstract: Real estate property listings expose structured metadata through the API. Still, the richest property-level information (i.e., legal status, structural condition, utility supplies, heating systems) sits in attached questionnaire documents that no automated system currently processes at scale. These documents are heterogeneous. Some are digitally generated with selectable text, others are scanned physical forms. There are even more complex layouts that contain checkbox annotations that defeat conventional text extraction. In this paper, we present an end-to-end pipeline for acquiring, classifying, and extracting structured data from selectable text documents. The pipeline was applied to 3965 questionnaire documents collected from a live property platform via reverse-engineered REST APIs. First, we classified each document into one of three structural categories (text_only, scanned, and special_char), then extracted 35 predefined property attributes from eligible documents using DeepSeek R1 as the Large Language Model, prompted to return a structured JSON object. All 2781 submitted documents were processed successfully, producing a final dataset of 2766 unique property records. Downstream validation confirmed the data quality. Cosine similarity matching achieves a Jaccard consistency score of 0.82, and K-Means clustering produces interpretable market segments with a silhouette score of 0.2088. Results show that the proposed extraction from each property document is both feasible and reliable at this scale.
Authors: Zheng Guo, Jiaqi Cui, Haocheng Xiong, Jize Han, Bo Liu, Qianwen Zhang, Rui Chen, Yan Wang
Abstract: Non-invasive prediction of Gleason Grade Group (GGG) in prostate cancer using multiparametric MRI (mpMRI) is clinically vital for reducing unnecessary biopsies. Existing GGG prediction methods face two major limitations. First, they often overlook non-image information critical for GGG prediction, including age, prostate-specific antigen (PSA), and expert priors embedded in radiology reports. Second, they tend to oversimplify GGG as flat categorical labels, failing to account for its intrinsic hierarchy of primary and secondary Gleason patterns. To this end, we propose a novel Knowledge-Driven Ordinal-Aware Learning (KOAL) framework with three synergistic modules. Specifically, the Clinical-Context Modulation (CCM) module uses clinical variables (e.g., age and PSA) to dynamically modulate discriminative image representations. The Knowledge-Guided Prototype Alignment (KGPA) module leverages an LLM to extract group-specific expert knowledge from training radiology reports and clinical guidelines, producing offline semantic anchors describing grade-specific radiological findings without requiring patient-specific reports at inference. Through prototype contrastive alignment, patient-specific mpMRI representations are matched with these anchors to promote pathology-aligned representation learning. The Hierarchical Ordinal-aware Constraints (HOC) module decouples primary and secondary Gleason pattern prediction and maps their probabilistic outputs to GGG via a Differentiable Bio-logic Mapping Layer (DBML), ensuring pathological grading consistency. Experiments on public PI-CAI and in-house datasets demonstrate that KOAL outperforms state-of-the-art methods. Code is available at: https://github.com/Gother-GZ/KOAL.
Authors: Giovanni Cioffi, Davide Scaramuzza
Abstract: Visual SLAM is a well-established technology utilized in a wide range of real-world applications. However, its performance still degrades under challenging visual conditions, such as low texture, severe motion blur, and poor illumination. Systems based on deep learning outperform classical geometry-based ones and achieve state-of-the-art results by combining learned 2D data association and uncertainty with differentiable geometric optimization in recurrent architectures. Still, it remains unclear exactly which components are fundamentally responsible for this success. In this paper, we ask: Is the superior performance of deep learning-based systems driven primarily by learned 2D data association, the combination of learned 2D data association and uncertainty, or the recurrent architecture itself? We investigate this question empirically by conducting a controlled study. Our findings reveal that the success of DL-based V-SLAM systems hinges on learned 2D data association and uncertainty rather than their recurrent architecture, underscoring the necessity of learning-based paradigms for the design of these components. Upon acceptance, the code will be released as open source.
Authors: Hamza Hussaini, Shahana Bano, Eyad Elyan, Carlos Francisco Moreno-Garc\'ia
Abstract: Existing deep learning methods perform well in medical image classification but struggle with multi-scale morphology and limited annotations due to fixed sampling and data-hungry training. Existing approaches address these challenges in isolation: DCN-based models provide adaptive sampling but lack explicit multi-scale attention fusion and label-efficient regularisation; multi-scale architectures typically rely on static fusion; and semi-supervised methods target label scarcity without jointly modelling adaptive cross-scale representations. We propose MSA-DCNN, a scale-consistent deformable attention learning framework that introduces adaptive multi-scale sampling, within-scale saliency refinement, learned cross-scale fusion, and auxiliary self-distillation within a unified optimisation scheme, with potential to generalise to structurally heterogeneous anatomy. We evaluate on three public benchmarks and an external hold-out set for leukaemia. MSA-DCNN demonstrates competitive and often better performance against ViT baselines, CNN baselines, and a MICCAI semi-supervised baseline under distribution shift and label scarcity in accuracy, F1, and AUC (binary), while using fewer parameters. Ablations confirm complementary component contributions, supporting MSA-DCNN as a practical foundation for data-efficient medical image classification.
Authors: Xiaopei Wu, Chenshu Hou, Liang Peng, Dan Xu, Binbin Lin, Xiaoshui Huang, Yuenan Hou, Yu Li, Wenxiao Wang, Haifeng Liu, Deng Cai, Wanli Ouyang
Abstract: 3D dense captioning, an emerging vision-language task, aims to generate descriptive sentences for each object in the 3D scene. Despite the impressive results achieved by previous methods, they suffer from two limitations. First, current research often employs global rigid transformations, such as rotation, to augment scenes without changing their spatial layouts. However, diverse spatial layouts are crucial for training a 3D dense captioning model to describe spatial relations between objects. Second, previous works mainly focus on the design of the caption generation pipeline while utilizing a simple network architecture for other components, i.e., backbone and detection head, which is crucial for extracting rich semantic information for captioning. In this paper, we propose PVCap to alleviate the aforementioned problems. Our PVCap consists of PseudoCap and VoxelCapNet. Specifically, PseudoCap employs a random mixing technique on instances within the dataset, generating numerous pseudo frames with diverse spatial layouts at the instance level. By utilizing a teacher-student framework, PseudoCap obtains pseudo caption labels for these pseudo frames. This data augmentation approach significantly increases the number of training samples and enhances the model's ability to describe the environment effectively. Regarding VoxelCapNet, we introduce a robust caption network that utilizes voxel features and adapts the caption head to the voxel-based network architecture. Our VoxelCapNet can serve as a competitive baseline for future research on 3D dense captioning. Extensive experiments are conducted on two prevalent benchmarks, i.e., ScanRefer and Nr3D. Notably, our method surpasses current state-of-the-art by 11.41% and 13.99% in CIDEr@0.5IoU, respectively. Codes will be made publicly available.
Authors: Innocent Onyenonachi, Peter J. Lawerance, Nadia Kanwal
Abstract: High-resolution RGB imagery acquired from low-altitude UAV surveys was processed through a modular pipeline incorporating transformer-based semantic segmentation, connected-component vegetation extraction, fine-grained species classification using a ConvNeXt architecture, and grid-based dominance scoring at 2x2m resolution. The framework targeted two ecologically significant halophytic grasses, Spartina maritima and Puccinellia maritima, and was trained using a curated and manually annotated UAV imagery, along with biodiversity imagery sourced from publicly accessible datasets. In order to identify these plants from the imagery, our segmentation yielded reliable species masks (mean IoU = 0.56; pixel-level accuracy = 0.96), while object-level classification achieved very good discrimination (F1 = 0.99). Dominance estimates closely matched quadrat-based field surveys, with mean absolute differences below 8%, preserving fine-scale spatial structure under realistic survey conditions. The developed system, named EcoVision, establishes a practical foundation for scalable, high-resolution salt marsh monitoring, demonstrating how AI-driven workflows can translate pixel-level predictions into ecologically interpretable metrics.
Authors: Woo Jae Kim, Kyle Min, Suhyeon Ha, Joonsung Jeon, Sung-eui Yoon
Abstract: Multi-perturbation adversarial training (MAT) aims to achieve robustness against multiple $\ell_p$ perturbations but suffers from robustness trade-offs between different threats. To address this, we employ a mixture of experts (MoE) to route different threats through distinct model pathways. However, naive application of MoE encounters two critical challenges: experts tend to overlook threat-specific features and redundantly capture features shared across threats, and gating networks suffer from threat-agnostic routing where they learn nearly identical routing patterns across threats, thus preventing the construction of threat-specific model pathways. To this end, we propose Robust Mixture of Low-Rank Experts (RoME), where each expert is a low-rank additive update to the shared backbone, allowing it to capture threat-common features while experts focus on threat-specific information. To address threat-agnostic routing, RoME introduces (i) dual-scale gating that exploits threat-discriminative signals from local and global level features, and (ii) threat-guided gating diversification that enforces diverse expert utilization across threats. Extensive experiments demonstrate that RoME outperforms existing state-of-the-art MAT in union robustness and natural accuracy and improves robustness against unseen threats. Codes are available at https://github.com/wkim97/RoME.
Authors: Wei Dong, Tianyu Fu, Zhe Yu, Hanning Wang, Anyang Su, Zhizhou Fang, Yuyang Chen, Shuo Wang, Minghui Wu, Ping Jiang, Zhen Lei, Chenxu Zhao
Abstract: As web agents increasingly demonstrate capabilities in automated task execution, the development of robust evaluation frameworks for assessing their navigation and task completion performance has emerged as a critical research priority. However, existing benchmarks exhibit fundamental limitations. First, they suffer from insufficient scale and limited domain diversity, constraining comprehensive evaluation of cross-domain generalization. Second, prevailing LLM-as-Judge evaluation methodologies inadequately capture fine-grained interaction semantics, particularly regarding precise query formulation and filtering operations. Third, current benchmarks predominantly emphasize navigation success metrics while neglecting critical requirements for real-world deployment scenarios. To address these limitations, we introduce WebRetriever, a large-scale benchmark encompassing 800 websites and 1,550 tasks across diverse domains, including consumer, professional, and enterprise sectors, with comprehensive coverage of user intent patterns. We propose NavEval (Navigation Evaluation), a novel LLM-as-Judge framework that leverages rich interaction context beyond visual screenshots, achieving state-of-the-art alignment with human judgment across multiple evaluation datasets. Furthermore, we establish three complementary evaluation protocols that collectively provide holistic assessment of web agent capabilities: navigation proficiency, knowledge-assisted interaction, and end-to-end task completion with information extraction. Extensive experimental analysis reveals substantial performance disparities across evaluation protocols, demonstrating that navigation success alone is an insufficient predictor of real-world application effectiveness. WebRetriever delivers fine-grained diagnostic insights into agent capabilities and establishes a rigorous foundation for advancing web agent research and development.
Authors: Yuanmin Huang, Zhenfei Zhang, Mi Zhang, Geng Hong, Qinqin He, Jialing Tao, Hui Xue, Min Yang
Abstract: Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization. This leaves a blind spot for visual synonym attacks (VSA), a jailbreak where benign-looking prompts elicit prohibited imagery through implicit visual associations. As a result, current defenses face a safety-utility dilemma: they may either under-mitigate VSA threats or over-suppress visually similar benign concepts. The core challenge is that VSA hides the unsafe target at the textual surface while revealing it through generation-time visual-semantic convergence. In this work, we therefore shift from static suppression of pre-specified unsafe concepts to dynamic tracing of how unsafe semantics emerge during generation. Our mechanistic analysis shows that VSA and explicit unsafe prompts converge through sparse semantic-injecting attention heads, which serve as inference-time bottlenecks for prohibited visual semantics. Based on this insight, we propose AEGIS (Adaptive Evasion Guard via Identification and Steering), an inference-time defense that applies similarity-aware repulsion only at the identified vulnerable heads. Evaluated against 16 baselines, AEGIS improves both safety and utility. On SD 1.4, it reduces ASR to $\mathbf{0.00}/\mathbf{0.03}$ for in-domain violence/nudity VSA and achieves ASRs $\le \mathbf{0.09}$ on out-of-domain explicit and adversarial attacks. It preserves benign fidelity, avoids suppressing hard-negative concepts, and transfers to SD 2.1 and FLUX.1 after re-identifying the critical heads for each backbone.
Authors: Wanglong Lu, Lingming Su, Kaijie Shi, Minglun Gong, Xiaogang Jin, Hanli Zhao, Xianta Jiang
Abstract: Recent diffusion-based generative models have shown impressive performance in image generation and editing. However, due to memory limitations and the high cost of collecting high-resolution training images, existing methods are typically restricted to inputs with linear resolutions below 1K. In contrast, photos captured by modern mobile devices often reach linear resolutions up to 8K, revealing a significant gap between current capabilities and real-world demands. Simply upscaling low-resolution edited results often results in visually enlarged but blurry images that lack fine details. This paper introduces UltraDiffEdit, a novel, tuning-free image editing framework that extends off-the-shelf latent diffusion models (LDMs) to ultrahigh resolutions. UltraDiffEdit employs a multi-scale progressive editing strategy, iteratively blending high-resolution edited content with unedited areas in a coarse-to-fine manner. We employ multi-patch encoding to preserve both edited and unedited visual details within the latent space. To mitigate editing artifacts, our global-local consistency denoising technique consistently integrates edited and unedited latent features, ensuring smooth transition at editing boundaries from the latent representation to the final image. We also introduce a patch-based hybrid sampling approach that captures local, intermediate, and global features, ensuring semantic coherence and enhancing fine detail during denoising. We conduct extensive experiments demonstrating UltraDiffEdit's superior editing quality and flexibility: it can handle image resolutions up to 8K using only a single NVIDIA GeForce RTX 3090 GPU. The source code is publicly available at https://github.com/LonglongaaaGo/UltraDiffEdit.
Authors: Junsong Wang, Weiqing Min, Guorui Sheng, Tao Yao, Lili Wang, Shuqiang Jiang
Abstract: Fine-grained food image retrieval is a key task in computational gastronomy, with applications in food traceability, dietary monitoring, and smart catering systems. Although hashing-based retrieval is attractive for large-scale search due to its storage efficiency and fast Hamming-distance computation, existing methods often perform poorly in fine-grained food scenarios, where subtle local semantics and frequency-sensitive visual cues are essential. To address this challenge, we propose RFHNet, a cascaded hierarchical hashing network that captures both global structure and fine-grained local details through multi-level representations. RFHNet includes three components: (1) Fine-grained Relation Modeling (FRM) to capture subtle visual differences among similar food components; (2) Multi-Frequency Modulated Fusion (MFMF) to extract informative multi-frequency features; and (3) Hierarchical Semantic Synergy (HSS) to adaptively integrate multi-level representations and generate discriminative hash codes. Experiments on six food-specific benchmarks show that RFHNet consistently outperforms state-of-the-art hashing methods, with mAP gains of 4.44\% to 17.20\% at 12 bits. These results validate the effectiveness of RFHNet for large-scale visual food retrieval and smart catering applications. The source code will be released upon publication.
Authors: Keonvin Park, Yong Ann Voeurn, Hyeokjun Kweon, Doyun Lee
Abstract: Reliable seam segmentation is essential for autonomous robotic welding in construction, where harsh illumination, specular reflections, and thin weld geometries often degrade segmentation performance. This study proposes a reflection-robust seam segmentation framework that enhances a BiSeNetV2 backbone through transfer learning and a hybrid Cross-Entropy--Lov\'asz loss. Rather than increasing architectural complexity, the proposed framework improves reflection robustness through learning-stability-oriented optimization. Experimental results show that the proposed method achieves 81.76\% Joint IoU and 90.73\% mIoU, improving Joint IoU by +22.36 percentage points over the OHEM-based baseline while maintaining identical FLOPs, parameter count, and inference speed. The proposed approach also recovers 96.33\% of severe zero-IoU failure cases under reflective conditions. Comparative experiments across BiSeNetV2, DeepLabV3+, UNet, and SegFormer further demonstrate that the proposed optimization strategy is particularly effective for lightweight real-time segmentation architectures. Qualitative analyses additionally show improved seam continuity and reflection robustness in challenging welding environments. These findings suggest that the proposed framework provides a practical and lightweight perception solution for robotic welding applications involving reflective metallic surfaces.
Authors: Junha Kim, Hyunjoon Park, Donghyeon Cho
Abstract: Image outpainting extends an image beyond its original borders, requiring seamless style integration and globally coherent scene completion. Building on the success of diffusion models, recent methods have achieved substantial improvements in visual quality. In practice, however, high-resolution outpainting is commonly performed via progressive expansion around a fixed source image, particularly in artwork scenarios. Despite this progress, existing approaches still suffer from three key limitations: (i) the absence of a reliable global planning mechanism, which leads to structural instability and error accumulation at high resolutions; (ii) limited spatial controllability beyond text prompts, making it difficult to place objects at user-specified locations; and (iii) high inference latency caused by inherently sequential patch generation. To address these issues, we propose a global blueprint-guided two-stage diffusion framework for layout-controllable high-resolution outpainting with efficient parallel synthesis. In Stage 1, we generate a low-resolution global blueprint using a layout adapter that injects bounding-box conditions into a Stable Diffusion inpainting backbone, producing a globally consistent structural plan while extracting global guidance features. In Stage 2, we synthesize high-resolution local patches in parallel by injecting the blueprint-derived global guidance and initializing each patch from the blueprint using the low-frequency preservation property of forward diffusion. This design eliminates sequential dependency while maintaining global coherence. Extensive experiments on large-scale artwork datasets demonstrate improved visual fidelity, stronger semantic consistency, and substantially reduced inference time compared to prior baselines, while uniquely supporting explicit layout control for artwork outpainting.
Authors: Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv, Ioannis Lelekas, Noor Fathima, Spyridon Stasis, Hanno Ackermann, Boris van Breugel, Markus Nagel, Fatih Porikli, Animesh Karnewar, Amirhossein Habibian
Abstract: Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coherence. In contrast, existing mobile video diffusion models remain limited to relatively small parameter budgets, typically 0.4-1.8B, restricting generation quality. In this work, we show that high-quality mobile video generation does not require small models. Instead, we demonstrate that a server-scale 5B-parameter video diffusion transformer can be deployed efficiently on memory-constrained mobile hardware through recurrent reformulation and structured compression. Starting from Wan2.2-5B, we rely on a recurrence distillation framework that converts video generation into a chunk-wise autoregressive process with constant-memory attention computation. Combined with causal linear attention, the model operates as an RNN at inference time while preserving temporal coherence across chunks. We further propose a learnable attention head pruning method based on binary per-head gates optimized end-to-end using a noise-biased sparsity objective and distillation-based finetuning. Together with sampling-step distillation and memory-optimized VAE decoding, MobileWan becomes the first 5B-scale video diffusion model deployable on a commercial mobile device. Our system generates 5-second 480x832 videos at 16 FPS in 20 seconds end-to-end latency, achieving a VBench score of 83.79 and establishing a new state of the art in mobile video generation. Project page: https://qualcomm-ai-research.github.io/mobilewan
Authors: Runfeng Qu, Pia K Bideau, Ole Hall, Julie Ouerfelli-Ethier, Klaus Obermayer, Olaf Hellwich
Abstract: Scene graph generation (SGG) approaches can be broadly classified into detector-based and query-based methods according to their underlying reasoning mechanisms. However, the discrepancy in their predictive behaviors, induced by these distinct mechanisms, has not been systematically analyzed. In this work, we design a controlled experimental setup to examine prediction discrepancies from the perspective of detector-conditioned reachability. The results suggest clear complementary clues. Motivated by this observation, we introduce a Dual-SGG method that consolidates both reasoning mechanisms via a dual-query design, thereby leveraging the complementary predictive behaviors of both detector-based and query-based methods. Extensive experiments on the Visual Genome, Open Images v6, and GQA-200 datasets demonstrate the effectiveness of the proposed method.
Authors: Xinda Liu, Qinyu Zhang, Weiqing Min, Guohua Geng, Shuqiang Jiang
Abstract: Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language models (VLMs) like CLIP provide a compelling zero-shot alternative, reducing reliance on extensive labeled data. However, their ability to capture subtle distinctions remains limited, leading to subpar recognition performance. While prompt tuning has proven effective for adapting VLMs, most existing methods treat class labels as isolated, discrete entities, overlooking the rich semantic relationships between them. This oversimplified assumption limits the model's ability to capture hierarchical dependencies and inter-class correlations -- both critical for distinguishing visually similar categories. The problem is especially acute in fine-grained classification, where accurate recognition depends on understanding complex label semantics. To address this, we propose Structured-Condensed Prompt Tuning (SCPT), which enhances semantic structure modeling in prompt learning. Specifically, we introduce Semantic Relation Encoding (SRE) to explicitly model inter-class semantic topology and encode structured label relationships. In parallel, we design a Semantic Condensation loss (ScLoss) to suppress redundant supervision and extract discriminative components from the global semantic space. Together, these components significantly improve semantic alignment and fine-grained discrimination. Extensive experiments on 14 fine-grained benchmarks show that SCPT effectively mitigates semantic ambiguity and achieves state-of-the-art performance in both few-shot and base-to-novel generalization settings.
Authors: Team Moxin, Deyi Ji, Tianrun Chen, Xin Zhang, Jiale Yang, Qi Zhu, An Zhao, Zihao Xie, Han Wang, Xuanyi Liu, Yixiang Zhou, Pei Liu, Yi Tan, Cheng Chen, Dayi Zhu, Mingyu Wei, Hanjie Xu, Jun Liao, Siqi Li, Lingyu Lu, Hongye Fang, Hongming Tan, Youjiang Zhu, Taiyu Zhang, Zejian Li, Chaotao Ding, Lanyun Zhu, Yunhe Pan, Lingyun Sun
Abstract: The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive perception, planning, and control in real-world autonomous systems. To this end, we present MoWorld, a cost-effective yet high-performance Flash World Model with an end-to-end framework spanning data generation, pre-training, distillation, and efficient inference, enabling up to 50 FPS real-time interaction with cinematic visual quality without the need of high-end GPUs. To enable large-scale real-world deployment, MoWorld jointly optimizes model capability and cost throughout the entire development pipeline. Specifically, unlike existing approaches that primarily rely on large-scale video corpora, MoWorld is built upon a scalable 3D-native data engine accumulated from our large-scale 3D vision and generative modeling pipeline, enabling the efficient construction of geometrically consistent training data across diverse real-world and synthetic environments. Based on this foundation, a curriculum cross-frame pre-training strategy for stable and scalable World Model learning, an efficient denoising-step distillation algorithm to reduce diffusion training cost, and a mixed-precision parallel inference framework for low-cost real-time deployment. MoWorld is the first real-time interactive World Model built on the Neural Processing Unit (NPU) and can achieves up to 50 FPS in such the devices, enabling practical and efficient deployment at scale. Comprehensive evaluations demonstrate that MoWorld achieves leading performance; notably, its average inference cost is only 30\%-50\% of that of existing World Models, providing a practical foundation for large-scale real-world applications of World Models. We also demonstrate diverse applications of MoWorld.
Authors: Onur Eker, Erkut Erdem, Aykut Erdem
Abstract: Enhancing videos under extreme low-light conditions remains challenging due to the difficulty of balancing restoration quality and computational efficiency in resource-constrained settings. This paper introduces EeveeDark, a low-light video enhancement framework that combines the spatial richness of sensor-level RAW data with the temporal precision of event streams. Central to our model is a Binary Neural Network (BNN) architecture that reduces computational overhead by quantizing weights and activations while preserving detail. EeveeDark incorporates (i) modality-specific binary encoders for processing RAW frames and event data, (ii) a lightweight fusion block for integrating spatial and temporal cues, and (iii) an event-guided skip gating mechanism for dynamic spatiotemporal refinement. Experiments on synthetic and real-world datasets show that EeveeDark outperforms prior BNN-based methods and offers a favorable performance-efficiency trade-off compared to full-precision models. The project page is available at https://cyberiada.github.io/EeveeDark.
Authors: Siyuan Mei, Yan Xia, Yipeng Sun, Siming Bayer, Zirong Li, Chengze Ye, Daiqi Liu, Fuxin Fan, Yixing Huang, Andreas Maier
Abstract: Generating CT volumes from MRI and CBCT can improve treatment planning in adaptive radiotherapy while avoiding additional radiation exposure. However, direct regression of CT intensities is challenged by the inherently high dynamic range and long-tailed distributions, thereby averaging out sparse yet clinically important structures. To alleviate this issue, we reformulate the regression target into multiple windowed representations, leveraging the inductive prior that CT intensities are structure-deterministic and window-separable. These windowed views exhibit smoother distributions and admit structured fusion back to the full-range CT. Building on this reformulation, we introduce WING, a WINdow-prior-based Generative network comprising: 1) a new Gated Inception Generator to produce multi-window predictions, enabling multi-shape kernel interactions to capture cross-modality correspondence; 2) a Fuse-and-Refine Transformer to aggregate the windowed outputs and learn residuals for detail refinement; and 3) a joint adversarial training objective to enhance window-conditioned realism. Extensive experiments demonstrate that our compact WING achieves state-of-the-art performance on the MRI-to-CT and CBCT-to-CT benchmarks, while supporting multi-anatomy synthesis with a single model.
Authors: Lihua Wei, Huatong Gao, Jia Gong, Zhiyu Tan, Hao Li, Jun Liu, Zhihua Ren
Abstract: Magnetic resonance imaging (MRI) super-resolution is vital for improving diagnostic accessibility, yet most methods treat it as a deterministic mapping from a fixed low-resolution input to a high-resolution target. This overlooks a key property of MRI acquisition physics: spatial resolution and signal-to-noise ratio (SNR) are inherently coupled, making any given low-resolution scan merely one of many possible realizations under varying acquisition trade-offs. We rethink MRI super-resolution as a physics-aware reconstruction problem, in which the goal is to identify the optimal resolution-SNR configuration and then super-resolve it to obtain high-quality MRI results. A key implication of this formulation is that MRI resolution becomes dynamic rather than fixed. To handle such resolution-heterogeneous inputs, we adapt 2D Gaussian Splatting (2D GS) to MRI by formulating reconstruction as a coordinate-based, resolution-agnostic rendering problem. To further enhance fidelity, we introduce three innovations: (1) a prior-aware Gaussian representation that combines an Anatomical Structure Prior for tissue-specific kernel initialization with an Imaging System Prior that captures hardware characteristics via a covariance dictionary; (2) a physics-constrained signal modeling scheme that predicts intrinsic tissue parameters (proton density rho and effective relaxation rate R2) and synthesizes intensities through governing physical equations, ensuring biophysically plausible contrast; and (3) a meta-learning framework that alleviates paired-data scarcity by pretraining on simulated data and adapting to real-world conditions. Extensive experiments on dynamic-resolution datasets and standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its strong potential for clinical deployment.
Authors: Sharayu N. Deshmukh, Md Rashidunnabi, Nelton Tiago Gemo, Kurundkar G. D., Mahamune M. R., Nilesh K. Deshmukh
Abstract: Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. Despite their widespread use, these paradigms are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. To ensure reliable assessment under the corpus's intentional class imbalance, models are ranked primarily by the Matthews correlation coefficient (MCC), with ROC-AUC reported as a threshold-independent measure of ranking ability. Rather than maximizing dataset size, VendorBench-100 emphasizes challenging real-world scenarios through a curated taxonomy of eight edge-case families, including face swaps, text-to-video stills, AI photo edits, avatar compositing, opaque-provenance images, and compressed research frames. Our evaluation shows that commercial APIs achieve the strongest median performance, followed by vision LLMs and open-source detectors. However, individual open-source models remain competitive with the best vision LLMs. More importantly, we identify a consistent divergence between ranking ability (ROC-AUC) and operating-point quality (MCC), demonstrating that strong score discrimination does not necessarily produce reliable default-threshold decisions. This metric disagreement, rather than any single leaderboard ranking, is the central finding of the benchmark. We release the complete evaluation framework and benchmark results to support reproducible future research. The source code and data are available at: https://github.com/sharayu-20/vendorbench-100
Authors: Chen Jia, Baochang Zhang, Fatia Kusuma Dewi, Amir Yousefi, Heribert Schunkert, Reza Ghotbi, Nassir Navab
Abstract: Multi-view reasoning in coronary X-ray angiography is inherently a cross-projection geometric problem, yet automated report generation in this setting remains largely unexplored. The 3D vascular topology leads to projection-dependent branch overlap and foreshortening, rendering single-view modeling fundamentally incomplete and unstable for lesion localization and stenosis grading. Although multi-view fusion appears promising, learning anatomically consistent fusion from real angiograms is impeded by a critical limitation: cross-view alignment is unobservable and cannot be explicitly supervised. Consequently, conventional fusion relies on implicit correlations rather than verified anatomical correspondence. We address this by reformulating multi-view stenosis reporting as an alignment-constrained aggregation problem. A controllable synthetic angiography generation strategy is introduced to expose geometry-derived patch-level correspondence supervision unavailable in real data. An anatomy-correspondence module learns cross-view correspondence matrices that explicitly align auxiliary features within the main-view coordinate space prior to fusion, thereby constraining evidence aggregation to anatomically consistent regions. Experiments on synthetic data and zero-shot transfer to real angiograms show that this alignment-constrained design improves correspondence consistency and structured stenosis reporting compared to single-view modeling and conventional multi-view fusion methods. The code will be publicly available upon publication.
Authors: Yiteng Yuan, Junyan Wang, Zheyuan Liu, Hong Jia, Lei Fan, Zhulin Tao, Lianbo Guo
Abstract: Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative approaches leverage diffusion models to recover missing views via stochastic noise-to-data trajectories. While expressive, such mechanisms are not explicitly designed for clustering, as they initialize from cluster-agnostic noise and rely on stochastic denoising dynamics. In this work, we revisit probability path design in end-to-end generative IMVC. We introduce a flow-matching framework with a linear interpolation path between paired view representations, that replaces diffusion with probability flows between observed and missing views. We provide a formal analysis showing that deterministic ODE flows are inherently better aligned with clustering objectives than diffusion-based stochastic trajectories, especially in terms of transport mechanisms that respect class-conditional data distributions and maintain cluster consistency in finite-step regimes. Building upon this insight, we develop an end-to-end IMVC architecture that integrates straight-path flow-matching view completion with cluster-level and entropy-based alignment to enforce cross-view clustering consistency. Extensive experiments on standard IMVC benchmarks demonstrate that the proposed framework establishes new state-of-the-art performance.
Authors: AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao
Abstract: Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after deployment. Recent advances in video world models offer a fundamentally different paradigm. Rather than explicitly authoring every component of a virtual environment, these models autoregressively synthesize future observations conditioned on the current world state and user interactions, enabling playable worlds to be generated online. Trained on both gameplay recordings and real-world videos, they can capture diverse visual appearances and physical dynamics, opening new opportunities for interactive applications beyond gaming, including embodied intelligence. In this paper, we present \textbf{AlayaWorld}, a full-stack open-source framework for building interactive generative worlds. AlayaWorld enables open-ended real-time interaction, allowing users to freely navigate and perform diverse actions such as combat, spell casting, and monster summoning. The framework unifies the complete development-from data preparation model architecture, model training, inference acceleration, and deployment-within a modular and extensible architecture. Alongside the framework, we release reproducible pipelines, reference implementations, evaluation tools, and comprehensive documentation, establishing a practical foundation for future research and real-time applications of generative world models.
Authors: Alessandra Ibba
Abstract: Deep learning models have emerged in machine learning and related fields, demonstrating astonishing performance in various visual tasks. Despite their great success, however, these models are unable to fully encode intrinsic visual structures, and often ignore the spatial, topological, and semantic information contained within an image. Graph neural networks offer a good framework to face this aspect, but their effective use for visual tasks has been only partly explored and mainly starting from a limited perspective. This work aims to address this gap by conducting a systematic comparison of current graph construction techniques within the context of a fixed three-layer GCN architecture. Through an empirical study, it demonstrates in particular how the network structure affects performance and provides an important methodological contribution regarding the computational stages preceding graph utilization, which will be strongly influenced by the structure itself.
Authors: Aysan Ghayouri Pirsoltan, Shima Babakordi, Mohammad Reza Mohammadi
Abstract: Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities. However, existing multi-view learning approaches typically rely on feature-level aggregation or single-stage cross-attention, which can entangle view-specific and shared representations and restrict interaction to limited network depths. To address these limitations, we propose a token-centric dual-view learning framework that unifies prompt-based adaptation and cross-view fusion within a frozen vision transformer backbone. The framework reformulates inter-view interaction as structured token-level communication, where dedicated fusion tokens explicitly encode bidirectional information exchange between CC and MLO views via cross-attention, serving as intermediate carriers of cross-view dependencies rather than relying on direct feature fusion. Unlike conventional methods that apply fusion at a single layer, fusion modules are inserted at multiple transformer depths, enabling progressive and repeated interaction across the encoder hierarchy. Fusion tokens are reintegrated into the token sequence and refined by subsequent transformer layers, facilitating hierarchical propagation of complementary information while preserving view-specific structure. Experiments on VinDr-Mammo and CMMD datasets demonstrate consistent improvements over linear probing, prompt-only adaptation, and conventional fusion baselines. On the VinDr-Mammo BI-RADS classification task, the framework achieves 50.40% F1-score and 0.8090 AUC, including a 0.10 AUC improvement over a dual-view fusion baseline in the binary setting. Ablation studies further validate the effectiveness of token-based fusion and multi-depth interaction design.
Authors: Yizheng Wu, Hongwei Fan, Kewei Wang, Ruibo Li, Xingyi Li, Xiao Song, Zhe Wang, Chenjing Ding, Dongliang Wang, Zhiguo Cao, Guosheng Lin
Abstract: Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A key challenge in this domain is the high cost associated with acquiring real-world motion labels. It is therefore ideal if we could transfer motion knowledge from synthetic data to real data. In this context, we explore the potential of synthetic-to-real translation for motion prediction (SRMP). However, the most used naive motion regression methods are notably sensitive to the synthetic-to-real domain shift, resulting in unreliable knowledge translation. To address this, we propose a novel approach integrating a motion knowledge translation framework with two key components: (1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and (2) objectness-aided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise. Furthermore, we present a physically-based pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research, addressing the lack of synthetic motion datasets. Experimental results demonstrate that our approach effectively bridges the domain gaps and yields superior performance on real scenes.
Authors: Jincheng Ying, Li Wenlin, Minghui Xu, Yinhao Xiao
Abstract: Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replaced by step distillation. We find that the direct replacement fails: after pruning an EDM2-XS teacher, starting SiDA from the pruned checkpoint produces unusable samples. We introduce a short teacher-alignment repair stage as a bridge between pruning and step distillation. The bridge matches the pruned generator to the teacher on noisy real-image latents, then hands the repaired checkpoint to one-step distillation. On ImageNet-512, the original EDM2-XS baseline uses 124.713M parameters and 63 network evaluations, reaching an FID of 3.53. With a suitable distillation objective, our 20% pruned one-step generator uses 98.826M parameters and one network evaluation, reaching an FID of 3.12. With 30% pruning, the model uses 88.029M parameters and one network evaluation, with an FID of 4.26.
Authors: Zhen Li, Gang Cao, Tian Zhang, Lifang Yu, Shaowei Weng
Abstract: The rapid advancement of large-scale generative models has accelerated the spread of highly deceptive AI-generated images, making generalized synthetic image detection a critical imperative. Existing forensic networks often struggle with cross-model generalization and realworld degradations due to their reliance on single-domain representations and conventional binary classification optimization. To overcome these limitations, we propose RNSIDNet, a novel forensic framework that achieves robust detection through enhanced RGB-Noise representation learning. Specifically, our method employs a dual-branch architecture where global RGB semantics, extracted by an attention-refined CLIP backbone, dynamically modulate highfrequency noise artifacts captured by Bayar convolutions via a Feature-wise Linear Modulation (FiLM) module. To further enhance the learned representations, we design a Hard Sample-aware Contrastive Learning (HSCL) strategy. By explicitly penalizing challenging training samples, HSCL reshapes the latent feature space to maximize the discriminative margin between pristine and synthetic domains. Extensive experiments across eight public benchmark datasets verify that our model achieves state-of-the-art performance, delivering superior generalization ability, robustness, and computational efficiency. Code and dataset will be publicly available on https://github.com/multimediaFor/RNSIDNet.
Authors: Jiazi Wang, Nonghai Zhang, Qiushi Xie, Zeyu Zhang, Yufeng Chen, Yang Zhao, Ling Shao, Hao Tang
Abstract: Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact exploration. However, in cultural heritage domains such as ancient Greek pottery, reliable VLM assistance is limited by two challenges. First, open-ended interpretation requires grounding fine-grained 2D/3D visual evidence in specialized curatorial knowledge, yet the retrieval process may introduce weak sources and unverifiable references. Second, when the available evidence is incomplete, noisy, or ambiguous, VLMs often produce confident but unsupported answers instead of calibrated uncertainty. To address these challenges, we propose VaseMuseum, a lightweight and modular multimodal agent framework for intelligent digital museums of ancient Greek pottery. VaseMuseum combines an interactive virtual museum with VaseAgent, which supports both 2D images and 3D artifacts through multimodal perception, 3D-aware reasoning, external knowledge retrieval, and inference-time reliability control. Specifically, VaseAgent retrieves evidence from authoritative web and museum knowledge sources, and source-level control selects diverse and verifiable evidence before generation. Meanwhile, response-level control checks generated claims against the evidence pool and encourages neutral, evidence-bounded answers when support is insufficient or conflicting. Moreover, a training-free GRPO-style selection mechanism favors responses with valid references and calibrated confidence without updating the VLM backbone. Experiments in a realistic digital museum simulation show that VaseMuseum improves citation validity, reduces hallucinations on knowledge-intensive queries, and produces more neutral answers under ambiguity compared with search-enabled VLM baselines.
Authors: Jin Jiang, Jia Wang, Panwen Hu, Weiran Zhao, Shengcai Liao
Abstract: Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degraded video sequences; however, existing methods still struggle to balance spatial fidelity and temporal coherence under complex degradations. To address this, we propose FADRA, a frequency-aware diffusion framework with iterative residual adaptation specifically tailored for robust VFR. We first leverage the strong temporal consistency of a pre-trained text-to-video diffusion model and introduce lightweight LoRA adapters together with a Low-Quality (LQ) Pixel-Alignment Feature Fusion module to efficiently adapt the frozen generative prior to the VFR task. To further adapt the frozen diffusion backbone to the downstream VFR task beyond LoRA-based adaptation, we introduce a Repeated Residual Adaptation Head (RRAH) for step-wise residual refinement after the diffusion backbone. To make this refinement explicitly guided by the degraded observation, RRAH further takes the LQ latent together with the current velocity prediction as input, allowing the model to repeatedly revisit LQ cues and predict residual updates at each flow-matching step. This LQ-guided repeated residual adaptation helps recover fine facial details while preserving the inherent temporal priors of the pre-trained model. Furthermore, to ensure the structural integrity of perceptually important details, we introduce a Frequency-Aware Loss that provides explicit supervision across multiple spectral bands, emphasizing visually sensitive frequency components that are crucial for perceptual quality and prone to temporal jittering. Extensive experiments demonstrate that FADRA recovers better facial structures and produces more temporally consistent videos than state-of-the-art methods, leading to clear gains in both quantitative metrics and visual perception.
Authors: Eleftherios Tsonis, Xi Wang, Vicky Kalogeiton
Abstract: Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a multimodal framework that uses language guidance as a semantic bridge between vision and olfaction. Our approach leverages Vision-Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient smell cues suggested by the visual scene. These descriptors provide semantic guidance for learning olfactory representations. We train a smell encoder that maps electronic-nose signals into a shared embedding space aligned with both visual and textual representations, and introduce a languageguided latent decomposition that separates object-specific odors from contextual environmental contributions. Experiments on the New York Smells dataset demonstrate that SCENT significantly improves crossmodal retrieval compared to vision-only baselines, achieving state-of-theart performance on smell-to-image and smell-to-text retrieval tasks. In addition, our framework produces interpretable olfactory representations that enable the disentanglement of complex smell mixtures. Our results reveal the importance of contextual semantic information for grounding olfactory perception in multimodal learning and pave the way for future research in this area.
Authors: Glen Pouliquen (IDnow Research Center, France, EPITA Research Lab), Joseph Chazalon (EPITA Research Lab), Guillaume Chiron (IDnow Research Center, France), Oriol Ramos Terrades (Computer Vision Center), Thierry G\'eraud (EPITA Research Lab), Ahmad Montaser Awal (IDnow Research Center, France)
Abstract: Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captured videos under uncontrolled conditions. Current systems, however, face critical limitations: existing methods often treat video frames in isolation, neglecting the intrinsic dynamic nature of OVDs and leaving systems vulnerable to swapping attacks, or focus on general holographic presence and lack the ability to verify specific OVD types. Moreover, the economic infeasibility of frame-by-frame video annotation makes supervised training impractical. In this work, we introduce two novel approaches for verifying the dynamic behavior of transparent OVDs protecting the holder's portrait, specifically designed for open-set scenarios where attack types are unknown during training. We demonstrate that these approaches can be trained without any attack samples in a self-supervised setting, surpassing previous state-of-the-art methods on public datasets while adhering strictly to industrial constraints. Our results confirm that modeling temporal dynamics is essential for defeating sophisticated attacks under realistic conditions, and underscores the promise of sequence modeling and anomaly detection for OVD verification. Code is available at https://github.com/EPITAResearchLab/pouliquen.26.icdar.
URLs: https://github.com/EPITAResearchLab/pouliquen.26.icdar.
Authors: Jinhong Deng, Limeng Qiao, Guanglu Wan
Abstract: Visual counting is a fundamental pillar of multimodal intelligence, requiring a seamless integration of fine-grained grounding and spatial reasoning. While Multimodal Large Language Models (MLLMs) have achieved remarkable success in qualitative scene understanding, their quantitative precision remains a significant bottleneck, often characterized by persistent numerical hallucinations. Existing counting benchmarks primarily focus on basic perception in simplified contexts, failing to capture the complex failure modes that emerge under logical constraints or adversarial conditions. To address these limitations, we introduce HoloCount, a holistic and diagnostically rich benchmark structured around a three-level hierarchical taxonomy. HoloCount evaluates MLLMs across: (1) Semantic Counting, focusing on atomic and property-based enumeration; (2) Analytical Counting, assessing logical composition through spatial and set-based reasoning; and (3) Robustness Testing, probing model integrity against adverse scenarios and grounded counter-priors, such as high-density scenes and linguistic biases. Through an exhaustive evaluation of over 20 state-of-the-art MLLMs, we reveal a critical performance gap: even top-tier models degrade significantly as tasks transition from perception to complex analytical reasoning and adverse scenarios. Our findings provide a systematic landscape of current MLLM counting capabilities and offer a roadmap for developing more grounded and reliable multimodal systems. The dataset is available at https://mm-mvr.github.io/HoloCount/.
Authors: Sofiane Daimellah, Sylvie Le H\'egarat-Mascle, Clotilde Boust
Abstract: X-ray fluorescence (XRF) spectroscopy is a key modality for material analysis in cultural heritage. However, automated learning from XRF spectra remains challenging: XRF spectra are complex one-dimensional signals composed of sharp elemental peaks, broader structures, and background variations that are not taken into account by existing learning-based models. This paper introduces XRFormer, a transformer architecture tailored to XRF spectra through a multiscale convolutional tokenizer that injects locality and multi-resolution inductive biases before global self-attention. The tokenizer progressively reduces spectral resolution while increasing embedding dimensionality, and the resulting token sequence is processed by a standard transformer encoder. We further investigate self-supervised pretraining for XRF representation learning using Masked Spectral modeling (MSM) and a physics-informed Peak Presence Prediction (PPP) objective. Experiments on the Pigments Checker STANDARD v.5 dataset for pigment identification and unmixing show that XRFormer consistently outperforms ViT, SpectralFormer (with and without CAF), and a 1D-CNN baseline for pigment identification. For pigment unmixing, XRFormer achieves robust abundance estimation while maintaining significantly higher parameter efficiency than SpectralFormer, operating at a lower token resolution (128 vs. 512 tokens) and with less than half the number of parameters (1.5M vs. 3.37M). MSM yields consistent gains across both tasks, while PPP further enhances performance for both identification and unmixing when tuned with an appropriate peak prominence. These results highlight multiscale, modality-aware tokenization as an effective and parameter efficient foundation for transformer-based XRF modeling under data-limited conditions. A GitHub repository is provided at https://github.com/sofiane1010/XRFormer.
Authors: Yuhang Wu, Shuxiang Zhang, Wee Hian Ching, Chi Zhang, Miao Liu
Abstract: Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences. We study personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. To this end, we introduce PIPBench, the first profile-inclusive benchmark for evaluating personalized image generation. We further propose a novel data construction pipeline that leverages psychological and demographic profiling dimensions for both real-user data collection and scalable agent-based data generation. Using PIPBench, we conduct a thorough evaluation of representative line of methods. Our experiments reveal key limitations in existing methods, suggesting new challenges and opportunities for personalized text-to-image synthesis. Project page: https://wuyuhang05.github.io/PIPBench/
Authors: Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik
Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities. While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this accuracy, particularly in complex, multi-entity scenes. In this work, we investigate this performance gap, hypothesizing that it stems from treating the VLM as a condition encoder. In this role, the model is restricted to a single forward pass, preventing the autoregressive generation process for which it was optimized, thereby failing to fully expose its capabilities. To investigate whether this spatial understanding persists when the VLM is used as a condition encoder, we introduce Analysis-by-Proxy. In this framework, we train a lightweight, interpretable proxy model on the VLM's intermediate representations using an auxiliary localization task. By analyzing the VLM through this proxy, we uncover the specific VLM representations that encode localization information. Our findings expose a fundamental mismatch between how spatial knowledge is represented within a VLM condition encoder and how it is extracted by current editing pipelines. We reveal that under single-pass constraints, the localization signal does not reliably propagate to the predefined layer configurations commonly used for conditioning. Instead, this crucial signal remains hidden within intermediate representations, at locations that vary depending on the input prompt. Using our introduced Analysis-by-Proxy framework, we reveal the fundamental failures of existing condition extraction strategies in editing pipelines, opening the door to more principled design of conditioning architectures.
Authors: Ritabrata Chakraborty, Divy Kala, Nisheeth Bhooshan Gupta, Ganji Sreeram, Pailla Balakrishna Reddy, Makarand Tapaswi
Abstract: Audio Descriptions (ADs) narrate visual content for Blind and Low Vision (BLV) audiences during gaps in audiovisual media. There is growing momentum around ADs in movies and TV shows, and with mandates from India's Central Board of Film Certification (CBFC), there is a need to expand ADs beyond English. Yet, there is no work that generates ADs for any Indian language. To address this gap, we present the first systematic study of ADs in Hindi, contributing to aspects such as data, generation, and evaluation. We introduce Andha-Dhun, the first dataset of human-authored Hindi ADs collected from 8 full-length movies. We explore two approaches for generating ADs in Hindi: (i) directly from English dense video descriptions, and (ii) translating English ADs into Hindi. We evaluate these approaches using perplexity and LLM-as-a-judge metrics to assess fluency and quality respectively. We also analyze movies that have both English and Hindi human-authored ADs and find that naive translation introduces artifacts and narrows diversity compared to original Hindi ADs. Direct machine translation fails to adapt cultural references, while human-translated ADs do better but still fall short. Our findings emphasize that the purpose of Hindi ADs is accessibility for Indian BLV audiences, and that this requires adapting content for the audience more than strict fidelity to the source.
Authors: Glen Pouliquen (IDnow Research Center, France, EPITA Research Lab), Joseph Chazalon (EPITA Research Lab), Guillaume Chiron (IDnow Research Center, France), Thierry G\'eraud (EPITA Research Lab), Ahmad Montaser Awal (IDnow Research Center, France)
Abstract: This paper addresses the remote verification of the authenticity of Optically Variable Devices (commonly known as holograms) on identity documents. Typically placed over the cardholder's photo, these devices provide strong and easily verifiable security for human inspection but pose challenges for automated verification. Existing approaches easily cover static frauds (e.g. paper photocopy) and can be evaluated for such, but their capacity to detect real, dynamic fraud cases (e.g. handcrafted hologram) has not been evaluated to date because of the lack of public datasets. Furthermore, they are usually trained to detect known attack types, and few of them can generalize to new, unseen attacks. This work features three contributions to address these limitations: 1) a new public dataset, MIDV-DynAttack, which extends the existing MIDV-Holo dataset with realistic, static and dynamic attacks against identity document specimens, tripling the number of attack samples compared to the original dataset, 2) a novel verification method which can assess the authenticity of a specific hologram thanks to the analysis of its dynamic behavior and appearance, can be trained without dynamic attack samples, and exhibits new state-of-the-art performance, 3) a benchmark of existing approaches which follows a clear evaluation protocol and emphasizes the inability of other approaches to deal with dynamic attacks, as well as new challenging attacks to deal with. Code and dataset are publicly available at https://github.com/EPITAResearchLab/pouliquen.25.icdar.
URLs: https://github.com/EPITAResearchLab/pouliquen.25.icdar.
Authors: Max Gonzalez Saez-Diez, Jihoon Chung, Adam D. Wolsky, Gregory Lanzalotto, Dean Knox, Jonathan Mummolo, Brandon M. Stewart, Olga Russakovsky
Abstract: We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera videos. We select police-civilian action labels that are critical for police behavioral research and annotate them at a second-by-second granularity. The videos feature rapid and irregular camera motion, dense human interactions, and rare high-stakes events, making the dataset a challenging benchmark for motion-robust and context-aware egocentric perception. We provide two different tasks, classification and multiple-choice question-answering, and benchmark both open-source and closed-source models. We find that even the best video models like Gemini 2.5 Pro still struggle to accurately predict high-risk actions such as "Weapon Out". Beyond serving as a benchmark, EgoPolice provides a foundation for developing models capable of identifying events of interest in large-scale body-worn camera video repositories, enabling more efficient downstream human review.
Authors: Linlin Zhang, Neema Jakisa Owor, Xiang Yu, Abby Watts, Yaw Adu-Gyamfi
Abstract: Traffic signs are crucial components of road safety, serving as visual tools under all lighting conditions. The Manual on Uniform Traffic Control Devices (MUTCD) specifies daytime visual factors such as legibility and color contrast, and nighttime retroreflectivity requirements. Traditional assessment methods rely on manual inspections, which the Federal Highway Administration (FHWA) notes are subjective, labor-intensive and pose safety concerns, while retroreflectometers are expensive and unaffordable for smaller agencies. Most existing studies focus on either daytime factors or nighttime retroreflectivity but rarely integrate both aspects comprehensively. This study develops a novel framework that systematically evaluates traffic signs through integrated daytime-nighttime assessment. The methodology employs three fine-tuned Vision Language Models (VLMs) for daytime visual performance assessment across four key factors: legibility, color, surface and shape integrity, and surrounding environment conditions. VLM predictions are converted to numerical scores through sentiment analysis and Contrastive Language-Image Pre-Training (CLIP) scoring, while nighttime performance is assessed using LiDAR-derived retroreflectivity following established calibration procedures. The framework integrates these components into a comprehensive Sign Condition Index (SCI) for maintenance guidance. Evaluation results demonstrated that LLaVA and Qwen outperformed InternVL, achieving bidirectional cosine similarity scores of 0.67-0.76 across all factors. Among 462 validated traffic signs, 68 were flagged by the proposed framework as requiring immediate replacement due to inadequate retroreflectivity performance. This research provides a cost-effective alternative to traditional manual inspections for comprehensive traffic sign condition assessment.
Authors: Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera
Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-to-video diffusion transformer frozen and augments it with low-rank temporal adapters conditioned by learned shot-role prompt tokens. To maintain long-horizon coherence, it builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates according to predicted narrative dependencies. A Shot-Local/Story-Global tuning objective combines next-shot reconstruction, cross-shot identity contrast, and prompt sparsity regularization, while an adapter composition schedule balances early-shot visual consistency with later-shot event progression and viewpoint change. Across six multi-shot and long-video benchmarks, PACR-Video outperforms text-to-video, tuning-based, memory-augmented, streaming, and recursive-context baselines on distributional quality, semantic alignment, identity consistency, temporal smoothness, motion stability, transition coherence, and human preference. These results show that compact prompt routing and lightweight temporal adaptation provide sufficient controllable capacity for stable long video extrapolation.
Authors: Matthieu Ospici, Arnaud Gueze, Luc Bourrat, Adrien Bernhardt
Abstract: Robustness to domain shift is a key requirement for floor plan generative models to be applicable beyond the single dataset they were trained on, as floor plans vary widely across regions due to distinct architectural cultures, spatial constraints, and construction practices, while acquiring new annotated datasets remains costly and domain-specific. Yet, no prior work has studied this robustness in the context of conditioned floor plan generation. In this paper, we evaluate state-of-the-art models from two fundamentally different generative paradigms across three public datasets (RPLAN, MagicPlan and Swiss Dwellings) and show that they are highly sensitive to domain shift, with up to an order of magnitude performance degradation when transferred across domains. To mitigate this with minimal target-domain supervision, we introduce a procedural method to generate a large-scale synthetic training dataset that enforces strict physical constraints (non-overlapping rooms, valid door placement, graph consistency) while intentionally sacrificing architectural realism through highly irregular spatial arrangements and aggressive geometric perturbation of room shapes. We show that pre-training on this synthetic data considerably improves zero-shot cross-domain performance, outperforming in-domain training on MagicPlan. Furthermore, it provides a highly effective initialization for fine-tuning, accelerating target domain adaptation and outperforming real-world initialization baselines by up to 40% in a low-data regime.
Authors: Cong Su, Jiaju Han, Xuemeng Sun, Chengyin Hu, Qike Zhang, Jiujiang Guo, Yiwei Wei, Jiahuan Long
Abstract: Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.
Authors: Songbur Wong, Xiaosong Jia, Junqi You, Bo Zhang, Pei Xu, Renqiu Xia, Yuping Qiu, Shaofeng Zhang, Zelin Zhao, Xuechao Yan, Yuchen Zhou, Yurui Chen, Wen Guo, Hang Xu, Junchi Yan
Abstract: Evaluating end-to-end autonomous driving (E2E-AD) remains challenging, as existing driving simulation methods often trade off closed-loop interactivity (e.g., CARLA) and real-world visual fidelity (e.g., nuScenes). We present \textbf{\emph{Point as Skeleton}}, a generative sensor simulation framework for state-updated autoregressive driving video generation, in which an autoregressive generator synthesizes visual observations from step-wise updated ego states, actor states, scene maps, and point-cloud skeleton conditions. To support closed-loop rollout, we introduce Reset-and-Roll, which adapts rolling diffusion inference to simulation by preventing future-conditioned latent states from being committed across simulation steps. To stabilize error accumulation during step-wise autoregressive rollout, we introduce point-cloud skeletons that decouple foreground and background assets and project them into camera-view painted-point and template-depth conditions, providing appearance and geometric cues. We further implement a nuPlan-based renderer-level closed-loop generative interface for evaluating generation under ego deviations from the original log. Experiments on nuScenes and nuPlan show that \textit{Point as Skeleton} improves autoregressive generation quality during closed-loop rollout, demonstrating its potential for visually faithful closed-loop driving simulation. The code is available at https://github.com/krauwu/point-as-skeleton.
Authors: He Liang, Chenyang Ma, Yiming Zhang, Sangyun Shin, Andrew Markham, Niki Trigoni, Yuhang He
Abstract: Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM for multi-room 3D scene understanding. CAIRN aligns transformer attention with scene hierarchy, giving the model explicit awareness of object-level relations and room-level connectivity. It enriches object tokens with room-local relational context via a graph neural network, introduces learned room tokens for room-level abstraction, and applies a hierarchical attention mask with geometric bias to route information according to scene topology. CAIRN is developed on CAIRN-MR, a benchmark we introduce on HM3D for multi-room 3D scene understanding, covering grounding, captioning, and four question-answering tasks that progressively evaluate from intra-room perception to cross-room reasoning. Experiments show that CAIRN outperforms prior 3D-LLMs by a large margin across all CAIRN-MR tasks while remaining competitive on five single-room benchmarks.
Authors: Xuan Liu, Derek L. Nguyen, Emily C. Barre, Jennifer Thomas, Thomas Lynch, Jeffrey R. Marks, E. Shelley Hwang, Marc D. Ryser, Joseph Y. Lo, Lars J. Grimm
Abstract: Deep learning-based computer-aided diagnosis (CAD) systems have shown strong performance in breast cancer diagnosis, particularly for classification tasks in mammography. However, domain shifts across multi-site datasets remain a challenge, especially when models are applied to unseen domains. In this work, we proposed a calcification classification framework to improve malignant versus benign breast disease classification across multi-site mammography datasets. The framework consisted of two components: (1) an unsupervised domain adaptation module based on style transfer models (AdaIN and CycleGAN) to generate vendor-specific and technique-specific training samples without additional annotations, and (2) a supervised classification module using Swin Transformer V2 as the backbone. We evaluated the proposed method on three datasets: cross-validation on OPTIMAM (National Health Service, United Kingdom; n=2994), followed by external validation on EMBED (Emory University; n=125), and Duke Calcification Dataset v1 (n=788). These datasets cover multiple vendors and include both full-field digital mammography and synthetic 2D images derived from digital breast tomosynthesis. The proposed framework improved cross-site performance for both EMBED (AUC 0.68 to 0.72) and the Duke Calcification Dataset (AUC 0.68 to 0.73). These findings indicate that domain adaptation can reduce domain shifts and improve the generalization for calcification classification across multi-site datasets.
Authors: Jiaju Han, Ma Yaqi, Yahui Chai, Xuemeng Sun, Xin Li, Qike Zhang, Yingying Zhao, Xiang Chen, Luwei Yang, Chengyin Hu, Jiahuan Long
Abstract: Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing vision-language resources and models focus on visible-band semantics, leaving infrared vision-language understanding underexplored. We introduce MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark that couples IR-aware data construction with CLIP-style contrastive adaptation and VLM instruction tuning. Built from the same source pool and split as FusionRS, MonoIR-RS retains the infrared image as the model-facing modality, yielding 600,000 synthesized infrared images and 59,032 retained IR-aware caption records. The model experiments use this retained language-supervision subset, whose captions rewrite supervision around grayscale structure and infrared-style contrast instead of RGB appearance. We show that the synthesized infrared imagery is markedly closer to real thermal imagery than a grayscale conversion on the AVIID benchmark. We fine-tune five CLIP backbones and six VLM backbones, and calibrate them against zero-shot behavior: IR-aware adaptation lifts CLIP mean recall by up to 12.8 points and drives VLM captioning IR-cue coverage to 100% while reducing residual RGB-color leakage to near zero. By isolating the infrared modality from RGB-IR dual-modal learning, MonoIR-RS offers a controlled, reproducible testbed for aligning infrared remote-sensing evidence with language.
Authors: Zanyi Wang, Xin Lin, Haodong Li, Dengyang Jiang, Yijiang Li, Pengtao Xie
Abstract: Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets. We argue this inherits more of the generative output interface than dense prediction requires: unlike RGB synthesis, dense prediction asks for pixel-correct, task-native fields on the same image plane, not new RGB content to be rendered. Our key observation is that a pretrained DiT already organizes RGB inputs through a patch-to-token-to-patch lattice on the image plane, so each token indexes a fixed output patch whose channels can carry task-native quantities instead of RGB appearance. We instantiate this as ReChannel: we keep the VAE encoder for the DiT's input distribution but drop the target-side decoder, adapt the frozen DiT with task LoRA, and map each token to its p x p x K_t pixel-space patch through a shared token-local linear head--about 33K parameters, no spatial mixing. Using FLUX-Klein, we evaluate on six dense prediction tasks and over a dozen benchmarks. This minimal interface sets new state-of-the-art on trimap-free matting, KITTI depth, and referring segmentation, and stays competitive on normals, saliency, and pose. In a matched 4B setting it is more accurate and 2.48x faster than an edit-plus-latent-decode counterpart--dense perception can benefit from generative pretraining without inheriting its output interface.
Authors: Ruihang Zhang, Felix Taubner, Pooja Ravi, Kiriakos N. Kutulakos, David B. Lindell
Abstract: Tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video is a long-standing problem in computer vision. To tackle this problem, existing methods require inputs beyond the video itself-such as 3D models, depth maps, object masks, or task-specific learned features-and they struggle with textureless, transparent, reflective, or deformable surfaces. Here, we introduce ProxyPose, which recasts 6-DoF pose tracking as video-to-video translation. Given only a video and a single marked pixel in the first frame, a fine-tuned video diffusion model translates the input into a proxy video-a synthetic video depicting a colored polyhedron undergoing the same local rigid-body motion as the surface region at the marked pixel. Because the proxy's geometry and appearance are known by construction, recovering its full 6-DoF trajectory reduces to classical pose estimation with off-the-shelf solvers. This formulation leverages large-scale video pre-training to absorb the hardest aspects of pose tracking-handling challenging materials, occlusions, and deformations-into the translation step, while operating at the pixel level with no assumptions about object identity, boundaries, or global rigidity. ProxyPose achieves state-of-the-art 6-DoF pose tracking accuracy without the additional inputs required by competing methods and after fine-tuning the video model only on synthetic data. We further demonstrate that ProxyPose extends to face tracking, camera pose estimation, and challenging in-the-wild scenes that are beyond the reach of existing approaches. Project page: https://ruihangzhang97.github.io/proxypose/.
Authors: Xiaoyang Han, Jianhua Li, Kewang Deng, Zukai Chen, Xuanke Shi, Sihan Wang, Boxuan Li, Linyan Wang, Siyi Xie, Xin You, Jinsheng Quan, Zhongang Cai, Haiwen Diao, Ziwei Liu, Lei Yang, Dahua Lin, Quan Wang
Abstract: We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks. To support large-scale training, we convert diverse computer vision annotations into instruction-response examples compatible with these generation spaces, resulting in the SenseNova-Vision Corpus, a computer-vision instruction-response corpus spanning text, image, and mixed targets. Starting from an off-the-shelf pretrained unified multimodal model, SenseNova-Vision is trained primarily on this corpus, with auxiliary multimodal data used as a capability-preserving mixture, and requires no task-specific prediction heads or architectural modifications. The resulting model covers a broad range of vision tasks, including detection, OCR, keypoint estimation, segmentation, depth estimation, surface normal prediction, point maps, and camera pose estimation, while supporting language-defined variants that combine category, color, region, and other visual cues. Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry. These results suggest unified multimodal generation as a scalable route for integrating computer vision capabilities into general-purpose foundation models. The model and corpus are publicly available.
Authors: Tianjiao Yu, Xinzhuo Li, Yifan Shen, Onkar Susladkar, Yuanzhe Liu, Xiaona Zhou, Ismini Lourentzou
Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existing methods concatenate text and 3D tokens into a flat sequence and rely on self-attention, collapsing coarse structural cues and fine geometric details into one undifferentiated representation. We introduce ELSA3D, a unified 3D model that addresses this with elastic semantic anchoring, structuring language and geometric reasoning jointly along matched abstraction scales. ELSA3D represents geometry with a scale-aware octree tokenizer and introduces Anchor Tokens, sparse cross-modal units that select semantic cues, route them to the most relevant 3D scale, retrieve scale-specific geometric evidence, and write the fused signal back into the unified representation, keeping interaction sparse yet precise. A lightweight per-block router makes both computation and reasoning elastic, choosing which text tokens instantiate anchors at which geometric scale so that cross-modal capacity concentrates where alignment is most needed. ELSA3D achieves state-of-the-art performance across image-to-3D generation, text-to-3D generation, and 3D captioning, outperforming the strongest unified baseline while roughly halving FLOPs and inference latency relative to the non-elastic version of the same model.
Authors: Junade Ali
Abstract: Artificial Intelligence (AI) models, at their core, apply general learnings from broad datasets to individual circumstances using probabilistic behaviour. This inductive approach stands in contrast to deductive reasoning approaches which seek to prove conclusions from their premises. However, research has shown that deductive reasoning with AI models is a challenging problem and in the real-world it may not always be feasible. An alternative way forward is to leverage abductive reasoning, seeking to corroborate the output of multiple approaches to identify the most likely conclusion from the factual matrix. We apply this to synthetic media detection in forensic settings, and find we are able to disproportionately lower the risk of false positives to true positive recall. We also provide the first empirical evaluation of OpenAI's rollout of SynthID on synthetic images and evaluate how complementary different synthetic media detection approaches are.
Authors: Ang Li, Chang Gao
Abstract: Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few milliseconds for neural-network inference. Bit-serial computing is attractive for such energy-efficient neural network acceleration, but many existing architectures still process all bits even when ReLU sets the final output to zero. This paper presents BitFair, a software-hardware co-designed bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering, working under the ultra-low-power and strict latency requirements of XR applications. BitFair exploits dynamic bit-level sparsity by learning per-layer thresholds that trigger early termination when partial sums reliably predict that the final ReLU output will be zero. Furthermore, it searches for layer-wise bit orders that prioritize informative bits, maximizing early termination without sacrificing accuracy. A GlobalFoundries 12nm FinFET implementation with a core area of 0.34 mm^2, 104 KB on-chip memory, and voltage scaling from 0.55 to 0.70 V achieves sub-millisecond latency, up to 117.0 BTOPS/W, and 0.07 pJ/SOP. On IBM DVS128 Gesture and N-MNIST, BitFair achieves 96.5% and 97.7% accuracy, respectively, while improving effective energy efficiency by 4.0-22.1x and accuracy by up to 9.2% over prior fabricated XR vision accelerators.
Authors: Girum Demisse
Abstract: Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior, rendering the latent code uninformative. Despite extensive research, a unified account of why collapse occurs has remained an open question. We identify and formalize two logically independent but coupled causes. \emph{Gradient imbalance} occurs when the decoder's reconstruction signal vanishes faster than the $\mathbb{KL}$ regularization pressure as the posterior widens. \emph{Information gap} occurs when the stochastic sampling step discards a substantial fraction of the encoder's computed representation, attenuating decoder sensitivity and making collapse inexpensive. Both causes share the same collapse trajectory, and we show that the information gap is algebraically equivalent to mismatch between the aggregate posterior and the prior, unifying two pathologies. Subsequently, we introduce $\lambda$-VAE, which resolves both causes through a single modification to the reparameterization step: the sampling noise is scaled by per-dimension exponent, while the $\mathbb{KL}$ penalty retains the original posterior variance. This asymmetry shifts the stable training attractor away from the degenerate collapsed state, driving all latent dimensions toward the same equilibrium -- a mechanism we term \emph{variance equalization}. A closed-form optimal exponent per dimension follows from a net information gain objective, with a single hyperparameter controlling the reconstruction-generation tradeoff. We validate on standard benchmarks (Binary MNIST, Binary Omniglot, CIFAR-10, CelebA-64), showing consistent reductions in collapsed dimensions, information capacity gains of up to $2.8\times$ nats, and reconstruction quality improvements of up to $+0.33$ BPD.
Authors: Hu Zhu, Bohan Li, Xianda Guo, Hongsi Liu, Baorui Peng, Mingqi Yuan, Xin Jin, Wenjun Zeng, Chang Wen Chen
Abstract: Semantic occupancy provides a structured spatial memory for embodied indoor agents by jointly representing occupied regions, observed free space, unknown areas, and object semantics. However, existing indoor occupancy benchmarks and methods mainly focus on single-view prediction or room-level online perception, leaving long-horizon semantic mapping across connected indoor spaces underexplored. We introduce HIOcc, a hierarchical indoor occupancy benchmark that unifies ScanNet, ScanNet++, and Matterport3D under a common sparse semantic occupancy format while preserving their native observation geometries, including perspective RGB-D frames and pano-centric observation groups. HIOcc supports three complementary evaluation regimes: local semantic occupancy prediction, room-level online occupancy mapping, and building-level mapping across connected panoramic environments. We further propose GEM-Occ, a Gaussian Evidence Memory framework for semantic occupancy mapping. Rather than using pointmaps as persistent map states, GEM-Occ treats local visual geometry predictions as transient evidence, converts them into semantic Gaussian occupancy evidence and free-space ray evidence, and fuses them into a persistent hierarchical memory through visibility- and uncertainty-aware causal updates. The memory is organized into local caches, room-level submaps, and a building-level graph, and can be queried at any time through Gaussian-to-occupancy splatting. Experiments on HIOcc show that GEM-Occ improves local occupancy prediction, online map stability, free-space reasoning, revisit consistency, and building-level scalability over prior indoor occupancy and Gaussian-based mapping baselines.
Authors: Kristof Overdulve, Lode Jorissen, Nick Michiels
Abstract: Novel View Synthesis (NVS) methods, such as 3D Gaussian Splatting (3DGS), rely heavily on the assumption of clean, multi-view consistent, posed input images. Real-world captures can violate this assumption due to screen-space artifacts-static occlusions fixed to the 2D image plane rather than to the 3D world. Common examples include physical sensor defects, environmental obstructions (such as rain or mud on the lens enclosure), capture obstructions (such as a thumb over the camera sensor or a dashboard visible in dashcam footage), and digital overlays (such as watermarks or UI elements). When present, they are erroneously baked into the 3D geometry as "floaters" or near-camera artifacts, degrading the quality of novel-view rendering. In this work, we propose SSA-3DGS, an unsupervised framework that jointly optimizes a 3D scene and a learnable 2D overlay to recover a clean 3D scene and the corrupting artifacts. By exploiting geometric consensus across views, our method effectively disentangles static artifacts from the 3D scene geometry without supervision or manual input. Across diverse synthetic corruptions and a self-captured real-world dataset, SSA-3DGS improves reconstruction fidelity by up to 9 dB PSNR over 3DGS trained on the same corrupted inputs, while faithfully preserving the corrupting artifact.
Authors: Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha, Ezharuddin Jubaer, Armun Alam, Pranjal Kumar Nandi, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman
Abstract: Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due to the scarcity of high-quality annotated data. To address this gap, we introduce BaFCo, a benchmark dataset for Bangla form comprehension with a focus on Document Layout Analysis (DLA) and Key Information Extraction (KIE). BaFCo curates 200 multi-page complex Bangladeshi government forms, sourced from across diverse sectors including agriculture, education, banking, and land management. To accurately capture the structural and contextual complexity of these forms, we define a fine-grained annotation schema comprising 26 types of form entities, along with a separate coarse form entity set consisting of 5 types. We evaluate the latest MLLMs from the ChatGPT, Gemini, Claude, Qwen, and Kimi series using zero-shot and chain-of-thought prompts under both low and high reasoning setups. Our results reveal limitations in current MLLMs' ability in comprehending Bangla forms, particularly in accurately localizing highly granular form entities. Our dataset and code is available at: https://huggingface.co/datasets/Mausul/bafco
Authors: Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov
Abstract: Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a weak target model using a stronger same-family source model from a neural-network database. We propose a source-guided candidate-generation protocol with non-source controls, source-conditioned candidates, and a no-LLM hp_copy ablation under equal evaluation budgets. The protocol reports validity separately from accuracy and selects the best valid candidate only when it improves the target. On CIFAR-10, the strongest source-guided candidate reaches 0.5049 accuracy versus 0.2398 for the best non-source candidate, a +0.2651 advantage, while improving a weak target originally at 0.1254; a five-epoch check preserves the gain at 0.7686 versus 0.4839. On SVHN AlexNet with DeepSeek-Coder-6.7B, source-guided transfer reaches 0.7880 versus 0.2254, a +0.5626 advantage; a fresh repeat reaches 0.8069 versus 0.2509, a +0.5560 advantage. Direct source-recipe copy produces 0.1959 on SVHN AlexNet, matching the original target, while hp_transfer reaches 0.7880, showing that the LLM adapts rather than copies the source recipe. Family-level analysis shows the clearest positive signals for AlexNet, with 6/8 wins across SVHN, Imagenette, and CelebA-Gender, and alt_nn1, with 8/10 wins on CIFAR-10.
Authors: Honglin Wang, Shiyao Pan, Yun-Fu Liu
Abstract: Multi-agent motion prediction is essential for automated vehicles to understand the intentions of surrounding vehicles. However, previous prediction-based and anchor-based methods have limitations in mode diversity and prediction accuracy, respectively. These limitations may cause inadequate safety assessments and behavioral deviations in automated vehicles. To address this issue, a mode-world weighted regression loss is proposed to bridge the gap between these features. Specifically, this approach mitigates mode collapse while simultaneously improving world ranking and top-1 confidence. Furthermore, the proposed iterative decoder improves prediction accuracy by recurrently and segmentally generating trajectories. Experimental results show the proposed method ranks first in the Argoverse 2 multi-agent motion forecasting benchmark against other methods.
Authors: Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, Maneesh Agrawala, Jun-Yan Zhu, Song Han, Yujun Lin, Muyang Li
Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by 2.25$\times$ and increases end-to-end training throughput by 2.27$\times$ compared to BF16 LoRA.
Authors: Chuhao Zhou, Liquan Wang, Shuxin Cao, Xiangyu Chen, Yuxuan Hu, Boyu Ma, Animesh Garg, Jianfei Yang
Abstract: While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to novel ones -- a gap we formalize as functional generalization. Such tools share a common functional intent that is visually recognizable, yet this perceptual similarity does not carry over to action space, where each tool demands an entirely different motor pattern. To bridge this gap, we explore intermediate representations including affordance images, human video prompts, and 2D keypoint trajectories, finding that keypoint trajectories best balance functional expressiveness and action groundability. Building on this, we propose FunctiOnal Reasoning and Grounded Execution (FORGE), a two-stage policy that decouples functional reasoning from action execution: predicting generalizable keypoint trajectories from action-free data, then grounding them into robot actions with limited demonstrations. On a seven-tool hitting-function benchmark, FORGE consistently outperforms state-of-the-art methods on unseen tools in both simulation and the real world, achieving over 2X improvement in average success rate.
Authors: Paul Koch. Adem Karakurt, Andr\'e Sers
Abstract: Robust robotic grasping of novel objects requires datasets that simultaneously provide photorealistic RGB-D observations, physically validated grasp quality annotations, and a principled bridge between simulation and the real world, which existing datasets lack to provide jointly. \textbf{GraspIT} addresses this gap: tabletop scenes in NVIDIA Isaac Sim are annotated via a four-stage physical slip-test on parallel Franka Panda instances, producing trajectory-reachability checks and continuous quality scores beyond force-closure.Of ${\sim}$2.3M candidates, 83% pass as \emph{good} ($s{\geq}0.50$); the 17% that passed force-closure but failed the slip-test provide graded hard negatives. A Real$\leftrightarrow$Sim loop back-projects these labels onto 100 real-world scenes. The release provides ${\sim}$316k annotated RGBD frame sets across 1035 sim and 100 real scenes, with instance masks, 6-DoF poses, physical object properties, and scored 6-DoF grasps. All tools are open-source and Docker-containerized. The trajectory planning within Isaac Sim further allows streaming of high resolution demonstrations for tabletop manipulation policy learning and behavior cloning.
Authors: Ryota Tanaka, Taku Hasegawa, Kyosuke Nishida
Abstract: Multimodal document retrieval aims to retrieve relevant pages while preserving both textual and visual content from the original document. However, existing benchmarks primarily evaluate simple lexical or semantic matching, and most methods encode pages independently. Consequently, they overlook the contextual information in the document required to resolve queries that aggregate information across multiple pages. In this paper, we introduce CMDR and CMDR-Bench, a new multimodal document retrieval task and benchmark that require modeling document context. To address this challenge, we propose CMDR-Embed, a contextual multimodal embedding framework that explicitly incorporates document context by jointly encoding multiple pages and deriving page-level embeddings from a shared contextual representation. Furthermore, we introduce CMCL, a contextual multimodal contrastive learning objective that effectively trains CMDR-Embed by balancing contextual modeling with page-level discriminability. Experiments demonstrate that CMDR-Embed significantly outperforms non-contextual embeddings, highlighting the importance of context-aware multimodal embeddings for advancing document retrieval.
Authors: Grace Man Chen, Litao Guo, Yifan Wu, Yiyu Chen, Yenchi Tseng, Sicheng Liu, Yuyu Luo, Ying-Cong Chen
Abstract: Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence. Image-driven paradigms, which take UI screenshots as input, align more closely with real development workflows. However, current benchmarks focus primarily on visual fidelity and lack a systematic evaluation of the interaction capabilities in generated artifacts. To address this gap, we introduce UI2App, the first benchmark targeting interaction inference, the ability to recover application behavior from screenshots alone, without any textual or behavioral guidance. UI2App comprises 327 screenshots grouped into 45 state-coherent screenshot sets for runnable multi-route web applications. We design an end-to-end pipeline that evaluates each artifact along four dimensions: executability, navigation reachability, visual fidelity, and interaction inference. The interaction metric (IIS) assesses inferred interactions by functional correctness and state-management complexity, crediting any valid implementation rather than matching a single reference. Experiments on six frontier vision-language models reveal a marked capability mismatch between visual reconstruction and interaction realization: the visual-fidelity leader scores only 7.5 on IIS, ranking fourth and trailing the IIS leader by 5.2x. High-complexity interactions such as cross-page state remain a pervasive bottleneck, with half of the evaluated models scoring exactly zero on this dimension. Overall, the results indicate that inferring complete interaction behavior from static screenshots remains a key challenge for models.
Authors: Franz Motzkus, Sebastian Bernhard
Abstract: The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavior. In this work, we integrate unsupervised dictionary learning as a post hoc interpretability module within state-of-the-art driving models to decompose driving behavior into semantically meaningful concepts while demonstrating their causal influence on the model's driving decisions. We propose a stepwise framework for extracting and interpreting meaningful concepts from the end-to-end model and connecting them to the multifaceted model outputs, thereby revealing the underlying decision-making logic for the prediction of future trajectories. Furthermore, targeted interventions at the concept level allow us to manipulate and correct driving decisions, resulting in measurable improvements in overall driving performance. We thus demonstrate how interpretability can effectively be used to reduce model opacity, uncover erroneous behavior, and enable targeted mitigation, ultimately boosting model performance.
Authors: Humphrey Munn
Abstract: Robotic tree-fruit harvesting is a flagship problem for agricultural automation, but progress is bottlenecked by the cost and irreproducibility of field experiments: an orchard is available only weeks a year, every tree is different, and a control error can permanently damage the crop or the plant. The tree models used in graphics and agronomy are geometrically detailed but physically inert, while the GPU-parallel simulators used in robot learning contain no plausible trees. We present OrchardBench, a physically-grounded, GPU-parallel simulation of apple-orchard trees on the Newton engine. Each tree is grown by a stochastic L-system and instantiated as a fully articulated body: branches are compliant torsional spring-dampers whose stiffness follows Euler-Bernoulli beam theory, they break at a wood modulus of rupture and fall as free hinges, and apples are independent bodies on stem tethers that detach at literature-grounded pull forces and load the branch when pulled. A moving, density-controllable foliage layer occludes the canopy as real leaves do. Every physical parameter is tied to a published source. Per-environment domain randomization makes each batched world a distinct tree, and a mobile manipulator with a wrist depth camera closes the loop with geometric fruit perception and an autonomous harvesting baseline. Careful engineering of the solver and the model lets OrchardBench run many parallel environments at interactive rates on a laptop GPU. We define the tasks and a metric suite spanning harvest completeness, throughput, and plant damage (with a per-canopy-zone breakdown), and report baseline results across foliage, fruit load, terrain, canopy zone, and parallelism. The analytic baseline succeeds on about 40% of the fruit it detects and harvests only about an eighth of the reachable fruit on a tree, leaving clear headroom for novel autonomy approaches.
Authors: Fadi Abdeladhim Zidi, Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Gaby Maroun, Fadi Dornaika, Cosimo Distante
Abstract: Accurate quantification of lung disease severity from chest imaging is critical for clinical decision-making and resource allocation. We propose a tri-modal deep learning framework, TMF-RSE (Tri-Modal Fusion with Regional Semantics and Evidential Uncertainty), that combines appearance features from two-dimensional chest inputs, structural features from lung segmentation masks, and semantic features from vision-language models (VLMs) for severity quantification. Our approach employs complementary fusion mechanisms that integrate semantic guidance, structural priors, and hierarchical interactions across modalities. The model employs evidential regression to provide both severity predictions and uncertainty estimates. Experiments on the Per-COVID-19 CT and RALO datasets show that TMF-RSE outperforms recent transformer-based baselines, achieving MAE of 4.02 and Pearson correlation of 0.9629 on Per-COVID-19 validation, and 0.339 MAE / 0.973 PC on RALO geographic extent.
Authors: Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, Daichi Fujiki
Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations. In particular, flow matching-based VLA models have shown remarkable success due to their capability to generate precise and smooth action sequences and capture multimodal distributions. However, the iterative denoising process in the action head acts as a major computational bottleneck, posing a critical challenge for real-time deployment. To address this challenge, we propose ActionCache, a plug-and-play external cache that opportunistically reuses past intermediate actions to warm-start generations from the vicinity of target actions, thereby drastically reducing the inference latency. Specifically, ActionCache stores the intermediate actions with compact multimodal keys, which enables retrieval from similar past contexts across different episodes or even different tasks. Experimental results in simulation and real-world environments demonstrate that ActionCache maintains high task success rates in a low-latency regime, achieving inference acceleration of up to $11.75\times$ and $34.43\times$ for representative flow-based VLA models, $\pi_{0.5}$ and GR00T-N1.6, respectively.
Authors: Mohammadreza Kasaei, Klemen Voncina, Hamidreza Kasaei
Abstract: Robotic throwing enables fast and efficient object placement beyond the robot's immediate workspace, but reliable throwing in cluttered environments remains underexplored. Existing approaches, such as TossingBot, learn throwing strategies from visual input but assume obstacle-free settings. In this paper, we address the problem of throwing objects into a target basket while avoiding obstacles placed randomly in the scene. We introduce a potential field state representation that compactly encodes both basket attraction and obstacle repulsion on a fixed-size grid, enabling reinforcement learning (RL) policies to generalize across arbitrary numbers and configurations of obstacles. The policy is initialized from kinesthetic demonstrations and optimized in simulation using three state-of-the-art RL algorithms (SAC, DDPG, TD3). Among these, SAC achieves the most consistent performance across scenarios. We compare the potential field representation against explicit state encodings and demonstrate that it achieves higher success rates and better scalability to unseen obstacle configurations. Real-robot experiments with unseen throwable objects confirm robust sim-to-real transfer, achieving up to $90\%$ success in cluttered scenes. These results demonstrate that PFR provides a practical and robust representation for safe and efficient robotic throwing in unstructured environments. A video showcasing our experiments is available at: https://youtu.be/ZZnJf8ua2dE
Authors: Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji
Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.
Authors: Wongyun Yu, Youngwoon Kim, Minsu Cho
Abstract: Retargeting human object interaction demonstrations to physics based simulation requires reproducing not only body motion but also the object motion and contacts that make manipulation succeed. However, position only hand trajectories do not specify the contact forces needed to manipulate objects, and directly tracking them can overconstrain contact rich finger behavior. We introduce WristMimic, a wrist guided whole body control framework that explicitly separates contact free body motion from contact rich hand manipulation. The contact free body and wrist are guided by kinematic pose targets, whereas the fingers are not directly supervised by human hand pose. Instead, they learn grasping and manipulation behaviors from object tracking and contact outcomes. Our key insight is that the wrist is the natural gate between these two regimes. It is largely free from contact and can be tracked kinematically, yet it determines the global hand configuration and places the fingers within reachable grasp affordances. To ensure reliable wrist placement during interaction, we introduce wrist specific reset constraints and reward prioritization. Experiments show that WristMimic matches or surpasses methods using full finger pose supervision while enabling finger agnostic retargeting across diverse hand embodiments.
Authors: Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano, Joaquin Garcia-Alfaro
Abstract: Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply over the learned models. Its impact over data augmentation models is unclear. While data augmentation reduces the likelihood of poisoning attack success, some valid questions remain. Is data augmentation affecting the impact of poisoning attacks? can it increase the number of poisoned samples or injected backdoors? We explore in this paper some of these questions. We assess the effects of augmenting poisoned 3D point cloud datasets and validate that poisoning is able to evade the sanitizing nature of augmentation techniques when using the concrete case of Generative Adversarial Network (GAN) techniques to exemplify the case of data augmentation processing. We also validate that poisoning propagates over the augmented datasets and perturbs the decision made by general-purpose classifiers, in the end. All the experimental material (including tools, datasets, and classifiers) is publicly available, to facilitate reproducibility and to foster further research in the topic.
Authors: Han-Jun Ko, Jr-Jen Chen, Haobo Yuan, Hsin-Ying Lee, Tiancheng Shen, Ming-Hsuan Yang, Yu-Chiang Frank Wang
Abstract: Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and Visual-Action Alignment Reward, which grounds reasoning in the visual outcome induced by the model's action. Together, these rewards suppress hallucinated CoT and reduce the gap between reasoning and behavior. To improve training stability, we further employ smooth, dense rewards by estimating success probabilities using a pre-trained in-domain expert agent. Experiments on PHYRE and Virtual Tool support our performances across novel-task and unseen-environment settings, confirming that grounded and generalizable physical intelligence can be induced through VAORA.
Authors: Jiaming Liu, Qingpo Wuwu, Nuowei Han, Hao Chen, Zhuoyang Liu, Fan Fei, Yueru Jia, Chenyang Gu, Yandong Guo, Boxin Shi, Shanghang Zhang
Abstract: Recently, Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse tasks. However, effective robotic manipulation in physical environments fundamentally requires geometric understanding and spatial reasoning. While some VLA approaches attempt to incorporate 3D information, they are constrained by limited data availability and geometric information loss in current 3D encoding pipelines, and fail to jointly capture 3D geometry and temporally structured actions in dynamic environments. To address these limitations, we introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation. First, building upon our previous work Lift3D, an enhanced 2D model-lifting strategy is proposed to geometrically align 3D points with pretrained 2D positional embeddings. This design enables direct point-cloud encoding within the VLA vision encoder while minimizing spatial information loss. Based on explicit 3D inputs, we propose Geometry-Centric Masked Autoencoding (GC-MAE), a dual-objective self-supervised framework that reconstructs the current point cloud while predicting its future geometric evolution. This formulation allows the 2D vision encoder to internalize both 3D structure and physical dynamics. To fully exploit 3D representations, we further design layer-wise temporal action modeling, which leverages multiple layers of the LLM to collaboratively predict action chunks, enabling temporally consistent predictions. Across 22 simulated tasks and 8 real-world manipulation tasks, Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods, and outperforms the strongest real-world baseline by 4 percentage points, while exhibiting stronger generalization to out-of-distribution perturbations.
Authors: Renzhen Wang, De cai, Kaiwen Xiao, Xixi Jia, Xiao Han, Deyu Meng
Abstract: Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address hierarchical classification by decoupling it into a series of multi-class classification tasks. However, such a multi-task learning strategy fails to fully exploit the correlation among various categories across different levels of the hierarchy. In this paper, we propose Label Hierarchy Transition (LHT), a unified probabilistic framework based on deep learning, to address the challenges of hierarchical classification. The LHT framework consists of a transition network and a confusion loss. The transition network focuses on explicitly learning the label hierarchy transition matrices, which has the potential to effectively encode the underlying correlations embedded within class hierarchies. The confusion loss encourages the classification network to learn correlations across different label hierarchies during training. The proposed framework can be readily adapted to any existing deep network with only minor modifications. We experiment with a series of public benchmark datasets for hierarchical classification problems, and the results demonstrate the superiority of our approach beyond current state-of-the-art methods. Furthermore, we extend our proposed LHT framework to the skin lesion diagnosis task and validate its great potential in computer-aided diagnosis. The code of our method is available at \href{https://github.com/renzhenwang/label-hierarchy-transition}{https://github.com/renzhenwang/label-hierarchy-transition}.
URLs: https://github.com/renzhenwang/label-hierarchy-transition, https://github.com/renzhenwang/label-hierarchy-transition
Authors: Shreyank N Gowda, Dheeraj Pandey, Shashank Narayana Gowda
Abstract: Talking head generation has progressed rapidly from landmark- and GAN-based facial animation to diffusion models, neural rendering, 3D-aware avatars, and foundation-model-assisted systems. This progress has enabled increasingly realistic audio-, image-, and video-driven talking heads, but it has also made the field difficult to navigate because methods differ substantially in their inputs, assumptions, controllability, temporal stability, computational cost, and risks of misuse. This survey provides a critical review of talking head generation techniques, organizing the literature into four broad families: image-driven, audio-driven, video-driven, and 3D/neural-rendering-based approaches. For each family, we discuss the underlying technical ideas, representative methods, strengths, limitations, datasets, and evaluation practices. Beyond cataloguing prior work, we analyse the persistent gap between commonly reported quantitative metrics and perceptual quality, and compare publicly available models in terms of inference time, memory requirements, and human-rated visual quality. We also examine emerging trends, including diffusion-based generation, 3D-aware representation learning, controllable emotional expression, real-time deployment, and the growing importance of provenance, watermarking, and deepfake detection. Finally, we identify open challenges around robust evaluation, identity preservation, lip synchronisation, temporal consistency, demographic fairness, computational efficiency, and responsible use. This review aims to provide researchers and practitioners with a structured and up-to-date map of the talking head generation landscape, while highlighting the technical and societal questions that should shape future work.
Authors: Gregor Kobsik, Isaak Lim, Leif Kobbelt
Abstract: Detecting partial extrinsic symmetry in 3D geometry is a fundamental yet persistent challenge in computer vision and graphics, critical for tasks ranging from shape completion to procedural generation. Classical transformation-space voting methods rely on pairwise matching, scaling as O(n^2) and struggling to resolve coherent multi-instance groups. Recent learning approaches advance global symmetry detection but restrict the solution space to reflection planes, failing to capture rotational or translational repetitions such as the legs of a chair or the steps of a staircase. We propose SymCL, a self-supervised contrastive learning framework that detects partial symmetries across rotation, translation, and reflection (with scale-invariant features) and requires no ground truth annotations. By mapping local geodesic patches to a latent space invariant to the Euclidean group, we reformulate symmetry detection as a density-based clustering problem, enabling the simultaneous discovery of multi-instance symmetric relationships in a single forward pass. We evaluate quantitatively on SymPartNet, a new benchmark annotating all PartNet categories with partial symmetry relations, and demonstrate class-agnostic generalization qualitatively on everyday objects outside the training distribution.
Authors: Wenjia Xu, Zijian Yu, Boyang Mu, Jiuniu Wang, Zhiwei Wei, Mugen Peng
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have shown promise for remote sensing tasks such as visual question answering and scene understanding. However, existing models remain limited to basic instruction-following and struggle with real-world scenarios that require multi-source data integration, fine-grained spatial reasoning, and domain expertise. To address this gap, we propose RS-Agent, a domain-adapted intelligent agent that connects user intent with professional remote sensing workflows through structured task planning and tool orchestration. RS-Agent consists of four components aligned with typical remote sensing workflows: a Central Controller for intent understanding and process planning, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain knowledge support. We further introduce Task-Aware Retrieval, which improves planning by identifying task types and retrieving expert-defined solutions, and DualRAG, a weighted dual-path retrieval-augmented generation method that enhances the relevance and completeness of retrieved knowledge. RS-Agent natively supports multiple imaging modalities, including optical and SAR imagery, and can automatically organize dedicated SAR processing tools into executable workflows. Experiments on 9 datasets and 18 remote sensing tasks show that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and strong results in scene classification, object counting, and remote sensing visual question answering. These results demonstrate the value of combining LLM reasoning with remote sensing expertise for intelligent geospatial analysis.
Authors: Wenhao Wang, Yifan Sun, Zongxin Yang, Zhengdong Hu, Zhentao Tan, Yi Yang
Abstract: Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content. However, they inevitably memorize training images or videos, subsequently replicating their concepts, content, or styles during inference. This phenomenon raises significant concerns about privacy, security, and copyright within generated outputs. In this survey, we provide the first comprehensive review of replication in visual diffusion models, marking a novel contribution to the field by systematically categorizing the existing studies into unveiling, understanding, and mitigating this phenomenon. Specifically, unveiling mainly refers to the methods used to detect replication instances. Understanding involves analyzing the underlying mechanisms and factors that contribute to this phenomenon. Mitigation focuses on developing strategies to reduce or eliminate replication. Beyond these aspects, we also review papers focusing on its real-world influence. For instance, in the context of healthcare, replication is critically worrying due to privacy concerns related to patient data. Finally, the paper concludes with a discussion of the ongoing challenges, such as the difficulty in detecting and benchmarking replication, and outlines future directions including the development of more robust mitigation techniques. By synthesizing insights from diverse studies, this paper aims to equip researchers and practitioners with a deeper understanding at the intersection between AI technology and social good. We release this project at https://github.com/WangWenhao0716/Awesome-Diffusion-Replication.
URLs: https://github.com/WangWenhao0716/Awesome-Diffusion-Replication.
Authors: Ruikai Cui, Binzhu Xie, Shi Qiu, Jiawei Liu, Saeed Anwar, Nick Barnes
Abstract: Reconstructing continuous surfaces from unoriented and unordered 3D points is a fundamental challenge in computer vision and graphics. Recent advancements address this problem by training neural signed distance functions to pull 3D location queries to their closest points on a surface, following the predicted signed distances and the analytical gradients computed by the network. In this paper, we introduce NumGrad-Pull, leveraging the representation capability of tri-plane structures to accelerate the learning of signed distance functions and enhance the fidelity of local details in surface reconstruction. To further improve the training stability of grid-based tri-planes, we propose to exploit numerical gradients, replacing conventional analytical computations. Additionally, we present a progressive plane expansion strategy to facilitate faster signed distance function convergence and design a data sampling strategy to mitigate reconstruction artifacts. These components are synergistically integrated into a unified tri-plane-based pulling framework, in which numerical gradients, progressive expansion, and complementary sampling jointly address the locality and sparsity challenges of learning SDFs from unoriented point clouds. Our extensive experiments across a variety of benchmarks demonstrate the effectiveness and robustness of our approach. Codes are available at: https://github.com/cuiruikai/numgrad-pull.
Authors: Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang
Abstract: Knowledge distillation (KD) has been widely studied in unsupervised image Anomaly Detection (AD), but its application to unsupervised multimodal AD remains underexplored. Existing KD-based methods for multimodal AD that use fused multimodal features to obtain teacher representations face challenges. Anomalies that only exist in one modality may not be effectively captured in the fused teacher features, leading to detection failures. Besides, these methods do not fully leverage the rich intra- and inter-modality information that are critical for effective anomaly detection. In this paper, we propose Tuned Reverse Distillation (TRD) based on Multi-branch design to realize Multimodal Industrial AD. By assigning independent branches to each modality, our method enables finer detection of anomalies within each modality. Furthermore, we enhance the interaction between modalities during the distillation process by designing two Crossmodal Tuners including Crossmodal Filter and Amplifier. With the idea of crossmodal mapping, the student network is allowed to better learn normal features while anomalies in all modalities are ensured to be effectively detected. Experimental verifications on multimodal AD datasets demonstrate that our method achieves state-of-the-art performance in multimodal anomaly detection and localization. Code is available at https://github.com/hito2448/TRD.
Authors: Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Florian Langer, Vyas Raina, Vatsal Raina, Hanyi Xiong, Vishaal Udandarao, Jingyi Lu, Shiyang Chen, Sam Purkis, Tianshuo Yan, Wenye Lin, Gyungin Shin, Qiaochu Yang, Anh Totti Nguyen, David I. Atkinson, Aaditya Baranwal, Alexandru Coca, Mikah Dang, Sebastian Dziadzio, Jakob D. Kunz, Kaiqu Liang, Alexander Lo, Brian Pulfer, Steven Walton, Charig Yang, Kai Han, Samuel Albanie
Abstract: Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they attain high scores on many popular visual benchmarks, with headroom rapidly eroded by model progress. This creates a need for difficult benchmarks that remain relevant for longer. We introduce ZeroBench - a lightweight visual reasoning benchmark curated using adversarial filtering to be "impossible" for frontier LMMs at its original release, with initial SotA scores of 0% pass@1 and pass^5. We track progress on ZeroBench over the subsequent year, observing SotA reaching 6% pass^5 and 19% pass@5, indicating the potential longevity of the benchmark. We evaluate 46 LMMs on ZeroBench, compare performance to a human baseline, analyse strengths and weaknesses, chart a year of progress in visual capabilities, and publicly release ZeroBench at https://zerobench.github.io.
Authors: Xiaoyang Liu, Bolin Qiu, Zheng Chen, Libo Zhu, Zihan Zhou, Kai Liu, Jiezhang Cao, Yulun Zhang
Abstract: Image demoir\'eing remains a challenging task due to the complex interplay between texture corruption and color distortions caused by moir\'e patterns. Existing methods, especially those relying on direct image-to-image restoration, often fail to disentangle these intertwined artifacts effectively. While frequency-aware approaches offer a promising direction, their potential is hindered by the discrete transform (e.g., Haar wavelet or block-based DCT), which may suffer from spatial discontinuity, channel redundancy, and further cause error accumulation during their fixed inverse processes. In this paper, we present Freqformer, a Transformer-based framework specifically designed for image demoir\'eing through targeted frequency separation. Our method performs an effective frequency decomposition that splits moir\'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions, which are then handled by a dual-branch architecture and an asymmetric training scheme tailored to their distinct characteristics. We further propose a learnable Frequency Composition Transform (FCT) module to adaptively fuse the frequency-specific outputs, enabling consistent and high-fidelity reconstruction. To better aggregate the spatial dependencies and the inter-channel complementary information, we introduce a Spatial-Aware Channel Attention (SA-CA) module that refines moir\'e-sensitive regions without incurring high computational cost. Extensive experiments on various demoir\'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size. The code will be made publicly available at https://github.com/xyLiu339/Freqformer.
Authors: Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh, Daochang Liu, Weidong Cai, Xiuying Wang, Chang Xu
Abstract: Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from salient regions within the image and leaving behind ambiguous, unfaithful features during sampling. We tackle this challenge with Information-Grounding Guidance (IGG), a novel framework that anchors guidance to semantically important tokens via an attention-based dynamic weighting formulation, consequently ensuring that guidance and semantic contents remain tightly aligned. Across both class-conditioned and text-to-image generation tasks, IGG delivers sharper, more coherent, and semantically grounded images, demonstrating its efficacy for correcting AR-based methods. Our code is available at https://github.com/dnngky/infoground-guidance.
Authors: Ermanno Bartoli, Dennis Rotondi, Buwei He, Patric Jensfelt, Kai O. Arras, Iolanda Leite
Abstract: Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-aware ways. While 3D Scene Graphs have emerged as a powerful semantic representation for scene understanding, existing approaches largely ignore humans in the scene, also due to the lack of annotated human-environment relationships. Moreover, existing methods typically capture only open-vocabulary relations from single image frames, which limits their ability to model long-range interactions beyond the observed content. We introduce Social 3D Scene Graphs, an augmented 3D Scene Graph representation that captures humans, their attributes, activities and relationships in the environment, both local and remote, using an open-vocabulary framework. Furthermore, we introduce a new benchmark consisting of synthetic environments with comprehensive human-scene relationship annotations and diverse types of queries for evaluating social scene understanding in 3D. The experiments demonstrate that our representation improves human activity prediction and reasoning about human-environment relations, paving the way toward socially intelligent robots.
Authors: Shunpeng Chen, Changwei Wang, Rongtao Xu, Xingtian Pei, Yukun Song, Jinzhou Lin, Wenhao Xu, Jingyi Zhang, Li Guo, Shibiao Xu
Abstract: Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborhoods, we seed clusters from high-affinity anchors and iteratively expand them with a greedy weighted clique expansion sampler. Implemented with a frozen DINOv2 backbone and parameter-efficient fine-tuning, SAGE achieves SOTA across eight benchmarks. Notably, our method obtains 100% Recall@10 on SPED only using 4096D global descriptors. The code and model are available at https://github.com/chenshunpeng/SAGE.
Authors: Hao Liu, Yunhao Gao, Wei Li, Mingyang Zhang, Maoguo Gong, Lorenzo Bruzzone
Abstract: Deep learning-based methods have achieved significant success in remote sensing Earth observation data analysis. Numerous feature fusion techniques address multimodal remote sensing image classification by integrating global and local features. However, these techniques often struggle to extract structural and detail features from heterogeneous and redundant multimodal images. With the goal of introducing frequency domain learning to model key and sparse detail features, this paper introduces the spatial-spectral-frequency interaction network (S$^2$Fin), which integrates pairwise fusion modules across the spatial, spectral, and frequency domains. Specifically, we propose a high-frequency sparse enhancement transformer that employs sparse spatial-spectral attention to optimize the parameters of the high-frequency filter. Subsequently, a two-level spatial-frequency fusion strategy is introduced, comprising an adaptive frequency channel module that fuses low-frequency structures with enhanced high-frequency details, and a high-frequency resonance mask that emphasizes sharp edges via phase similarity. In addition, a spatial-spectral attention fusion module further enhances feature extraction at intermediate layers of the network. Experiments on four benchmark multimodal datasets with limited labeled data demonstrate that S$^2$Fin performs superior classification, outperforming state-of-the-art methods. The code is available at https://github.com/HaoLiu-XDU/SSFin.
Authors: Dominick Reilly, Manish Kumar Govind, Le Xue, Srijan Das
Abstract: Large Vision Language Models (VLMs) excel at general visual reasoning but experience significant performance degradation when deployed in novel domains that exhibit substantial distribution shifts from their pretraining data. Existing domain adaptation methods rely on finetuning standard VLM components; however, depending on which components are updated, these approaches either limit the model's ability to learn domain-specific representations or cause catastrophic forgetting of previously acquired capabilities. We introduce Vision Contextualized Probing (VisCoP), a parameter-efficient adaptation framework that augments the VLM vision encoder with a compact set of learnable visual probes. By learning domain-specific visual representations through these probes while requiring only minimal updates to pretrained model components, VisCoP effectively adapts to new domains without sacrificing existing knowledge. We evaluate VisCoP across three challenging adaptation settings: cross-view (exocentric to egocentric), cross-modal (RGB to depth), and cross-task (human understanding to robot control). Across all scenarios, VisCoP consistently outperforms existing domain adaptation strategies, achieving superior target-domain performance while preserving the pretrained VLM's capabilities on the source domain. These results demonstrate that lightweight visual probing provides an effective and robust solution for adapting VLMs under substantial distribution shifts. Code, models, and evaluation protocols are available at https://github.com/dominickrei/VisCoP.
Authors: Yannan Chen, Ruoyu Chen, Wei Wang, Bin Zeng, Jinke Li, Shiming Liu, Qunli Zhang, Yaowei Wang, Xiaochun Cao
Abstract: Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when these cues are missing. Faithful attribution methods can reveal such problematic reliance through localized explanations, but they are typically used post hoc and are not fed back into the model. To address this limitation, we propose Subset-Selected Counterfactual Augmentation (SS-CA), a training strategy that masks decision-relevant regions to construct counterfactual samples and guide the model toward more robust decision boundaries. Specifically, we extend LIMA, a subset-selection-based faithful attribution method, to Counterfactual LIMA to identify regions whose removal shifts the model toward a competing class. SS-CA then selects near-boundary masks that reduce the logit gap while preserving the original semantics, and applies an adaptive counterfactual filling strategy to replace the masked regions without introducing external semantics. Feeding these counterfactual samples back into training encourages the model to exploit the remaining informative evidence and shifts the decision boundary toward a more robust one. Extensive experiments across five ImageNet variants show that SS-CA effectively improves ID accuracy, OOD generalization, and perturbation robustness, achieving gains of 5.70%/18.04% on ImageNet-1k/ImageNet-R with CLIP ViT/32b, 9.52%/11.33% on ImageNet-R/ImageNet-S on TinyImageNet-200 with ResNet-101, and about 4% under Gaussian Noise corruption. The code will be released soon.
Authors: Lorenzo Olearo, Giulio Vigan\`o, Daniele Baieri, Filippo Maggioli, Simone Melzi
Abstract: We introduce a novel neural representation for maps between 3D shapes based on flow-matching models, which is computationally efficient and supports cross-representation shape matching without large-scale training or data-driven procedures. 3D shapes are represented as the probability distribution induced by a continuous and invertible flow mapping from a fixed anchor distribution. Given a source and a target shape, the composition of the inverse flow (source to anchor) with the forward flow (anchor to target), we map points between the two surfaces. By encoding the shapes with a pointwise task-tailored embedding, this construction provides an invertible and modality-agnostic representation of maps between shapes across point clouds, meshes, signed distance fields (SDFs), and volumetric data. The resulting representation consistently achieves high coverage and accuracy across diverse benchmarks and challenging settings in shape matching. Beyond shape matching, our framework shows promising results in other tasks, including UV mapping and registration of raw point cloud scans of human bodies.
Authors: Li Yu, Yingbo Zhao, Shiyu Wu, Siyue Yu, Moncef Gabbouj, Qingshan Liu
Abstract: Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enhancement models for each QP setting, which are referred to as non-blind methods. However, in practical scenarios such as transcoding and transmission, QPs may be partially or entirely unavailable, which limits the applicability of these methods and motivates the development of blind QECV techniques. Existing blind methods typically generate degradation vectors using classification models trained with cross-entropy loss, and employ them as channel attention to guide artifact reduction. Nevertheless, such degradation representations mainly capture global compression information and lack fine-grained spatial cues, making them less effective in handling spatially varying artifact patterns. To address this issue, we propose a pre-trained degradation representation learning module that decouples and extracts high-dimensional, multi-scale degradation representations from compressed video content, providing fine-grained guidance for artifact reduction. Furthermore, most existing blind and nonblind methods adopt a uniform inference architecture for all compression levels, ignoring the distinct computational demands of different QPs. To overcome this limitation, we introduce a sequential inference strategy that adaptively adjusts the number of artifact reduction stages according to the estimated compression level. Extensive experiments show that the proposed method significantly improves enhancement performance. In particular, at QP = 22, it raises PSNR improvement from 0.31 dB to 0.65 dB over the previous state-of-the-art blind method. Meanwhile, with the proposed sequential inference strategy, the average inference time at QP = 22 is reduced by 50% compared with that at QP = 42.
Authors: Juntao Cheng, Wanyue Zhang, Zhiwei Yu, Shuo Ren, Zheqi He, Shaoxuan Xie, Guocai Yao, Jieru Lin, B\"orje F. Karlsson, Jiajun Zhang
Abstract: Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting with these interfaces requires agents not only to ground language in visual observations,but also to execute actions, track temporally evolving state changes, and verify whether intended outcomes have been achieved. However, existing benchmarks predominantly evaluate open-loop perception or single-step action execution, failing to capture this continuous cycle of interaction, feedback, and correction. We introduce SWITCH, a benchmark for closed-loop interactive reasoning with TCIs in realistic egocentric environments1. SWITCH comprises 1,170 temporally interactive videos across diverse functional categories, providing structured annotations of instructions, actions, state transitions, outcomes, and recovery behaviors over time. To probe generative world modeling, SWITCH also evaluates video generation models on interaction-centered tasks using both LLM-as-judge and human evaluation2.Experiments with frontier proprietary and opensource multimodal models reveal persistent weaknesses in fine-grained visual-temporal perception, outcome verification, and error recovery, highlighting SWITCH as a testbed for closed-loop embodied intelligence.
Authors: Chen Ling, Henglin Shi, Hedvig Kjellstr\"om
Abstract: Monocular 3D face reconstruction estimates a 3D morphable model (3DMM) representation from a single image, providing geometry-aware expression codes that are useful for facial expression analysis and affect understanding. Despite strong progress, most pipelines are trained with image-level self-supervision and evaluated primarily by geometric fidelity, which does not necessarily maximize the affective utility of the learned expression representation and may encourage intensity-amplifying shortcuts when affect supervision is naively coupled. We propose FIELDS (Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision), a task-driven framework that learns FLAME expression codes for facial expression recognition (FER) under a geometric plausibility constraint. Using hybrid 2D/3D supervision, FIELDS improves affect prediction in both in-domain and external evaluations while maintaining competitive geometric fidelity on held-out and out-of-domain 3D benchmarks.
Authors: Sandeep Mishra, Yasamin Jafarian, Andreas Lugmayr, Yingwei Li, Varsha Ramakrishnan, Srivatsan Varadharajan, Alan C. Bovik, Ira Kemelmacher-Shlizerman
Abstract: Photographs of people taken by professional photographers typically present the person in beautiful lighting, with an interesting pose, and flattering quality. This is unlike common photos people take of themselves in uncontrolled conditions. In this paper, we explore how to canonicalize a person's 'in-the-wild' photograph into a controllable, high-fidelity avatar -- reposed in a simple environment with standardized minimal clothing. A key challenge is preserving the person's unique whole-body identity, facial features, and body shape while stripping away the complex occlusions of their original garments. While a large paired dataset of the same person in varied clothing and poses would simplify this, such data does not exist. To that end, we propose two key insights: 1) Our method transforms the input photo into a canonical full-body UV space, which we couple with a novel reposing methodology to model occlusions and synthesize novel views. Operating in UV space allows us to decouple pose from appearance and leverage massive unpaired datasets. 2) We personalize the output photo via multi-image finetuning to ensure robust identity preservation under extreme pose changes. Our approach yields high-quality, reposed portraits that achieve strong quantitative performance on real-world imagery, providing an ideal, clean biometric canvas that significantly improves the fidelity of downstream applications like Virtual Try-On (VTO).
Authors: Wenyuan Huang, Zhenyu Zhang, Zhao Wang, Zhou Wei, Ting Huang, Fang Zhao, Jian Yang
Abstract: 3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes. Existing supervised methods are limited by generalization and recent zero-shot methods typically rely on a predefined Object Lookup Table (OLT) to query Visual Language Models (VLMs) for reasoning about object locations via a single step grounding, which limits the applications in scenarios with undefined targets and complex queries. To address these problems, we present OpenGround, a novel zero-shot framework for open-world 3D visual grounding that remains compatible with recent zero-shot methods. OpenGround integrates Task-Chain Planning to decompose a query into a plan of context-to-target sub-goals for progressive grounding, and Context-Guided Perception to perceive novel objects online under context guidance from the task chain. We also propose a new dataset named OpenTarget, which contains over 7000 object-description pairs to mimic open-world evaluation. Extensive experiments demonstrate that OpenGround achieves competitive performance on Nr3D, state-of-the-art on ScanRefer, and delivers a substantial 17.6\% improvement on OpenTarget. Project Page at https://why-102.github.io/openground.io/.
Authors: Taeyeon Kim, Youngju Na, Jumin Lee, Sebin Lee, Minhyuk Sung, Sung-Eui Yoon
Abstract: Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source and target. Existing approaches often follow a reconstruct-then-retarget paradigm, tying transfer quality to intermediate 3D reconstruction and limiting applicability to categories with parametric templates. We propose MorphGS, a framework that formulates motion retargeting as a target-driven analysis-by-synthesis problem, directly optimizing target morphology and pose through image-space supervision. A rig-coupled morphology parameterization factorizes character identity from time-varying joint rotations, while dense 2D-3D correspondences and synthesized views provide complementary structural and multi-view guidance. Experiments on synthetic benchmarks and real-world videos show consistent improvements over baselines. Project page: https://xodus777.github.io/MorphGS/
Authors: Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu
Abstract: Nighttime color constancy still remains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods with deep reinforcement learning for nighttime white balance. Our method begins with a statistical algorithm tailored for nighttime scenes, integrating salient gray pixel detection with novel illuminant estimation. Building on this foundation, we develop the first deep reinforcement learning approach for color constancy that leverages the statistical algorithm as its core, mimicking professional AWB tuning experts by dynamically determining image-specific parameters at inference time, without requiring ground-truth illuminants or reference images. To further facilitate cross-sensor evaluation, we introduce the first multi-sensor nighttime dataset. Experiment results demonstrate that our method achieves strong generalization capability across low-light and well-illuminated images. Project page: https://ntuneillee.github.io/research/rl-awb/
Authors: Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Ming Wu, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li
Abstract: While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.
Authors: Yu Wu, Minsik Jeon, Jen-Hao Rick Chang, Oncel Tuzel, Shubham Tulsiani
Abstract: We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene. We find that prior (absolute or relative) encoding schemes for multi-view attention do not meet these desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays and computes query-frame projective coordinates to ensure SE(3) invariance. To adapt to scene geometry, RayRoPE predicts (without direct supervision) a per-token depth to obtain its position along the corresponding ray, while also modeling uncertainty and analytically computing the expected positional encoding. We validate our method on the tasks of novel-view synthesis, stereo depth estimation, and feed-forward 3DGS reconstruction. While remaining efficient, RayRoPE consistently improves over alternate position encoding schemes (e.g., 24% relative improvement on LPIPS in RE10K).
Authors: Baoliang Chen, Danni Huang, Hanwei Zhu, Lingyu Zhu, Wei Zhou, Shiqi Wang, Yuming Fang, Weisi Lin
Abstract: Evaluation of Image Quality Assessment (IQA) models has long been dominated by global correlation metrics, such as Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank-Order Correlation Coefficient (SRCC). While widely adopted, these metrics reduce performance to a single scalar, failing to capture how ranking consistency varies across the local quality spectrum. For example, two IQA models may achieve identical SRCC values, yet one ranks high-quality images (related to high Mean Opinion Score, MOS) more reliably, while the other better discriminates image pairs with small quality/MOS differences (related to $|\Delta$MOS$|$). Such complementary behaviors are invisible under global metrics. Moreover, SRCC and PLCC are sensitive to test-sample quality distributions, yielding unstable comparisons across test sets. To address these limitations, we propose \textbf{Granularity-Modulated Correlation (GMC)}, which provides a structured, fine-grained analysis of IQA performance. GMC includes: (1) a \textbf{Granularity Modulator} that applies Gaussian-weighted correlations conditioned on absolute MOS values and pairwise MOS differences ($|\Delta$MOS$|$) to examine local performance variations, and (2) a \textbf{Distribution Regulator} that regularizes correlations to mitigate biases from non-uniform quality distributions. The resulting \textbf{correlation surface} maps correlation values as a joint function of MOS and $|\Delta$MOS$|$, providing a 3D representation of IQA performance. Experiments on standard benchmarks show that GMC reveals performance characteristics invisible to scalar metrics, offering a more informative and reliable paradigm for analyzing, comparing, and deploying IQA models. Codes are available at https://github.com/Dniaaa/GMC.
Authors: Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu, Jason Li, Mengyuan Liu
Abstract: Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms suffer from severe fragmentation. First, the field is split between ``perception'' models that understand motion from video but only output text, and ``generation'' models that cannot perceive from raw visual input. Second, generative MLLMs are often limited to single-frame, static poses using dense, parametric SMPL models, failing to handle temporal motion. Third, existing motion vocabularies are built from skeleton data alone, severing the link to the visual domain. To address these challenges, we introduce Superman, a unified framework that bridges visual perception with temporal, skeleton-based motion generation. Our solution is twofold. First, to overcome the modality disconnect, we propose a Vision-Guided Motion Tokenizer. Leveraging the natural geometric alignment between 3D skeletons and visual data, this module pioneers robust joint learning from both modalities, creating a unified, cross-modal motion vocabulary. Second, grounded in this motion language, a single, unified MLLM architecture is trained to handle all tasks. This module flexibly processes diverse, temporal inputs, unifying 3D skeleton pose estimation from video (perception) with skeleton-based motion prediction and in-betweening (generation). Extensive experiments on standard benchmarks, including Human3.6M, demonstrate that our unified method achieves state-of-the-art or competitive performance across all motion tasks. This showcases a more efficient and scalable path for generative motion analysis using skeletons.
Authors: Julia Werner, Julius Oexle, Oliver Bause, Maxime Le Floch, Franz Brinkmann, Hannah Tolle, Jochen Hampe, Oliver Bringmann
Abstract: The classification performance of deep neural networks relies strongly on access to large, accurately annotated datasets. In medical imaging, however, obtaining such datasets is particularly challenging since annotations must be provided by specialized physicians, which severely limits the pool of annotators. Furthermore, class boundaries can often be ambiguous or difficult to define which further complicates machine learning-based classification. In this paper, we want to address this problem and introduce a framework for mislabel detection in medical datasets. This is validated on the two largest, publicly available datasets for Video Capsule Endoscopy, an important imaging procedure for examining the gastrointestinal tract based on a video stream of lowresolution images. In addition, potentially mislabeled samples identified by our pipeline were reviewed and re-annotated by three experienced gastroenterologists. Our results show that the proposed framework successfully detects incorrectly labeled data and results in an improved anomaly detection performance after cleaning the datasets compared to current baselines.
Authors: Kerri Lu, Dan M. Kluger, Stephen Bates, Sherrie Wang
Abstract: Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth. To address this limitation, we introduce a conformal prediction algorithm to generate adaptive confidence sets for instance segmentation. Given an image and a pixel coordinate query, our algorithm generates a confidence set of instance predictions for that pixel, with a provable guarantee for the probability that at least one of the predictions has high Intersection-Over-Union (IoU) with the true object instance mask. We apply our algorithm to instance segmentation examples in agricultural field delineation, cell segmentation, and vehicle detection. Empirically, we find that our prediction sets vary in size based on query difficulty and attain the target coverage, outperforming baselines (naive best parameter and morphological dilation-based methods). We provide versions of the algorithm with asymptotic and finite sample guarantees. Our work is the first to capture structural uncertainty in instance segmentation by constructing confidence sets of diverse segmentation predictions.
Authors: Jialin Ma
Abstract: With the increasing availability of high-resolution remote sensing and aerial imagery, oriented object detection has become a key capability for geographic information updating, maritime surveillance, and disaster response. However, it remains challenging due to cluttered backgrounds, severe scale variation, and large orientation changes. Existing approaches largely improve performance through multi-scale feature fusion with feature pyramid networks or contextual modeling with attention, but they often lack explicit foreground modeling and do not leverage geometric orientation priors, which limits feature discriminability. To overcome these limitations, we propose FGAA-FPN, a Foreground-Guided Angle-Aware Feature Pyramid Network for oriented object detection. FGAA-FPN is built on a hierarchical functional decomposition that accounts for the distinct spatial resolution and semantic abstraction across pyramid levels, thereby strengthening multi-scale representations. Concretely, a Foreground-Guided Feature Modulation module learns foreground saliency under weak supervision to enhance object regions and suppress background interference in low-level features. In parallel, an Angle-Aware Multi-Head Attention module encodes relative orientation relationships to guide global interactions among high-level semantic features. Extensive experiments on DOTA v1.0 and DOTA v1.5 demonstrate that FGAA-FPN achieves state-of-the-art results, reaching 75.5% and 68.3% mAP, respectively.
Authors: Shufan Li, Yuchen Zhu, Jiuxiang Gu, Kangning Liu, Zhe Lin, Yongxin Chen, Molei Tao, Aditya Grover, Jason Kuen
Abstract: Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.
Authors: Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu
Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in a unified camera-centric space, and a post-training phase for efficient embodiment alignment within robot-specific action space. By introducing discrete pose tokens as a universal representation, Pose-VLA seamlessly integrates spatial grounding from diverse 3D datasets with geometry-level trajectories from robotic demonstrations. Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment through trajectory supervision. Extensive evaluations demonstrate that Pose-VLA achieves state-of-the-art results on RoboTwin 2.0 with a 79.5% average success rate and competitive performance on LIBERO at 96.0%. Real-world experiments further showcase robust generalization across diverse objects using only 100 demonstrations per task, validating the efficiency of our pre-training paradigm.
Authors: Chao Wu, Mahesh Bhosale, Kangxian Xie, Pouya Karimian, David Doermann, Mingchen Gao
Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deterministic models preserve coherent volumetric structures but collapse expert disagreement into a single mask, while stochastic generative models can produce diverse samples but may introduce disconnected components or slice-to-slice inconsistency when generating full 3D masks from unstructured noise. We propose Volumetric Directional Diffusion (VDD), a prior-anchored diffusion framework that shifts stochastic generation from full-mask synthesis to residual boundary exploration. VDD uses a coarse consensus prediction as an anatomical anchor and learns a directional diffusion process to generate plausible boundary variations around ambiguous regions while preserving stable volumetric topology. Experiments on three multi-rater datasets, including LIDC-IDRI, KiTS21, and ISBI 2015, show that VDD improves uncertainty distribution alignment while maintaining competitive segmentation accuracy and 3D structural consistency. These results suggest that prior-anchored residual diffusion can model clinically plausible expert disagreement without sacrificing anatomical fidelity.
Authors: Yiyang Lin, Chenhui Wang, Zhihao Peng, Yixuan Yuan
Abstract: Magnetic Resonance Imaging (MRI) field-strength enhancement holds immense value for both clinical diagnostics and advanced research. However, existing methods typically focus on isolated enhancement tasks, such as specific 64mT-to-3T or 3T-to-7T transitions using limited subject cohorts, thereby failing to exploit the shared degradation patterns inherent across different field strengths and severely restricting model generalization. To address this challenge, we propose \methodname, a unified framework integrating multiple modalities and enhancement tasks to mutually promote representation learning by exploiting these shared degradation characteristics. Specifically, our main contributions are threefold. Firstly, to overcome MRI data scarcity and capture continuous anatomical structures, \methodname departs from conventional methods that treat 3D MRI volumes as independent 2D slices. Instead, we directly exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models, thereby embedding generalized and robust structural representations to significantly boost enhancement performance. In addition, to mitigate the spectral bias of mainstream flow-matching models that often over-smooth high-frequency details, we explicitly incorporate the physical mechanisms of magnetic fields to introduce a Field-Aware Spectral Rectification Mechanism (FASRM), tailoring customized spectral corrections to distinct field strengths. Finally, to resolve the fundamental data bottleneck, we organize and publicly release a comprehensive paired multi-field MRI dataset, which is an order of magnitude larger than existing datasets. Extensive experiments demonstrate our method's superiority over state-of-the-art approaches, achieving an average improvement of approximately 1.81 dB in PSNR and 9.47% in SSIM. Codes and datasets are available at: https://github.com/linyiyang98/UniField.
Authors: Siyi Qian, Xiongfei Bai, Bingtao Fu, Yichen Lu, Gaoyang Zhang, Xudong Yang, Peng Zhang
Abstract: In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the Overall metric of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, LingDT-VL-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.
Authors: Mengfei Duan, Hao Shi, Fei Teng, Guoqiang Zhao, Yuheng Zhang, Zhiyong Li, Kailun Yang
Abstract: Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for autonomous agents and embodied systems. However, existing 3D occupancy prediction methods are constrained by limited perspective inputs and a predefined training distribution, making them difficult to apply to embodied agents that require comprehensive and safe perception of scenes in open-world exploration. To address this, we present O3N, the first framework for open-vocabulary occupancy prediction from a single omnidirectional RGB image. O3N embeds omnidirectional voxels in a polar-spiral topology via the Polar-spiral Mamba (PsM) module, enabling continuous spatial representation and long-range context modeling across 360{\deg}. The Occupancy Cost Aggregation (OCA) module introduces a principled mechanism for unifying geometric and semantic supervision within the voxel space, ensuring consistency between the reconstructed geometry and the underlying semantic structure. Moreover, Natural Modality Alignment (NMA) establishes a gradient-free alignment pathway that harmonizes visual features, voxel embeddings, and text semantics, forming a consistent ``pixel-voxel-text'' representation triad. Extensive experiments on multiple models demonstrate that our method not only achieves state-of-the-art performance on QuadOcc and Human360Occ benchmarks but also exhibits remarkable cross-scene generalization and semantic scalability, highlighting the potential of O3N for scalable open-world 3D scene understanding. The source code will be made publicly available at https://github.com/MengfeiD/O3N.
Authors: James Song, Yifan Wang, Chuan Zhou, Liyue Shen
Abstract: Lung cancer remains the leading cause of cancer-related mortality worldwide, with survival outcomes critically dependent on early and accurate detection. When low-dose computed tomography (LDCT) findings are indeterminate, clinicians typically defer diagnosis pending follow-up CT imaging obtained up to 12 months later, inevitably delaying treatment for patients with malignant nodules. To address this clinical gap, we propose Nodule-Aligned Multimodal (Latent) Diffusion (NAMD), a novel generative framework that synthesizes one-year follow-up nodule CT images conditioned on the baseline CT scan, quantitative nodule biomarkers, and patient-level Electronic Health Records (EHR), enabling timely prediction of nodule malignant progression without requiring actual follow-up scans. NAMD introduces two key contributions: (i) a nodule-aligned latent space regularized so that embedding distances reflect clinically meaningful biomarker changes, and (ii) an LLM-driven multimodal conditioning mechanism encoding heterogeneous EHR data into the diffusion backbone. Evaluated on the National Lung Screening Trial (NLST), our method's synthetic follow-up images achieve an AUROC of 0.805 and an AUPRC of 0.346 for lung nodule malignancy prediction, outperforming both the baseline LDCT performance without virtual follow-up generation, and existing state-of-the-art conditional generation methods, while maintaining competitive image quality. These findings suggest that NAMD enables earlier and more accurate lung cancer diagnosis by capturing clinically meaningful features of nodule progression.
Authors: Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi, Philipp Berens
Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, a critical issue in high-stakes domains such as medical imaging. We propose \model, a foundation model that is interpretable-by-design via a BagNet backbone whose small receptive fields generate class evidence maps that are faithful to the model's decision-making process. Additionally, \model{} incorporates a $2D$ projection layer during pretraining that enables direct visualization of the representation space, providing a dataset-level view of the learned structure including meaningful clinical clusters as well as potential spurious correlations. We trained \model{} on over 800,000 color fundus photographs from various sources to learn generalizable representations for different downstream tasks. Our model achieves performance comparable to RETFound, which has $16\times$ more parameters, while providing interpretable predictions on out-of-distribution data. These results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging. Code and pretrained models are available at \href{https://anonymous.4open.science/r/dual-ifm-3D5A/README.md}{www.anonymous.4open.science/dual-IFM}.
URLs: https://anonymous.4open.science/r/dual-ifm-3D5A/README.md
Authors: Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, Jerry Xiong, Yifan Shen, Ying Shen, Ismini Lourentzou
Abstract: Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment.
Authors: Wen Jiang, Kangyao Huang, Li Wang, Wang Xu, Wei Fan, Jinyuan Liu, Shaoyu Liu, Hanfang Liang, Hongwei Duan, Bin Xu, Xiangyang Ji, Huaping Liu
Abstract: UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN in complex 3D environments remains challenging. A key difficulty is the structural representation mismatch between 2D visual perception and the 3D trajectory decision space, which limits spatial reasoning. To this end, we propose SpatialFly, a geometry-guided spatial representation framework for UAV VLN. Operating on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D adaptive representation mechanism. Specifically, the geometric prior injection module injects global structural cues into 2D semantic tokens to provide scene-level geometric guidance. The geometry-aware reparameterization module then uses geometry-conditioned cross-modal attention and gated residual fusion to adaptively reparameterize the visual tokens. Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments, reducing NE by 4.03m and improving SR by 1.27% over the strongest baseline on the unseen Full split. Additional trajectory-level analysis shows that SpatialFly produces trajectories with better path alignment and smoother, more stable motion.
Authors: Detao Bai, Zhiheng Ma, Xihan Wei
Abstract: While Omni-modal Large Language Models have made strides in joint sensory processing, they fundamentally struggle with a cornerstone of human interaction: deciphering complex, multi-person conversational dynamics to accurately answer ``Who said what and when.'' Current models suffer from an ``illusion of competence'' -- they exploit visual biases in conventional benchmarks to bypass genuine cross-modal alignment, while relying on sparse, low-frame-rate visual sampling that destroys crucial high-frequency dynamics like lip movements. To shatter this illusion, we introduce Visual-Registered Speaker Diarization and Recognition (VR-SDR) and the HumanOmni-Speaker Benchmark. By strictly eliminating visual shortcuts, this rigorous paradigm demands true end-to-end spatio-temporal identity binding using only natural language queries. To overcome the underlying architectural perception gap, we propose HumanOmni-Speaker, powered by a Visual Delta Encoder. By sampling raw video at 25 fps and explicitly compressing inter-frame motion residuals into just 6 tokens per frame, it captures fine-grained visemes and speaker trajectories without triggering a catastrophic token explosion. Ultimately, HumanOmni-Speaker demonstrates strong multimodal synergy, natively enabling end-to-end lip-reading and high-precision spatial localization without intrusive cropping, and achieving superior performance across a wide spectrum of speaker-centric tasks.
Authors: Jiajian Huang, Dongliang Zhu, Zitong YU, Hui Ma, Jiayu Zhang, Chunmei Zhu, Xiaochun Cao
Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-stakes settings, investigators need verifiable evidence connecting audiovisual cues to final decisions, along with reliable generalization across domains and cultural contexts. However, existing benchmarks provide only binary labels without intermediate reasoning cues. Datasets are also small with limited scenario coverage, leading to shortcut learning. We address these issues through three contributions. First, we construct reasoning datasets by augmenting existing benchmarks with structured cue-level descriptions and reasoning chains, enabling models to output auditable reports. Second, we release T4-Deception, a multicultural dataset based on the unified ``To Tell the Truth'' television format implemented across four countries. With 1695 samples, it is the largest non-laboratory deception detection dataset. Third, we propose two modules for robust learning under small-data conditions. Stabilized Individuality-Commonality Synergy (SICS) refines multimodal representations by combining learnable global priors with sample-adaptive residuals and applying polarity-aware recalibration. Distilled Modality Consistency (DMC) aligns modality-specific predictions with the fused multimodal predictions via knowledge distillation to prevent unimodal shortcut learning. Experiments on three established benchmarks and our novel dataset demonstrate that our method achieves state-of-the-art performance in both in-domain and cross-domain scenarios, while exhibiting superior transferability across diverse cultural contexts. The datasets and code are available at this link.
Authors: Yicheng Xu, Jiangning Zhang, Zhucun Xue, Teng Hu, Ran Yi, Xiaobin Hu, Yong Liu, Dacheng Tao
Abstract: In-context learning (ICL) enables fast task adaptation from demonstrations without per-task parameter updates but remains highly sensitive to example selection and formatting. In unified multimodal models spanning understanding and generation, this sensitivity is exacerbated by cross-modal interference and varying cognitive demands. Consequently, in-context learning efficacy is often non-monotonic and highly task-dependent. To diagnose these behaviors, we introduce a six-level Capability-Oriented Taxonomy that categorizes the functional role of demonstrations from basic perception to high-order discernment. Guided by this cognitive framework, we construct UniICL-760K, a large-scale corpus featuring curated 8-shot in-context learning episodes across 15 subtasks, alongside UniICL-Bench for rigorous, controlled evaluation. We show that this data-driven assembly is the primary source of our gains. As a complementary, lightweight stabilizer, we additionally propose the Context-Adaptive Prototype Modulator, a plug-and-play module that further improves few-shot stability. Evaluations on UniICL-Bench show that our approach yields highly competitive unified results, outperforming larger-parameter multimodal large language model baselines on most understanding in-context learning tasks. Data and code are available at https://github.com/xuyicheng-zju/UniICL.
Authors: Jiho Choi, Jaemin Kim, Sanghwan Kim, Seunghoon Hong, Jin-Hwi Park
Abstract: Attention sinks are defined as tokens that attract disproportionate attention. While these have been studied in single modality transformers, their cross-modal impact in Large Vision-Language Models (LVLM) remains largely unexplored: are they redundant artifacts or essential global priors? This paper first categorizes visual sinks into two distinct categories: ViT-emerged sinks (V-sinks), which propagate from the vision encoder, and LLM-emerged sinks (L-sinks), which arise within deep LLM layers. Based on the new definition, our analysis reveals a fundamental performance trade-off: while sinks effectively encode global scene-level priors, their dominance can suppress the fine-grained visual evidence required for local perception. Furthermore, we identify specific functional layers where modulating these sinks most significantly impacts downstream performance. To leverage these insights, we propose Layer-wise Sink Gating (LSG), a lightweight, plug-and-play module that dynamically scales the attention contributions of V-sink and the rest visual tokens. LSG is trained via standard next-token prediction, requiring no task-specific supervision while keeping the LVLM backbone frozen. In most layers, LSG yields improvements on representative multimodal benchmarks, effectively balancing global reasoning and precise local evidence.
Authors: Changdao Chen, Qinqiuhong Ye, Hao Chen, Jinyu Wang
Abstract: It remains challenging to assess driver fatigue from untrimmed videos under constrained computational budgets, due to the difficulty of modeling long-range temporal dependencies in subtle facial expressions. Some existing approaches rely on computationally heavy architectures, whereas others employ traditional lightweight pairwise graph networks, despite their limited capacity to model high-order synergies and global temporal context. Therefore, we propose HST-HGN, a novel Heterogeneous Spatial-Temporal Hypergraph Network driven by Bidirectional State Space Models. Spatially, we introduce a hierarchical hypergraph network to fuse pose-disentangled geometric topologies with multi-modal texture patches dynamically. This formulation encapsulates high-order synergistic facial deformations, effectively overcoming the limitations of conventional methods. In temporal terms, a Bi-Mamba module with linear complexity is applied to perform bidirectional sequence modeling. This explicit temporal-evolution filtering enables the network to distinguish highly ambiguous transient actions, such as yawning versus speaking, while encompassing their complete physiological lifecycles. Extensive evaluations across diverse fatigue benchmarks demonstrate that HST-HGN achieves state-of-the-art performance. In particular, our method strikes a balance between discriminative power and computational efficiency, making it well-suited for real-time in-cabin edge deployment.
Authors: Guillermo Auza Banegas, Diego Calvimontes Vera, Natalia Condori Peredo, Edwin Salcedo, Sergio Castro Sandoval
Abstract: Robust license plate recognition in unconstrained environments remains a significant challenge, particularly in underrepresented regions with limited data availability and unique visual characteristics, such as Bolivia. Recognition accuracy in real-world conditions is often degraded by illumination changes and viewpoint distortion. To address these challenges, we introduce BLPR, a deep learning-based License Plate Detection and Recognition (LPDR) framework designed for Bolivian license plates. BLPR adaptively applies geometric rectification, illumination correction, and VLM-assisted fallback based on image-condition and confidence cues. The proposed system uses a YOLO-based detector pretrained on synthetic data generated in Blender to simulate extreme perspectives and lighting conditions, and is fine-tuned on street-level data collected in La Paz, Bolivia. Detected plates are processed by a YOLO-based character recognizer, while a lightweight vision-language model (Gemma3 4B) is selectively triggered in ambiguous cases as a confidence-driven fallback mechanism. We also introduce the first publicly available Bolivian LPDR dataset for academic research, supporting evaluation under diverse viewpoint and illumination conditions. The system achieves a character-level recognition accuracy of 89.6% on real-world data, demonstrating its effectiveness for deployment in challenging urban environments.
Authors: Sohwi Lim, Lee Hyoseok, Jungjoon Park, Tae-Hyun Oh
Abstract: Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieval systems fail to reflect this flexibility, relying on a fixed, monolithic metric that cannot incorporate multiple conditions simultaneously. To address this, we propose CLAY, an adaptive similarity computation method that reframes the embedding space of pretrained Vision-Language Models (VLMs) as a text-conditional similarity space without additional training. This design separates the textual conditioning process and visual feature extraction, allowing highly efficient and multi-conditioned retrieval with fixed visual embeddings. We also construct a synthetic evaluation dataset CLAY-EVAL, for comprehensive assessment under diverse conditioned retrieval settings. Experiments on standard datasets and our proposed dataset show that CLAY achieves high retrieval accuracy and notable computational efficiency compared to previous works.
Authors: Jian Han, Jinlai Liu, Jiahuan Wang, Bingyue Peng, Zehuan Yuan
Abstract: While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently complexity-aware, as evidenced by their variable likelihoods, but are often hindered by lossy discrete tokenization and error accumulation. In this work, we introduce Generative Refinement Networks (GRN), a next-generation visual synthesis paradigm that addresses these issues. At its core, GRN addresses the discrete tokenization bottleneck through a theoretically near-lossless Hierarchical Binary Quantization (HBQ), achieving a reconstruction quality comparable to continuous counterparts. Built upon HBQ's latent space, GRN fundamentally upgrades AR generation with a global refinement mechanism that progressively perfects and corrects artworks -- like a human artist painting. Besides, GRN integrates an entropy-guided sampling strategy, enabling complexity-aware, adaptive-step generation without compromising visual quality. On the ImageNet benchmark, GRN establishes new records in image reconstruction (0.56 rFID) and class-conditional image generation (1.81 gFID). We also scale GRN to more challenging text-to-image and text-to-video generation, delivering superior performance on an equivalent scale. We release all models and code to foster further research on GRN.
Authors: Finn Rasmus Sch\"afer, Yuan Gao, Dingrui Wang, Thomas Stauner, Stephan G\"unnemann, Mattia Piccinini, Sebastian Schmidt, Johannes Betz
Abstract: While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving, their ability to ground this reasoning in the underlying physics of ego-motion remains poorly understood. We introduce EgoDyn-Bench [Project page: (https://tum-avs.github.io/EgoDyn-Bench-Website/), Code: (https://github.com/TUM-AVS/EgoDyn-Bench), Dataset: (https://huggingface.co/datasets/fnc1901/EgoDyn-Bench)], a diagnostic benchmark for evaluating the semantic ego-motion understanding of vision-centric foundation models. By mapping continuous vehicle kinematics to discrete motion concepts via a deterministic oracle, we decouple a model's internal physical logic from its visual perception. Our large-scale empirical audit spanning 20$+$ models, including closed-source MLLMs, open-source VLMs across multiple scales, and specialized VLAs, identifies a significant Perception Bottleneck: while models exhibit logical physical concepts, they consistently fail to accurately align them with visual observations, frequently underperforming classical non-learned geometric baselines. This failure persists across model scales and domain-specific training, indicating a structural deficit in how current architectures couple visual perception with physical reasoning. We demonstrate that providing explicit trajectory encodings substantially restores physical consistency across all evaluated models, revealing a functional disentanglement between vision and language: ego-motion logic is derived almost exclusively from the language modality, while visual observations contribute negligible temporal signal. This structural finding provides a standardized diagnostic framework and a practical pathway toward physically aligned embodied AI. Ego-motion - Physical Reasoning - Foundation Models
URLs: https://tum-avs.github.io/EgoDyn-Bench-Website/),, https://github.com/TUM-AVS/EgoDyn-Bench),, https://huggingface.co/datasets/fnc1901/EgoDyn-Bench)],
Authors: Mingliang Liang, Zhuoran Liu, Arjen P. de Vries, Martha Larson
Abstract: The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of topics in the data to improve VLM accuracy. However, existing efficient pre-training approaches may disproportionately remove rare concepts from the training corpus. As a result, long-tail concepts remain insufficiently represented in the training data and are not effectively captured during training. In this work, we introduce a dynamic cluster-based sampling approach (DynamiCS) that downsamples large clusters of data and upsamples small ones. We first demonstrate the advantage of our cluster-scaling approach, which maintains the relative order of semantic clusters in the data and emphasizes the long-tail. This approach contrasts with current work, which focuses only on flattening the semantic distribution of the data. Then, we show the importance of dynamic sampling, which applies sampling at each epoch to improve cross-epoch data diversity and make upsampling practical. Our experiments show that DynamiCS reduces the computational cost of VLM training and provides a performance advantage for long-tail concepts. Code available at https://github.com/MingliangLiang3/DynamiCS.
Authors: Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai, Wang Chen
Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize training images, causing generated outputs to reproduce copyrighted or sensitive content. This risk is particularly concerning in LoRA-sharing ecosystems, where users distribute trained LoRAs without releasing the underlying training data. Existing approaches for mitigating memorization rely on access to the training pipeline, training data, or control over the inference process, making them difficult to apply when only the released LoRA weights are available. We propose \textbf{Base-Anchored Filtering (BAF)}, a training-free and data-free framework for post-hoc memorization mitigation in diffusion LoRAs. BAF decomposes LoRA updates into spectral channels and measures their alignment with the principal subspace of the pretrained backbone. Channels strongly aligned with this subspace are retained as generalizable adaptations, while weakly aligned channels are suppressed as potential carriers of memorized content. Experiments on multiple datasets and diffusion backbones demonstrate that BAF consistently reduces memorization while preserving or even improving generation quality. Our code is available in the supplementary material.
Authors: Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia
Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we study massive activations: a small subset of hidden-state channels whose responses are consistently much larger than the rest. We show that, despite their sparsity, these few channels effectively draw the whole picture, in three complementary senses. First, they are functionally critical: a controlled disruption probe that zeroes the massive channels causes a sharp collapse in generation quality, while disrupting an equally-sized set of low-statistic channels has marginal effect. Second, they are spatially organized: restricting image-stream tokens to massive channels and clustering them yields coherent partitions that closely align with the main subject and salient regions, exposing a structured spatial code hidden inside an apparently outlier-like subspace. Third, they are transferable: transporting massive activations from one prompt-conditioned trajectory into another, shifts the final image toward the source prompt while preserving substantial content from the target, producing localized semantic interpolation rather than unstructured pixel blending. We exploit this property in two use cases: text-conditioned and image-conditioned semantic transport, where massive activations transport enables prompt interpolation and subject-driven generation without any additional training. Together, these results recast massive activations not as activation anomalies, but as a sparse prompt-conditioned carrier subspace that organizes and controls semantic information in modern DiT models.
Authors: Nikita Starodubcev, Ilia Sudakov, Ilya Drobyshevskiy, Artem Babenko, Dmitry Baranchuk
Abstract: Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by register tokens. As diffusion models increasingly adopt transformer architectures and move toward pixel-space training, they become closer in form to ViTs, raising the question of whether register tokens are also useful for Diffusion Transformers (DiTs). In this work, we show that DiTs differ from ViTs in a key respect: they do not exhibit patch-token outliers but still benefit from registers. Interestingly, registers are more effective in pixel-space DiTs than in latent-space DiTs. By analyzing intermediate representations, we find that register tokens produce cleaner feature maps at high noise levels, which may contribute to their effectiveness in pixel-space generation. We further observe that recent pixel-space DiT architectures implicitly incorporate register-like mechanisms, which may partially account for their strong empirical performance. Motivated by these observations, we propose Register Guidance, a technique that amplifies the contribution of register tokens responsible for improving visual structure and coherence.
Authors: Franciskus Xaverius Erick, Johanna Paula M\"uller, Bernhard Kainz
Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billions of parameters on scarce, expert-annotated pathology data is prohibitive, while in-context learning (ICL), which conditions the VLM on demonstrative image-text pairs without parameter updates, suffers from high sensitivity to which examples are selected and how the query is phrased, producing unreliable diagnostics. Existing selection strategies rely on query-dependent nearest-neighbour retrieval that ignores global data structure, require costly parameter updates, or disregard the joint vision-text embedding geometry of VLMs. We propose GAUC, a training-free coreset selection method operating directly in the pre-trained multimodal embedding space. GAUC jointly optimises three objectives: (1) a Maximum Mean Discrepancy term enforcing distributional fidelity between coreset and full dataset, (2) an Effective Mutual Information Difference regulariser bounding performance degradation under prompt paraphrases by exploiting the VLM's joint vision-text alignment, and (3) a predictive-uncertainty (entropy) penalty suppressing ambivalent, hallucination-prone outputs. On CRC-100K and MHIST across multiple open-source VLM architectures, GAUC \emph{matches} the accuracy of the strongest ICL selection and dataset-distillation baselines while substantially improving calibration, prompt robustness, and hallucination rates, all without a single gradient update.
Authors: Michal Shlapentokh-Rothman, Prachi Garg, Yu-Xiong Wang, Derek Hoiem
Abstract: Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require, and finding the right frames depends on knowing what to look for. Existing keyframe selectors either score every frame against a single query, or decompose the query into a fixed schema evaluated by a single visual tool. We propose ToolMerge, a keyframe retrieval method based on decomposition and merging: an Large Language Model (LLM) based planner decomposes the query into tool calls and specifies how their per-tool rankings are merged using boolean operators. To evaluate retrieval directly, we construct Molmo-2 Moments (M2M), a benchmark in which every question is anchored to a specific time interval by construction. Across QA, question retrieval, and caption retrieval, ToolMerge is competitive with prior keyframe selectors, most notably on caption retrieval, outperforming other methods by 5%. Code and data can be found at https://github.com/michalsr/ToolMerge .
Authors: Yuan Li, Congyi Zhang, Xifeng Gao, Xiaohu Guo
Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence prediction, while uniform or octree-based voxel grids preserve ordering at the cost of severe redundancy and excessively long sequences. This structural trade-off limits stable and efficient autoregressive 3D generation. We present SuperVoxelGPT, a representation-first framework that resolves this tension through adaptive and deterministically ordered supervoxel tokenization. Given a prompt, we first predict a coarse geometric saliency distribution and construct a shape-adaptive supervoxel partition using saliency-guided centroidal Voronoi tessellation, allocating fine-grained cells to complex regions and larger cells to smooth regions. Conditioned on this prompt and ordered supervoxel layout, we introduce a SuperVoxelVAE and fine-tune a pretrained MLLM to autoregressively generate supervoxel tokens. Experiments using Trellis-500K data show that SuperVoxelGPT reduces token sequence length to 12.8% of uniform voxel tokenization while achieving state-of-the-art generation quality and an average 10x speedup over prior methods.
Authors: Qian Kou, Xiaofeng Shi, Yulin Li, Xiaosong Qiu, Xinyang Wang, Hua Zhou, Cao Dongxing
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical engineering drawings, where high annotation density and weak domain knowledge, compounded by unreliable spatial relation reasoning under strict projection rules and geometric constraints, make decisive cues easy to miss and frequently lead to wrong answers. To bridge this gap, we introduce the first comprehensive mechanical drawing understanding dataset, MechVQA, created through a semi-automated construction and quality-control pipeline. MechVQA contains 3.3k high-density pictures with 21K question-answer pairs, spanning 10 different fine-grained tasks across three capability levels: Recognition, Reasoning, and Judging, providing a testbed to evaluate and improve MLLM understanding on real-world mechanical drawings. On top of MechVQA, we then develop the MechVL model through a multi-stage training paradigm, building a strong domain-specialized baseline. Extensive experimental results demonstrate that MechVL outperforms the strongest closed-source baseline by 7.57 percentage points on the MechVQA total score, significantly enhancing mechanical drawing understanding ability and providing a reusable foundation for deploying MLLMs in mechanical design and inspection scenarios.
Authors: Jiahao Sun, Dingkun Wei, Zehong Shen, Hongyu Zhou, Yujun Shen, Liang Li
Abstract: Converting multi-view RGB observations into simulation-ready 3D environments remains challenging because current reconstruction pipelines produce monolithic scene representations without explicit physical structure. They are typically defined up to an arbitrary global rotation and entangle rigid foreground objects with background geometry, which hinders stable physical interaction. Existing solutions often recover interactivity by replacing reconstructed objects with retrieved CAD assets, but this introduces a slow retrieval-and-replacement stage and weakens scene-specific geometric fidelity. We propose GARDEN, an RGB-only framework that reformulates reconstruction as physically-grounded scene factorization and outputs a structured hybrid scene representation. The key idea is to use gravity as a universal physical prior: we first align the reconstruction to a unified Gravity-View frame to resolve gauge ambiguity, then recover object-centric rigid meshes with accurate 6-DoF placement, and finally remove duplicate object geometry from the background through conditional 3D point classification. The resulting representation combines explicit rigid bodies with a decoupled background, enabling direct physics simulation while preserving visual realism. Experiments on both simulated and real multi-view scenes show that GARDEN improves object placement reliability, disentanglement quality, and rendering-simulation efficiency compared with retrieval-based baselines. Project page: https://sunjiahaovo.github.io/garden/
Authors: Zhiwen Yang, Jiayin Li, Hao Lu, Hui Zhang, Zihua Wang, Yan Xu
Abstract: Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.
Authors: Ying Li, Xiaobao Wei, Jiajun Cao, Hao Wang, Xiaowei Chi, Chengyu Bai, Qianpu Sun, Jiajun Li, Xiaojie Zhang, Peidong Jia, Jian Tang, Sirui Han, Shanghang Zhang
Abstract: World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video or latent spaces, where visually plausible rollouts miss the 3D spatial constraints and occluded contact geometry required for precise manipulation. While geometric foundation models offer strong priors for recovering dense 3D structure and motion from visual observations, forcing WAMs to predict the dense 4D representation introduces costly geometric decoding and slows down causal action generation. To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. To prevent non-causal shortcuts, we further design causal mixture attention for the Mixture-of-Transformers (MoT) WAM backbone, defining modality-specific visibility among video, action, and geometry tokens. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.
Authors: Zexi Chen, Zitai Huang, Qiwen Gu, Zhiqi Li, Shengli Dong, Chenlei Wang, Junqiao Zhao, Hongdong Wang, Bing Han
Abstract: Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between visually distinct domains: open decks with sparse textures and severe illumination changes, and enclosed cabins with repetitive structures and high visual ambiguity. Existing VPR methods, designed primarily for urban or indoor scenes, fail to generalize reliably across these starkly different scenarios. To address this, we propose ProteusVPR, a two-stage retrieval-refinement framework. The first stage employs any standard VPR model for initial image retrieval. The second stage introduces a geometric-visual estimation network that fuses the retrieved image with two temporally preceding frames, incorporating geometric descriptors, a local affine coordinate system, and camera azimuth encoding to achieve precise localization. To support this task, we introduce the XHZ dataset, an 8K-panoramic ship-borne dataset collected from an operational vessel, featuring multi-floor cabin structures, deck transition zones, and strict query-database separation for rigorous evaluation. Extensive experiments on the XHZ dataset demonstrate that ProteusVPR consistently improves the localization accuracy across multiple VPR backbones, reducing mean localization error by over 60\% on average and that ProteusVPR offers an effective and robust solution for precise visual localization in challenging, cross-scene maritime environments.
Authors: Shiyi Mu, Zichong Gu, Zhiqi Ai, Yilin Gao, Shugong Xu
Abstract: Stereo-based 3D obstacle perception for autonomous driving is currently constrained by an imbalanced triplet: deployment cost, detection accuracy, and open-set adaptability. While existing methods struggle to balance these three competing objectives, there is an urgent demand for high-precision, real-time algorithms capable of detecting arbitrary obstacles in the wild. In this paper, we present DDStereo, a novel Dual-Decoder Stereo Transformer that achieves a synergistic integration of 3D object detection and Out-of-Distribution (OoD) road anomaly detection. Leveraging the geometric priors of stereo disparity, our approach effectively couples 3D attribute regression with open-set foreground detection within a streamlined dual-branch decoder architecture. Conventional methods rely on complex feature-level fusion; DDStereo maintains execution efficiency by employing a decoupled decoding strategy and shared object-level queries to ensure cross-modal target alignment. Extensive evaluations of public benchmarks demonstrate that DDStereo not only achieves state-of-the-art accuracy under open-set and closed-set protocols. Our method delivers real-time performance comparable to monocular 3D detection baselines, providing a cost-effective solution for the perception of obstacles of the normal and OoD category. Code and models are available at https://github.com/shiyi-mu/DDStereo.
Authors: Wei Zhou, Xiongwei Zhu, Zelin Xu, Bo Dong, Lixue Gong, Yongyuan Liang, Meng Chu, Leigang Qu, Lingdong Kong, Wei Liu, Tat-Seng Chua
Abstract: Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation model training. To tackle this, we introduce DanceOPD, an on-policy generative field distillation framework for flow-matching models that routes each sample to one capability field, queries one low-noise student-induced state, and trains with a simple velocity MSE objective. With each capability source defined as a velocity field over the shared flow state space, the student learns from fields queried on its own rollout states to compose expert capabilities. This formulation also absorbs operator-defined fields such as classifier-free guidance. Comprehensive experiments on T2I, editing, realism-field absorption, and CFG absorption show that our approach improves multi-capability composition, strengthening target capabilities while preserving anchor generation quality. We believe this work establishes a practical route for generative field distillation in flow-matching models.
Authors: Nuo Chen, Lulin Liu, Zihao Li, Ziyao Zeng, Zihao Zhu, Wenyan Cong, Junyuan Hong, Yunhao Yang, Zhengzhong Tu, Yan Wang, Boris Ivanovic, Marco Pavone, Zhangyang Wang, Yang Zhou, Zhiwen Fan
Abstract: Generative world models hold immense promise as scalable simulators for autonomous systems, particularly for synthesizing rare but safety-critical multi-agent interactions, such as vehicle collisions. However, current evaluation paradigms index heavily on visual fidelity and semantic alignment, leaving a critical blind spot: they cannot reliably quantify whether generated dynamics actually obey the fundamental physical laws required for reliable simulation. Assessing this physical plausibility is inherently difficult due to a lack of physical metrics and the challenge of extracting metric-scale kinematics from uncalibrated video rollouts. To bridge this gap, we introduce CrashTwin, a physics-grounded evaluation framework designed to stress-test the physical trustworthiness of world models. CrashTwin couples a diverse dataset of multi-agent collision scenarios, comprising 25K controllable synthetic and 12K in-the-wild real-world collision sequences with a novel calibration-free reconstruction pipeline, enabling the recovery of 3D physical attributes directly from world model rollouts. We propose a diagnostic suite that systematically evaluates three dimensions: spatio-temporal consistency, momentum and kinetic energy conservation, and world-dynamics integrity. Extensive benchmarking of state-of-the-art models reveals a crucial insight: high perceptual quality frequently masks severe physical violations during complex interactions. By quantitatively exposing these failure modes, CrashTwin provides a vital diagnostic tool for developing physically grounded world models capable of reliable real-world simulation.
Authors: Seongro Yoon, Donghyeon Cho, Jinsun Park, Fran\c{c}ois Br\'emond
Abstract: Understanding facial expressions in videos requires modeling subtle and localized facial dynamics under unconstrained conditions. Although recent Vision Transformer (ViT)-based video models have shown strong performance through large-scale self-supervised pretraining, their attention mechanisms often emphasize dominant global motions and coarse temporal dynamics, limiting sensitivity to fine-grained facial variations. To address this limitation, we propose MiRA (Marginal-induced Attention Redistribution), a plug-in frame-marginal attention redistribution framework for ViT backbones that enhances spatio-temporal selectivity toward subtle facial dynamics without introducing additional trainable parameters. MiRA derives frame-level confidence and intra-frame concentration statistics from self-attention maps to estimate frame-wise marginal importance and redistribute attention toward spatiotemporally localized facial cues. We first introduce a principled exact mode based on post-softmax attention redistribution. To further improve efficiency, we propose flashLite mode, a lightweight pre-softmax approximation that integrates frame-marginal redistribution into FlashAttention kernels while preserving the effectiveness of the exact formulation. Experimental results on challenging Facial Expression Recognition (FER) benchmarks demonstrate consistent improvements over strong ViT baselines.
Authors: Ke Wang, Xiaoyi Pan, Zhaoyu Gu, Xiaofeng Ai, Zhiming Xu, Feng Zhao, Shunping Xiao
Abstract: Synthetic aperture radar automatic target recognition (SAR ATR) is critical for Earth observation and defense, but its practical deployment is constrained by scarce annotated training data. Self-supervised pre-training alleviates this label bottleneck, yet prevailing Transformer architectures incur prohibitive quadratic computational complexity, and conventional universal masking neglects the unique electromagnetic scattering properties intrinsic to SAR imagery. To address these limitations, we propose SAMBA (Scattering-Guided Bidirectional Mamba), an efficient self-supervised pre-training foundation model for SAR target interpretation. Our framework features three core innovations: (i) a linear-complexity Mamba encoder with a mid-sequence class token to mitigate computational bottlenecks; (ii) a three-level hierarchical Scattering-Guided Masked Autoencoder (SG-MAE) masking strategy guided by SAR physical priors, aligning the pretext task with SAR's intrinsic imaging mechanism; (iii) a lightweight SpatialMix feature interaction module to enhance cross-region feature fusion. We also design a two-stage cross-domain pre-training pipeline to optimize the overall pre-training process. Extensive evaluations demonstrate that SAMBA consistently delivers superior performance across all pre-training configurations, with substantially fewer parameters than both CNN and Transformer baselines. Compared with the default masking strategy in standard MAE, the proposed SG-MAE strategy further boosts the model's few-shot transfer capability. Benchmarking on seven downstream datasets covering classification and detection tasks shows SAMBA achieves state-of-the-art (SOTA) performance on most metrics, fully validating its robust generalizability across diverse SAR interpretation tasks. Source code and pre-trained weights are publicly available at https://github.com/mynswkk/SAMBA.
Authors: Yeonghwan Song, Chanhui Lee, Jinsoo Park, Jeany Son
Abstract: Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image, inducing visible inconsistencies and structural failures in text-guided I2V generation. Our method is motivated by a simple empirical observation. When text guidance is removed from modern I2V models, generation quality degrades markedly, not only in motion realism but also in subject preservation, structural coherence, and temporal consistency. Building on this insight, Anti-Prompt exploits the model reliance on textual guidance by attenuating text-conditioned interactions during denoising while strengthening visual-only pathways. To further systematically evaluate protection effectiveness, we introduce a Video-LLM-assisted evaluation protocol that provides interpretable, frame-grounded analyses of generation artifacts and inconsistencies. Experiments on two representative I2V architectures demonstrate that our method achieves strong protection performance while improving efficiency and cross-model transferability.
Authors: Marwane Hariat, David Filliat, Antoine Manzanera
Abstract: Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojection Consistency (VLRC), a scalable auxiliary objective that exploits frozen vision-language representations as semantic multi-view supervision. Given a predicted 3D reconstruction, VLRC reprojects dense vision-language features across views and enforces feature consistency between corresponding image locations, requiring no additional 3D annotations. The objective integrates seamlessly with both self-supervised monocular reconstruction and supervised-pretrained feed-forward 3D models during unlabeled adaptation. By aligning geometry with language-grounded features, VLRC not only improves depth and camera estimation but also enables more coherent multi-view semantic fusion for open-vocabulary 3D scene understanding. Experiments on indoor and outdoor benchmarks demonstrate consistent gains in 3D reconstruction accuracy and zero-shot open-vocabulary 3D semantic segmentation.
Authors: Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning. We present CONFLUX, a latent diffusion model for chest computed tomography (CT): a 3D variational autoencoder compresses each volume, and a rectified-flow transformer generates in the latent space. Generation is conditioned on structured radiological metadata (18 abnormality findings, sex, age, and reconstruction kernel) through adaptive layer normalization. The model leads strong volumetric baselines on tri-planar Frechet distance (FID 32.3 vs. 74.6 for MAISI) while exposing direct control over clinical attributes. To strengthen that control we add an online reinforcement-learning post-training stage (group-relative policy optimization) that rewards how reliably a classifier recovers the requested findings from each generated volume. Judged by a separate, independent classifier, post-training removes 47% of the shortfall relative to real-scan reliability. We release the model and a ~200k synthetic chest-CT dataset with conditioning metadata spanning a wide variety of clinical findings.
Authors: Jin Hong, Jisoo Park, Junseok Kwon
Abstract: Active Speaker Detection determines whether a visible person in a video is speaking at each moment. While recent audio-visual fusion methods perform well on clean data, they degrade under real-world corruptions such as background noise, occlusion, or simultaneous modality degradation. We attribute this limitation to the absence of explicit consistency constraints that promote robust, semantically aligned representations across modalities. Without such guidance, models tend to learn fragile modality-specific shortcuts that fail under corrupted conditions. We propose $C^3$ASD, a multi-level consistency-driven framework with three complementary constraints: embedding-level inter-modality consistency aligns audio-visual representations during speech; sequence-level intra-modality consistency separates speaking and non-speaking clusters via track-aware contrastive learning; and prediction-level consistency stabilizes fusion through knowledge distillation. Extensive experiments demonstrate significant improvements under diverse audio, visual and joint corruptions, while maintaining competitive performance on clean data.
Authors: Taiting Lu, Kaiyuan Lin, Mingjia Wang, Haolin Ye, Runze Liu, Yuxin Tian, Vahe Melkonyan, Haoyu Wang, Muchuan Wang, Chufan Hong, Yifan Yang, Sung-Liang Chen, Yi-Chao Chen, Yicheng Jin, Mahanth Gowda
Abstract: Recent large language models (LLMs) have demonstrated remarkable progress in 3D spatial reasoning, spatial grounding, and fine-grained geometric understanding. However, their ability to reason about densely packed object placement under strict spatial and functional constraints remains largely unexplored, despite being a fundamental challenge in practical electronic design automation (EDA) workflows. To bridge this gap, we introduce OmniLayout, the first benchmark designed to evaluate LLMs on printed-circuit-board (PCB) layout placement reasoning under real-world geometric, routing, and connectivity constraints. OmniLayout contains 1,681 industrial-grade schematic-coupled PCB layouts and includes four tasks: (1) geometric reasoning for IC physical placement, with 77.24K placement instances constrained within PCB board boundaries; (2) routability-aware placement reasoning, generating physically valid component placements; (3) electrical functionality, preserving schematic-specified connectivity and electronic functional correctness; and (4) tool-augmented agentic reasoning for invoking external tools to accomplish tasks (1)-(3). Our results reveal substantial limitations of current LLMs in PCB layout placement, including weak geometric reasoning, poor routability optimization, and inconsistent preservation of electrical functionality.
Authors: Zixiang Zhou, Zhentao Yu, Yifeng Ma, Hongmei Wang, Wenqing Yu, Cong Wang, Zilin Yang, Rui Chen, Jiarong Ou, Yezhou Liu, Yuan Zhou, Qinglin Lu
Abstract: Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity consistency and model complex relationships among multiple subjects. In this paper, we propose Aura, a unified framework for high-fidelity and identity-consistent video generation. To better capture scene dynamics and subject interactions, we introduce AI director-level captions that provide dense and structured descriptions of video content. We further leverage a vision-language model (VLM) with learnable queries to extract multimodal semantic features from textual and visual references, covering both global semantics and fine-grained visual cues. To bridge the representational gap between the VLM and the Diffusion Transformer (DiT), we design a two-stage alignment strategy that progressively maps VLM features into the DiT feature space. For visual conditioning, we adopt token concatenation to inject reference information directly into the generation process. To distinguish heterogeneous subject types and reduce common copy-paste artifacts, we develop a subject-aware RoPE-Shift mechanism. To further differentiate reference images of different categories, we introduce subject-aware learnable tokens. In addition, we introduce Memory Tokens to balance the training signal across examples with different numbers of reference subjects. During inference, Progressive-APG (Adaptive Prompt Guidance) further alleviates oversaturation and improves semantic alignment with user prompts. Finally, we build a high-quality video-subject image dataset through a dedicated data construction pipeline. Extensive experiments show that our method achieves state-of-the-art performance on both single-subject generation and more challenging multi-element scenarios.
Authors: Jiwon Kang, Heeji Yoon, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong Kim
Abstract: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied. We investigate $\boldsymbol{\mathsf{transferability}}$ in UMMs: whether training a capability on one task improves the same capability on the other without explicit supervision. Through controlled experiments, we empirically find that transferability depends on architecture-models with fully shared transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none. Leveraging this transferability, we propose a practical training strategy. The most straightforward way to improve a target generative capability (e.g., counting) is to fine-tune generation directly, but this can degrade visual quality due to distribution shift. Instead, we train the corresponding understanding task and let it transfer into generation, which improves capability-specific generative performance while minimizing distribution shift. We validate this across three capabilities-counting, spatial relation, and text recognition/generation-showing that cross-task transferability can be systematically exploited in UMMs.
Authors: Lianghua Huang, Zhi-Fan Wu, Yupeng Shi, Wei Wang, Mengyang Feng, Junjie He, Chen-Wei Xie, Yu Liu, Jingren Zhou, Ang Wang, Bang Zhang, Baole Ai, Chen Liang, Cheng Yu, Chongyang Zhong, Jinwei Qi, Kai Zhu, Pandeng Li, Peng Zhang, Wenyuan Zhang, Xinhua Cheng, Yitong Huang, Yun Zheng, Yuxiang Bao, Yuzheng Wang, Zoubin Bi
Abstract: We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a single-GPU low-latency path for streaming perception, the short language/state Transformer pass that builds the generation cache, and final decoding. The performer becomes a multi-GPU Ulysses-style context-parallel group for the expensive next-unit latent generation. Each performer rank writes incoming K/V into a pre-sharded local cache. The long high-resolution latent video sequence is split across ranks for denoising and gathered through Ulysses communication, while the much shorter audio latent sequence is generated without sequence sharding. In this split, the thinker's language/state computation reaches the performer only as K/V conditioning, so no separate language sequence has to be communicated inside the performer group. This concentrates additional hardware on visual generation while preserving the compact thinker-performer boundary, keeping total remote interaction latency at approximately 550 ms when a 350 ms bidirectional network budget is included.
Authors: Gengtian Shi, Jinze Yu, Chenhao Wu, Shaofei Wang, Eiji Fukuzawa, Junjie Tang, Hiroshi Onoda, Jiang Liu
Abstract: Video-text temporal localization requires precise alignment between natural language queries and corresponding video segments, a fundamental challenge in multimodal understanding. We present a novel framework that addresses two critical limitations of existing methods: inadequate modeling of hierarchical temporal structure and inability to handle complex many-to-many correspondences between modalities. Our approach introduces a multi-scale temporal convolutional encoder that captures motion patterns across different temporal granularities - from instantaneous frame transitions to extended action sequences. We further propose a capsule-based dynamic routing mechanism that iteratively refines segment-query associations through structured agreement updates, enabling flexible modeling of non-monotonic alignments. These components are unified through a multi-task learning objective that jointly optimizes temporal boundary regression, cross-modal semantic alignment, and capsule diversity. Extensive experiments on ActivityNet Captions demonstrate significant improvements, achieving 42.9% Recall@0.5 and 41.1% mean IoU, surpassing strong transformer-based baselines while maintaining computational efficiency. Our results validate that combining hierarchical temporal modeling with structured semantic routing provides an effective solution for fine-grained video-language understanding.
Authors: Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhengyi Pan
Abstract: Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency aliasing and truncation, leading to inadequate preservation of high-frequency components for SOD. To tackle these limitations, we propose a Frequency-Spatial Domain Collaborative Detection Transformer (FSDC-DETR), a novel collaborative framework that explicitly models complementary spatial and frequency representations. Specifically, we first introduce Dual-Branch Frequency-Spatial Adaptive Fusion (DBFSAF) to enhance frequency diversity and adaptively capture frequency-spatial domain discriminative representations. Building on these representations, a frequency-spatial interaction scheme is further explored within the hybrid encoder to enable progressive feature propagation to the decoder. In particular, structure-aware frequency-spatial aggregation is achieved through Shunt Frequency-Spatial Feature Fusion (SFS-FF), establishing bidirectional interaction and progressive cross-scale propagation between frequency and spatial representations for coherent discriminative modeling. Meanwhile, informative high-frequency responses are preserved during scale transitions through Frequency-Spatial Dynamic Downsampling (FSD-Down), thereby minimizing frequency degradation throughout multi-scale fusion for the precise SOD. Experimental results demonstrate that FSDC-DETR achieves state-of-the-art performance, improving AP by 6.4 on VisDrone-DET2019 and 6.6 on AITODv2, with gains of 6.8 and 6.9 AP for small objects. The code is available at github.com/nevereverinsomnia/FSDC-DETR.
Authors: Jiaxiang Fang, Shiqiang Ma, Jing Wang, Siyu Chen, Fei Guo, Shengfeng He
Abstract: Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repurposes CLIP to perform pixel-level localization. By tracing back CLIP's classification process, CLIPix identifies object-specific attentive regions and repurposes them as pixel-level localization cues. To address noise introduced by global biases, we propose a Noise-Resistant Correction strategy, refining these cues for more precise segmentation. Additionally, we introduce a Localization Embedding strategy to integrate both localization and enriched detail information, enabling accurate, high-resolution segmentation. Our approach preserves CLIP's generalization strength and unlocks its potential for segmenting arbitrary objects. Extensive experiments on the PASCAL and COCO datasets demonstrate that CLIPix achieves state-of-the-art performance, underscoring its effectiveness.
Authors: Akshay Gokhale, Mansi Dhamne
Abstract: Automated detection of intracranial aneurysms (IAs) from CT angiography (CTA) is severely hindered by high false-positive rates. Convolutional neural networks (CNNs) rely on local pixel intensities, causing systematic confusion between saccular aneurysms and vascular bifurcations - a problem especially acute for small lesions (<3 mm), where detection sensitivity falls below 60%. We propose a plug-and-play, topology-aware false-positive reduction framework evaluating the Smooth Euler Characteristic Transform (SECT) - a directional representation encoding global 3D vascular geometry independently of intensity - against persistence-based summaries (Persistence Images and Landscapes), tested on a stratified subset of the RSNA 2025 dataset. SECT achieves an AUC of 0.943, substantially outperforming direction-agnostic methods (AUC ~0.68), and exhibits a clinical performance inversion: it excels on the sub-3 mm cohort, maintaining 0.943 AUC and 78.5% sensitivity at 95% specificity. The representation is also scanner-agnostic, achieving 0.927 mean AUC under leave-one-scanner-out (LOGO) validation across four manufacturers. By capturing asymmetric geometric invariants rather than intensity profiles, SECT reliably resolves the primary structural confounder in IA detection, positioning it as a robust downstream filter for hybrid deep-learning diagnostic pipelines.
Authors: Anthony Hu, V\'aclav Volhejn, Adrien Ramanana Rahary, Chris Mulder, Aditya Makkar, Alyx Liao, Am\'elie Royer, Manu Orsini, Adam Jelley, Eloi Alonso, Florian Laurent, Fredrik Nor\'en, James Swingos, Jan H\"unermann, Kent Rollins, Lucas Hosseini, Matthieu Le Cauchois, Maxim Peter, Pim de Witte, Tim Brown, Vincent Micheli, Moritz B\"ohle, Gabriel de Marmiesse, Viktoriia Sharmanska, Lucia Specia, Michael Black, Patrick P\'erez
Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents as part of the environment, ours conditions on the action streams of multiple agents, learning to attribute changes in the scene to the correct player and to stay coherent under arbitrary combinations of their actions. We study this problem in the game of Rocket League, where players compete and cooperate under fast, tightly coupled dynamics. Trained on 10,000 hours of gameplay collected with publicly available bots, our 5-billion-parameter latent diffusion model generates four-player matches in real time, producing 20 frames per second on a single Nvidia B200 GPU. Although trained only on short clips, its rollouts stay stable far beyond the training horizon: distributional quality holds steady out to five minutes, the longest horizon we measure, and in practice we observe rollouts continuing for hours with no sign of collapse. We systematically investigate the central design choices: the video codec, the generative objective, and the multiplayer conditioning scheme. In addition, we characterize how behavior changes with model and data scale, including the capabilities that emerge and the failure modes that persist. We further develop targeted evaluations that probe the model's physical understanding rather than visual appearance alone. To support continued research on multiplayer world models, we release our dataset, our full training and inference codebase, and a live demo.
Authors: Christiaan Meijer, E. G. Patrick Bos
Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
Authors: Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang
Abstract: Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM), estimate high-dimensional data distributions conditioned on scalar regression labels such as angles, ages, or temperatures. However, fixed-size vicinal training in CcGAN can be sensitive to non-uniform label densities, whereas CCDM relies on computationally expensive iterative sampling. To address these issues, we propose CcGAN-AVAR, an imbalance-aware extension of CcGAN that combines soft/hybrid adaptive vicinity with auxiliary discriminator-guided regularization. The adaptive vicinity constructs a label-dependent local radius according to the available samples around each target condition, and the multi-task discriminator supplies both a regression signal for label consistency and a density-ratio-estimation signal for distribution matching. We further provide a theoretical interpretation characterizing how adaptive vicinal weighting affects the local bias-variance behavior of the discriminator target, how hybrid truncation reduces objective-level cross-condition mixing, and how the density-ratio-based generator penalty approximates a Pearson Chi-square discrepancy up to the estimation error of the density-ratio branch. Extensive experiments on four datasets, including the newly constructed imbalanced RC-49-I, covering resolutions from 64x64 to 256x256 across eleven settings, demonstrate that CcGAN-AVAR obtains strong generation quality and label consistency while preserving the one-step sampling efficiency of GANs, achieving 300x--2000x faster inference than CCDM.
Authors: Quentin Uhl, Tommaso Pavan, Julianna Gerold, Kwok-Shing Chan, Yohan Jun, Shohei Fujita, Aneri Bhatt, Yixin Ma, Qiaochu Wang, Hong-Hsi Lee, Susie Y. Huang, Berkin Bilgic, Ileana Jelescu
Abstract: Biophysical diffusion MRI models like Neurite Exchange Imaging (NEXI) are essential for probing gray matter microstructure, estimating compartment diffusivities, neurite fraction, and exchange time. However, NEXI's multi-shell, multi-diffusion-time requirements cause prohibitively long acquisitions. Leveraging the Connectome 2.0 ultra-high gradient scanner, we developed a time-efficient protocol using an Explainable AI (XAI) framework. Combining XGBoost, SHAP, and Recursive Feature Elimination trained on synthetic signals, XAI identified an optimal 8-feature subset, cutting scan time from 27 to 14 minutes. Validated in vivo in seven healthy participants, the XAI protocol was benchmarked against the full 15-feature acquisition, a Cram'er-Rao Lower Bound (CRLB) theoretical optimum, and two heuristics ("Mid-Range" and "Corner"). It robustly reproduced parameter estimates and maintained test-retest reproducibility. Remarkably, the XAI selection converged to the CRLB optimum. This validates XAI's optimality while highlighting its main advantage: achieving gold-standard optimization without complex analytical Jacobians, making it easily adaptable to numerical models or complex noise where CRLB is intractable. Furthermore, XAI showed superior in vivo robustness over heuristics: "Mid-Range" sampling yielded biased exchange time estimates from insufficient temporal diversity, while "Corner" sampling gave unstable intra-neurite diffusivity estimates (5-fold higher CV) due to noise sensitivity. Ultimately, this robust 14-minute protocol accelerates exchange-sensitive microstructural mapping, establishing a model-agnostic optimization framework adaptable to future ultra-high gradient systems and existing clinical scanners.
Authors: Mrinmay Sen, Ankita Das, Sidhant Nair, C Krishna Mohan
Abstract: Federated Domain Adaptation (FDA) is a federated learning (FL) approach that improves model performance at the target client by collaborating with source clients while preserving data privacy. FDA faces two primary challenges: domain shifts between source and target data and limited labeled data at the target. Most existing FDA methods focus on domain shifts, assuming ample target data, yet often neglect the combined challenges of both domain shifts and data scarcity. Moreover, approaches that address both challenges fail to prioritize sharing relevant information from source clients according to the target's objective. In this paper, we propose FedDAF, a novel approach addressing both challenges in FDA. FedDAF uses similarity-based aggregation of the global source model and target model by calculating model functional distance from their mean gradient fields computed on target data. This enables effective model aggregation based on the target objective, constructed using target data, even with limited data. While computing model functional distance between these two models, FedDAF computes the angle between their mean gradient fields and then normalizes with the Gompertz function. To construct the global source model, all the local source models are aggregated using simple average in the server. Experiments on real-world datasets demonstrate FedDAF's superiority over existing FL, PFL, and FDA methods in terms of achieving better test accuracy.
Authors: Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner
Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose" inconsistently and lacks precise definitions, hindering comparability. We introduce a theoretical framework for meta-learning which formally defines practical universality and introduces a distinction between algorithm-explicit and algorithm-implicit learning, providing a principled vocabulary for reasoning about universal meta-learning methods. Guided by this framework, we present TAIL, a transformer-based algorithm-implicit meta-learner that functions across tasks with varying domains, modalities, and label configurations. TAIL features three innovations over prior transformer-based meta-learners: random projections for cross-modal feature encoding, random injection label embeddings that extrapolate to larger label spaces, and efficient inline query processing. TAIL achieves state-of-the-art performance on standard few-shot benchmarks while generalizing to unseen domains. Unlike other meta-learning methods, it also generalizes to unseen modalities, solving text classification tasks despite training exclusively on images, handles tasks with up to 20$\times$ more classes than seen during training, and provides orders-of-magnitude computational savings over prior transformer-based approaches.
Authors: Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Yao Mu
Abstract: Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive "Observers" that recognize ongoing events rather than evaluating the current state relative to the final task goal. In this paper, we introduce PRIMO R1 (Process Reasoning Induced Monitoring), a 7B framework that transforms video MLLMs into active "Critics". We leverage outcome-based Reinforcement Learning to incentivize explicit Chain-of-Thought generation for progress estimation. Furthermore, our architecture constructs a structured temporal input by explicitly anchoring the video sequence between initial and current state images. Supported by the proposed PRIMO Dataset and Benchmark, extensive experiments across diverse in-domain environments and out-of-domain real-world humanoid scenarios demonstrate that PRIMO R1 achieves state-of-the-art performance. Quantitatively, our 7B model achieves a 50% reduction in the mean absolute error of specialized reasoning baselines, demonstrating significant relative accuracy improvements over 72B-scale general MLLMs. Furthermore, PRIMO R1 exhibits strong zero-shot generalization on difficult failure detection tasks. We establish state-of-the-art performance on RoboFail benchmark with 67.0% accuracy, surpassing closed-source models like OpenAI o1 by 6.0%.
Authors: Ryan Punamiya, Simar Kareer, Zeyi Liu, Josh Citron, Ri-Zhao Qiu, Xiongyi Cai, Alexey Gavryushin, Jiaqi Chen, Davide Liconti, Lawrence Y. Zhu, Patcharapong Aphiwetsa, Baoyu Li, Aniketh Cheluva, Pranav Kuppili, Yangcen Liu, Dhruv Patel, Aidan Gao, Hye-Young Chung, Ryan Co, Renee Zbizika, Jeff Liu, Xiaomeng Xu, Haoyu Xiong, Geng Chen, Sebastiano Oliani, Wenkai Xuan, Chenyu Yang, Xi Wang, James Fort, Richard Newcombe, Josh Gao, Jason Chong, Garrett Matsuda, Aseem Doriwala, Marc Pollefeys, Robert Katzschmann, Xiaolong Wang, Shuran Song, Judy Hoffman, Danfei Xu
Abstract: Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human data offer a promising alternative by capturing rich manipulation behavior across everyday environments. However, existing human datasets are often limited in scope, difficult to extend, and fragmented across institutions. We introduce EgoVerse, a collaborative platform for human data-driven robot learning that unifies data collection, processing, and access under a shared framework, enabling contributions from individual researchers, academic labs, and industry partners. The current release includes 1,362 hours (80k episodes) of human demonstrations spanning 1,965 tasks, 240 scenes, and 2,087 unique demonstrators, with standardized formats, manipulation-relevant annotations, and tooling for downstream learning. Beyond the dataset, we conduct a large-scale study of human-to-robot transfer with experiments replicated across multiple labs, tasks, and robot embodiments under shared protocols. We find that policy performance generally improves with increased human data, but that effective scaling depends on alignment between human data and robot learning objectives. Together, the dataset, platform, and study establish a foundation for reproducible progress in human data-driven robot learning. Videos and additional information can be found at https://egoverse.ai/
URLs: https://egoverse.ai/
Authors: Jos\'e A. Ch\'avez
Abstract: Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales. In this work, we challenge the necessity of these temporal signals by analyzing their impact on U-Net and Diffusion Transformer architectures. Beyond empirical evidence, we provide a theoretical framework demonstrating that, under certain conditions, the global minimizer of the diffusion training objective can be achieved without explicit timestep conditioning. Our findings reveal a surprising robustness when timestep embeddings are completely removed. Extensive ablation studies on the CelebA and CIFAR-10 datasets show that these time-agnostic models can maintain high structural fidelity and even surpass their conditioned counterparts in competitive metrics, including FID, precision, and recall. Our analysis suggests these architectures can implicitly infer noise scales from the corrupted input under specific assumptions, rendering explicit temporal conditioning redundant. This study challenges long-standing temporal conditioning paradigms and paves the way for more efficient and structurally focused generative architectures.
Authors: Kwan Soo Shin, In Seok Kang, Yunkyung Min, Judy Yang, Munho Lee
Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We show that conditioning a language or vision model on a narrow task suppresses its reporting of co-present, safety-critical signals it can otherwise report, a machine analogue of human inattentional blindness, produced by a different mechanism. Across radiology and driving text scenarios and chest-radiograph vision tasks, the ordinary focused instructions under which such systems are deployed suppressed reporting by up to 0.92 in report rate relative to the same models when unconstrained, and an explicit exclusive instruction abolished reporting entirely in radiology. Suppression appeared in every model tested, did not diminish with scale, persisted in a reasoning model, and varied more by model family than by size. We name this dissociation the Inattentional Gap and argue that it decouples measured benchmark safety from real-world safety: a system can score near-perfectly on the hazards an evaluation specifies while remaining blind to those that cause harm. Probing the mechanism, we localize the proximal trigger to output scope and find System-1-style task capture without reliable intrinsic oversight in the sampled systems. Oversight could, however, be supplied externally: routing each narrow report to an independent open-ended critic restored every omitted finding, demonstrating that the gap is both measurable and mitigable. We propose reporting-complete evaluation, scoring what a system fails to report alongside what it is asked to find, as a requirement for safety-critical deployment.
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: Tianxing Chen, Yue Chen, Zixuan Li, Junyuan Tang, Kailun Su, Haoran Lu, Weijie Wan, Baijun Chen, Songling Liu, Haowen Yan, Honghao Su, Zhiyang Dou, Kaixuan Wang, Dandan Zhang, Yunze Liu, Yan Qin, Qiwei Liang, Qiwei Wu, Zijian Lin, Wenwei Lin, Yuran Wang, Minghua He, Tianshu Wu, Ruihai Wu, Jingquan Zhou, Kai-Chong Lei, Haibao Yu, Yuanfeng Ji, Weiyang Jin, Guanyu Lin, Xiaofan Li, Qi Xiong, Renjing Xu, Zhongyu Li, Wenhao Chai, Enze Xie, Ziwei Wang, Yao Mu, Hao Dong, Wojciech Matusik, Mingyu Ding, Wenbo Ding, Ping Luo, Masayoshi Tomizuka
Abstract: Generalist robot manipulation policies have advanced rapidly, yet existing benchmarks remain limited in systematically evaluating their capabilities. Many rely on simple, short-horizon, or skill-narrow tasks with limited capability coverage, and are often conducted only in simulation or only in the real world. Simulation enables scalable feedback but misses physical deployment challenges, while real-world evaluation is costly, time-consuming, and difficult to reproduce. We introduce RoboDojo, a unified sim-and-real benchmark for comprehensive evaluation of generalist robot manipulation policies. RoboDojo includes 42 simulation tasks and 18 real-world tasks covering diverse and complementary manipulation capabilities. The simulation benchmark evaluates five dimensions: generalization, memory, precision, long-horizon execution, and open-vocabulary instruction following, while the real-world benchmark exposes policies to challenging physical-world deployment conditions. RoboDojo supports scalable evaluation through heterogeneous parallel simulation in Isaac Sim and provides RoboDojo-RealEval, a reproducible real-world evaluation system with remote cloud access, standardized hardware, scene reset, evaluation protocol, and deployment interface. Together with XPolicyLab, policies can be integrated once and evaluated across simulation and real-world settings with minimal adaptation. We integrate 30 policies into XPolicyLab and evaluate them on RoboDojo, establishing a public leaderboard and systematic analysis of current policy performance. The website is available at http://robodojo-benchmark.com/.
Authors: Ilya Burenko, Dmitry Vetrov
Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks. When modality imbalance is pronounced, various regularization techniques have been proposed to balance the learning process and overcome the inferior performance of late-fusion networks. In contrast, this work demonstrates that multimodal data can be effectively classified without any explicit modality fusion, using deep ensembles of unimodal networks. We systematically compare deep ensembles to late-fusion networks at equal parameter count and show that ensembles consistently outperform state-of-the-art late-fusion methods designed to address modality imbalance. This advantage also holds over intermediate-fusion techniques we evaluated and over hybrid methods that combine unimodal and multimodal predictions. We propose and empirically validate a method for selecting the number of models per modality in an ensemble, avoiding computationally expensive exhaustive search. Under extreme modality imbalance and small ensemble sizes, the heuristic indicates that ensembles of unimodal models trained solely on the stronger modality are preferable; as the ensemble scales up, incorporating models from the weaker modality becomes beneficial. Both predictions align with our empirical findings. To systematically explore the challenges of optimizing multimodal models, we propose a synthetic multimodal framework that allows control over both the number of modalities and their predictive strength; our findings are consistent across synthetic and real-world datasets. Finally, by fitting scaling laws to bimodal datasets, we estimate the asymptotic performance of ensembles.