Authors: Alexander Okupnik, Johannes Schneider, Kyriakos Flouris
Abstract: Recent success with large language models has sparked a new wave of verbal human-AI interaction. While such models support users in a variety of creative tasks, they lack the embodied nature of human interaction. Dance, as a primal form of human expression, is predestined to complement this experience. To explore creative human-AI interaction exemplified by dance, we build an interactive model based on motion capture (MoCap) data. It generates an artificial other by partially mimicking and also "creatively" enhancing an incoming sequence of movement data. It is the first model, which leverages single-person motion data and high level features in order to do so and, thus, it does not rely on low level human-human interaction data. It combines ideas of two diffusion models, motion inpainting, and motion style transfer to generate movement representations that are both temporally coherent and responsive to a chosen movement reference. The success of the model is demonstrated by quantitatively assessing the convergence of the feature distribution of the generated samples and the test set which serves as simulating the human performer. We show that our generations are first steps to creative dancing with AI as they are both diverse showing various deviations from the human partner while appearing realistic.
Authors: Julio Jerison E. Macrohon, Gordon Hung
Abstract: Coral reefs support numerous marine organisms and are an important source of coastal protection from storms and floods, representing a major part of marine ecosystems. However coral reefs face increasing threats from pollution, ocean acidification, and sea temperature anomalies, making efficient protection and monitoring heavily urgent. Therefore, this study presents a novel machine-learning-based coral bleaching classification system based on a diverse global dataset with samples of healthy and bleached corals under varying environmental conditions, including deep seas, marshes, and coastal zones. We benchmarked and compared three state-of-the-art models: Residual Neural Network (ResNet), Vision Transformer (ViT), and Convolutional Neural Network (CNN). After comprehensive hyperparameter tuning, the CNN model achieved the highest accuracy of 88%, outperforming existing benchmarks. Our findings offer important insights into autonomous coral monitoring and present a comprehensive analysis of the most widely used computer vision models.
Authors: Jules Gerard, Leandro Di Bella, Filip Huyghe, Marc Kochzius
Abstract: Coral reef monitoring in the Western Indian Ocean is limited by the labor demands of underwater visual censuses. This work evaluates a YOLOv8-based deep learning pipeline for automating family-level fish identification from video transects collected in Kenya and Tanzania. A curated dataset of 24 families was tested under different configurations, providing the first region-specific benchmark for automated reef fish monitoring in the Western Indian Ocean. The best model achieved mAP@0.5 of 0.52, with high accuracy for abundant families but weaker detection of rare or complex taxa. Results demonstrate the potential of deep learning as a scalable complement to traditional monitoring methods.
Authors: Hanyang Chen, Yanchao Yang
Abstract: Representation learning methods utilizing the InfoNCE loss have demonstrated considerable capacity in reducing human annotation effort by training invariant neural feature extractors. Although different variants of the training objective adhere to the information maximization principle between the data and learned features, data selection and augmentation still rely on human hypotheses or engineering, which may be suboptimal. For instance, data augmentation in contrastive learning primarily focuses on color jittering, aiming to emulate real-world illumination changes. In this work, we investigate the potential of selecting training data based on their mutual information computed from real-world distributions, which, in principle, should endow the learned features with better generalization when applied in open environments. Specifically, we consider patches attached to scenes that exhibit high mutual information under natural perturbations, such as color changes and motion, as positive samples for learning with contrastive loss. We evaluate the proposed mutual-information-informed data augmentation method on several benchmarks across multiple state-of-the-art representation learning frameworks, demonstrating its effectiveness and establishing it as a promising direction for future research.
Authors: Riya Gupta, Alexander Chowdhury, Sahil Nalawade
Abstract: Federated Learning (FL) has emerged as a transformative paradigm in medical AI, enabling collaborative model training across institutions without direct data sharing. This study benchmarks three prominent FL frameworks NVIDIA FLARE, Flower, and Owkin Substra to evaluate their suitability for medical imaging applications in real-world settings. Using the PathMNIST dataset, we assess model performance, convergence efficiency, communication overhead, scalability, and developer experience. Results indicate that NVIDIA FLARE offers superior production scalability, Flower provides flexibility for prototyping and academic research, and Owkin Substra demonstrates exceptional privacy and compliance features. Each framework exhibits strengths optimized for distinct use cases, emphasizing their relevance to practical deployment in healthcare environments.
Authors: Rupjyoti Chutia, Dibya Jyoti Bora
Abstract: Digital image processing involves the systematic handling of images using advanced computer algorithms, and has gained significant attention in both academic and practical fields. Image enhancement is a crucial preprocessing stage in the image-processing chain, improving image quality and emphasizing features. This makes subsequent tasks (segmentation, feature extraction, classification) more reliable. Image enhancement is essential for rice leaf analysis, aiding in disease detection, nutrient deficiency evaluation, and growth analysis. Denoising followed by contrast enhancement are the primary steps. Image filters, generally employed for denoising, transform or enhance visual characteristics like brightness, contrast, and sharpness, playing a crucial role in improving overall image quality and enabling the extraction of useful information. This work provides an extensive comparative study of well-known image-denoising methods combined with CLAHE (Contrast Limited Adaptive Histogram Equalization) for efficient denoising of rice leaf images. The experiments were performed on a rice leaf image dataset to ensure the data is relevant and representative. Results were examined using various metrics to comprehensively test enhancement methods. This approach provides a strong basis for assessing the effectiveness of methodologies in digital image processing and reveals insights useful for future adaptation in agricultural research and other domains.
Authors: Zhiqi Qi, Runxin Zhao, Hanyang Zhuang, Chunxiang Wang, Ming Yang
Abstract: LiDAR-based roadside perception is a cornerstone of advanced Intelligent Transportation Systems (ITS). While considerable research has addressed optimal LiDAR placement for infrastructure, the profound impact of differing LiDAR scanning patterns on perceptual performance remains comparatively under-investigated. The inherent nature of various scanning modes - such as traditional repetitive (mechanical/solid-state) versus emerging non-repetitive (e.g. prism-based) systems - leads to distinct point cloud distributions at varying distances, critically dictating the efficacy of object detection and overall environmental understanding. To systematically investigate these differences in infrastructure-based contexts, we introduce the "InfraLiDARs' Benchmark," a novel dataset meticulously collected in the CARLA simulation environment using concurrently operating infrastructure-based LiDARs exhibiting both scanning paradigms. Leveraging this benchmark, we conduct a comprehensive statistical analysis of the respective LiDAR scanning abilities and evaluate the impact of these distinct patterns on the performance of various leading 3D object detection algorithms. Our findings reveal that non-repetitive scanning LiDAR and the 128-line repetitive LiDAR were found to exhibit comparable detection performance across various scenarios. Despite non-repetitive LiDAR's limited perception range, it's a cost-effective option considering its low price. Ultimately, this study provides insights for setting up roadside perception system with optimal LiDAR scanning patterns and compatible algorithms for diverse roadside applications, and publicly releases the "InfraLiDARs' Benchmark" dataset to foster further research.
Authors: NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao, Prithvijit Chattopadhyay, Mike Chen, Yongxin Chen, Yu Chen, Shuai Cheng, Yin Cui, Jenna Diamond, Yifan Ding, Jiaojiao Fan, Linxi Fan, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Ruiyuan Gao, Yunhao Ge, Jinwei Gu, Aryaman Gupta, Siddharth Gururani, Imad El Hanafi, Ali Hassani, Zekun Hao, Jacob Huffman, Joel Jang, Pooya Jannaty, Jan Kautz, Grace Lam, Xuan Li, Zhaoshuo Li, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Yen-Chen Lin, Huan Ling, Ming-Yu Liu, Xian Liu, Yifan Lu, Alice Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Seungjun Nah, Yashraj Narang, Abhijeet Panaskar, Lindsey Pavao, Trung Pham, Morteza Ramezanali, Fitsum Reda, Scott Reed, Xuanchi Ren, Haonan Shao, Yue Shen, Stella Shi, Shuran Song, Bartosz Stefaniak, Shangkun Sun, Shitao Tang, Sameena Tasmeen, Lyne Tchapmi, Wei-Cheng Tseng, Jibin Varghese, Andrew Z. Wang, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Jiashu Xu, Dinghao Yang, Xiaodong Yang, Haotian Ye, Seonghyeon Ye, Xiaohui Zeng, Jing Zhang, Qinsheng Zhang, Kaiwen Zheng, Andrew Zhu, Yuke Zhu
Abstract: We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.
URLs: https://github.com/nvidia-cosmos/cosmos-predict2.5, https://github.com/nvidia-cosmos/cosmos-transfer2.5.
Authors: Harald Kristen, Daniel Kulmer, Manuela Hirschmugl
Abstract: Rapid climate change and other disturbances in alpine ecosystems demand frequent habitat monitoring, yet manual mapping remains prohibitively expensive for the required temporal resolution. We employ deep learning for change detection using long-term alpine habitat data from Gesaeuse National Park, Austria, addressing a major gap in applying geospatial foundation models (GFMs) to complex natural environments with fuzzy class boundaries and highly imbalanced classes. We compare two paradigms: post-classification change detection (CD) versus direct CD. For post-classification CD, we evaluate GFMs Prithvi-EO-2.0 and Clay v1.0 against U-Net CNNs; for direct CD, we test the transformer ChangeViT against U-Net baselines. Using high-resolution multimodal data (RGB, NIR, LiDAR, terrain attributes) covering 4,480 documented changes over 15.3 km2, results show Clay v1.0 achieves 51% overall accuracy versus U-Net's 41% for multi-class habitat change, while both reach 67% for binary change detection. Direct CD yields superior IoU (0.53 vs 0.35) for binary but only 28% accuracy for multi-class detection. Cross-temporal evaluation reveals GFM robustness, with Clay maintaining 33% accuracy on 2020 data versus U-Net's 23%. Integrating LiDAR improves semantic segmentation from 30% to 50% accuracy. Although overall accuracies are lower than in more homogeneous landscapes, they reflect realistic performance for complex alpine habitats. Future work will integrate object-based post-processing and physical constraints to enhance applicability.
Authors: Huanlin Gao, Ping Chen, Fuyuan Shi, Chao Tan, Zhaoxiang Liu, Fang Zhao, Kai Wang, Shiguo Lian
Abstract: We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of global errors, leading to noticeable content degradation between accelerated and original videos. To address this issue, we formulate cache scheduling as a directed graph with error-weighted edges and introduce a Lexicographic Minimax Path Optimization strategy that explicitly bounds the worst-case path error. This approach substantially improves the consistency of global content and style across generated frames. Extensive experiments on multiple text-to-video benchmarks demonstrate that LeMiCa delivers dual improvements in both inference speed and generation quality. Notably, our method achieves a 2.9x speedup on the Latte model and reaches an LPIPS score of 0.05 on Open-Sora, outperforming prior caching techniques. Importantly, these gains come with minimal perceptual quality degradation, making LeMiCa a robust and generalizable paradigm for accelerating diffusion-based video generation. We believe this approach can serve as a strong foundation for future research on efficient and reliable video synthesis. Our code is available at :https://github.com/UnicomAI/LeMiCa
Authors: Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Yuqi Xie, Fengyuan Hu, Jimmy Wu, Zhengyi Luo, Linxi "Jim" Fan, Guanya Shi, Yuke Zhu
Abstract: Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn, Distill (PLD), a three-stage plug-and-play framework that improves VLAs through residual reinforcement learning (RL) and distribution-aware data collection. In Stage 1, we train lightweight residual actors to probe failure regions of the VLA generalist. In Stage 2, we use a hybrid rollout scheme that aligns collected trajectories with the generalist's deployment distribution while capturing recovery behaviors. In Stage 3, we distill the curated trajectories back into the generalist with standard SFT. PLD achieves near-saturated 99% task success on LIBERO, over 50% gains in SimplerEnv, and 100% success on real-world Franka and YAM arm manipulation tasks. Ablations show that residual probing and distribution-aware replay are key to collecting deployment-aligned data that improves both seen and unseen tasks, offering a scalable path toward self-improving VLA models.
Authors: Jiaming Liu, Dingwei Fan, Junyong Zhao, Chunlin Li, Haipeng Si, Liang Sun
Abstract: The anatomical structure segmentation of the spine and adjacent structures from computed tomography (CT) images is a key step for spinal disease diagnosis and treatment. However, the segmentation of CT images is impeded by low contrast and complex vertebral boundaries. Although advanced models such as the Segment Anything Model (SAM) have shown promise in various segmentation tasks, their performance in spinal CT imaging is limited by high annotation requirements and poor domain adaptability. To address these limitations, we propose SpinalSAM-R1, a multimodal vision-language interactive system that integrates a fine-tuned SAM with DeepSeek-R1, for spine CT image segmentation. Specifically, our SpinalSAM-R1 introduces an anatomy-guided attention mechanism to improve spine segmentation performance, and a semantics-driven interaction protocol powered by DeepSeek-R1, enabling natural language-guided refinement. The SpinalSAM-R1 is fine-tuned using Low-Rank Adaptation (LoRA) for efficient adaptation. We validate our SpinalSAM-R1 on the spine anatomical structure with CT images. Experimental results suggest that our method achieves superior segmentation performance. Meanwhile, we develop a PyQt5-based interactive software, which supports point, box, and text-based prompts. The system supports 11 clinical operations with 94.3\% parsing accuracy and sub-800 ms response times. The software is released on https://github.com/6jm233333/spinalsam-r1.
Authors: Nils Porsche, Flurin M\"uller-Diesing, Sweta Banerjee, Miguel Goncalves, Marc Aubreville
Abstract: Confocal laser endomicroscopy (CLE) is a non-invasive, real-time imaging modality that can be used for in-situ, in-vivo imaging and the microstructural analysis of mucous structures. The diagnosis using CLE is, however, complicated by images being hard to interpret for non-experienced physicians. Utilizing machine learning as an augmentative tool would hence be beneficial, but is complicated by the shortage of histopathology-correlated CLE imaging sequences with respect to the plurality of patterns in this domain, leading to overfitting of machine learning models. To overcome this, self-supervised learning (SSL) can be employed on larger unlabeled datasets. CLE is a video-based modality with high inter-frame correlation, leading to a non-stratified data distribution for SSL training. In this work, we propose a filter functionality on CLE video sequences to reduce the dataset redundancy in SSL training and improve SSL training convergence and training efficiency. We use four state-of-the-art baseline networks and a SSL teacher-student network with a vision transformer small backbone for the evaluation. These networks were evaluated on downstream tasks for a sinonasal tumor dataset and a squamous cell carcinoma of the skin dataset. On both datasets, we found the highest test accuracy on the filtered SSL-pretrained model, with 67.48% and 73.52%, both considerably outperforming their non-SSL baselines. Our results show that SSL is an effective method for CLE pretraining. Further, we show that our proposed CLE video filter can be utilized to improve training efficiency in self-supervised scenarios, resulting in a reduction of 67% in training time.
Authors: Rotem Ezra, Hedi Zisling, Nimrod Berman, Ilan Naiman, Alexey Gorkor, Liran Nochumsohn, Eliya Nachmani, Omri Azencot
Abstract: Diffusion models have become state-of-the-art generative models for images, audio, and video, yet enabling fine-grained controllable generation, i.e., continuously steering specific concepts without disturbing unrelated content, remains challenging. Concept Sliders (CS) offer a promising direction by discovering semantic directions through textual contrasts, but they require per-concept training and architecture-specific fine-tuning (e.g., LoRA), limiting scalability to new modalities. In this work we introduce FreeSliders, a simple yet effective approach that is fully training-free and modality-agnostic, achieved by partially estimating the CS formula during inference. To support modality-agnostic evaluation, we extend the CS benchmark to include both video and audio, establishing the first suite for fine-grained concept generation control with multiple modalities. We further propose three evaluation properties along with new metrics to improve evaluation quality. Finally, we identify an open problem of scale selection and non-linear traversals and introduce a two-stage procedure that automatically detects saturation points and reparameterizes traversal for perceptually uniform, semantically meaningful edits. Extensive experiments demonstrate that our method enables plug-and-play, training-free concept control across modalities, improves over existing baselines, and establishes new tools for principled controllable generation. An interactive presentation of our benchmark and method is available at: https://azencot-group.github.io/FreeSliders/
Authors: Piyushkumar Patel
Abstract: Text to video generation has emerged as a critical frontier in generative artificial intelligence, yet existing approaches struggle with maintaining temporal consistency, compositional understanding, and fine grained control over visual narratives. We present MOVAI (Multimodal Original Video AI), a novel hierarchical framework that integrates compositional scene understanding with temporal aware diffusion models for high fidelity text to video synthesis. Our approach introduces three key innovations: (1) a Compositional Scene Parser (CSP) that decomposes textual descriptions into hierarchical scene graphs with temporal annotations, (2) a Temporal-Spatial Attention Mechanism (TSAM) that ensures coherent motion dynamics across frames while preserving spatial details, and (3) a Progressive Video Refinement (PVR) module that iteratively enhances video quality through multi-scale temporal reasoning. Extensive experiments on standard benchmarks demonstrate that MOVAI achieves state-of-the-art performance, improving video quality metrics by 15.3% in LPIPS, 12.7% in FVD, and 18.9% in user preference studies compared to existing methods. Our framework shows particular strength in generating complex multi-object scenes with realistic temporal dynamics and fine-grained semantic control.
Authors: YingQiao Wang, Eric Bigelow, Boyi Li, Tomer Ullman
Abstract: We propose a novel cognitively-inspired method to improve and interpret physical simulation in vision-language models. Our ``Chain of Time" method involves generating a series of intermediate images during a simulation, and it is motivated by in-context reasoning in machine learning, as well as mental simulation in humans. Chain of Time is used at inference time, and requires no additional fine-tuning. We apply the Chain-of-Time method to synthetic and real-world domains, including 2-D graphics simulations and natural 3-D videos. These domains test a variety of particular physical properties, including velocity, acceleration, fluid dynamics, and conservation of momentum. We found that using Chain-of-Time simulation substantially improves the performance of a state-of-the-art image generation model. Beyond examining performance, we also analyzed the specific states of the world simulated by an image model at each time step, which sheds light on the dynamics underlying these simulations. This analysis reveals insights that are hidden from traditional evaluations of physical reasoning, including cases where an image generation model is able to simulate physical properties that unfold over time, such as velocity, gravity, and collisions. Our analysis also highlights particular cases where the image generation model struggles to infer particular physical parameters from input images, despite being capable of simulating relevant physical processes.
Authors: Hanae Elmekki, Amanda Spilkin, Ehsan Zakeri, Antonela Mariel Zanuttini, Ahmed Alagha, Hani Sami, Jamal Bentahar, Lyes Kadem, Wen-Fang Xie, Philippe Pibarot, Rabeb Mizouni, Hadi Otrok, Azzam Mourad, Sami Muhaidat
Abstract: Cardiac ultrasound (US) is among the most widely used diagnostic tools in cardiology for assessing heart health, but its effectiveness is limited by operator dependence, time constraints, and human error. The shortage of trained professionals, especially in remote areas, further restricts access. These issues underscore the need for automated solutions that can ensure consistent, and accessible cardiac imaging regardless of operator skill or location. Recent progress in artificial intelligence (AI), especially in deep reinforcement learning (DRL), has gained attention for enabling autonomous decision-making. However, existing DRL-based approaches to cardiac US scanning lack reproducibility, rely on proprietary data, and use simplified models. Motivated by these gaps, we present the first end-to-end framework that integrates generative AI and DRL to enable autonomous and reproducible cardiac US scanning. The framework comprises two components: (i) a conditional generative simulator combining Generative Adversarial Networks (GANs) with Variational Autoencoders (VAEs), that models the cardiac US environment producing realistic action-conditioned images; and (ii) a DRL module that leverages this simulator to learn autonomous, accurate scanning policies. The proposed framework delivers AI-driven guidance through expert-validated models that classify image type and assess quality, supports conditional generation of realistic US images, and establishes a reproducible foundation extendable to other organs. To ensure reproducibility, a publicly available dataset of real cardiac US scans is released. The solution is validated through several experiments. The VAE-GAN is benchmarked against existing GAN variants, with performance assessed using qualitative and quantitative approaches, while the DRL-based scanning system is evaluated under varying configurations to demonstrate effectiveness.
Authors: Md Selim Sarowar, Sungho Kim
Abstract: The primary challenge in computer vision is precisely calculating the pose of 6D objects, however many current approaches are still fragile and have trouble generalizing from synthetic data to real-world situations with fluctuating lighting, textureless objects, and significant occlusions. To address these limitations, VLM6D, a novel dual-stream architecture that leverages the distinct strengths of visual and geometric data from RGB-D input for robust and precise pose estimation. Our framework uniquely integrates two specialized encoders: a powerful, self-supervised Vision Transformer (DINOv2) processes the RGB modality, harnessing its rich, pre-trained understanding of visual grammar to achieve remarkable resilience against texture and lighting variations. Concurrently, a PointNet++ encoder processes the 3D point cloud derived from depth data, enabling robust geometric reasoning that excels even with the sparse, fragmented data typical of severe occlusion. These complementary feature streams are effectively fused to inform a multi task prediction head. We demonstrate through comprehensive experiments that VLM6D obtained new SOTA performance on the challenging Occluded-LineMOD, validating its superior robustness and accuracy.
Authors: Gaby Maroun, Salah Eddine Bekhouche, Fadi Dornaika
Abstract: Age estimation from facial images is a complex and multifaceted challenge in computer vision. In this study, we present a novel hybrid architecture that combines ConvNeXt, a state-of-the-art advancement of convolutional neural networks (CNNs), with Vision Transformers (ViT). While each model independently delivers excellent performance on a variety of tasks, their integration leverages the complementary strengths of the CNNs localized feature extraction capabilities and the Transformers global attention mechanisms. Our proposed ConvNeXt-ViT hybrid solution was thoroughly evaluated on benchmark age estimation datasets, including MORPH II, CACD, and AFAD, and achieved superior performance in terms of mean absolute error (MAE). To address computational constraints, we leverage pre-trained models and systematically explore different configurations, using linear layers and advanced regularization techniques to optimize the architecture. Comprehensive ablation studies highlight the critical role of individual components and training strategies, and in particular emphasize the importance of adapted attention mechanisms within the CNN framework to improve the model focus on age-relevant facial features. The results show that the ConvNeXt-ViT hybrid not only outperforms traditional methods, but also provides a robust foundation for future advances in age estimation and related visual tasks. This work underscores the transformative potential of hybrid architectures and represents a promising direction for the seamless integration of CNNs and transformers to address complex computer vision challenges.
Authors: Janghoon Cho, Jungsoo Lee, Munawar Hayat, Kyuwoong Hwang, Fatih Porikli, Sungha Choi
Abstract: Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs specialized for processing extended video sequences. However, the scalability of these models is severely limited by the overwhelming volume of visual tokens generated from extended video sequences. To address this challenge, this paper proposes FLoC, an efficient visual token compression framework based on the facility location function, a principled approach that swiftly selects a compact yet highly representative and diverse subset of visual tokens within a predefined budget on the number of visual tokens. By integrating the lazy greedy algorithm, our method achieves remarkable efficiency gains by swiftly selecting a compact subset of tokens, drastically reducing the number of visual tokens while guaranteeing near-optimal performance. Notably, our approach is training-free, model-agnostic, and query-agnostic, providing a versatile solution that seamlessly integrates with diverse video-LLMs and existing workflows. Extensive evaluations on large-scale benchmarks, such as Video-MME, MLVU, and LongVideoBench, demonstrate that our framework consistently surpasses recent compression techniques, highlighting not only its effectiveness and robustness in addressing the critical challenges of long video understanding, but also its efficiency in processing speed.
Authors: Jinsu Kim, Yunhun Nam, Minseon Kim, Sangpil Kim, Jongheon Jeong
Abstract: Recent advances in text-to-image models have increased the exposure of powerful image editing techniques as a tool, raising concerns about their potential for malicious use. An emerging line of research to address such threats focuses on implanting "protective" adversarial noise into images before their public release, so future attempts to edit them using text-to-image models can be impeded. However, subsequent works have shown that these adversarial noises are often easily "reversed," e.g., with techniques as simple as JPEG compression, casting doubt on the practicality of the approach. In this paper, we argue that adversarial noise for image protection should not only be imperceptible, as has been a primary focus of prior work, but also irreversible, viz., it should be difficult to detect as noise provided that the original image is hidden. We propose a surprisingly simple method to enhance the robustness of image protection methods against noise reversal techniques. Specifically, it applies an adaptive per-region Gaussian blur on the noise to adjust the overall frequency spectrum. Through extensive experiments, we show that our method consistently improves the per-sample worst-case protection performance of existing methods against a wide range of reversal techniques on diverse image editing scenarios, while also reducing quality degradation due to noise in terms of perceptual metrics. Code is available at https://github.com/jsu-kim/BlurGuard.
Authors: Rahul Ghosh, Baishali Chaudhury, Hari Prasanna Das, Meghana Ashok, Ryan Razkenari, Sungmin Hong, Chun-Hao Liu
Abstract: Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods often rely on task-specific deep learning models trained on manually labeled datasets, which are costly to build and limited in generalizability. While recent multi-modal large language models (MLLMs) offer broad real-world knowledge and policy understanding, they struggle to reason over fine-grained visual details and apply structured compliance rules effectively on their own. In this paper, we propose CompAgent, the first agentic framework for visual compliance verification. CompAgent augments MLLMs with a suite of visual tools - such as object detectors, face analyzers, NSFW detectors, and captioning models - and introduces a planning agent that dynamically selects appropriate tools based on the compliance policy. A verification agent then integrates image, tool outputs, and policy context to perform multi-modal reasoning. Experiments on public benchmarks show that CompAgent outperforms specialized classifiers, direct MLLM prompting, and curated routing baselines, achieving up to 76% F1 score and a 10% improvement over the state-of-the-art on the UnsafeBench dataset. Our results demonstrate the effectiveness of agentic planning and tool-augmented reasoning for scalable, accurate, and adaptable visual compliance verification.
Authors: Mengfei Liang, Yiting Qu, Yukun Jiang, Michael Backes, Yang Zhang
Abstract: The rapid evolution of AI-generated images poses unprecedented challenges to information integrity and media authenticity. Existing detection approaches suffer from fundamental limitations: traditional classifiers lack interpretability and fail to generalize across evolving generative models, while vision-language models (VLMs), despite their promise, remain constrained to single-shot analysis and pixel-level reasoning. To address these challenges, we introduce AIFo (Agent-based Image Forensics), a novel training-free framework that emulates human forensic investigation through multi-agent collaboration. Unlike conventional methods, our framework employs a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and VLM analysis, coordinated by specialized LLM-based agents that collect, synthesize, and reason over cross-source evidence. When evidence is conflicting or insufficient, a structured multi-agent debate mechanism allows agents to exchange arguments and reach a reliable conclusion. Furthermore, we enhance the framework with a memory-augmented reasoning module that learns from historical cases to improve future detection accuracy. Our comprehensive evaluation spans 6,000 images across both controlled laboratory settings and challenging real-world scenarios, including images from modern generative platforms and diverse online sources. AIFo achieves 97.05% accuracy, substantially outperforming traditional classifiers and state-of-the-art VLMs. These results demonstrate that agent-based procedural reasoning offers a new paradigm for more robust, interpretable, and adaptable AI-generated image detection.
Authors: Ziliang Chen, Xin Huang, Quanlong Guan, Liang Lin, Weiqi Luo
Abstract: The vision community is undergoing the unprecedented progress with the emergence of Vision-Language Pretraining Models (VLMs). Prompt learning plays as the holy grail of accessing VLMs since it enables their fast adaptation to downstream tasks with limited resources. Whereas existing researches milling around single-prompt paradigms, rarely investigate the technical potential behind their multi-prompt learning counterparts. This paper aims to provide a principled retrospect for vision-language multi-prompt learning. We extend the recent constant modality gap phenomenon to learnable prompts and then, justify the superiority of vision-language transfer with multi-prompt augmentation, empirically and theoretically. In terms of this observation, we propose an Energy-based Multi-prompt Learning (EMPL) to generate multiple prompt embeddings by drawing instances from an energy-based distribution, which is implicitly defined by VLMs. So our EMPL is not only parameter-efficient but also rigorously lead to the balance between in-domain and out-of-domain open-vocabulary generalization. Comprehensive experiments have been conducted to justify our claims and the excellence of EMPL.
Authors: Wenxuan Zhang, Peng Hu
Abstract: The increasing adoption of satellite Internet with low-Earth-orbit (LEO) satellites in mega-constellations allows ubiquitous connectivity to rural and remote areas. However, weather events have a significant impact on the performance and reliability of satellite Internet. Adverse weather events such as snow and rain can disturb the performance and operations of satellite Internet's essential ground terminal components, such as satellite antennas, significantly disrupting the space-ground link conditions between LEO satellites and ground stations. This challenge calls for not only region-based weather forecasts but also fine-grained detection capability on ground terminal components of fine-grained weather conditions. Such a capability can assist in fault diagnostics and mitigation for reliable satellite Internet, but its solutions are lacking, not to mention the effectiveness and generalization that are essential in real-world deployments. This paper discusses an efficient transfer learning (TL) method that can enable a ground component to locally detect representative weather-related conditions. The proposed method can detect snow, wet, and other conditions resulting from adverse and typical weather events and shows superior performance compared to the typical deep learning methods, such as YOLOv7, YOLOv9, Faster R-CNN, and R-YOLO. Our TL method also shows the advantage of being generalizable to various scenarios.
Authors: Rajatsubhra Chakraborty, Ana Espinosa-Momox, Riley Haskin, Depeng Xu, Rosario Porras-Aguilar
Abstract: Cell segmentation in single-shot quantitative phase microscopy (ssQPM) faces challenges from traditional thresholding methods that are sensitive to noise and cell density, while deep learning approaches using simple channel concatenation fail to exploit the complementary nature of polarized intensity images and phase maps. We introduce DM-QPMNet, a dual-encoder network that treats these as distinct modalities with separate encoding streams. Our architecture fuses modality-specific features at intermediate depth via multi-head attention, enabling polarized edge and texture representations to selectively integrate complementary phase information. This content-aware fusion preserves training stability while adding principled multi-modal integration through dual-source skip connections and per-modality normalization at minimal overhead. Our approach demonstrates substantial improvements over monolithic concatenation and single-modality baselines, showing that modality-specific encoding with learnable fusion effectively exploits ssQPM's simultaneous capture of complementary illumination and phase cues for robust cell segmentation.
Authors: Fuming Yang, Yicong Li, Hanspeter Pfister, Jeff W. Lichtman, Yaron Meirovitch
Abstract: Petascale electron microscopy (EM) datasets push storage, transfer, and downstream analysis toward their current limits. We present a vector-quantized variational autoencoder-based (VQ-VAE) compression framework for EM that spans 16x to 1024x and enables pay-as-you-decode usage: top-only decoding for extreme compression, with an optional Transformer prior that predicts bottom tokens (without changing the compression ratio) to restore texture via feature-wise linear modulation (FiLM) and concatenation; we further introduce an ROI-driven workflow that performs selective high-resolution reconstruction from 1024x-compressed latents only where needed.
Authors: Yan Bin Ng, Xianfeng Gu
Abstract: The optimal transport (OT) problem aims to find the most efficient mapping between two probability distributions under a given cost function, and has diverse applications in many fields such as machine learning, computer vision and computer graphics. However, existing methods for computing optimal transport maps are primarily developed for Euclidean spaces and the sphere. In this paper, we explore the problem of computing the optimal transport map in hyperbolic space, which naturally arises in contexts involving hierarchical data, networks, and multi-genus Riemann surfaces. We propose a novel and efficient algorithm for computing the optimal transport map in hyperbolic space using a geometric variational technique by extending methods for Euclidean and spherical geometry to the hyperbolic setting. We also perform experiments on synthetic data and multi-genus surface models to validate the efficacy of the proposed method.
Authors: Shurui Gui, Deep Anil Patel, Xiner Li, Martin Renqiang Min
Abstract: Recent advances in video diffusion models have enabled the generation of high-quality videos. However, these videos still suffer from unrealistic deformations, semantic violations, and physical inconsistencies that are largely rooted in the absence of 3D physical priors. To address these challenges, we propose an object-aware 4D human motion generation framework grounded in 3D Gaussian representations and motion diffusion priors. With pre-generated 3D humans and objects, our method, Motion Score Distilled Interaction (MSDI), employs the spatial and prompt semantic information in large language models (LLMs) and motion priors through the proposed Motion Diffusion Score Distillation Sampling (MSDS). The combination of MSDS and LLMs enables our spatial-aware motion optimization, which distills score gradients from pre-trained motion diffusion models, to refine human motion while respecting object and semantic constraints. Unlike prior methods requiring joint training on limited interaction datasets, our zero-shot approach avoids retraining and generalizes to out-of-distribution object aware human motions. Experiments demonstrate that our framework produces natural and physically plausible human motions that respect 3D spatial context, offering a scalable solution for realistic 4D generation.
Authors: Aaron Sun, Subhransu Maji, Grant Van Horn
Abstract: In the single-positive multi-label (SPML) setting, each image in a dataset is labeled with the presence of a single class, while the true presence of other classes remains unknown. The challenge is to narrow the performance gap between this partially-labeled setting and fully-supervised learning, which often requires a significant annotation budget. Prior SPML methods were developed and benchmarked on synthetic datasets created by randomly sampling single positive labels from fully-annotated datasets like Pascal VOC, COCO, NUS-WIDE, and CUB200. However, this synthetic approach does not reflect real-world scenarios and fails to capture the fine-grained complexities that can lead to difficult misclassifications. In this work, we introduce the L48 dataset, a fine-grained, real-world multi-label dataset derived from recordings of bird sounds. L48 provides a natural SPML setting with single-positive annotations on a challenging, fine-grained domain, as well as two extended settings in which domain priors give access to additional negative labels. We benchmark existing SPML methods on L48 and observe significant performance differences compared to synthetic datasets and analyze method weaknesses, underscoring the need for more realistic and difficult benchmarks.
Authors: Fangxun Liu, S M Rayeed, Samuel Stevens, Alyson East, Cheng Hsuan Chiang, Colin Lee, Daniel Yi, Junke Yang, Tejas Naik, Ziyi Wang, Connor Kilrain, Elijah H Buckwalter, Jiacheng Hou, Saul Ibaven Bueno, Shuheng Wang, Xinyue Ma, Yifan Liu, Zhiyuan Tao, Ziheng Zhang, Eric Sokol, Michael Belitz, Sydne Record, Charles V. Stewart, Wei-Lun Chao
Abstract: In entomology and ecology research, biologists often need to collect a large number of insects, among which beetles are the most common species. A common practice for biologists to organize beetles is to place them on trays and take a picture of each tray. Given the images of thousands of such trays, it is important to have an automated pipeline to process the large-scale data for further research. Therefore, we develop a 3-stage pipeline to detect all the beetles on each tray, sort and crop the image of each beetle, and do morphological segmentation on the cropped beetles. For detection, we design an iterative process utilizing a transformer-based open-vocabulary object detector and a vision-language model. For segmentation, we manually labeled 670 beetle images and fine-tuned two variants of a transformer-based segmentation model to achieve fine-grained segmentation of beetles with relatively high accuracy. The pipeline integrates multiple deep learning methods and is specialized for beetle image processing, which can greatly improve the efficiency to process large-scale beetle data and accelerate biological research.
Authors: Linzhe Jiang, Jiayuan Huang, Sophia Bano, Matthew J. Clarkson, Zhehua Mao, Mobarak I. Hoque
Abstract: Accurate 3D point cloud registration underpins reliable image-guided colonoscopy, directly affecting lesion localization, margin assessment, and navigation safety. However, biological tissue exhibits repetitive textures and locally homogeneous geometry that cause feature degeneracy, while substantial domain shifts between pre-operative anatomy and intra-operative observations further degrade alignment stability. To address these clinically critical challenges, we introduce a novel 3D registration method tailored for endoscopic navigation and a high-quality, clinically grounded dataset to support rigorous and reproducible benchmarking. We introduce C3VD-Raycasting-10k, a large-scale benchmark dataset with 10,014 geometrically aligned point cloud pairs derived from clinical CT data. We propose MambaNetLK, a novel correspondence-free registration framework, which enhances the PointNetLK architecture by integrating a Mamba State Space Model (SSM) as a cross-modal feature extractor. As a result, the proposed framework efficiently captures long-range dependencies with linear-time complexity. The alignment is achieved iteratively using the Lucas-Kanade algorithm. On the clinical dataset, C3VD-Raycasting-10k, MambaNetLK achieves the best performance compared with the state-of-the-art methods, reducing median rotation error by 56.04% and RMSE translation error by 26.19% over the second-best method. The model also demonstrates strong generalization on ModelNet40 and superior robustness to initial pose perturbations. MambaNetLK provides a robust foundation for 3D registration in surgical navigation. The combination of a globally expressive SSM-based feature extractor and a large-scale clinical dataset enables more accurate and reliable guidance systems in minimally invasive procedures like colonoscopy.
Authors: Neha Balamurugan, Sarah Wu, Adam Chun, Gabe Gaw, Cristobal Eyzaguirre, Tobias Gerstenberg
Abstract: Humans excel at visual social inference, the ability to infer hidden elements of a scene from subtle behavioral cues such as other people's gaze, pose, and orientation. This ability drives everyday social reasoning in humans and is critical for developing more human-like AI agents. We introduce Spot The Ball, a challenging benchmark for evaluating visual social inference in vision-language models (VLMs) using sports as a test domain. The task is to localize a removed sports ball from soccer, basketball, and volleyball images. We present a curated evaluation set with human baselines and a scalable pipeline for generating additional test items. We evaluate four state-of-the-art VLMs (Gemini, GPT, LLaMA, Qwen) using three prompting strategies, finding that humans are consistently two to three times more accurate (20-34%) than models ($\leq$ 17%) across all sports. Our analyses show that models rely on superficial spatial heuristics--such as guessing near the image center or nearby players--while humans leverage social cues like gaze direction and body pose. These findings reveal a persistent human-model gap in visual social reasoning and underscore the need for architectures that explicitly encode structured behavioral cues to achieve robust, human-like inference.
Authors: Long Li, Jiajia Li, Dong Chen, Lina Pu, Haibo Yao, Yanbo Huang
Abstract: Accurate classification plays a pivotal role in smart agriculture, enabling applications such as crop monitoring, fruit recognition, and pest detection. However, conventional centralized training often requires large-scale data collection, which raises privacy concerns, while standard federated learning struggles with non-independent and identically distributed (non-IID) data and incurs high communication costs. To address these challenges, we propose a federated learning framework that integrates a frozen Contrastive Language-Image Pre-training (CLIP) vision transformer (ViT) with a lightweight transformer classifier. By leveraging the strong feature extraction capability of the pre-trained CLIP ViT, the framework avoids training large-scale models from scratch and restricts federated updates to a compact classifier, thereby reducing transmission overhead significantly. Furthermore, to mitigate performance degradation caused by non-IID data distribution, a small subset (1%) of CLIP-extracted feature representations from all classes is shared across clients. These shared features are non-reversible to raw images, ensuring privacy preservation while aligning class representation across participants. Experimental results on agricultural classification tasks show that the proposed method achieve 86.6% accuracy, which is more than 4 times higher compared to baseline federated learning approaches. This demonstrates the effectiveness and efficiency of combining vision-language model features with federated learning for privacy-preserving and scalable agricultural intelligence.
Authors: Hengjia Li, Jianjin Xu, Keli Cheng, Lei Wang, Ning Bi, Boxi Wu, Fernando De la Torre, Deng Cai
Abstract: Recent advances in personalized generative models demonstrate impressive results in creating identity-consistent images of the same person under diverse settings. Yet, we note that most methods cannot control the viewpoint of the generated image, nor generate consistent multiple views of the person. To address this problem, we propose a lightweight adaptation method, PersonalView, capable of enabling an existing model to acquire multi-view generation capability with as few as 100 training samples. PersonalView consists of two key components: First, we design a conditioning architecture to take advantage of the in-context learning ability of the pre-trained diffusion transformer. Second, we preserve the original generative ability of the pretrained model with a new Semantic Correspondence Alignment Loss. We evaluate the multi-view consistency, text alignment, identity similarity, and visual quality of PersonalView and compare it to recent baselines with potential capability of multi-view customization. PersonalView significantly outperforms baselines trained on a large corpus of multi-view data with only 100 training samples.
Authors: Isai Daniel Chac\'on, Paola Ruiz Puentes, Jillian Pearse, Pablo Arbel\'aez
Abstract: Petrography is a branch of geology that analyzes the mineralogical composition of rocks from microscopical thin section samples. It is essential for understanding rock properties across geology, archaeology, engineering, mineral exploration, and the oil industry. However, petrography is a labor-intensive task requiring experts to conduct detailed visual examinations of thin section samples through optical polarization microscopes, thus hampering scalability and highlighting the need for automated techniques. To address this challenge, we introduce the Large-scale Imaging and Thin section Optical-polarization Set (LITHOS), the largest and most diverse publicly available experimental framework for automated petrography. LITHOS includes 211,604 high-resolution RGB patches of polarized light and 105,802 expert-annotated grains across 25 mineral categories. Each annotation consists of the mineral class, spatial coordinates, and expert-defined major and minor axes represented as intersecting vector paths, capturing grain geometry and orientation. We evaluate multiple deep learning techniques for mineral classification in LITHOS and propose a dual-encoder transformer architecture that integrates both polarization modalities as a strong baseline for future reference. Our method consistently outperforms single-polarization models, demonstrating the value of polarization synergy in mineral classification. We have made the LITHOS Benchmark publicly available, comprising our dataset, code, and pretrained models, to foster reproducibility and further research in automated petrographic analysis.
Authors: Weidong Zhang, Pak Lun Kevin Ding, Huan Liu
Abstract: Lightweight vision classification models such as MobileNet, ShuffleNet, and EfficientNet are increasingly deployed in mobile and embedded systems, yet their performance has been predominantly benchmarked on ImageNet. This raises critical questions: Do models that excel on ImageNet also generalize across other domains? How can cross-dataset robustness be systematically quantified? And which architectural elements consistently drive generalization under tight resource constraints? Here, we present the first systematic evaluation of 11 lightweight vision models (2.5M parameters), trained under a fixed 100-epoch schedule across 7 diverse datasets. We introduce the Cross-Dataset Score (xScore), a unified metric that quantifies the consistency and robustness of model performance across diverse visual domains. Our results show that (1) ImageNet accuracy does not reliably predict performance on fine-grained or medical datasets, (2) xScore provides a scalable predictor of mobile model performance that can be estimated from just four datasets, and (3) certain architectural components--such as isotropic convolutions with higher spatial resolution and channel-wise attention--promote broader generalization, while Transformer-based blocks yield little additional benefit, despite incurring higher parameter overhead. This study provides a reproducible framework for evaluating lightweight vision models beyond ImageNet, highlights key design principles for mobile-friendly architectures, and guides the development of future models that generalize robustly across diverse application domains.
Authors: Yuhao Fang, Zijian Wang, Yao Lu, Ye Zhang, Chun Li
Abstract: This work presents a novel hybrid approach that integrates Deep Operator Networks (DeepONet) with the Neural Tangent Kernel (NTK) to solve complex inverse problem. The method effectively addresses tasks such as source localization governed by the Navier-Stokes equations and image reconstruction, overcoming challenges related to nonlinearity, sparsity, and noisy data. By incorporating physics-informed constraints and task-specific regularization into the loss function, the framework ensures solutions that are both physically consistent and accurate. Validation on diverse synthetic and real datasets demonstrates its robustness, scalability, and precision, showcasing its broad potential applications in computational physics and imaging sciences.
Authors: Xihang Qiu, Jiarong Cheng, Yuhao Fang, Wanpeng Zhang, Yao Lu, Ye Zhang, Chun Li
Abstract: Multimodal Emotion Recognition in Conversations (MERC) enhances emotional understanding through the fusion of multimodal signals. However, unpredictable modality absence in real-world scenarios significantly degrades the performance of existing methods. Conventional missing-modality recovery approaches, which depend on training with complete multimodal data, often suffer from semantic distortion under extreme data distributions, such as fixed-modality absence. To address this, we propose the Federated Dialogue-guided and Semantic-Consistent Diffusion (FedDISC) framework, pioneering the integration of federated learning into missing-modality recovery. By federated aggregation of modality-specific diffusion models trained on clients and broadcasting them to clients missing corresponding modalities, FedDISC overcomes single-client reliance on modality completeness. Additionally, the DISC-Diffusion module ensures consistency in context, speaker identity, and semantics between recovered and available modalities, using a Dialogue Graph Network to capture conversational dependencies and a Semantic Conditioning Network to enforce semantic alignment. We further introduce a novel Alternating Frozen Aggregation strategy, which cyclically freezes recovery and classifier modules to facilitate collaborative optimization. Extensive experiments on the IEMOCAP, CMUMOSI, and CMUMOSEI datasets demonstrate that FedDISC achieves superior emotion classification performance across diverse missing modality patterns, outperforming existing approaches.
Authors: Amir Ziashahabi, Narges Ghasemi, Sajjad Shahabi, John Krumm, Salman Avestimehr, Cyrus Shahabi
Abstract: Accurate and up-to-date geospatial data are essential for urban planning, infrastructure monitoring, and environmental management. Yet, automating urban monitoring remains difficult because curated datasets of specific urban features and their changes are scarce. We introduce OSMGen, a generative framework that creates realistic satellite imagery directly from raw OpenStreetMap (OSM) data. Unlike prior work that relies on raster tiles, OSMGen uses the full richness of OSM JSON, including vector geometries, semantic tags, location, and time, giving fine-grained control over how scenes are generated. A central feature of the framework is the ability to produce consistent before-after image pairs: user edits to OSM inputs translate into targeted visual changes, while the rest of the scene is preserved. This makes it possible to generate training data that addresses scarcity and class imbalance, and to give planners a simple way to preview proposed interventions by editing map data. More broadly, OSMGen produces paired (JSON, image) data for both static and changed states, paving the way toward a closed-loop system where satellite imagery can automatically drive structured OSM updates. Source code is available at https://github.com/amir-zsh/OSMGen.
Authors: Mohd Ruhul Ameen, Akif Islam
Abstract: The rapid rise of generative diffusion models has made distinguishing authentic visual content from synthetic imagery increasingly challenging. Traditional deepfake detection methods, which rely on frequency or pixel-level artifacts, fail against modern text-to-image systems such as Stable Diffusion and DALL-E that produce photorealistic and artifact-free results. This paper introduces a diffusion-based forensic framework that leverages multi-strength image reconstruction dynamics, termed diffusion snap-back, to identify AI-generated images. By analysing how reconstruction metrics (LPIPS, SSIM, and PSNR) evolve across varying noise strengths, we extract interpretable manifold-based features that differentiate real and synthetic images. Evaluated on a balanced dataset of 4,000 images, our approach achieves 0.993 AUROC under cross-validation and remains robust to common distortions such as compression and noise. Despite using limited data and a single diffusion backbone (Stable Diffusion v1.5), the proposed method demonstrates strong generalization and interpretability, offering a foundation for scalable, model-agnostic synthetic media forensics.
Authors: Niklas W\"olki, Lukas Kondmann, Christian Molli\`ere, Martin Langer, Julia Gottfriedsen, Martin Werner
Abstract: Onboard cloud segmentation is a critical yet underexplored task in thermal Earth observation (EO), particularly for CubeSat missions constrained by limited hardware and spectral information. CubeSats often rely on a single thermal band and lack sufficient labeled data, making conventional cloud masking techniques infeasible. This work addresses these challenges by applying transfer learning to thermal cloud segmentation for the FOREST-2 CubeSat, using a UNet with a lightweight MobileNet encoder. We pretrain the model on the public Landsat-7 Cloud Cover Assessment Dataset and fine-tune it with a small set of mission-specific samples in a joint-training setup, improving the macro F1 from 0.850 to 0.877 over FOREST-2-only baselines. We convert the model to a TensorRT engine and demonstrate full-image inference in under 5 seconds on an NVIDIA Jetson Nano. These results show that leveraging public datasets and lightweight architectures can enable accurate, efficient thermal-only cloud masking on-orbit, supporting real-time decision-making in data-limited EO missions.
Authors: Momen Khandoker Ope, Akif Islam, Mohd Ruhul Ameen, Abu Saleh Musa Miah, Md Rashedul Islam, Jungpil Shin
Abstract: Cultural heritage restoration in Bangladesh faces a dual challenge of limited resources and scarce technical expertise. Traditional 3D digitization methods, such as photogrammetry or LiDAR scanning, require expensive hardware, expert operators, and extensive on-site access, which are often infeasible in developing contexts. As a result, many of Bangladesh's architectural treasures, from the Paharpur Buddhist Monastery to Ahsan Manzil, remain vulnerable to decay and inaccessible in digital form. This paper introduces Oitijjo-3D, a cost-free generative AI framework that democratizes 3D cultural preservation. By using publicly available Google Street View imagery, Oitijjo-3D reconstructs faithful 3D models of heritage structures through a two-stage pipeline - multimodal visual reasoning with Gemini 2.5 Flash Image for structure-texture synthesis, and neural image-to-3D generation through Hexagen for geometry recovery. The system produces photorealistic, metrically coherent reconstructions in seconds, achieving significant speedups compared to conventional Structure-from-Motion pipelines, without requiring any specialized hardware or expert supervision. Experiments on landmarks such as Ahsan Manzil, Choto Sona Mosque, and Paharpur demonstrate that Oitijjo-3D preserves both visual and structural fidelity while drastically lowering economic and technical barriers. By turning open imagery into digital heritage, this work reframes preservation as a community-driven, AI-assisted act of cultural continuity for resource-limited nations.
Authors: Chaochen Wu, Guan Luo, Meiyun Zuo, Zhitao Fan
Abstract: Video moment retrieval uses a text query to locate a moment from a given untrimmed video reference. Locating corresponding video moments with text queries helps people interact with videos efficiently. Current solutions for this task have not considered conflict within location results from different models, so various models cannot integrate correctly to produce better results. This study introduces a reinforcement learning-based video moment retrieval model that can scan the whole video once to find the moment's boundary while producing its locational evidence. Moreover, we proposed a multi-agent system framework that can use evidential learning to resolve conflicts between agents' localization output. As a side product of observing and dealing with conflicts between agents, we can decide whether a query has no corresponding moment in a video (out-of-scope) without additional training, which is suitable for real-world applications. Extensive experiments on benchmark datasets show the effectiveness of our proposed methods compared with state-of-the-art approaches. Furthermore, the results of our study reveal that modeling competition and conflict of the multi-agent system is an effective way to improve RL performance in moment retrieval and show the new role of evidential learning in the multi-agent framework.
Authors: Jiaming Li, Junlei Wu, Sheng Wang, Honglin Xiong, Jiangdong Cai, Zihao Zhao, Yitao Zhu, Yuan Yin, Dinggang Shen, Qian Wang
Abstract: Widespread clinical deployment of computer-aided diagnosis (CAD) systems is hindered by the challenge of integrating with existing hospital IT infrastructure. Here, we introduce VisionCAD, a vision-based radiological assistance framework that circumvents this barrier by capturing medical images directly from displays using a camera system. The framework operates through an automated pipeline that detects, restores, and analyzes on-screen medical images, transforming camera-captured visual data into diagnostic-quality images suitable for automated analysis and report generation. We validated VisionCAD across diverse medical imaging datasets, demonstrating that our modular architecture can flexibly utilize state-of-the-art diagnostic models for specific tasks. The system achieves diagnostic performance comparable to conventional CAD systems operating on original digital images, with an F1-score degradation typically less than 2\% across classification tasks, while natural language generation metrics for automated reports remain within 1\% of those derived from original images. By requiring only a camera device and standard computing resources, VisionCAD offers an accessible approach for AI-assisted diagnosis, enabling the deployment of diagnostic capabilities in diverse clinical settings without modifications to existing infrastructure.
Authors: Fan Zhang, Haoxuan Li, Shengju Qian, Xin Wang, Zheng Lian, Hao Wu, Zhihong Zhu, Yuan Gao, Qiankun Li, Yefeng Zheng, Zhouchen Lin, Pheng-Ann Heng
Abstract: Multimodal Large Language Models (MLLMs) have revolutionized numerous research fields, including computer vision and affective computing. As a pivotal challenge in this interdisciplinary domain, facial expression recognition (FER) has evolved from separate, domain-specific models to more unified approaches. One promising avenue to unify FER tasks is converting conventional FER datasets into visual question-answering (VQA) formats, enabling the direct application of powerful generalist MLLMs for inference. However, despite the success of cutting-edge MLLMs in various tasks, their performance on FER tasks remains largely unexplored. To address this gap, we provide FERBench, a systematic benchmark that incorporates 20 state-of-the-art MLLMs across four widely used FER datasets. Our results reveal that, while MLLMs exhibit good classification performance, they still face significant limitations in reasoning and interpretability. To this end, we introduce post-training strategies aimed at enhancing the facial expression reasoning capabilities of MLLMs. Specifically, we curate two high-quality and large-scale datasets: UniFER-CoT-230K for cold-start initialization and UniFER-RLVR-360K for reinforcement learning with verifiable rewards (RLVR), respectively. Building upon them, we develop a unified and interpretable FER foundation model termed UniFER-7B, which outperforms many open-sourced and closed-source generalist MLLMs (e.g., Gemini-2.5-Pro and Qwen2.5-VL-72B).
Authors: Xuanle Zhao, Deyang Jiang, Zhixiong Zeng, Lei Chen, Haibo Qiu, Jing Huang, Yufeng Zhong, Liming Zheng, Yilin Cao, Lin Ma
Abstract: Multimodal code generation has garnered significant interest within the research community. Despite the notable success of recent vision-language models (VLMs) on specialized tasks like Chart-to-code generation, their reliance on single-task training regimens fosters a narrow paradigm that hinders the development of generalized \textbf{VI}sio\textbf{N} \textbf{C}ode \textbf{I}ntelligence. In this work, we introduce \textbf{VinciCoder}, a unified multimodal code generation model that addresses this limitation via a two-stage training framework. We begin by constructing a large-scale Supervised Finetuning (SFT) corpus comprising 1.6M image-code pairs for tasks involving direct code generation and visual-based code refinement. Subsequently, we introduce a Visual Reinforcement Learning (ViRL) strategy, which employs a coarse-to-fine reward mechanism to improve visual fidelity by calculating visual similarity across local and global image patches. Extensive experiments on various multimodal code generation benchmarks demonstrate that VinciCoder achieves state-of-the-art performance, underscoring the effectiveness of our coarse-to-fine ViRL strategy. The code and model will be available at https://github.com/DocTron-hub/VinciCoder.
Authors: Long Li, Shuichen Ji, Ziyang Luo, Nian Liu, Dingwen Zhang, Junwei Han
Abstract: We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks, eg, SOD, CoSOD, and SIS, by casting each as a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity. CoT training follows a two-stage paradigm: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). To enhance CoT quality in RL, we propose Confidence-Guided Policy Optimization (CGPO), a lightweight single-sample algorithm that leverages the discrepancy between reward and model confidence as a per-sample advantage signal. This design naturally focuses updates on informative responses while eliminating group sampling, thereby addressing GRPO's key limitations: confidence-agnostic learning, signal dilution, and prohibitive computational overhead. We also introduce an "output-to-reasoning" strategy to construct high-fidelity SFT data that ensures logical consistency with ground-truth masks. Experiments show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks, especially achieving an S-measure of 0.899 on CoCA for CoSOD, surpassing the prior best by 8.0 percentage points, despite using far less training data.
Authors: Thanh Hieu Cao, Trung Khang Tran, Gia Thinh Pham, Tuong Nghiem Diep, Thanh Binh Nguyen
Abstract: Recent advancements in large-scale pretraining in natural language processing have enabled pretrained vision-language models such as CLIP to effectively align images and text, significantly improving performance in zero-shot image classification tasks. Subsequent studies have further demonstrated that cropping images into smaller regions and using large language models to generate multiple descriptions for each caption can further enhance model performance. However, due to the inherent sensitivity of CLIP, random image crops can introduce misinformation and bias, as many images share similar features at small scales. To address this issue, we propose Localized-Globalized Cross-Alignment (LGCA), a framework that first captures the local features of an image and then repeatedly selects the most salient regions and expands them. The similarity score is designed to incorporate both the original and expanded images, enabling the model to capture both local and global features while minimizing misinformation. Additionally, we provide a theoretical analysis demonstrating that the time complexity of LGCA remains the same as that of the original model prior to the repeated expansion process, highlighting its efficiency and scalability. Extensive experiments demonstrate that our method substantially improves zero-shot performance across diverse datasets, outperforming state-of-the-art baselines.
Authors: Daichi Zhang, Tong Zhang, Jianmin Bao, Shiming Ge, Sabine S\"usstrunk
Abstract: With the rapid development of generative models, detecting generated fake images to prevent their malicious use has become a critical issue recently. Existing methods frame this challenge as a naive binary image classification task. However, such methods focus only on visual clues, yielding trained detectors susceptible to overfitting specific image patterns and incapable of generalizing to unseen models. In this paper, we address this issue from a multi-modal perspective and find that fake images cannot be properly aligned with corresponding captions compared to real images. Upon this observation, we propose a simple yet effective detector termed ITEM by leveraging the image-text misalignment in a joint visual-language space as discriminative clues. Specifically, we first measure the misalignment of the images and captions in pre-trained CLIP's space, and then tune a MLP head to perform the usual detection task. Furthermore, we propose a hierarchical misalignment scheme that first focuses on the whole image and then each semantic object described in the caption, which can explore both global and fine-grained local semantic misalignment as clues. Extensive experiments demonstrate the superiority of our method against other state-of-the-art competitors with impressive generalization and robustness on various recent generative models.
Authors: Daichi Zhang, Tong Zhang, Shiming Ge, Sabine S\"usstrunk
Abstract: Diffusion models have achieved remarkable success in image synthesis, but the generated high-quality images raise concerns about potential malicious use. Existing detectors often struggle to capture discriminative clues across different models and settings, limiting their generalization to unseen diffusion models and robustness to various perturbations. To address this issue, we observe that diffusion-generated images exhibit progressively larger differences from natural real images across low- to high-frequency bands. Based on this insight, we propose a simple yet effective representation by enhancing the Frequency Forgery Clue (F^2C) across all frequency bands. Specifically, we introduce a frequency-selective function which serves as a weighted filter to the Fourier spectrum, suppressing less discriminative bands while enhancing more informative ones. This approach, grounded in a comprehensive analysis of frequency-based differences between natural real and diffusion-generated images, enables general detection of images from unseen diffusion models and provides robust resilience to various perturbations. Extensive experiments on various diffusion-generated image datasets demonstrate that our method outperforms state-of-the-art detectors with superior generalization and robustness.
Authors: Xin Yao, Haiyang Zhao, Yimin Chen, Jiawei Guo, Kecheng Huang, Ming Zhao
Abstract: The Contrastive Language-Image Pretraining (CLIP) model has significantly advanced vision-language modeling by aligning image-text pairs from large-scale web data through self-supervised contrastive learning. Yet, its reliance on uncurated Internet-sourced data exposes it to data poisoning and backdoor risks. While existing studies primarily investigate image-based attacks, the text modality, which is equally central to CLIP's training, remains underexplored. In this work, we introduce ToxicTextCLIP, a framework for generating high-quality adversarial texts that target CLIP during the pre-training phase. The framework addresses two key challenges: semantic misalignment caused by background inconsistency with the target class, and the scarcity of background-consistent texts. To this end, ToxicTextCLIP iteratively applies: 1) a background-aware selector that prioritizes texts with background content aligned to the target class, and 2) a background-driven augmenter that generates semantically coherent and diverse poisoned samples. Extensive experiments on classification and retrieval tasks show that ToxicTextCLIP achieves up to 95.83% poisoning success and 98.68% backdoor Hit@1, while bypassing RoCLIP, CleanCLIP and SafeCLIP defenses. The source code can be accessed via https://github.com/xinyaocse/ToxicTextCLIP/.
Authors: Kiran Shahi, Anup Bagale
Abstract: This study proposes a weakly supervised deep learning framework for pneumonia classification and localization from chest X-rays, utilizing Grad-CAM explanations. Instead of costly pixel-level annotations, our approach utilizes image-level labels to generate clinically meaningful heatmaps that highlight regions affected by pneumonia. We evaluate seven ImageNet-pretrained architectures ResNet-18/50, DenseNet-121, EfficientNet-B0, MobileNet-V2/V3, and ViT-B16 under identical training conditions with focal loss and patient-wise splits to prevent data leakage. Experimental results on the Kermany CXR dataset demonstrate that ResNet-18 and EfficientNet-B0 achieve the best overall test accuracy of 98\%, ROC-AUC = 0.997, and F1 = 0.987, while MobileNet-V2 provides an optimal trade-off between accuracy and computational cost. Grad-CAM visualizations confirm that the proposed models focus on clinically relevant lung regions, supporting the use of interpretable AI for radiological diagnostics. This work highlights the potential of weakly supervised explainable models that enhance pneumonia screening transparency, and clinical trust in AI-assisted medical imaging. https://github.com/kiranshahi/pneumonia-analysis
Authors: Panwang Pan, Tingting Shen, Chenxin Li, Yunlong Lin, Kairun Wen, Jingjing Zhao, Yixuan Yuan
Abstract: Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables the joint modeling of appearance and human-part semantics from a single image in a feed-forward manner. Specifically, we integrate human geometric priors in the reconstruction stage and self-supervised semantic priors in the segmentation stage. To address labeled 3D human datasets scarcity, we further develop an interactive annotation procedure for generating high-quality data-label pairs. Our pixel-aligned aggregation enables cross-task synergy, while the multi-task objective simultaneously optimizes texture modeling fidelity and semantic consistency. Extensive experiments demonstrate that HumanCrafter surpasses existing state-of-the-art methods in both 3D human-part segmentation and 3D human reconstruction from a single image.
Authors: Navodini Wijethilake, Marina Ivory, Oscar MacCormac, Siddhant Kumar, Aaron Kujawa, Lorena Garcia-Foncillas Macias, Rebecca Burger, Amanda Hitchings, Suki Thomson, Sinan Barazi, Eleni Maratos, Rupert Obholzer, Dan Jiang, Fiona McClenaghan, Kazumi Chia, Omar Al-Salihi, Nick Thomas, Steve Connor, Tom Vercauteren, Jonathan Shapey
Abstract: Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62).
Authors: Weihao Bo, Yanpeng Sun, Yu Wang, Xinyu Zhang, Zechao Li
Abstract: In this paper, we introduce FedMGP, a new paradigm for personalized federated prompt learning in vision-language models. FedMGP equips each client with multiple groups of paired textual and visual prompts, enabling the model to capture diverse, fine-grained semantic and instance-level cues. A diversity loss is introduced to drive each prompt group to specialize in distinct and complementary semantic aspects, ensuring that the groups collectively cover a broader range of local characteristics. During communication, FedMGP employs a dynamic prompt aggregation strategy based on similarity-guided probabilistic sampling: each client computes the cosine similarity between its prompt groups and the global prompts from the previous round, then samples s groups via a softmax-weighted distribution. This soft selection mechanism preferentially aggregates semantically aligned knowledge while still enabling exploration of underrepresented patterns effectively balancing the preservation of common knowledge with client-specific features. Notably, FedMGP maintains parameter efficiency by redistributing a fixed prompt capacity across multiple groups, achieving state-of-the-art performance with the lowest communication parameters among all federated prompt learning methods. Theoretical analysis shows that our dynamic aggregation strategy promotes robust global representation learning by reinforcing shared semantics while suppressing client-specific noise. Extensive experiments demonstrate that FedMGP consistently outperforms prior approaches in both personalization and domain generalization across diverse federated vision-language benchmarks. The code will be released on https://github.com/weihao-bo/FedMGP.git.
Authors: Panwang Pan, Chenguo Lin, Jingjing Zhao, Chenxin Li, Yuchen Lin, Haopeng Li, Honglei Yan, Kairun Wen, Yunlong Lin, Yixuan Yuan, Yadong Mu
Abstract: We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusion models with geometry and motion constraints learned from large-scale 4D datasets. Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion, all in a single forward pass, without test-time optimization or post-hoc refinement. At the core of our framework lies a video latent transformer, which augments video diffusion models to jointly capture spatio-temporal dependencies and predict time-varying 3D Gaussian primitives. Training is guided by objectives on appearance fidelity, geometric accuracy, and motion consistency, enabling Diff4Splat to synthesize high-quality 4D scenes in 30 seconds. We demonstrate the effectiveness of Diff4Splatacross video generation, novel view synthesis, and geometry extraction, where it matches or surpasses optimization-based methods for dynamic scene synthesis while being significantly more efficient.
Authors: Hai-Dang Nguyen, Ha-Hieu Pham, Hao T. Nguyen, Huy-Hieu Pham
Abstract: We present VinDr-CXR-VQA, a large-scale chest X-ray dataset for explainable Medical Visual Question Answering (Med-VQA) with spatial grounding. The dataset contains 17,597 question-answer pairs across 4,394 images, each annotated with radiologist-verified bounding boxes and clinical reasoning explanations. Our question taxonomy spans six diagnostic types-Where, What, Is there, How many, Which, and Yes/No-capturing diverse clinical intents. To improve reliability, we construct a balanced distribution of 41.7% positive and 58.3% negative samples, mitigating hallucinations in normal cases. Benchmarking with MedGemma-4B-it demonstrates improved performance (F1 = 0.624, +11.8% over baseline) while enabling lesion localization. VinDr-CXR-VQA aims to advance reproducible and clinically grounded Med-VQA research. The dataset and evaluation tools are publicly available at huggingface.co/datasets/Dangindev/VinDR-CXR-VQA.
Authors: Kai Luo, Hao Shi, Kunyu Peng, Fei Teng, Sheng Wu, Kaiwei Wang, Kailun Yang
Abstract: This paper investigates Multi-Object Tracking (MOT) in panoramic imagery, which introduces unique challenges including a 360{\deg} Field of View (FoV), resolution dilution, and severe view-dependent distortions. Conventional MOT methods designed for narrow-FoV pinhole cameras generalize unsatisfactorily under these conditions. To address panoramic distortion, large search space, and identity ambiguity under a 360{\deg} FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception with trajectory cues. A DynamicSSM block first stabilizes panoramic features, implicitly alleviating geometric distortion. On top of normalized representations, FlexiTrack Instances use trajectory-informed feedback for flexible localization and reliable short-term association. To ensure long-term robustness, an ExpertTrack Memory consolidates appearance cues via a Mixture-of-Experts design, enabling recovery from fragmented tracks and reducing identity drift. Finally, a Tracklet Management module adaptively switches between end-to-end and tracking-by-detection modes according to scene dynamics, offering a balanced and scalable solution for panoramic MOT. To support rigorous evaluation, we establish the EmboTrack benchmark, a comprehensive dataset for panoramic MOT that includes QuadTrack, captured with a quadruped robot, and BipTrack, collected with a bipedal wheel-legged robot. Together, these datasets span wide-angle environments and diverse motion patterns, providing a challenging testbed for real-world panoramic perception. Extensive experiments on JRDB and EmboTrack demonstrate that OmniTrack++ achieves state-of-the-art performance, yielding substantial HOTA improvements of +25.5% on JRDB and +43.07% on QuadTrack over the original OmniTrack. Datasets and code will be made publicly available at https://github.com/xifen523/OmniTrack.
Authors: Panwang Pan, Jingjing Zhao, Yuchen Lin, Chenguo Lin, Chenxin Li, Haopeng Li, Honglei Yan, Tingting Shen, Yadong Mu
Abstract: Video generative models pretrained on large-scale datasets can produce high-quality videos, but are often conditioned on text or a single image, limiting controllability and applicability. We introduce ID-Composer, a novel framework that addresses this gap by tackling multi-subject video generation from a text prompt and reference images. This task is challenging as it requires preserving subject identities, integrating semantics across subjects and modalities, and maintaining temporal consistency. To faithfully preserve the subject consistency and textual information in synthesized videos, ID-Composer designs a \textbf{hierarchical identity-preserving attention mechanism}, which effectively aggregates features within and across subjects and modalities. To effectively allow for the semantic following of user intention, we introduce \textbf{semantic understanding via pretrained vision-language model (VLM)}, leveraging VLM's superior semantic understanding to provide fine-grained guidance and capture complex interactions between multiple subjects. Considering that standard diffusion loss often fails in aligning the critical concepts like subject ID, we employ an \textbf{online reinforcement learning phase} to drive the overall training objective of ID-Composer into RLVR. Extensive experiments demonstrate that our model surpasses existing methods in identity preservation, temporal consistency, and video quality.
Authors: Fangyu Wu, Yujun Cai
Abstract: Vision language models such as CLIP have shown remarkable performance in zero shot classification, but remain susceptible to spurious correlations, where irrelevant visual features influence predictions. Existing debiasing methods often require access to training data and explicit group labels to perform fine-tuning or adjust embeddings, which limits their practicality in real-world settings. Test-time methods attempt to avoid this constraint, but many still depend on prior knowledge of dataset specific biases, limiting their generalizability in open set settings. In this work, we propose a test-time debiasing method for ViT based CLIP models that requires no additional training or assumptions of bias annotations. Our approach uses a pretrained segmentation model to isolate the target visual attribute, then adjusts the non target regions so that their embeddings are uniformly similar to all class specific text prompts. This procedure removes unintended bias signals from confounding visual regions while preserving the target attribute. Experiments on Waterbirds and CelebA show that our method outperforms existing test-time debiasing approaches in both group robustness metrics and Attention IoU. These results demonstrate the effectiveness of segmentation guided interventions for scalable and annotation free bias mitigation in vision language models.
Authors: Jihao Gu, Kun Li, He Wang, Kaan Ak\c{s}it
Abstract: Video Anomaly Detection (VAD) aims to identify anomalous events within video segments. In scenarios such as surveillance or industrial process monitoring, anomaly detection is of critical importance. While existing approaches are semi-automated, requiring human assessment for anomaly detection, traditional VADs offer limited output as either normal or anomalous. We propose Text-guided Fine-Grained Video Anomaly Detection (T-VAD), a framework built upon Large Vision-Language Model (LVLM). T-VAD introduces an Anomaly Heatmap Decoder (AHD) that performs pixel-wise visual-textual feature alignment to generate fine-grained anomaly heatmaps. Furthermore, we design a Region-aware Anomaly Encoder (RAE) that transforms the heatmaps into learnable textual embeddings, guiding the LVLM to accurately identify and localize anomalous events in videos. This significantly enhances both the granularity and interactivity of anomaly detection. The proposed method achieving SOTA performance by demonstrating 94.8% Area Under the Curve (AUC, specifically micro-AUC) and 67.8%/76.7% accuracy in anomaly heatmaps (RBDC/TBDC) on the UBnormal dataset, and subjectively verified more preferable textual description on the ShanghaiTech-based dataset (BLEU-4: 62.67 for targets, 88.84 for trajectories; Yes/No accuracy: 97.67%), and on the UBnormal dataset (BLEU-4: 50.32 for targets, 78.10 for trajectories; Yes/No accuracy: 89.73%).
Authors: Wenbing Zhu, Chengjie Wang, Bin-Bin Gao, Jiangning Zhang, Guannan Jiang, Jie Hu, Zhenye Gan, Lidong Wang, Ziqing Zhou, Linjie Cheng, Yurui Pan, Bo Peng, Mingmin Chi, Lizhuang Ma
Abstract: Industrial Anomaly Detection (IAD) is critical for enhancing operational safety, ensuring product quality, and optimizing manufacturing efficiency across global industries. However, the IAD algorithms are severely constrained by the limitations of existing public benchmarks. Current datasets exhibit restricted category diversity and insufficient scale, frequently resulting in metric saturation and limited model transferability to real-world scenarios. To address this gap, we introduce Real-IAD Variety, the largest and most diverse IAD benchmark, comprising 198,960 high-resolution images across 160 distinct object categories. Its diversity is ensured through comprehensive coverage of 28 industries, 24 material types, and 22 color variations. Our comprehensive experimental analysis validates the benchmark's substantial challenge: state-of-the-art multi-class unsupervised anomaly detection methods experience significant performance degradation when scaled from 30 to 160 categories. Crucially, we demonstrate that vision-language models exhibit remarkable robustness to category scale-up, with minimal performance variation across different category counts, significantly enhancing generalization capabilities in diverse industrial contexts. The unprecedented scale and complexity of Real-IAD Variety position it as an essential resource for training and evaluating next-generation foundation models for anomaly detection. By providing this comprehensive benchmark with rigorous evaluation protocols across multi-class unsupervised, multi-view, and zero-/few-shot settings, we aim to accelerate research beyond domain-specific constraints, enabling the development of scalable, general-purpose anomaly detection systems. Real-IAD Variety will be made publicly available to facilitate innovation in this critical field.
Authors: Kailun Su, Ziqi He, Xi Wang, Yang Zhou
Abstract: This paper proposes a method for precise learning and synthesizing multi-instance semantics from a single image. The difficulty of this problem lies in the limited training data, and it becomes even more challenging when the instances to be learned have similar semantics or appearance. To address this, we propose a penalty-based attention optimization to disentangle similar semantics during the learning stage. Then, in the synthesis, we introduce and optimize box control in attention layers to further mitigate semantic leakage while precisely controlling the output layout. Experimental results demonstrate that our method achieves disentangled and high-quality semantic learning and synthesis, strikingly balancing editability and instance consistency. Our method remains robust when dealing with semantically or visually similar instances or rare-seen objects. The code is publicly available at https://github.com/Kareneveve/MIFO
Authors: Chun-Tin Wu, Jun-Cheng Chen
Abstract: Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge, we propose 4D Neural Voxel Splatting (4D-NVS), which combines voxel-based representations with neural Gaussian splatting for efficient dynamic scene modeling. Instead of generating separate Gaussian sets per timestamp, our method employs a compact set of neural voxels with learned deformation fields to model temporal dynamics. The design greatly reduces memory consumption and accelerates training while preserving high image quality. We further introduce a novel view refinement stage that selectively improves challenging viewpoints through targeted optimization, maintaining global efficiency while enhancing rendering quality for difficult viewing angles. Experiments demonstrate that our method outperforms state-of-the-art approaches with significant memory reduction and faster training, enabling real-time rendering with superior visual fidelity.
Authors: Wei Feng, Zongyuan Ge
Abstract: Generalized Category Discovery (GCD) aims to leverage labeled samples from known categories to cluster unlabeled data that may include both known and unknown categories. While existing methods have achieved impressive results under standard conditions, their performance often deteriorates in the presence of distribution shifts. In this paper, we explore a more realistic task: Domain-Shifted Generalized Category Discovery (DS\_GCD), where the unlabeled data includes not only unknown categories but also samples from unknown domains. To tackle this challenge, we propose a \textbf{\underline{F}}requency-guided Gene\textbf{\underline{r}}alized Cat\textbf{\underline{e}}gory Discov\textbf{\underline{e}}ry framework (FREE) that enhances the model's ability to discover categories under distributional shift by leveraging frequency-domain information. Specifically, we first propose a frequency-based domain separation strategy that partitions samples into known and unknown domains by measuring their amplitude differences. We then propose two types of frequency-domain perturbation strategies: a cross-domain strategy, which adapts to new distributions by exchanging amplitude components across domains, and an intra-domain strategy, which enhances robustness to intra-domain variations within the unknown domain. Furthermore, we extend the self-supervised contrastive objective and semantic clustering loss to better guide the training process. Finally, we introduce a clustering-difficulty-aware resampling technique to adaptively focus on harder-to-cluster categories, further enhancing model performance. Extensive experiments demonstrate that our method effectively mitigates the impact of distributional shifts across various benchmark datasets and achieves superior performance in discovering both known and unknown categories.
Authors: Yousuf Ahmed Siddiqui, Sufiyaan Usmani, Umer Tariq, Jawwad Ahmed Shamsi, Muhammad Burhan Khan
Abstract: Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which seriously limits their capability to generalize to new, real-life situations. Our work addresses the context-aware zero-shot anomaly detection challenge, in which systems need to learn adaptively to detect new events by correlating temporal and appearance features with textual traces of memory in real time. Our approach defines a memory-augmented pipeline, correlating temporal signals with visual embeddings using cross-attention, and real-time zero-shot anomaly classification by contextual similarity scoring. We achieve 90.4\% AUC on UCF-Crime and 83.67\% AP on XD-Violence, a new state-of-the-art among zero-shot models. Our model achieves real-time inference with high precision and explainability for deployment. We show that, by fusing cross-attention temporal fusion and contextual memory, we achieve high fidelity anomaly detection, a step towards the applicability of zero-shot models in real-world surveillance and infrastructure monitoring.
Authors: Yating Yu, Congqi Cao, Zhaoying Wang, Weihua Meng, Jie Li, Yuxin Li, Zihao Wei, Zhongpei Shen, Jiajun Zhang
Abstract: How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or comprehending anomalous events with interpretable descriptions. However, they exhibit only a superficial comprehension of real-world anomalies, with limited breadth in complex principles and subtle context that distinguish the anomalies from normalities, e.g., climbing cliffs with safety gear vs. without it. To this end, we introduce CueBench, the first of its kind Benchmark, devoted to Context-aware video anomalies within a Unified Evaluation framework. We comprehensively establish an event-centric hierarchical taxonomy that anchors two core event types: 14 conditional and 18 absolute anomaly events, defined by their refined semantics from diverse contexts across 174 scenes and 198 attributes. Based on this, we propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation. This also serves as a rigorous and fair probing evaluation suite for generative-discriminative as well as generalized-specialized vision-language models (VLMs). To address the challenges underlying CueBench, we further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards in a unified generative manner. Extensive results on CueBench reveal that, existing VLMs are still far from satisfactory real-world anomaly understanding, while our Cue-R1 surpasses these state-of-the-art approaches by over 24% on average.
Authors: Oluwatosin Alabi, Meng Wei, Charlie Budd, Tom Vercauteren, Miaojing Shi
Abstract: Understanding surgical instrument-tissue interactions requires not only identifying which instrument performs which action on which anatomical target, but also grounding these interactions spatially within the surgical scene. Existing surgical action triplet recognition methods are limited to learning from frame-level classification, failing to reliably link actions to specific instrument instances.Previous attempts at spatial grounding have primarily relied on class activation maps, which lack the precision and robustness required for detailed instrument-tissue interaction analysis.To address this gap, we propose grounding surgical action triplets with instrument instance segmentation, or triplet segmentation for short, a new unified task which produces spatially grounded
Authors: Lassi Ruoppa, Tarmo Hietala, Verneri Sepp\"anen, Josef Taher, Teemu Hakala, Xiaowei Yu, Antero Kukko, Harri Kaartinen, Juha Hyypp\"a
Abstract: Individual tree segmentation (ITS) from LiDAR point clouds is fundamental for applications such as forest inventory, carbon monitoring and biodiversity assessment. Traditionally, ITS has been achieved with unsupervised geometry-based algorithms, while more recent advances have shifted toward supervised deep learning (DL). In the past, progress in method development was hindered by the lack of large-scale benchmark datasets, and the availability of novel data formats, particularly multispectral (MS) LiDAR, remains limited to this day, despite evidence that MS reflectance can improve the accuracy of ITS. This study introduces FGI-EMIT, the first large-scale MS airborne laser scanning benchmark dataset for ITS. Captured at wavelengths 532, 905, and 1,550 nm, the dataset consists of 1,561 manually annotated trees, with a particular focus on small understory trees. Using FGI-EMIT, we comprehensively benchmarked four conventional unsupervised algorithms and four supervised DL approaches. Hyperparameters of unsupervised methods were optimized using a Bayesian approach, while DL models were trained from scratch. Among the unsupervised methods, Treeiso achieved the highest test set F1-score of 52.7%. The DL approaches performed significantly better overall, with the best model, ForestFormer3D, attaining an F1-score of 73.3%. The most significant difference was observed in understory trees, where ForestFormer3D exceeded Treeiso by 25.9 percentage points. An ablation study demonstrated that current DL-based approaches generally fail to leverage MS reflectance information when it is provided as additional input features, although single channel reflectance can improve accuracy marginally, especially for understory trees. A performance analysis across point densities further showed that DL methods consistently remain superior to unsupervised algorithms, even at densities as low as 10 points/m$^2$.
Authors: Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez, Paul Wright, Mehmet Yigitsoy, Sebastien Ourselin, Jorge Cardoso
Abstract: Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representation of MRI contrast would enable a wide range of downstream utilities, from automatic sequence recognition to harmonization and quality control, without relying on manual annotations. To this end, we introduce MR-CLIP, a metadata-guided framework that learns MRI contrast representations by aligning volumetric images with their DICOM acquisition parameters. The resulting embeddings shows distinct clusters of MRI sequences and outperform supervised 3D baselines under data scarcity in few-shot sequence classification. Moreover, MR-CLIP enables unsupervised data quality control by identifying corrupted or inconsistent metadata through image-metadata embedding distances. By transforming routinely available acquisition metadata into a supervisory signal, MR-CLIP provides a scalable foundation for label-efficient MRI analysis across diverse clinical datasets.
Authors: Hailing Wang, jianglin Lu, Yitian Zhang, Yun Fu
Abstract: Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered significant attention as it eliminates the need for ground truth and model retraining. However, existing PTQ methods for SR often fail to achieve satisfactory performance as they overlook the impact of outliers in activation. Our empirical analysis reveals that these prevalent activation outliers are strongly correlated with image color information, and directly removing them leads to significant performance degradation. Motivated by this, we propose a dual-region quantization strategy that partitions activations into an outlier region and a dense region, applying uniform quantization to each region independently to better balance bit-width allocation. Furthermore, we observe that different network layers exhibit varying sensitivities to quantization, leading to different levels of performance degradation. To address this, we introduce sensitivity-aware finetuning that encourages the model to focus more on highly sensitive layers, further enhancing quantization performance. Extensive experiments demonstrate that our method outperforms existing PTQ approaches across various SR networks and datasets, while achieving performance comparable to QAT methods in most scenarios with at least a 75 speedup.
Authors: Alex Inch, Passawis Chaiyapattanaporn, Yuchen Zhu, Yuan Lu, Ting-Wen Ko, Davide Paglieri
Abstract: Text-to-image diffusion models, while proficient at generating high-fidelity im- ages, often suffer from limited output diversity, hindering their application in exploratory and ideation tasks. Existing prompt optimization techniques typically target aesthetic fitness or are ill-suited to the creative visual domain. To address this shortcoming, we introduce WANDER, a novelty search-based approach to generating diverse sets of images from a single input prompt. WANDER operates directly on natural language prompts, employing a Large Language Model (LLM) for semantic evolution of diverse sets of images, and using CLIP embeddings to quantify novelty. We additionally apply emitters to guide the search into distinct regions of the prompt space, and demonstrate that they boost the diversity of the generated images. Empirical evaluations using FLUX-DEV for generation and GPT-4o-mini for mutation demonstrate that WANDER significantly outperforms existing evolutionary prompt optimization baselines in diversity metrics. Ablation studies confirm the efficacy of emitters.
Authors: Taifour Yousra, Beghdadi Azeddine, Marie Luong, Zuheng Ming
Abstract: Low-dose CT (LDCT) imaging is widely used to reduce radiation exposure to mitigate high exposure side effects, but often suffers from noise and artifacts that affect diagnostic accuracy. To tackle this issue, deep learning models have been developed to enhance LDCT images. Various loss functions have been employed, including classical approaches such as Mean Square Error and adversarial losses, as well as customized loss functions(LFs) designed for specific architectures. Although these models achieve remarkable performance in terms of PSNR and SSIM, these metrics are limited in their ability to reflect perceptual quality, especially for medical images. In this paper, we focus on one of the most critical elements of DL-based architectures, namely the loss function. We conduct an objective analysis of the relevance of different loss functions for LDCT image quality enhancement and their consistency with image quality metrics. Our findings reveal inconsistencies between LFs and quality metrics, and highlight the need of consideration of image quality metrics when developing a new loss function for image quality enhancement.
Authors: Hugo Massaroli, Hernan Chaves, Pilar Anania, Mauricio Farez, Emmanuel Iarussi, Viviana Siless
Abstract: Deep learning models have shown strong performance in diagnosing Alzheimer's disease (AD) using neuroimaging data, particularly 18F-FDG PET scans, with training datasets largely composed of North American cohorts such as those in the Alzheimer's Disease Neuroimaging Initiative (ADNI). However, their generalization to underrepresented populations remains underexplored. In this study, we benchmark convolutional and Transformer-based models on the ADNI dataset and assess their generalization performance on a novel Latin American clinical cohort from the FLENI Institute in Buenos Aires, Argentina. We show that while all models achieve high AUCs on ADNI (up to .96, .97), their performance drops substantially on FLENI (down to .82, .80, respectively), revealing a significant domain shift. The tested architectures demonstrated similar performance, calling into question the supposed advantages of transformers for this specific task. Through ablation studies, we identify per-image normalization and a correct sampling selection as key factors for generalization. Occlusion sensitivity analysis further reveals that models trained on ADNI, generally attend to canonical hypometabolic regions for the AD class, but focus becomes unclear for the other classes and for FLENI scans. These findings highlight the need for population-aware validation of diagnostic AI models and motivate future work on domain adaptation and cohort diversification.
Authors: Dmitrii Khizbullin, Maksim Konoplia
Abstract: Place recognition is a crucial task in autonomous driving, allowing vehicles to determine their position using sensor data. While most existing methods rely on contrastive learning, we explore an alternative approach by framing place recognition as a multi-class classification problem. Our method assigns discrete location labels to LiDAR scans and trains an encoder-decoder model to classify each scan's position directly. We evaluate this approach on the NuScenes dataset and show that it achieves competitive performance compared to contrastive learning-based methods while offering advantages in training efficiency and stability.
Authors: Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie, Ioannis Konstas
Abstract: Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.
Authors: Anis Suttan Shahrir, Zakiah Ayop, Syarulnaziah Anawar, Norulzahrah Mohd Zainudin
Abstract: Durian plantation suffers from animal intrusions that cause crop damage and financial loss. The traditional farming practices prove ineffective due to the unavailability of monitoring without human intervention. The fast growth of machine learning and Internet of Things (IoT) technology has led to new ways to detect animals. However, current systems are limited by dependence on single object detection algorithms, less accessible notification platforms, and limited deterrent mechanisms. This research suggests an IoT-enabled animal detection system for durian crops. The system integrates YOLOv5 and SSD object detection algorithms to improve detection accuracy. The system provides real-time monitoring, with detected intrusions automatically reported to farmers via Telegram notifications for rapid response. An automated sound mechanism (e.g., tiger roar) is triggered once the animal is detected. The YOLO+SSD model achieved accuracy rates of elephant, boar, and monkey at 90%, 85% and 70%, respectively. The system shows the highest accuracy in daytime and decreases at night, regardless of whether the image is still or a video. Overall, this study contributes a comprehensive and practical framework that combines detection, notification, and deterrence, paving the way for future innovations in automated farming solutions.
Authors: Juan Wang, Yasutomo Kawanishi, Tomo Miyazaki, Zhijie Wang, Shinichiro Omachi
Abstract: 3D instance segmentation is an important task for real-world applications. To avoid costly manual annotations, existing methods have explored generating pseudo labels by transferring 2D masks from foundation models to 3D. However, this approach is often suboptimal since the video frames are processed independently. This causes inconsistent segmentation granularity and conflicting 3D pseudo labels, which degrades the accuracy of final segmentation. To address this, we introduce a Granularity-Consistent automatic 2D Mask Tracking approach that maintains temporal correspondences across frames, eliminating conflicting pseudo labels. Combined with a three-stage curriculum learning framework, our approach progressively trains from fragmented single-view data to unified multi-view annotations, ultimately globally coherent full-scene supervision. This structured learning pipeline enables the model to progressively expose to pseudo-labels of increasing consistency. Thus, we can robustly distill a consistent 3D representation from initially fragmented and contradictory 2D priors. Experimental results demonstrated that our method effectively generated consistent and accurate 3D segmentations. Furthermore, the proposed method achieved state-of-the-art results on standard benchmarks and open-vocabulary ability.
Authors: Viswa Chaitanya Marella, Suhasnadh Reddy Veluru, Sai Teja Erukude
Abstract: Federated Learning (FL) allows multiple institutions to cooperatively train machine learning models while retaining sensitive data at the source, which has great utility in privacy-sensitive environments. However, FL systems remain vulnerable to membership-inference attacks and data heterogeneity. This paper presents FedOnco-Bench, a reproducible benchmark for privacy-aware FL using synthetic oncologic CT scans with tumor annotations. It evaluates segmentation performance and privacy leakage across FL methods: FedAvg, FedProx, FedBN, and FedAvg with DP-SGD. Results show a distinct trade-off between privacy and utility: FedAvg is high performance (Dice around 0.85) with more privacy leakage (attack AUC about 0.72), while DP-SGD provides a higher level of privacy (AUC around 0.25) at the cost of accuracy (Dice about 0.79). FedProx and FedBN offer balanced performance under heterogeneous data, especially with non-identical distributed client data. FedOnco-Bench serves as a standardized, open-source platform for benchmarking and developing privacy-preserving FL methods for medical image segmentation.
Authors: Zhihui Chen, Mengling Feng
Abstract: Recent advances in multimodal large language models have enabled remarkable medical image editing capabilities. However, the research community's progress remains constrained by the absence of large-scale, high-quality, and openly accessible datasets built specifically for medical image editing with strict anatomical and clinical constraints. We introduce Med-Banana-50K, a comprehensive 50K-image dataset for instruction-based medical image editing spanning three modalities (chest X-ray, brain MRI, fundus photography) and 23 disease types. Our dataset is constructed by leveraging Gemini-2.5-Flash-Image to generate bidirectional edits (lesion addition and removal) from real medical images. What distinguishes Med-Banana-50K from general-domain editing datasets is our systematic approach to medical quality control: we employ LLM-as-Judge with a medically grounded rubric (instruction compliance, structural plausibility, realism, and fidelity preservation) and history-aware iterative refinement up to five rounds. Beyond single-turn editing, Med-Banana-50K includes 37K failed attempts with full conversation logs for preference learning and alignment research. By providing this large-scale, medically validated, and fully documented resource, Med-Banana-50K establishes a foundation for training and evaluating the next generation of medical image editing models.Our dataset and code are publicly available at [https://github.com/richardChenzhihui/med-banana-50k].
Authors: Shijie Zhou, Viet Dac Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang
Abstract: Graphical user interface (GUI) grounding is a key function of computer-use agents, which maps natural-language instructions to actionable screen regions. Existing approaches based on Multimodal Large Language Models (MLLMs) typically formulate it as a text-based coordinate generation task, yet directly generating precise coordinates from visual inputs remains challenging and computationally intensive. An intuitive way to implement GUI grounding is to first select visual patches relevant to the instructions and then determine the precise click location within those patches. Based on the observations that general MLLMs have some native grounding capability, nested within their attentions, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 85k screenshots, demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 58.6% on ScreenSpot-Pro and 62.2% on OSWorld-G. Project page: https://github.com/sjz5202/GUI-AIMA
Authors: Yue Gou, Fanghui Song, Yuming Xing, Shengzhu Shi, Zhichang Guo, Boying Wu
Abstract: Pancreas segmentation in medical image processing is a persistent challenge due to its small size, low contrast against adjacent tissues, and significant topological variations. Traditional level set methods drive boundary evolution using gradient flows, often ignoring pointwise topological effects. Conversely, deep learning-based segmentation networks extract rich semantic features but frequently sacrifice structural details. To bridge this gap, we propose a novel model named TA-LSDiff, which combined topology-aware diffusion probabilistic model and level set energy, achieving segmentation without explicit geometric evolution. This energy function guides implicit curve evolution by integrating the input image and deep features through four complementary terms. To further enhance boundary precision, we introduce a pixel-adaptive refinement module that locally modulates the energy function using affinity weighting from neighboring evidence. Ablation studies systematically quantify the contribution of each proposed component. Evaluations on four public pancreas datasets demonstrate that TA-LSDiff achieves state-of-the-art accuracy, outperforming existing methods. These results establish TA-LSDiff as a practical and accurate solution for pancreas segmentation.
Authors: Ruoxiang Huang, Xindian Ma, Rundong Kong, Zhen Yuan, Peng Zhang
Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential structure of textual information and the spatial structure of visual information. However, current VLMs commonly adopt modality-unified 1D or 2D positional indexing strategies, which treat textual and visual tokens uniformly without accounting for their distinct structural properties and sequential continuity for text and spatial coherence for vision. To address this limitation, we propose OMEGA, a novel position encoding framework that employs Modality-Specific Position Encoding (MSPE) to assign positional indices while preserving the inherent structures of each modality across separate coordinate dimensions. Additionally, to align the information density of multimodal data in the positional index space, OMEGA introduces Global Adaptive Encoding Step Scaling (GAESS), which adaptively adjusts the position encoding step size of visual tokens based on the embedding entropy of both modalities. Experimental results demonstrate that OMEGA consistently enhances VLM performance across diverse architectures and VQA benchmarks. On visual-intensive tasks, OMEGA achieves up to 3.43% improvement over baseline position encoding strategies on Qwen2.5-VL-3B, with consistent gains observed across larger models including Qwen2.5-VL-7B and LLaVA-v1.5-7B.
Authors: Xin Liu, Aoyang Zhou, Aoyang Zhou
Abstract: Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prior efforts focus on improving the adversarial transferability of multimodal adversarial examples through cross-modal interactions, these approaches suffer from overfitting issues, due to a lack of input diversity by relying excessively on information from adversarial examples in one modality when crafting attacks in another. To address this issue, we draw inspiration from strategies in some adversarial training methods and propose a novel attack called Local Shuffle and Sample-based Attack (LSSA). LSSA randomly shuffles one of the local image blocks, thus expanding the original image-text pairs, generating adversarial images, and sampling around them. Then, it utilizes both the original and sampled images to generate the adversarial texts. Extensive experiments on multiple models and datasets demonstrate that LSSA significantly enhances the transferability of multimodal adversarial examples across diverse VLP models and downstream tasks. Moreover, LSSA outperforms other advanced attacks on Large Vision-Language Models.
Authors: Yifan Pu, Jixuan Ying, Qixiu Li, Tianzhu Ye, Dongchen Han, Xiaochen Wang, Ziyi Wang, Xinyu Shao, Gao Huang, Xiu Li
Abstract: Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N N C) to O(N n C) with n << N. VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.
Authors: Xin Liu, Yichen Yang, Kun He, John E. Hopcroft
Abstract: Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks. However, existing adversarial training methods show that the model robustness has apparent oscillations and overfitting issues in the training process, degrading the defense efficacy. To address these issues, we propose a novel framework called Parameter Interpolation Adversarial Training (PIAT). PIAT tunes the model parameters between each epoch by interpolating the parameters of the previous and current epochs. It makes the decision boundary of model change more moderate and alleviates the overfitting issue, helping the model converge better and achieving higher model robustness. In addition, we suggest using the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the relative magnitude of logits between clean and adversarial examples rather than the absolute magnitude. Extensive experiments conducted on several benchmark datasets demonstrate that our framework could prominently improve the robustness of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).
Authors: Zhihao Peng, Cheng Wang, Shengyuan Liu, Zhiying Liang, Yixuan Yuan
Abstract: Brain imaging analysis is vital for diagnosing and treating brain disorders, and multimodal large language models (MLLMs) are increasingly assisting in that analysis. However, current brain-oriented visual question-answering (VQA) benchmarks either cover a few imaging modalities or are limited to coarse-grained pathological descriptions, hindering a comprehensive assessment of MLLMs throughout the full clinical continuum. To address these, we introduce OmniBrainBench, the first comprehensive multimodal VQA benchmark specifically designed to assess the multimodal comprehension capabilities of MLLMs in brain imaging analysis.OmniBrainBench consists of 15 distinct brain imaging modalities collected from 30 verified medical sources, yielding 9,527 validated VQA pairs and 31,706 images. It simulates clinical workflows and encompasses 15 multi-stage clinical tasks rigorously validated by a professional radiologist. Evaluation of 24 state-of-the-art models, including open-source, medical, and proprietary MLLMs, highlights the substantial challenges posed by OmniBrainBench. Our experiments reveal: (1) proprietary MLLMs (e.g., GPT-5) beat open-source and medical models but lag physicians; (2) medical MLLMs vary widely in performance; (3) open-source MLLMs trail overall but excel in specific tasks; (4) MLLMs underperform sharply in complex preoperative tasks, revealing a visual-to-clinical reasoning gap. OmniBrainBench sets a new standard for evaluating and advancing MLLMs in brain imaging analysis, highlighting gaps compared to expert clinical reasoning. We release it at benchmark \& code.
Authors: Yu Liu, Zhijie Liu, Zedong Yang, You-Fu Li, He Kong
Abstract: Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete observation under occlusion scenarios. To tackle this challenge, we propose an Occlusion-Aware Diffusion Model (ODM) that reconstructs occluded motion patterns and leverages them to guide future intention prediction. During the denoising stage, we introduce an occlusion-aware diffusion transformer architecture to estimate noise features associated with occluded patterns, thereby enhancing the model's ability to capture contextual relationships in occluded semantic scenarios. Furthermore, an occlusion mask-guided reverse process is introduced to effectively utilize observation information, reducing the accumulation of prediction errors and enhancing the accuracy of reconstructed motion features. The performance of the proposed method under various occlusion scenarios is comprehensively evaluated and compared with existing methods on popular benchmarks, namely PIE and JAAD. Extensive experimental results demonstrate that the proposed method achieves more robust performance than existing methods in the literature.
Authors: Jaehyun Park, Konyul Park, Daehun Kim, Junseo Park, Jun Won Choi
Abstract: In autonomous driving, transparency in the decision-making of perception models is critical, as even a single misperception can be catastrophic. Yet with multi-sensor inputs, it is difficult to determine how each modality contributes to a prediction because sensor information becomes entangled within the fusion network. We introduce Layer-Wise Modality Decomposition (LMD), a post-hoc, model-agnostic interpretability method that disentangles modality-specific information across all layers of a pretrained fusion model. To our knowledge, LMD is the first approach to attribute the predictions of a perception model to individual input modalities in a sensor-fusion system for autonomous driving. We evaluate LMD on pretrained fusion models under camera-radar, camera-LiDAR, and camera-radar-LiDAR settings for autonomous driving. Its effectiveness is validated using structured perturbation-based metrics and modality-wise visual decompositions, demonstrating practical applicability to interpreting high-capacity multimodal architectures. Code is available at https://github.com/detxter-jvb/Layer-Wise-Modality-Decomposition.
URLs: https://github.com/detxter-jvb/Layer-Wise-Modality-Decomposition.
Authors: Heng Zheng, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Hao Zhang, Wenjun Huang, Jin Huang
Abstract: Visual geo-localization requires extensive geographic knowledge and sophisticated reasoning to determine image locations without GPS metadata. Traditional retrieval methods are constrained by database coverage and quality. Recent Large Vision-Language Models (LVLMs) enable direct location reasoning from image content, yet individual models struggle with diverse geographic regions and complex scenes. Existing multi-agent systems improve performance through model collaboration but treat all agent interactions uniformly. They lack mechanisms to handle conflicting predictions effectively. We propose \textbf{GraphGeo}, a multi-agent debate framework using heterogeneous graph neural networks for visual geo-localization. Our approach models diverse debate relationships through typed edges, distinguishing supportive collaboration, competitive argumentation, and knowledge transfer. We introduce a dual-level debate mechanism combining node-level refinement and edge-level argumentation modeling. A cross-level topology refinement strategy enables co-evolution between graph structure and agent representations. Experiments on multiple benchmarks demonstrate GraphGeo significantly outperforms state-of-the-art methods. Our framework transforms cognitive conflicts between agents into enhanced geo-localization accuracy through structured debate.
Authors: Yan Shu, Chi Liu, Robin Chen, Derek Li, Bryan Dai
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable effectiveness in various general-domain scenarios, such as visual question answering and image captioning. Recently, researchers have increasingly focused on empowering MLLMs with medical conversational abilities, which hold significant promise for clinical applications. However, medical data presents unique challenges due to its heterogeneous nature -- encompassing diverse modalities including 2D images, 3D volumetric scans, and temporal video sequences. The substantial domain gap and data format inconsistencies across these modalities have hindered the development of unified medical MLLMs. To address these challenges, we propose Fleming-VL, a unified end-to-end framework for comprehensive medical visual understanding across heterogeneous modalities. Fleming-VL tackles this problem from a data-centric perspective through three key strategies: (1) scaling up pretraining by integrating long-context data from both natural and medical-specific domains; (2) complementing fine-tuning with rare medical data, including holistic video analysis and underrepresented 2D modalities such as ultrasound and dermoscopy images; (3) extending existing evaluation frameworks to incorporate 3D volumetric and video understanding benchmarks. Through supervised fine-tuning (SFT) and group relative policy optimization (GRPO), we develop Fleming-VL in multiple model scales. Extensive experiments demonstrate that Fleming-VL achieves state-of-the-art performance across multiple benchmarks, including medical VQA, video QA, and 3D medical image understanding. We publicly release Fleming-VL to promote transparent, reproducible, and auditable progress in medical AI.
Authors: Hanwen Su, Ge Song, Jiyan Wang, Yuanbo Zhu
Abstract: The problem of zero-shot sketch-based image retrieval (ZS-SBIR) has achieved increasing attention due to its wide applications, e.g. e-commerce. Despite progress made in this field, previous works suffer from using imbalanced samples of modalities and inconsistent low-quality information during training, resulting in sub-optimal performance. Therefore, in this paper, we introduce an approach called Dynamic Multi-level Weighted Alignment Network for ZS-SBIR. It consists of three components: (i) a Uni-modal Feature Extraction Module that includes a CLIP text encoder and a ViT for extracting textual and visual tokens, (ii) a Cross-modal Multi-level Weighting Module that produces an alignment weight list by the local and global aggregation blocks to measure the aligning quality of sketch and image samples, (iii) a Weighted Quadruplet Loss Module aiming to improve the balance of domains in the triplet loss. Experiments on three benchmark datasets, i.e., Sketchy, TU-Berlin, and QuickDraw, show our method delivers superior performances over the state-of-the-art ZS-SBIR methods.
Authors: Liuzhuozheng Li, Yue Gong, Shanyuan Liu, Bo Cheng, Yuhang Ma, Liebucha Wu, Dengyang Jiang, Zanyi Wang, Dawei Leng, Yuhui Yin
Abstract: We propose EVTAR, an End-to-End Virtual Try-on model with Additional Reference, that directly fits the target garment onto the person image while incorporating reference images to enhance try-on accuracy. Most existing virtual try-on approaches rely on complex inputs such as agnostic person images, human pose, densepose, or body keypoints, making them labor-intensive and impractical for real-world applications. In contrast, EVTAR adopts a two-stage training strategy, enabling simple inference with only the source image and the target garment inputs. Our model generates try-on results without masks, densepose, or segmentation maps. Moreover, EVTAR leverages additional reference images of different individuals wearing the same clothes to preserve garment texture and fine-grained details better. This mechanism is analogous to how humans consider reference models when choosing outfits, thereby simulating a more realistic and high-quality dressing effect. We enrich the training data with supplementary references and unpaired person images to support these capabilities. We evaluate EVTAR on two widely used benchmarks and diverse tasks, and the results consistently validate the effectiveness of our approach.
Authors: Dongheng Lin, Mengxue Qu, Kunyang Han, Jianbo Jiao, Xiaojie Jin, Yunchao Wei
Abstract: Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific. We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation. Our approach is built upon a chained test-time reasoning process that sequentially connects these tasks, enabling holistic zero-shot anomaly analysis without any additional training. Specifically, our approach leverages intra-task reasoning to refine temporal detections and inter-task chaining for spatial and semantic understanding, yielding improved interpretability and generalization in a fully zero-shot manner. Without any additional data or gradients, our method achieves state-of-the-art zero-shot performance across multiple video anomaly detection, localization, and explanation benchmarks. The results demonstrate that careful prompt design with task-wise chaining can unlock the reasoning power of foundation models, enabling practical, interpretable video anomaly analysis in a fully zero-shot manner. Project Page: https://rathgrith.github.io/Unified_Frame_VAA/.
Authors: Suzhong Fu, Rui Sun, Xuan Ding, Jingqi Dong, Yiming Yang, Yao Zhu, Min Chang Jordan Ren, Delin Deng, Angelica Aviles-Rivero, Shuguang Cui, Zhen Li
Abstract: Accurate vessel segmentation is critical for clinical applications such as disease diagnosis and surgical planning, yet remains challenging due to thin, branching structures and low texture contrast. While foundation models like the Segment Anything Model (SAM) have shown promise in generic segmentation, they perform sub-optimally on vascular structures. In this work, we present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation. VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, including skeletons, bifurcation points, and segment midpoints, via hierarchical cross-attention, and (3) a lightweight mask decoder to reduce jagged artifacts. We also introduce an automated pipeline to generate structured multi-prompt annotations, and curate a diverse benchmark dataset spanning 8 datasets across 5 imaging modalities. Experimental results demonstrate that VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU, and achieves competitive performance compared to fully fine-tuned methods, with significantly fewer parameters. VesSAM also generalizes well to out-of-distribution (OoD) settings, outperforming all baselines in average OoD Dice and IoU.
Authors: Chang Nie, Tianchen Deng, Zhe Liu, Hesheng Wang
Abstract: Data denoising is a persistent challenge across scientific and engineering domains. Real-world data is frequently corrupted by complex, non-linear noise, rendering traditional rule-based denoising methods inadequate. To overcome these obstacles, we propose a novel self-supervised multimodal iterative denoising (MID) framework. MID models the collected noisy data as a state within a continuous process of non-linear noise accumulation. By iteratively introducing further noise, MID learns two neural networks: one to estimate the current noise step and another to predict and subtract the corresponding noise increment. For complex non-linear contamination, MID employs a first-order Taylor expansion to locally linearize the noise process, enabling effective iterative removal. Crucially, MID does not require paired clean-noisy datasets, as it learns noise characteristics directly from the noisy inputs. Experiments across four classic computer vision tasks demonstrate MID's robustness, adaptability, and consistent state-of-the-art performance. Moreover, MID exhibits strong performance and adaptability in tasks within the biomedical and bioinformatics domains.
Authors: Hassan Ugail, Ismail Lujain Jaleel
Abstract: Art authentication of Francisco Goya's works presents complex computational challenges due to his heterogeneous stylistic evolution and extensive historical patterns of forgery. We introduce a novel multimodal machine learning framework that applies identical feature extraction techniques to both visual and X-ray radiographic images of Goya paintings. The unified feature extraction pipeline incorporates Grey-Level Co-occurrence Matrix descriptors, Local Binary Patterns, entropy measures, energy calculations, and colour distribution analysis applied consistently across both imaging modalities. The extracted features from both visual and X-ray images are processed through an optimised One-Class Support Vector Machine with hyperparameter tuning. Using a dataset of 24 authenticated Goya paintings with corresponding X-ray images, split into an 80/20 train-test configuration with 10-fold cross-validation, the framework achieves 97.8% classification accuracy with a 0.022 false positive rate. Case study analysis of ``Un Gigante'' demonstrates the practical efficacy of our pipeline, achieving 92.3% authentication confidence through unified multimodal feature analysis. Our results indicate substantial performance improvement over single-modal approaches, establishing the effectiveness of applying identical computational methods to both visual and radiographic imagery in art authentication applications.
Authors: Mohammad Amanour Rahman
Abstract: B-mode ultrasound for breast cancer diagnosis faces challenges: speckle, operator dependency, and indistinct boundaries. Existing deep learning suffers from single-task learning, architectural constraints (CNNs lack global context, Transformers local features), and black-box decision-making. These gaps hinder clinical adoption. We propose HyFormer-Net, a hybrid CNN-Transformer for simultaneous segmentation and classification with intrinsic interpretability. Its dual-branch encoder integrates EfficientNet-B3 and Swin Transformer via multi-scale hierarchical fusion blocks. An attention-gated decoder provides precision and explainability. We introduce dual-pipeline interpretability: (1) intrinsic attention validation with quantitative IoU verification (mean: 0.86), and (2) Grad-CAM for classification reasoning. On the BUSI dataset, HyFormer-Net achieves Dice Score 0.761 +/- 0.072 and accuracy 93.2%, outperforming U-Net, Attention U-Net, and TransUNet. Malignant Recall of 92.1 +/- 2.2% ensures minimal false negatives. Ensemble modeling yields exceptional Dice 90.2%, accuracy 99.5%, and perfect 100% Malignant Recall, eliminating false negatives. Ablation studies confirm multi-scale fusion contributes +16.8% Dice and attention gates add +5.9%. Crucially, we conduct the first cross-dataset generalization study for hybrid CNN-Transformers in breast ultrasound. Zero-shot transfer fails (Dice: 0.058), confirming domain shift. However, progressive fine-tuning with only 10% target-domain data (68 images) recovers 92.5% performance. With 50% data, our model achieves 77.3% Dice, exceeding source-domain performance (76.1%) and demonstrating true generalization.
Authors: JunXi Yuan
Abstract: We present FastBoost, a parameter-efficient neural architecture that achieves state-of-the-art performance on CIFAR benchmarks through a novel Dynamically Scaled Progressive Attention (DSPA) mechanism. Our design establishes new efficiency frontiers with: CIFAR-10: 95.57% accuracy (0.85M parameters) and 93.80% (0.37M parameters) CIFAR-100: 81.37% accuracy (0.92M parameters) and 74.85% (0.44M parameters) The breakthrough stems from three fundamental innovations in DSPA: (1) Adaptive Fusion: Learnt channel-spatial attention blending with dynamic weights. (2) Phase Scaling: Training-stage-aware intensity modulation (from 0.5 to 1.0). (3) Residual Adaptation: Self-optimized skip connections (gamma from 0.5 to 0.72). By integrating DSPA with enhanced MBConv blocks, FastBoost achieves a 2.1 times parameter reduction over MobileNetV3 while improving accuracy by +3.2 percentage points on CIFAR-10. The architecture features dual attention pathways with real-time weight adjustment, cascaded refinement layers (increasing gradient flow by 12.7%), and a hardware-friendly design (0.28G FLOPs). This co-optimization of dynamic attention and efficient convolution operations demonstrates unprecedented parameter-accuracy trade-offs, enabling deployment in resource-constrained edge devices without accuracy degradation.
Authors: Nikolay I. Kalmykov, Razan Dibo, Kaiyu Shen, Xu Zhonghan, Anh-Huy Phan, Yipeng Liu, Ivan Oseledets
Abstract: Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of classifiers. Existing adversarial attacks on NICs are often naive adaptations of pixel-space methods, overlooking the unique, structured nature of the compression pipeline. In this work, we propose a more advanced class of vulnerabilities by introducing T-MLA, the first targeted multiscale log--exponential attack framework. Our approach crafts adversarial perturbations in the wavelet domain by directly targeting the quality of the attacked and reconstructed images. This allows for a principled, offline attack where perturbations are strategically confined to specific wavelet subbands, maximizing distortion while ensuring perceptual stealth. Extensive evaluation across multiple state-of-the-art NIC architectures on standard image compression benchmarks reveals a large drop in reconstruction quality while the perturbations remain visually imperceptible. Our findings reveal a critical security flaw at the core of generative and content delivery pipelines.
Authors: Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Cyrus Shahabi
Abstract: Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses. Analogously, our model predicts geographic tokens hierarchically, first identifying a general region and then sequentially refining predictions to increasingly precise locations. Rather than relying on explicit semantic partitions, our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions. This procedure mirrors autoregressive text generation in large language models. Much like in language modeling, final performance depends not only on training but also on inference-time strategy. We investigate multiple top-down traversal methods for autoregressive sampling, incorporating techniques from test-time compute scaling used in language models. Specifically, we integrate beam search and multi-sample inference while exploring various selection strategies to determine the final output. This enables the model to manage uncertainty by exploring multiple plausible paths through the hierarchy. We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines: those that operate without a Multimodal Large Language Model (MLLM) and those that leverage one. In the MLLM-free setting, our model surpasses other comparable baselines on nearly all metrics, achieving state-of-the-art performance with accuracy gains of up to 13.9%. When augmented with an MLLM, our model outperforms all baselines, setting a new state-of-the-art across all metrics. The source code is available at https://github.com/NNargesNN/GeoToken.
Authors: Md. Abid Hasan Rafi, Mst. Fatematuj Johora, Pankaj Bhowmik
Abstract: The emergence of 5G and 6G networks has established network slicing as a significant part of future service-oriented architectures, demanding refined identification methods supported by robust datasets. The article presents SliceVision-F2I, a dataset of synthetic samples for studying feature visualization in network slicing for next-generation networking systems. The dataset transforms multivariate Key Performance Indicator (KPI) vectors into visual representations through four distinct encoding methods: physically inspired mappings, Perlin noise, neural wallpapering, and fractal branching. For each encoding method, 30,000 samples are generated, each comprising a raw KPI vector and a corresponding RGB image at low-resolution pixels. The dataset simulates realistic and noisy network conditions to reflect operational uncertainties and measurement imperfections. SliceVision-F2I is suitable for tasks involving visual learning, network state classification, anomaly detection, and benchmarking of image-based machine learning techniques applied to network data. The dataset is publicly available and can be reused in various research contexts, including multivariate time series analysis, synthetic data generation, and feature-to-image transformations.
Authors: Veronica Marsico, Antonio Quintero-Rincon, Hadj Batatia
Abstract: This study presents a novel method for diagnosing respiratory diseases using image data. It combines Epanechnikov's non-parametric kernel density estimation (EKDE) with a bimodal logistic regression classifier in a statistical-model-based learning scheme. EKDE's flexibility in modeling data distributions without assuming specific shapes and its adaptability to pixel intensity variations make it valuable for extracting key features from medical images. The method was tested on 13808 randomly selected chest X-rays from the COVID-19 Radiography Dataset, achieved an accuracy of 70.14%, a sensitivity of 59.26%, and a specificity of 74.18%, demonstrating moderate performance in detecting respiratory disease while showing room for improvement in sensitivity. While clinical expertise remains essential for further refining the model, this study highlights the potential of EKDE-based approaches to enhance diagnostic accuracy and reliability in medical imaging.
Authors: Alexander Thorley, Agis Chartsias, Jordan Strom, Jeremy Slivnick, Dipak Kotecha, Alberto Gomez, Jinming Duan
Abstract: Video transformers have recently demonstrated strong potential for echocardiogram (echo) analysis, leveraging self-supervised pre-training and flexible adaptation across diverse tasks. However, like other models operating on videos, they are prone to learning spurious correlations from non-diagnostic regions such as image backgrounds. To overcome this limitation, we propose the Video Anatomically Constrained Transformer (ViACT), a novel framework that integrates anatomical priors directly into the transformer architecture. ViACT represents a deforming anatomical structure as a point set and encodes both its spatial geometry and corresponding image patches into transformer tokens. During pre-training, ViACT follows a masked autoencoding strategy that masks and reconstructs only anatomical patches, enforcing that representation learning is focused on the anatomical region. The pre-trained model can then be fine-tuned for tasks localized to this region. In this work we focus on the myocardium, demonstrating the framework on echo analysis tasks such as left ventricular ejection fraction (EF) regression and cardiac amyloidosis (CA) detection. The anatomical constraint focuses transformer attention within the myocardium, yielding interpretable attention maps aligned with regions of known CA pathology. Moreover, ViACT generalizes to myocardium point tracking without requiring task-specific components such as correlation volumes used in specialized tracking networks.
Authors: Fabio Diniz Rossi
Abstract: Computer vision applications, especially those using augmented reality technology, are becoming quite popular in mobile devices. However, this type of application is known as presenting significant demands regarding resources. In order to enable its utilization in devices with more modest resources, edge computing can be used to offload certain high intensive tasks. Still, edge computing is usually composed of devices with limited capacity, which may impact in users quality of experience when using computer vision applications. This work proposes the use of embedded devices with graphics processing units (GPUs) to overcome such limitation. Experiments performed shown that GPUs can attain a performance gain when compared to using only CPUs, which guarantee a better experience to users using such kind of application.
Authors: Md Nahiduzzaman, Steven Korevaar, Alireza Bab-Hadiashar, Ruwan Tennakoon
Abstract: Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical contexts. Recent attempts to bypass annotation, such as zero-shot vision-language models or concept-generation frameworks, struggle to capture domain-specific medical features, leading to poor reliability. In this paper, we propose a novel Prior-guided Concept Predictor (PCP), a weakly supervised framework that enables concept answer prediction without explicit supervision or reliance on language models. PCP leverages class-level concept priors as weak supervision and incorporates a refinement mechanism with KL divergence and entropy regularization to align predictions with clinical reasoning. Experiments on PH2 (dermoscopy) and WBCatt (hematology) show that PCP improves concept-level F1-score by over 33% compared to zero-shot baselines, while delivering competitive classification performance on four medical datasets (PH2, WBCatt, HAM10000, and CXR4) relative to fully supervised concept bottleneck models (CBMs) and V-IP.
Authors: Yoshihiro Maruyama
Abstract: We propose CatEquiv, a category-equivariant neural network for Human Activity Recognition (HAR) from inertial sensors that systematically encodes temporal, amplitude, and structural symmetries. In particular, we introduce the categorical symmetry product where cyclic time shifts, positive gains and the sensor-hierarchy poset together capture the categorical symmetry structure of the data. CatEquiv achieves equivariance with respect to the categorical symmetry product. On UCI-HAR under out-of-distribution perturbations, CatEquiv attains markedly higher robustness compared with circularly padded CNNs and plain CNNs. These results demonstrate that enforcing categorical symmetries yields strong invariance and generalization without additional model capacity.
Authors: Ziyi Wang, Yuanmei Zhang, Dorna Esrafilzadeh, Ali R. Jalili, Suncheng Xiang
Abstract: Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segmentation outputs or rely on heavy architectures with high computational complexity, resulting in insufficient inference speeds for real-time colorectal endoscopic applications. To address this problem, we propose MicroAUNet, a light-weighted attention-based segmentation network that combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to strengthen multi-scale boundary features. On the basis of it, a progressive two-stage knowledge-distillation scheme is introduced to transfer semantic and boundary cues from a high-capacity teacher. Extensive experiments on benchmarks also demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation. The code is publicly available at https://github.com/JeremyXSC/MicroAUNet.
Authors: Yongyuan Liang, Wei Chow, Feng Li, Ziqiao Ma, Xiyao Wang, Jiageng Mao, Jiuhai Chen, Jiatao Gu, Yue Wang, Furong Huang
Abstract: Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat these abilities in isolation, such that tasks with multimodal inputs and outputs are scored primarily through unimodal reasoning, i.e., textual benchmarks emphasize language-based reasoning, while visual benchmarks emphasize reasoning outcomes manifested in the pixels. We introduce ROVER to address this pressing need to test reciprocal cross-modal reasoning, the use of one modality to guide, verify, or refine outputs in the other, an ability central to the vision of unified multimodal intelligence. ROVER is a human-annotated benchmark that explicitly targets reciprocal cross-modal reasoning, which contains 1312 tasks grounded in 1876 images, spanning two complementary settings. Verbally-augmented reasoning for visual generation evaluates whether models can use verbal prompts and reasoning chains to guide faithful image synthesis. Visually-augmented reasoning for verbal generation evaluates whether models can generate intermediate visualizations that strengthen their own reasoning processes for question answering. Experiments on 17 unified models reveal two key findings: (i) Cross-modal reasoning determines visual generation quality, with interleaved models significantly outperforming non-interleaved ones; notably, combining strong unimodal models fails to achieve comparable reasoning. (ii) Models show dissociation between physical and symbolic reasoning: they succeed at interpreting perceptual concepts literally but fail to construct visual abstractions for symbolic tasks, where faulty reasoning harms performance. These results highlight reciprocal cross-modal reasoning as a critical frontier for enabling true omnimodal generation.
Authors: Brian Nlong Zhao, Jiajun Wu, Shangzhe Wu
Abstract: Computer vision for animals holds great promise for wildlife research but often depends on large-scale data, while existing collection methods rely on controlled capture setups. Recent data-driven approaches show the potential of single-view, non-invasive analysis, yet current animal video datasets are limited--offering as few as 2.4K 15-frame clips and lacking key processing for animal-centric 3D/4D tasks. We introduce an automated pipeline that mines YouTube videos and processes them into object-centric clips, along with auxiliary annotations valuable for downstream tasks like pose estimation, tracking, and 3D/4D reconstruction. Using this pipeline, we amass 30K videos (2M frames)--an order of magnitude more than prior works. To demonstrate its utility, we focus on the 4D quadruped animal reconstruction task. To support this task, we present Animal-in-Motion (AiM), a benchmark of 230 manually filtered sequences with 11K frames showcasing clean, diverse animal motions. We evaluate state-of-the-art model-based and model-free methods on Animal-in-Motion, finding that 2D metrics favor the former despite unrealistic 3D shapes, while the latter yields more natural reconstructions but scores lower--revealing a gap in current evaluation. To address this, we enhance a recent model-free approach with sequence-level optimization, establishing the first 4D animal reconstruction baseline. Together, our pipeline, benchmark, and baseline aim to advance large-scale, markerless 4D animal reconstruction and related tasks from in-the-wild videos. Code and datasets are available at https://github.com/briannlongzhao/Animal-in-Motion.
Authors: Peng Du, Hui Li, Han Xu, Paul Barom Jeon, Dongwook Lee, Daehyun Ji, Ran Yang, Feng Zhu
Abstract: Discrete Wavelet Transform (DWT) has been widely explored to enhance the performance of image superresolution (SR). Despite some DWT-based methods improving SR by capturing fine-grained frequency signals, most existing approaches neglect the interrelations among multiscale frequency sub-bands, resulting in inconsistencies and unnatural artifacts in the reconstructed images. To address this challenge, we propose a Diffusion Transformer model based on image Wavelet spectra for SR (DTWSR).DTWSR incorporates the superiority of diffusion models and transformers to capture the interrelations among multiscale frequency sub-bands, leading to a more consistence and realistic SR image. Specifically, we use a Multi-level Discrete Wavelet Transform (MDWT) to decompose images into wavelet spectra. A pyramid tokenization method is proposed which embeds the spectra into a sequence of tokens for transformer model, facilitating to capture features from both spatial and frequency domain. A dual-decoder is designed elaborately to handle the distinct variances in lowfrequency (LF) and high-frequency (HF) sub-bands, without omitting their alignment in image generation. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our method, with high performance on both perception quality and fidelity.
Authors: Minmin Zeng
Abstract: Action Quality Assessment (AQA) requires fine-grained understanding of human motion and precise evaluation of pose similarity. This paper proposes a topology-aware Graph Convolutional Network (GCN) framework, termed GCN-PSN, which models the human skeleton as a graph to learn discriminative, topology-sensitive pose embeddings. Using a Siamese architecture trained with a contrastive regression objective, our method outperforms coordinate-based baselines and achieves competitive performance on AQA-7 and FineDiving benchmarks. Experimental results and ablation studies validate the effectiveness of leveraging skeletal topology for pose similarity and action quality assessment.
Authors: Mengyuan Liu, Sheng Yan, Yong Wang, Yingjie Li, Gui-Bin Bian, Hong Liu
Abstract: We introduce MoSa, a novel hierarchical motion generation framework for text-driven 3D human motion generation that enhances the Vector Quantization-guided Generative Transformers (VQ-GT) paradigm through a coarse-to-fine scalable generation process. In MoSa, we propose a Multi-scale Token Preservation Strategy (MTPS) integrated into a hierarchical residual vector quantization variational autoencoder (RQ-VAE). MTPS employs interpolation at each hierarchical quantization to effectively retain coarse-to-fine multi-scale tokens. With this, the generative transformer supports Scalable Autoregressive (SAR) modeling, which predicts scale tokens, unlike traditional methods that predict only one token at each step. Consequently, MoSa requires only 10 inference steps, matching the number of RQ-VAE quantization layers. To address potential reconstruction degradation from frequent interpolation, we propose CAQ-VAE, a lightweight yet expressive convolution-attention hybrid VQ-VAE. CAQ-VAE enhances residual block design and incorporates attention mechanisms to better capture global dependencies. Extensive experiments show that MoSa achieves state-of-the-art generation quality and efficiency, outperforming prior methods in both fidelity and speed. On the Motion-X dataset, MoSa achieves an FID of 0.06 (versus MoMask's 0.20) while reducing inference time by 27 percent. Moreover, MoSa generalizes well to downstream tasks such as motion editing, requiring no additional fine-tuning. The code is available at https://mosa-web.github.io/MoSa-web
Authors: Heyu Guo, Shanmu Wang, Ruichun Ma, Shiqi Jiang, Yasaman Ghasempour, Omid Abari, Baining Guo, Lili Qi
Abstract: Vision-language-action (VLA) models have shown strong generalization for action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their perception and, consequently, manipulation capabilities. We present OmniVLA, an omni-modality VLA model that integrates novel sensing modalities for physically-grounded spatial intelligence beyond RGB perception. The core of our approach is the sensor-masked image, a unified representation that overlays spatially grounded and physically meaningful masks onto the RGB images, derived from sensors including an infrared camera, a mmWave radar, and a microphone array. This image-native unification keeps sensor input close to RGB statistics to facilitate training, provides a uniform interface across sensor hardware, and enables data-efficient learning with lightweight per-sensor projectors. Built on this, we present a multisensory vision-language-action model architecture and train the model based on an RGB-pretrained VLA backbone. We evaluate OmniVLA on challenging real-world tasks where sensor-modality perception is needed to guide the manipulation. OmniVLA achieves an average task success rate of 84%, significantly outperforms both RGB-only and raw-sensor-input baseline models by 59% and 28% respectively, meanwhile showing higher learning efficiency and stronger generalization capability.
Authors: Riddhi Jain, Manasi Patwardhan, Parijat Deshpande, Venkataramana Runkana
Abstract: The immense diversity in the culture and culinary of Indian cuisines calls attention to the major shortcoming of the existing Visual Question Answering(VQA) systems which are inclined towards the foods from Western region. Recent attempt towards building a VQA dataset for Indian food is a step towards addressing this challenge. However, their approach towards VQA follows a two-step process in which the answer is generated first, followed by the explanation of the expected answer. In this work, we claim that food VQA requires to follow a multi-step reasoning process to arrive at an accurate answer, especially in the context of India food, which involves understanding complex culinary context and identifying relationships between various food items. With this hypothesis we create reasoning chains upon the QA with minimal human intervention. We fine-tune smaller LLMs and VLMs with auto-validated reasoning chains and further train them using reinforcement learning with larger data. With augmentation of reasoning chains, we observed accuracy improvement of an average 10 percentage points on the baseline. We provide detailed analysis in terms the effect of addition of reasoning chains for the Indian Food VQA task. Index Terms - FoodVQA, Reasoning Chains, Reinforcement Learning, Knowledge Graph.
Authors: Zahra Mehraban, Sebastien Glaser, Michael Milford, Ronald Schroeter
Abstract: Domain adaptation is required for automated driving models to generalize well across diverse road conditions. This paper explores a training method for domain adaptation to adapt PilotNet, an end-to-end deep learning-based model, for left-hand driving conditions using real-world Australian highway data. Four training methods were evaluated: (1) a baseline model trained on U.S. right-hand driving data, (2) a model trained on flipped U.S. data, (3) a model pretrained on U.S. data and then fine-tuned on Australian highways, and (4) a model pretrained on flipped U.S. data and then finetuned on Australian highways. This setup examines whether incorporating flipped data enhances the model adaptation by providing an initial left-hand driving alignment. The paper compares model performance regarding steering prediction accuracy and attention, using saliency-based analysis to measure attention shifts across significant road regions. Results show that pretraining on flipped data alone worsens prediction stability due to misaligned feature representations, but significantly improves adaptation when followed by fine-tuning, leading to lower prediction error and stronger focus on left-side cues. To validate this approach across different architectures, the same experiments were done on ResNet, which confirmed similar adaptation trends. These findings emphasize the importance of preprocessing techniques, such as flipped-data pretraining, followed by fine-tuning to improve model adaptation with minimal retraining requirements.
Authors: Rajmund Nagy (KTH Royal Institute of Technology), Hendric Voss (Bielefeld University), Thanh Hoang-Minh (University of Science -- VNUHCM), Mihail Tsakov (Independent Researcher), Teodor Nikolov (Motorica AB), Zeyi Zhang (Peking University), Tenglong Ao (Peking University), Sicheng Yang (Huawei Technologies Ltd), Shaoli Huang (Astribot), Yongkang Cheng (Astribot), M. Hamza Mughal (Max-Planck Institute for Informatics, SIC), Rishabh Dabral (Max-Planck Institute for Informatics, SIC), Kiran Chhatre (KTH Royal Institute of Technology), Christian Theobalt (Max-Planck Institute for Informatics, SIC), Libin Liu (Peking University), Stefan Kopp (Bielefeld University), Rachel McDonnell (Trinity College Dublin), Michael Neff (University of California, Davis), Taras Kucherenko (SEED -- Electronic Arts), Youngwoo Yoon (Electronics and Telecommunications Research Institute), Gustav Eje Henter (KTH Royal Institute of Technology, Motorica AB)
Abstract: We review human evaluation practices in automated, speech-driven 3D gesture generation and find a lack of standardisation and frequent use of flawed experimental setups. This leads to a situation where it is impossible to know how different methods compare, or what the state of the art is. In order to address common shortcomings of evaluation design, and to standardise future user studies in gesture-generation works, we introduce a detailed human evaluation protocol for the widely-used BEAT2 motion-capture dataset. Using this protocol, we conduct large-scale crowdsourced evaluation to rank six recent gesture-generation models -- each trained by its original authors -- across two key evaluation dimensions: motion realism and speech-gesture alignment. Our results provide strong evidence that 1) newer models do not consistently outperform earlier approaches; 2) published claims of high motion realism or speech-gesture alignment may not hold up under rigorous evaluation; and 3) the field must adopt disentangled assessments of motion quality and multimodal alignment for accurate benchmarking in order to make progress. Finally, in order to drive standardisation and enable new evaluation research, we will release five hours of synthetic motion from the benchmarked models; over 750 rendered video stimuli from the user studies -- enabling new evaluations without model reimplementation required -- alongside our open-source rendering script, and the 16,000 pairwise human preference votes collected for our benchmark.
Authors: Vishakha Lall, Yisi Liu
Abstract: Human gaze offers rich supervisory signals for understanding visual attention in complex visual environments. In this paper, we propose Eyes on Target, a novel depth-aware and gaze-guided object detection framework designed for egocentric videos. Our approach injects gaze-derived features into the attention mechanism of a Vision Transformer (ViT), effectively biasing spatial feature selection toward human-attended regions. Unlike traditional object detectors that treat all regions equally, our method emphasises viewer-prioritised areas to enhance object detection. We validate our method on an egocentric simulator dataset where human visual attention is critical for task assessment, illustrating its potential in evaluating human performance in simulation scenarios. We evaluate the effectiveness of our gaze-integrated model through extensive experiments and ablation studies, demonstrating consistent gains in detection accuracy over gaze-agnostic baselines on both the custom simulator dataset and public benchmarks, including Ego4D Ego-Motion and Ego-CH-Gaze datasets. To interpret model behaviour, we also introduce a gaze-aware attention head importance metric, revealing how gaze cues modulate transformer attention dynamics.
Authors: Zhixuan Zhang, Pingyu Wang, Xingjian Zheng, Linbo Qing, Qi Liu
Abstract: Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent studies still fall into suboptimal regions, especially the flat-yet-sharp areas, termed as deceptive flatness. In this paper, we introduce a novel black-box gradient-based transferable attack from a perspective of dual-order information. Specifically, we feasibly propose Adversarial Flatness (AF) to the deceptive flatness problem and a theoretical assurance for adversarial transferability. Based on this, using an efficient approximation of our objective, we instantiate our attack as Adversarial Flatness Attack (AFA), addressing the altered gradient sign issue. Additionally, to further improve the attack ability, we devise MonteCarlo Adversarial Sampling (MCAS) by enhancing the inner-loop sampling efficiency. The comprehensive results on ImageNet-compatible dataset demonstrate superiority over six baselines, generating adversarial examples in flatter regions and boosting transferability across model architectures. When tested on input transformation attacks or the Baidu Cloud API, our method outperforms baselines.
Authors: Yu Tian, Zhongheng Yang, Chenshi Liu, Yiyun Su, Ziwei Hong, Zexi Gong, Jingyuan Xu
Abstract: Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning. At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy to enable center-prioritized, axis-reinforced, and diagonally compensated information aggregation. This design enhances sensitivity to weak boundaries and tiny foci while maintaining sparse yet effective feature representation. A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts without user interaction, thereby improving inter-slice coherence. The memory-augmented multi-scale decoder integrates memory attention modules at multiple levels, combining deep supervision with progressive refinement to restore fine details while preserving global consistency. Extensive experiments on public benchmarks demonstrate that CenterMamba-SAM achieves state-of-the-art performance in brain lesion segmentation.
Authors: YoungJae Cheong, Jhonghyun An
Abstract: LiDAR semantic segmentation degrades in adverse weather because refraction, scattering, and point dropouts corrupt geometry. Prior work in weather simulation, mixing-based augmentation, domain randomization, and uncertainty or boundary regularization improves robustness but still overlooks structural vulnerabilities near boundaries, corners, and sparse regions. We present a Light Geometry-aware adapter. The module aligns azimuth and applies horizontal circular padding to preserve neighbor continuity across the 0~360 degree wrap-around boundary. A local-window K-Nearest Neighbors gathers nearby points and computes simple local statistics, which are compressed into compact geometry-aware cues. During training, these cues drive region-aware regularization that stabilizes predictions in structurally fragile areas. The adapter is plug and play, complements augmentation, and can be enabled only during training with negligible inference cost. We adopt a source-only cross-weather setup where models train on SemanticKITTI and are evaluated on SemanticSTF without target labels or fine-tuning. The adapter improves mIoU by 7.9 percentage points over the data-centric augmentation baseline and by 0.6 points over the class-centric regularization baseline. These results indicate that geometry-driven regularization is a key direction for all-weather LiDAR segmentation.
Authors: Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Schechtman, Xun Huang
Abstract: Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. Our approach begins by augmenting a text-to-video model with motion control, which generates high-quality videos that adhere to the global text prompt and local motion guidance, but does not perform inference on the fly. As such, we distill this bidirectional teacher into a causal student through Self Forcing with Distribution Matching Distillation, enabling real-time streaming inference. Several key challenges arise when generating videos of long, potentially infinite time-horizons: (1) bridging the domain gap from training on finite length and extrapolating to infinite horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without incurring growth in computational cost due to increasing context windows. A key to our approach is introducing carefully designed sliding-window causal attention, combined with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we properly simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Our models achieve state-of-the-art results in motion following and video quality while being two orders of magnitude faster, uniquely enabling infinite-length streaming. With MotionStream, users can paint trajectories, control cameras, or transfer motion, and see results unfold in real-time, delivering a truly interactive experience.
Authors: Tan Tang, Yanhong Wu, Junming Gao, Yingcai Wu
Abstract: Ancient Chinese paintings are a valuable cultural heritage that is damaged by irreversible color degradation. Reviving color-degraded paintings is extraordinarily difficult due to the complex chemistry mechanism. Progress is further slowed by the lack of comprehensive, high-quality datasets, which hampers the creation of end-to-end digital restoration tools. To revive colors, we propose PRevivor, a prior-guided color transformer that learns from recent paintings (e.g., Ming and Qing Dynasty) to restore ancient ones (e.g., Tang and Song Dynasty). To develop PRevivor, we decompose color restoration into two sequential sub-tasks: luminance enhancement and hue correction. For luminance enhancement, we employ two variational U-Nets and a multi-scale mapping module to translate faded luminance into restored counterparts. For hue correction, we design a dual-branch color query module guided by localized hue priors extracted from faded paintings. Specifically, one branch focuses attention on regions guided by masked priors, enforcing localized hue correction, whereas the other branch remains unconstrained to maintain a global reasoning capability. To evaluate PRevivor, we conduct extensive experiments against state-of-the-art colorization methods. The results demonstrate superior performance both quantitatively and qualitatively.
Authors: Karma Phuntsho, Abdullah, Kyungmi Lee, Ickjai Lee, Euijoon Ahn
Abstract: Foundation models (FMs) have emerged as a transformative paradigm in medical image analysis, offering the potential to provide generalizable, task-agnostic solutions across a wide range of clinical tasks and imaging modalities. Their capacity to learn transferable representations from large-scale data has the potential to address the limitations of conventional task-specific models. However, adaptation of FMs to real-world clinical practice remains constrained by key challenges, including domain shifts, limited availability of high-quality annotated data, substantial computational demands, and strict privacy requirements. This review presents a comprehensive assessment of strategies for adapting FMs to the specific demands of medical imaging. We examine approaches such as supervised fine-tuning, domain-specific pretraining, parameter-efficient fine-tuning, self-supervised learning, hybrid methods, and multimodal or cross-modal frameworks. For each, we evaluate reported performance gains, clinical applicability, and limitations, while identifying trade-offs and unresolved challenges that prior reviews have often overlooked. Beyond these established techniques, we also highlight emerging directions aimed at addressing current gaps. These include continual learning to enable dynamic deployment, federated and privacy-preserving approaches to safeguard sensitive data, hybrid self-supervised learning to enhance data efficiency, data-centric pipelines that combine synthetic generation with human-in-the-loop validation, and systematic benchmarking to assess robust generalization under real-world clinical variability. By outlining these strategies and associated research gaps, this review provides a roadmap for developing adaptive, trustworthy, and clinically integrated FMs capable of meeting the demands of real-world medical imaging.
Authors: Yonggang Zhang, Jun Nie, Xinmei Tian, Mingming Gong, Kun Zhang, Bo Han
Abstract: The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on training binary classifiers, which depend heavily on the quantity and quality of available generated images. In this work, we propose a novel framework that exploits geometric differences between the data manifolds of natural and generated images. To exploit this difference, we employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones, leveraging the property that their gradients reside in mutually orthogonal subspaces. This design enables a simple yet effective detection method: an image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images. Further more, to address diminishing manifold disparities in advanced generative models, we leverage normalizing flows to amplify detectable differences by extruding generated images away from the natural image manifold. Extensive experiments demonstrate the efficacy of this method. Code is available at https://github.com/tmlr-group/ConV.
Authors: Feng Han, Yibin Wang, Chenglin Li, Zheming Liang, Dianyi Wang, Yang Jiao, Zhipeng Wei, Chao Gong, Cheng Jin, Jingjing Chen, Jiaqi Wang
Abstract: Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects.
Authors: Nu-Fnag Xiao, De-Xing Huang, Le-Tian Wang, Mei-Jiang Gui, Qi Fu, Xiao-Liang Xie, Shi-Qi Liu, Shuangyi Wang, Zeng-Guang Hou, Ying-Wei Wang, Xiao-Hu Zhou
Abstract: Accurate assessment of gastric content from ultrasound is critical for stratifying aspiration risk at induction of general anesthesia. However, traditional methods rely on manual tracing of gastric antra and empirical formulas, which face significant limitations in both efficiency and accuracy. To address these challenges, a novel two-stage probability map-guided dual-branch fusion framework (REASON) for gastric content assessment is proposed. In stage 1, a segmentation model generates probability maps that suppress artifacts and highlight gastric anatomy. In stage 2, a dual-branch classifier fuses information from two standard views, right lateral decubitus (RLD) and supine (SUP), to improve the discrimination of learned features. Experimental results on a self-collected dataset demonstrate that the proposed framework outperforms current state-of-the-art approaches by a significant margin. This framework shows great promise for automated preoperative aspiration risk assessment, offering a more robust, efficient, and accurate solution for clinical practice.
Authors: Chentao Li, Behzad Bozorgtabar, Yifang Ping, Pan Huang, Jing Qin
Abstract: Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these challenges, we propose a latent factor grouping-boosted cluster-reasoning instance disentangled learning framework for whole-slide image (WSI) interpretable representation in three phases. First, we introduce a novel positive semi-definite latent factor grouping that maps instances into a latent subspace, effectively mitigating spatial entanglement in MIL. To alleviate semantic entanglement, we employs instance probability counterfactual inference and optimization via cluster-reasoning instance disentangling. Finally, we employ a generalized linear weighted decision via instance effect re-weighting to address decision entanglement. Extensive experiments on multicentre datasets demonstrate that our model outperforms all state-of-the-art models. Moreover, it attains pathologist-aligned interpretability through disentangled representations and a transparent decision-making process.
Authors: Tae-Young Lee, Juwon Seo, Jong Hwan Ko, Gyeong-Moon Park
Abstract: Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks, as personalization techniques can be misused by malicious users to generate unauthorized content. Although several studies have attempted to counter this by generating adversarially perturbed samples designed to disrupt personalization, they rely on unrealistic assumptions and become ineffective in the presence of even a few clean images or under simple image transformations. To address these challenges, we shift the protection target from the images to the diffusion model itself to hinder the personalization of specific subjects, through our novel framework called Anti-Personalized Diffusion Models (APDM). We first provide a theoretical analysis demonstrating that a naive approach of existing loss functions to diffusion models is inherently incapable of ensuring convergence for robust anti-personalization. Motivated by this finding, we introduce Direct Protective Optimization (DPO), a novel loss function that effectively disrupts subject personalization in the target model without compromising generative quality. Moreover, we propose a new dual-path optimization strategy, coined Learning to Protect (L2P). By alternating between personalization and protection paths, L2P simulates future personalization trajectories and adaptively reinforces protection at each step. Experimental results demonstrate that our framework outperforms existing methods, achieving state-of-the-art performance in preventing unauthorized personalization. The code is available at https://github.com/KU-VGI/APDM.
Authors: Jianfei Jiang, Qiankun Liu, Hongyuan Liu, Haochen Yu, Liyong Wang, Jiansheng Chen, Huimin Ma
Abstract: Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features extracted by conventional feature pyramid networks. However, the quadratic complexity of Transformer-based MVS methods poses challenges to balance performance and efficiency. Motivated by the global modeling capability and linear complexity of the Mamba architecture, we propose MVSMamba, the first Mamba-based MVS network. MVSMamba enables efficient global feature aggregation with minimal computational overhead. To fully exploit Mamba's potential in MVS, we propose a Dynamic Mamba module (DM-module) based on a novel reference-centered dynamic scanning strategy, which enables: (1) Efficient intra- and inter-view feature interaction from the reference to source views, (2) Omnidirectional multi-view feature representations, and (3) Multi-scale global feature aggregation. Extensive experimental results demonstrate MVSMamba outperforms state-of-the-art MVS methods on the DTU dataset and the Tanks-and-Temples benchmark with both superior performance and efficiency. The source code is available at https://github.com/JianfeiJ/MVSMamba.
Authors: Sampriti Soor, Alik Pramanick, Jothiprakash K, Arijit Sur
Abstract: The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to inaccurate predictions. In this paper, a generative adversarial attack method is proposed that uses the CLIP model to create highly effective and visually imperceptible adversarial perturbations. The CLIP model's ability to align text and image representation helps incorporate natural language semantics with a guided loss to generate effective adversarial examples that look identical to the original inputs. This integration allows extensive scene manipulation, creating perturbations in multi-object environments specifically designed to deceive multilabel classifiers. Our approach integrates the concentrated perturbation strategy from Saliency-based Auto-Encoder (SSAE) with the dissimilar text embeddings similar to Generative Adversarial Multi-Object Scene Attacks (GAMA), resulting in perturbations that both deceive classification models and maintain high structural similarity to the original images. The model was tested on various tasks across diverse black-box victim models. The experimental results show that our method performs competitively, achieving comparable or superior results to existing techniques, while preserving greater visual fidelity.
Authors: Jierui Qu, Jianchun Zhao
Abstract: Medical image segmentation is essential for computer-assisted diagnosis and treatment planning, yet substantial anatomical variability and boundary ambiguity hinder reliable delineation of fine structures. We propose RDTE-UNet, a segmentation network that unifies local modeling with global context to strengthen boundary delineation and detail preservation. RDTE-UNet employs a hybrid ResBlock detail-aware Transformer backbone and three modules: ASBE for adaptive boundary enhancement, HVDA for fine-grained feature modeling, and EulerFF for fusion weighting guided by Euler's formula. Together, these components improve structural consistency and boundary accuracy across morphology, orientation, and scale. On Synapse and BUSI dataset, RDTE-UNet has achieved a comparable level in terms of segmentation accuracy and boundary quality.
Authors: Trishanu Das, Abhilash Nandy, Khush Bajaj, Deepiha S
Abstract: Understanding Rebus Puzzles (Rebus Puzzles use pictures, symbols, and letters to represent words or phrases creatively) requires a variety of skills such as image recognition, cognitive skills, commonsense reasoning, multi-step reasoning, image-based wordplay, etc., making this a challenging task for even current Vision-Language Models. In this paper, we present $\left|\,\circlearrowright\,\boxed{\text{BUS}}\,\right|$, a large and diverse benchmark of $1,333$ English Rebus Puzzles containing different artistic styles and levels of difficulty, spread across 18 categories such as food, idioms, sports, finance, entertainment, etc. We also propose $RebusDescProgICE$, a model-agnostic framework which uses a combination of an unstructured description and code-based, structured reasoning, along with better, reasoning-based in-context example selection, improving the performance of Vision-Language Models on $\left|\,\circlearrowright\,\boxed{\text{BUS}}\,\right|$ by $2.1-4.1\%$ and $20-30\%$ using closed-source and open-source models respectively compared to Chain-of-Thought Reasoning.
Authors: Jierui Qu, Jianchun Zhao
Abstract: Accurate segmentation of medical images is fundamental to tumor diagnosis and treatment planning. SAM-based interactive segmentation has gained attention for its strong generalization, but most methods follow a single-point-to-single-object paradigm, which limits multi-lesion segmentation. Moreover, ViT backbones capture global context but often miss high-fidelity local details. We propose MIQ-SAM3D, a multi-instance 3D segmentation framework with a competitive query optimization strategy that shifts from single-point-to-single-mask to single-point-to-multi-instance. A prompt-conditioned instance-query generator transforms a single point prompt into multiple specialized queries, enabling retrieval of all semantically similar lesions across the 3D volume from a single exemplar. A hybrid CNN-Transformer encoder injects CNN-derived boundary saliency into ViT self-attention via spatial gating. A competitively optimized query decoder then enables end-to-end, parallel, multi-instance prediction through inter-query competition. On LiTS17 and KiTS21 dataset, MIQ-SAM3D achieved comparable levels and exhibits strong robustness to prompts, providing a practical solution for efficient annotation of clinically relevant multi-lesion cases.
Authors: Linhao Huang
Abstract: Recent advancements in text-to-image diffusion models have significantly improved the personalization and stylization of generated images. However, previous studies have only assessed content similarity under a single style intensity. In our experiments, we observe that increasing style intensity leads to a significant loss of content features, resulting in a suboptimal content-style frontier. To address this, we propose a novel approach to expand the content-style frontier by leveraging Content-Style Subspace Blending and a Content-Style Balance loss. Our method improves content similarity across varying style intensities, significantly broadening the content-style frontier. Extensive experiments demonstrate that our approach outperforms existing techniques in both qualitative and quantitative evaluations, achieving superior content-style trade-off with significantly lower Inverted Generational Distance (IGD) and Generational Distance (GD) scores compared to current methods.
Authors: Qiangguo Jin, Xianyao Zheng, Hui Cui, Changming Sun, Yuqi Fang, Cong Cong, Ran Su, Leyi Wei, Ping Xuan, Junbo Wang
Abstract: Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments between vision and language. Moreover, classification-based methods rely on predefined answer sets. Treating this task as a simple classification problem may make it unable to adapt to the diversity of free-form answers and overlook the detailed semantic information of free-form answers. In order to tackle these challenges, we introduce a Cross-Mamba Interaction based Multi-Task Learning (CMI-MTL) framework that learns cross-modal feature representations from images and texts. CMI-MTL comprises three key modules: fine-grained visual-text feature alignment (FVTA), cross-modal interleaved feature representation (CIFR), and free-form answer-enhanced multi-task learning (FFAE). FVTA extracts the most relevant regions in image-text pairs through fine-grained visual-text feature alignment. CIFR captures cross-modal sequential interactions via cross-modal interleaved feature representation. FFAE leverages auxiliary knowledge from open-ended questions through free-form answer-enhanced multi-task learning, improving the model's capability for open-ended Med-VQA. Experimental results show that CMI-MTL outperforms the existing state-of-the-art methods on three Med-VQA datasets: VQA-RAD, SLAKE, and OVQA. Furthermore, we conduct more interpretability experiments to prove the effectiveness. The code is publicly available at https://github.com/BioMedIA-repo/CMI-MTL.
Authors: Hitesh Kyatham, Arjun Suresh, Aadi Palnitkar, Yiannis Aloimonos
Abstract: The underwater domain presents a vast array of challenges for roboticists and computer vision researchers alike, such as poor lighting conditions and high dynamic range scenes. In these adverse conditions, traditional vision techniques struggle to adapt and lead to suboptimal performance. Event-based cameras present an attractive solution to this problem, mitigating the issues of traditional cameras by tracking changes in the footage on a frame-by-frame basis. In this paper, we introduce a pipeline which can be used to generate realistic synthetic data of an event-based camera mounted to an AUV (Autonomous Underwater Vehicle) in an underwater environment for training vision models. We demonstrate the effectiveness of our pipeline using the task of rock detection with poor visibility and suspended particulate matter, but the approach can be generalized to other underwater tasks.
Authors: Xinyu Mao, Junsi Li, Haoji Zhang, Yu Liang, Ming Sun
Abstract: Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23\%-86\% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.
Authors: Ya Wen, Yutong Qiao, Chi Chiu Lam, Ioannis Brilakis, Sanghoon Lee, Mun On Wong
Abstract: Inventory management of firefighting assets is crucial for emergency preparedness, risk assessment, and on-site fire response. However, conventional methods are inefficient due to limited capabilities in automated asset recognition and reconstruction. To address the challenge, this research introduces the Fire-ART dataset and develops a panoramic image-based reconstruction approach for semantic enrichment of firefighting assets into BIM models. The Fire-ART dataset covers 15 fundamental assets, comprising 2,626 images and 6,627 instances, making it an extensive and publicly accessible dataset for asset recognition. In addition, the reconstruction approach integrates modified cube-map conversion and radius-based spherical camera projection to enhance recognition and localization accuracy. Through validations with two real-world case studies, the proposed approach achieves F1-scores of 73% and 88% and localization errors of 0.620 and 0.428 meters, respectively. The Fire-ART dataset and the reconstruction approach offer valuable resources and robust technical solutions to enhance the accurate digital management of fire safety equipment.
Authors: Reza Karimzadeh, Albert Alonso, Frans Zdyb, Julius B. Kirkegaard, Bulat Ibragimov
Abstract: Faithful yet compact explanations for vision models remain a challenge, as commonly used dense perturbation masks are often fragmented and overfitted, needing careful post-processing. Here, we present a training-free explanation method that replaces dense masks with smooth tunable contours. A star-convex region is parameterized by a truncated Fourier series and optimized under an extremal preserve/delete objective using the classifier gradients. The approach guarantees a single, simply connected mask, cuts the number of free parameters by orders of magnitude, and yields stable boundary updates without cleanup. Restricting solutions to low-dimensional, smooth contours makes the method robust to adversarial masking artifacts. On ImageNet classifiers, it matches the extremal fidelity of dense masks while producing compact, interpretable regions with improved run-to-run consistency. Explicit area control also enables importance contour maps, yielding a transparent fidelity-area profiles. Finally, we extend the approach to multi-contour and show how it can localize multiple objects within the same framework. Across benchmarks, the method achieves higher relevance mass and lower complexity than gradient and perturbation based baselines, with especially strong gains on self-supervised DINO models where it improves relevance mass by over 15% and maintains positive faithfulness correlations.
Authors: Yongqi Yang, Huayang Huang, Xu Peng, Xiaobin Hu, Donghao Luo, Jiangning Zhang, Chengjie Wang, Yu Wu
Abstract: Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a distillation-based framework for efficient causal video generation that enables high-quality synthesis with extremely limited denoising steps. Our approach builds upon the Distribution Matching Distillation (DMD) framework and proposes a novel Adversarial Self-Distillation (ASD) strategy, which aligns the outputs of the student model's n-step denoising process with its (n+1)-step version at the distribution level. This design provides smoother supervision by bridging small intra-student gaps and more informative guidance by combining teacher knowledge with locally consistent student behavior, substantially improving training stability and generation quality in extremely few-step scenarios (e.g., 1-2 steps). In addition, we present a First-Frame Enhancement (FFE) strategy, which allocates more denoising steps to the initial frames to mitigate error propagation while applying larger skipping steps to later frames. Extensive experiments on VBench demonstrate that our method surpasses state-of-the-art approaches in both one-step and two-step video generation. Notably, our framework produces a single distilled model that flexibly supports multiple inference-step settings, eliminating the need for repeated re-distillation and enabling efficient, high-quality video synthesis.
Authors: Yinchao Ma, Yuyang Tang, Wenfei Yang, Tianzhu Zhang, Xu Zhou, Feng Wu
Abstract: Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0\% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0\% main metric across all three RGB+X video modalities.
Authors: Seongkyu Choi, Jhonghyun An
Abstract: Off-road semantic segmentation suffers from thick, inconsistent boundaries, sparse supervision for rare classes, and pervasive label noise. Designs that fuse only at low resolution blur edges and propagate local errors, whereas maintaining high-resolution pathways or repeating high-resolution fusions is costly and fragile to noise. We introduce a resolutionaware token decoder that balances global semantics, local consistency, and boundary fidelity under imperfect supervision. Most computation occurs at a low-resolution bottleneck; a gated cross-attention injects fine-scale detail, and only a sparse, uncertainty-selected set of pixels is refined. The components are co-designed and tightly integrated: global self-attention with lightweight dilated depthwise refinement restores local coherence; a gated cross-attention integrates fine-scale features from a standard high-resolution encoder stream without amplifying noise; and a class-aware point refinement corrects residual ambiguities with negligible overhead. During training, we add a boundary-band consistency regularizer that encourages coherent predictions in a thin neighborhood around annotated edges, with no inference-time cost. Overall, the results indicate competitive performance and improved stability across transitions.
Authors: SiWoo Kim, JhongHyun An
Abstract: Robust perception at night remains challenging for thermal-infrared detection: low contrast and weak high-frequency cues lead to duplicate, overlapping boxes, missed small objects, and class confusion. Prior remedies either translate TIR to RGB and hope pixel fidelity transfers to detection -- making performance fragile to color or structure artifacts -- or fuse RGB and TIR at test time, which requires extra sensors, precise calibration, and higher runtime cost. Both lines can help in favorable conditions, but do not directly shape the thermal representation used by the detector. We keep mono-modality inference and tackle the root causes during training. Specifically, we introduce training-only objectives that sharpen instance-level decision boundaries by pulling together features of the same class and pushing apart those of different classes -- suppressing duplicate and confusing detections -- and that inject cross-modal semantic priors by aligning the student's multi-level pyramid features with an RGB-trained teacher, thereby strengthening texture-poor thermal features without visible input at test time. In experiments, our method outperformed prior approaches and achieved state-of-the-art performance.
Authors: Riddhi Jain, Manasi Patwardhan, Aayush Mishra, Parijat Deshpande, Beena Rai
Abstract: To effectively manage the wastage of perishable fruits, it is crucial to accurately predict their freshness or shelf life using non-invasive methods that rely on visual data. In this regard, deep learning techniques can offer a viable solution. However, obtaining fine-grained fruit freshness labels from experts is costly, leading to a scarcity of data. Closed proprietary Vision Language Models (VLMs), such as Gemini, have demonstrated strong performance in fruit freshness detection task in both zero-shot and few-shot settings. Nonetheless, food retail organizations are unable to utilize these proprietary models due to concerns related to data privacy, while existing open-source VLMs yield sub-optimal performance for the task. Fine-tuning these open-source models with limited data fails to achieve the performance levels of proprietary models. In this work, we introduce a Model-Agnostic Ordinal Meta-Learning (MAOML) algorithm, designed to train smaller VLMs. This approach utilizes meta-learning to address data sparsity and leverages label ordinality, thereby achieving state-of-the-art performance in the fruit freshness classification task under both zero-shot and few-shot settings. Our method achieves an industry-standard accuracy of 92.71%, averaged across all fruits. Keywords: Fruit Quality Prediction, Vision Language Models, Meta Learning, Ordinal Regression
Authors: Jie Du, Xinyu Gong, Qingshan Tan, Wen Li, Yangming Cheng, Weitao Wang, Chenlu Zhan, Suhui Wu, Hao Zhang, Jun Zhang
Abstract: Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largely follow image-domain paradigms and are mainly developed on small-scale models (approximately 2B parameters), limiting their ability to address the unique challenges of video tasks, such as costly data construction, unstable training, and heavy memory consumption. To overcome these limitations, we introduce a GT-Pair that automatically builds high-quality preference pairs by using real videos as positives and model-generated videos as negatives, eliminating the need for any external annotation. We further present Reg-DPO, which incorporates the SFT loss as a regularization term into the DPO objective to enhance training stability and generation fidelity. Additionally, by combining the FSDP framework with multiple memory optimization techniques, our approach achieves nearly three times higher training capacity than using FSDP alone. Extensive experiments on both I2V and T2V tasks across multiple datasets demonstrate that our method consistently outperforms existing approaches, delivering superior video generation quality.
Authors: Dennis Pierantozzi, Luca Carlini, Mauro Orazio Drago, Chiara Lena, Cesare Hassan, Elena De Momi, Danail Stoyanov, Sophia Bano, Mobarak I. Hoque
Abstract: Safety and reliability are essential for deploying Visual Question Answering (VQA) in surgery, where incorrect or ambiguous responses can harm the patient. Most surgical VQA research focuses on accuracy or linguistic quality while overlooking safety behaviors such as ambiguity awareness, referral to human experts, or triggering a second opinion. Inspired by Automatic Failure Detection (AFD), we study uncertainty estimation as a key enabler of safer decision making. We introduce Question Aligned Semantic Nearest Neighbor Entropy (QA-SNNE), a black box uncertainty estimator that incorporates question semantics into prediction confidence. It measures semantic entropy by comparing generated answers with nearest neighbors in a medical text embedding space, conditioned on the question. We evaluate five models, including domain specific Parameter-Efficient Fine-Tuned (PEFT) models and zero-shot Large Vision-Language Models (LVLMs), on EndoVis18-VQA and PitVQA. PEFT models degrade under mild paraphrasing, while LVLMs are more resilient. Across three LVLMs and two PEFT baselines, QA-SNNE improves AUROC in most in-template settings and enhances hallucination detection. The Area Under the ROC Curve (AUROC) increases by 15-38% for zero-shot models, with gains maintained under out-of-template stress. QA-SNNE offers a practical and interpretable step toward AFD in surgical VQA by linking semantic uncertainty to question context. Combining LVLM backbones with question aligned uncertainty estimation can improve safety and clinician trust. The code and model are available at https://github.com/DennisPierantozzi/QASNNE
Authors: Peng Xia, Junbiao Pang, Tianyang Cai
Abstract: Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically overlook the relationship between a well-trained NN and the quantized model, leading to considerable quantization error for PTQ. However, it is unclear how to efficiently train a model-agnostic neural network which is tailored for a predefined precision low-bit model. In this paper, we firstly discover that a flat full precision neural network is crucial for low-bit quantization. To achieve this, we propose a framework that proactively pre-conditions the model by measuring and disentangling the error sources. Specifically, both the Activation Quantization Error (AQE) and the Weight Quantization Error (WQE) are statistically modeled as independent Gaussian noises. We study several noise injection optimization methods to obtain a flat minimum. Experimental results attest to the effectiveness of our approach. These results open novel pathways for obtaining low-bit PTQ models.
Authors: Lei Hu, Yongjing Ye, Shihong Xia
Abstract: The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively integrated with these foundation models to enhance multimodal understanding and cross-modal generation capabilities. However, the modality gap between human motion and text raises unresolved concerns about catastrophic forgetting during this integration. In addition, developing autoregressive-compatible pose representations that preserve generalizability across heterogeneous downstream tasks remains a critical technical barrier. To address these issues, we propose the Human Motion-Vision-Language Model (HMVLM), a unified framework based on the Mixture of Expert Low-Rank Adaption(MoE LoRA) strategy. The framework leverages the gating network to dynamically allocate LoRA expert weights based on the input prompt, enabling synchronized fine-tuning of multiple tasks. To mitigate catastrophic forgetting during instruction-tuning, we introduce a novel zero expert that preserves the pre-trained parameters for general linguistic tasks. For pose representation, we implement body-part-specific tokenization by partitioning the human body into different joint groups, enhancing the spatial resolution of the representation. Experiments show that our method effectively alleviates knowledge forgetting during instruction-tuning and achieves remarkable performance across diverse human motion downstream tasks.
Authors: Changyuan Zhao, Jiacheng Wang, Ruichen Zhang, Dusit Niyato, Hongyang Du, Zehui Xiong, Dong In Kim, Ping Zhang
Abstract: Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable to physical-layer adversarial threats, such as pilot spoofing and subcarrier jamming, compromising semantic fidelity. In this paper, we propose SecDiff, a plug-and-play, diffusion-aided decoding framework that significantly enhances the security and robustness of deep JSCC under adversarial wireless environments. Different from prior diffusion-guided JSCC methods that suffer from high inference latency, SecDiff employs pseudoinverse-guided sampling and adaptive guidance weighting, enabling flexible step-size control and efficient semantic reconstruction. To counter jamming attacks, we introduce a power-based subcarrier masking strategy and recast recovery as a masked inpainting problem, solved via diffusion guidance. For pilot spoofing, we formulate channel estimation as a blind inverse problem and develop an expectation-minimization (EM)-driven reconstruction algorithm, guided jointly by reconstruction loss and a channel operator. Notably, our method alternates between pilot recovery and channel estimation, enabling joint refinement of both variables throughout the diffusion process. Extensive experiments over orthogonal frequency-division multiplexing (OFDM) channels under adversarial conditions show that SecDiff outperforms existing secure and generative JSCC baselines by achieving a favorable trade-off between reconstruction quality and computational cost. This balance makes SecDiff a promising step toward practical, low-latency, and attack-resilient semantic communications.
Authors: Zhiyang Jia, Hongyan Cui, Ge Gao, Bo Li, Minjie Zhang, Zishuo Gao, Huiwen Huang, Caisheng Zhuo
Abstract: Person re-identification (ReID) plays a pivotal role in computer vision, particularly in surveillance and security applications within IoT-enabled smart environments. This study introduces the Enhanced Pedestrian Alignment Network (EPAN), tailored for robust ReID across diverse IoT surveillance conditions. EPAN employs a dual-branch architecture to mitigate the impact of perspective and environmental changes, extracting alignment information under varying scales and viewpoints. Here, we demonstrate EPAN's strong feature extraction capabilities, achieving outstanding performance on the Inspection-Personnel dataset with a Rank-1 accuracy of 90.09% and a mean Average Precision (mAP) of 78.82%. This highlights EPAN's potential for real-world IoT applications, enabling effective and reliable person ReID across diverse cameras in surveillance and security systems. The code and data are available at: https://github.com/ggboy2580/EPAN
Authors: Yufeng Jin, Niklas Funk, Vignesh Prasad, Zechu Li, Mathias Franzius, Jan Peters, Georgia Chalvatzaki
Abstract: Object pose estimation is a fundamental problem in robotics and computer vision, yet it remains challenging due to partial observability, occlusions, and object symmetries, which inevitably lead to pose ambiguity and multiple hypotheses consistent with the same observation. While deterministic deep networks achieve impressive performance under well-constrained conditions, they are often overconfident and fail to capture the multi-modality of the underlying pose distribution. To address these challenges, we propose a novel probabilistic framework that leverages flow matching on the SE(3) manifold for estimating 6D object pose distributions. Unlike existing methods that regress a single deterministic output, our approach models the full pose distribution with a sample-based estimate and enables reasoning about uncertainty in ambiguous cases such as symmetric objects or severe occlusions. We achieve state-of-the-art results on Real275, YCB-V, and LM-O, and demonstrate how our sample-based pose estimates can be leveraged in downstream robotic manipulation tasks such as active perception for disambiguating uncertain viewpoints or guiding grasp synthesis in an uncertainty-aware manner.
Authors: Mengtan Zhang, Zizhan Guo, Hongbo Zhao, Yi Feng, Zuyi Xiong, Yue Wang, Shaoyi Du, Hanli Wang, Rui Fan
Abstract: Unsupervised learning of depth and ego-motion, two fundamental 3D perception tasks, has made significant strides in recent years. However, most methods treat ego-motion as an auxiliary task, either mixing all motion types or excluding depth-independent rotational motions in supervision. Such designs limit the incorporation of strong geometric constraints, reducing reliability and robustness under diverse conditions. This study introduces a discriminative treatment of motion components, leveraging the geometric regularities of their respective rigid flows to benefit both depth and ego-motion estimation. Given consecutive video frames, network outputs first align the optical axes and imaging planes of the source and target cameras. Optical flows between frames are transformed through these alignments, and deviations are quantified to impose geometric constraints individually on each ego-motion component, enabling more targeted refinement. These alignments further reformulate the joint learning process into coaxial and coplanar forms, where depth and each translation component can be mutually derived through closed-form geometric relationships, introducing complementary constraints that improve depth robustness. DiMoDE, a general depth and ego-motion joint learning framework incorporating these designs, achieves state-of-the-art performance on multiple public datasets and a newly collected diverse real-world dataset, particularly under challenging conditions. Our source code will be publicly available at mias.group/DiMoDE upon publication.
Authors: Derong Kong, Zhixiong Yang, Shengxi Li, Shuaifeng Zhi, Li Liu, Zhen Liu, Jingyuan Xia
Abstract: Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus on deterministic pixel-level mappings between paired low/normal-light images, they often neglect the continuous physical process of luminance transitions in real-world environments, leading to performance drop when normal-light references are unavailable. Inspired by empirical analysis of natural luminance dynamics revealing power-law distributed intensity transitions, this paper introduces Luminance-Aware Statistical Quantification (LASQ), a novel framework that reformulates LLIE as a statistical sampling process over hierarchical luminance distributions. Our LASQ re-conceptualizes luminance transition as a power-law distribution in intensity coordinate space that can be approximated by stratified power functions, therefore, replacing deterministic mappings with probabilistic sampling over continuous luminance layers. A diffusion forward process is designed to autonomously discover optimal transition paths between luminance layers, achieving unsupervised distribution emulation without normal-light references. In this way, it considerably improves the performance in practical situations, enabling more adaptable and versatile light restoration. This framework is also readily applicable to cases with normal-light references, where it achieves superior performance on domain-specific datasets alongside better generalization-ability across non-reference datasets.
Authors: Andrei-Timotei Ardelean, Tim Weyrich
Abstract: In this work, we propose a system that covers the complete workflow for achieving controlled authoring and editing of textures that present distinctive local characteristics. These include various effects that change the surface appearance of materials, such as stains, tears, holes, abrasions, discoloration, and more. Such alterations are ubiquitous in nature, and including them in the synthesis process is crucial for generating realistic textures. We introduce a novel approach for creating textures with such blemishes, adopting a learning-based approach that leverages unlabeled examples. Our approach does not require manual annotations by the user; instead, it detects the appearance-altering features through unsupervised anomaly detection. The various textural features are then automatically clustered into semantically coherent groups, which are used to guide the conditional generation of images. Our pipeline as a whole goes from a small image collection to a versatile generative model that enables the user to interactively create and paint features on textures of arbitrary size. Notably, the algorithms we introduce for diffusion-based editing and infinite stationary texture generation are generic and should prove useful in other contexts as well. Project page: https://reality.tf.fau.de/pub/ardelean2025examplebased.html
URLs: https://reality.tf.fau.de/pub/ardelean2025examplebased.html
Authors: Serkan Ozturk, Samet Hicsonmez, Pinar Duygulu
Abstract: Current text conditioned image generation methods output realistic looking images, but they fail to capture specific styles. Simply finetuning them on the target style datasets still struggles to grasp the style features. In this work, we present a novel contrastive learning framework to improve the stylization capability of large text-to-image diffusion models. Motivated by the astonishing advance in image generation models that makes synthetic data an intrinsic part of model training in various computer vision tasks, we exploit synthetic image generation in our approach. Usually, the generated synthetic data is dependent on the task, and most of the time it is used to enlarge the available real training dataset. With NSYNC, alternatively, we focus on generating negative synthetic sets to be used in a novel contrastive training scheme along with real positive images. In our proposed training setup, we forward negative data along with positive data and obtain negative and positive gradients, respectively. We then refine the positive gradient by subtracting its projection onto the negative gradient to get the orthogonal component, based on which the parameters are updated. This orthogonal component eliminates the trivial attributes that are present in both positive and negative data and directs the model towards capturing a more unique style. Experiments on various styles of painters and illustrators show that our approach improves the performance over the baseline methods both quantitatively and qualitatively. Our code is available at https://github.com/giddyyupp/NSYNC.
Authors: Arthur Hubert, Gamal Elghazaly, Rapha\"el Frank
Abstract: Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to structure driving scenario representations in a layer model, we propose a structured five-layer model to improve the evaluation and generation of rare scenarios. We use this model alongside large foundational models to generate new driving scenarios using a data augmentation strategy. Unlike previous representations, our structure introduces subclasses and characteristics for every agent of the scenario, allowing us to compare them using an embedding specific to our layer-model. We study and adapt two metrics to evaluate the relevance of a synthetic dataset in the context of a structured representation: the diversity score estimates how different the scenarios of a dataset are from one another, while the originality score calculates how similar a synthetic dataset is from a real reference set. This paper showcases both metrics in different generation setup, as well as a qualitative evaluation of synthetic videos generated from structured scenario descriptions. The code and extended results can be found at https://github.com/Valgiz/5LMSG.
Authors: Ge Gao, Zishuo Gao, Hongyan Cui, Zhiyang Jia, Zhuang Luo, ChaoPeng Liu
Abstract: Occluded pedestrian re-identification (ReID) in base station environments is a critical task in computer vision, particularly for surveillance and security applications. This task faces numerous challenges, as occlusions often obscure key body features, increasing the complexity of identification. Traditional ResNet-based ReID algorithms often fail to address occlusions effectively, necessitating new ReID methods. We propose the PCD-ReID (Pedestrian Component Discrepancy) algorithm to address these issues. The contributions of this work are as follows: To tackle the occlusion problem, we design a Transformer-based PCD network capable of extracting shared component features, such as helmets and uniforms. To mitigate overfitting on public datasets, we collected new real-world patrol surveillance images for model training, covering six months, 10,000 individuals, and over 50,000 images. Comparative experiments with existing ReID algorithms demonstrate that our model achieves a mean Average Precision (mAP) of 79.0% and a Rank-1 accuracy of 82.7%, marking a 15.9% Rank-1 improvement over ResNet50-based methods. Experimental evaluations indicate that PCD-ReID effectively achieves occlusion-aware ReID performance for personnel in tower inspection scenarios, highlighting its potential for practical deployment in surveillance and security applications.
Authors: Mikhail Konov, Lion J. Gleiter, Khoa Co, Monica Yabal, Tingying Peng
Abstract: AI tools can greatly enhance the analysis of organoid microscopy images, from detection and segmentation to feature extraction and classification. However, their limited accessibility to biologists without programming experience remains a major barrier, resulting in labor-intensive and largely manual workflows. Although a few AI models for organoid analysis have been developed, most existing tools remain narrowly focused on specific tasks. In this work, we introduce the Napari Organoid Analyzer (NOA), a general purpose graphical user interface to simplify AI-based organoid analysis. NOA integrates modules for detection, segmentation, tracking, feature extraction, custom feature annotation and ML-based feature prediction. It interfaces multiple state-of-the-art algorithms and is implemented as an open-source napari plugin for maximal flexibility and extensibility. We demonstrate the versatility of NOA through three case studies, involving the quantification of morphological changes during organoid differentiation, assessment of phototoxicity effects, and prediction of organoid viability and differentiation state. Together, these examples illustrate how NOA enables comprehensive, AI-driven organoid image analysis within an accessible and extensible framework.
Authors: Wenqi Liang, Gan Sun, Yao He, Jiahua Dong, Suyan Dai, Ivan Laptev, Salman Khan, Yang Cong
Abstract: Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways: (i) they struggle with pixel-level scene understanding, and (ii) they rely heavily on textual prompts, which reduces their flexibility in real-world settings. To address these challenges, we introduce PixelVLA, the first VLA model designed to support both pixel-level reasoning and multimodal prompting with text and visual inputs. Our approach is built on a new visuomotor instruction tuning framework that integrates a multiscale pixel-aware encoder with a visual prompting encoder. To train PixelVLA effectively, we further propose a two-stage automated annotation pipeline that generates Pixel-160K, a large-scale dataset with pixel-level annotations derived from existing robot data. Experiments on three standard VLA benchmarks and two VLA model variants show that PixelVLA improves manipulation success rates by 10.1%-17.8% over OpenVLA, while requiring only 1.5% of its pretraining cost. These results demonstrate that PixelVLA can be integrated into existing VLAs to enable more accurate, efficient, and versatile robot control in complex environments. The dataset and code will be released as open source.
Authors: Md Sumon Ali, Muzammil Behzad
Abstract: Compared to traditional methods, Deep Learning (DL) becomes a key technology for computer vision tasks. Synthetic data generation is an interesting use case for DL, especially in the field of medical imaging such as Magnetic Resonance Imaging (MRI). The need for this task since the original MRI data is limited. The generation of realistic medical images is completely difficult and challenging. Generative Adversarial Networks (GANs) are useful for creating synthetic medical images. In this paper, we propose a DL based methodology for creating synthetic MRI data using the Deep Convolutional Generative Adversarial Network (DC-GAN) to address the problem of limited data. We also employ a Convolutional Neural Network (CNN) classifier to classify the brain tumor using synthetic data and real MRI data. CNN is used to evaluate the quality and utility of the synthetic images. The classification result demonstrates comparable performance on real and synthetic images, which validates the effectiveness of GAN-generated images for downstream tasks.
Authors: Yizhu Chen, Chen Ju, Zhicheng Wang, Shuai Xiao, Xu Chen, Jinsong Lan, Xiaoyong Zhu, Ying Chen
Abstract: The unification of understanding and generation within a single multi-modal large model (MLLM) remains one significant challenge, largely due to the dichotomy between continuous and discrete visual tokenizations. Continuous tokenizer (CT) achieves strong performance by bridging multiple independently-trained understanding modules and generation modules, but suffers from complex multi-stage pipelines and substantial engineering overhead. Conversely, discrete tokenizers (DT) offer a conceptually elegant idea by quantizing each image into a primitive, but inevitably leading to information loss and performance degradation. To resolve this tension, we question the binary choice between CT and DT, inspired by the wave-particle duality of light, and propose the Continuous-Discrete Dualistic Visual Tokenizer (CDD-VT). We treat visual data as a flexible composition of image primitives derived from quantized codebooks, with the crucial insight that the primitive number assigned to each visual sample is adaptively determined according to its complexity: simple instances use a few primitives, emulating discrete tokenization, while complex instances use many, approximating continuous tokenization. Two core components are designed: Diverse Quantitative Primitives, which encourage primitives orthogonality to better populate information space, and Dynamic Primitive Allocator, which assesses sample complexity to determine the optimal set of primitives. Extensive experiments on reconstruction, retrieval and classification show that CDD-VT achieves superior performance over to specialized CT and DT, effectively getting strong result within a concise and scalable MLLM.
Authors: Agnar Martin Bj{\o}rnstad, Elias Stenhede, Arian Ranjbar
Abstract: Accurate tumor size measurement is a cornerstone of evaluating cancer treatment response. The most widely adopted standard for this purpose is the Response Evaluation Criteria in Solid Tumors (RECIST) v1.1, which relies on measuring the longest tumor diameter in a single plane. However, volumetric measurements have been shown to provide a more reliable assessment of treatment effect. Their clinical adoption has been limited, though, due to the labor-intensive nature of manual volumetric annotation. In this paper, we present Lite ENSAM, a lightweight adaptation of the ENSAM architecture designed for efficient volumetric tumor segmentation from CT scans annotated with RECIST annotations. Lite ENSAM was submitted to the MICCAI FLARE 2025 Task 1: Pan-cancer Segmentation in CT Scans, Subtask 2, where it achieved a Dice Similarity Coefficient (DSC) of 60.7% and a Normalized Surface Dice (NSD) of 63.6% on the hidden test set, and an average total RAM time of 50.6 GBs and an average inference time of 14.4 s on CPU on the public validation dataset.
Authors: Mahmut Selman Gokmen, Cody Bumgardner
Abstract: Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications.
Authors: Tom\'a\v{s} Krsi\v{c}ka, Tibor Kub\'ik
Abstract: Progress in anatomical 3D shape classification is limited by the complexity of mesh data and the lack of standardized benchmarks, highlighting the need for robust learning methods and reproducible evaluation. We introduce two key steps toward clinically and benchmark-ready anatomical shape classification via self-supervised graph autoencoding. We propose Precomputed Structural Pooling (PSPooling), a non-learnable mesh pooling operator designed for efficient and structure-preserving graph coarsening in 3D anatomical shape analysis. PSPooling precomputes node correspondence sets based on geometric proximity, enabling parallelizable and reversible pooling and unpooling operations with guaranteed support structure. This design avoids the sparsity and reconstruction issues of selection-based methods and the sequential overhead of edge contraction approaches, making it particularly suitable for high-resolution medical meshes. To demonstrate its effectiveness, we integrate PSPooling into a self-supervised graph autoencoder that learns anatomy-aware representations from unlabeled surface meshes. We evaluate the downstream benefits on MedShapeNet19, a new curated benchmark dataset we derive from MedShapeNet, consisting of 19 anatomical classes with standardized training, validation, and test splits. Experiments show that PSPooling significantly improves reconstruction fidelity and classification accuracy in low-label regimes, establishing a strong baseline for medical 3D shape learning. We hope that MedShapeNet19 will serve as a widely adopted benchmark for anatomical shape classification and further research in medical 3D shape analysis. Access the complete codebase, model weights, and dataset information here: https://github.com/TomasKrsicka/MedShapeNet19-PSPooling.
URLs: https://github.com/TomasKrsicka/MedShapeNet19-PSPooling.
Authors: Mohamed Eltahir, Ali Habibullah, Lama Ayash, Tanveer Hussain, Naeemullah Khan
Abstract: In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they rely solely on rank or score signals, disregarding candidates' representations. This work introduces Vote-in-Context (ViC), a generalized, training-free framework that re-thinks list-wise reranking and fusion as a zero-shot reasoning task for a Vision-Language Model (VLM). The core insight is to serialize both content evidence and retriever metadata directly within the VLM's prompt, allowing the model to adaptively weigh retriever consensus against visual-linguistic content. We demonstrate the generality of this framework by applying it to the challenging domain of cross-modal video retrieval. To this end, we introduce the S-Grid, a compact serialization map that represents each video as an image grid, optionally paired with subtitles to enable list-wise reasoning over video candidates. ViC is evaluated both as a single-list reranker, where it dramatically improves the precision of individual retrievers, and as an ensemble fuser, where it consistently outperforms strong baselines like CombSUM. Across video retrieval benchmarks including ActivityNet and VATEX, the framework establishes new state-of-the-art zero-shot retrieval performance, demonstrating its effectiveness in handling complex visual and temporal signals alongside text. In zero-shot settings, ViC achieves Recall@1 scores of 87.1% (t2v) / 89.0% (v2t) on MSR-VTT and 99.6% (v2t) on VATEX, representing massive gains of up to +40 Recall@1 over previous state-of-the-art baselines. We present ViC as a simple, reproducible, and highly effective recipe for turning modern VLMs into powerful zero-shot rerankers and fusers. Code and resources are publicly available at: https://github.com/mohammad2012191/ViC
Authors: Xiaoyu Zhan, Wenxuan Huang, Hao Sun, Xinyu Fu, Changfeng Ma, Shaosheng Cao, Bohan Jia, Shaohui Lin, Zhenfei Yin, Lei Bai, Wanli Ouyang, Yuanqi Li, Jie Guo, Yanwen Guo
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.
Authors: Xiaogang Xu, Ruihang Chu, Jian Wang, Kun Zhou, Wenjie Shu, Harry Yang, Ser-Nam Lim, Hao Chen, Liang Lin
Abstract: Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-based image restoration models is suboptimal, as the objective of restoration fundamentally differs from that of pure generation: it places greater emphasis on fidelity. In this paper, we investigate how to effectively integrate RL into diffusion-based restoration models. First, through extensive experiments with various reward functions, we find that an effective reward can be derived from an Image Quality Assessment (IQA) model, instead of intuitive ground-truth-based supervision, which has already been optimized during the Supervised Fine-Tuning (SFT) stage prior to RL. Moreover, our strategy focuses on using RL for challenging samples that are significantly distant from the ground truth, and our RL approach is innovatively implemented using MLLM-based IQA models to align distributions with high-quality images initially. As the samples approach the ground truth's distribution, RL is adaptively combined with SFT for more fine-grained alignment. This dynamic process is facilitated through an automatic weighting strategy that adjusts based on the relative difficulty of the training samples. Our strategy is plug-and-play that can be seamlessly applied to diffusion-based restoration models, boosting its performance across various restoration tasks. Extensive experiments across multiple benchmarks demonstrate the effectiveness of our proposed RL framework.
Authors: Ropeway Liu, Hangjie Yuan, Bo Dong, Jiazheng Xing, Jinwang Wang, Rui Zhao, Yan Xing, Weihua Chen, Fan Wang
Abstract: Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results, such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom.
Authors: Yuhang Kang, Ziyu Su, Tianyang Wang, Zaibo Li, Wei Chen, Muhammad Khalid Khan Niazi
Abstract: Compared to hematoxylin-eosin (H&E) staining, immunohistochemistry (IHC) not only maintains the structural features of tissue samples, but also provides high-resolution protein localization, which is essential for aiding in pathology diagnosis. Despite its diagnostic value, IHC remains a costly and labor-intensive technique. Its limited scalability and constraints in multiplexing further hinder widespread adoption, especially in resource-limited settings. Consequently, researchers are increasingly exploring computational stain translation techniques to synthesize IHC-equivalent images from H&E-stained slides, aiming to extract protein-level information more efficiently and cost-effectively. However, most existing stain translation techniques rely on a linearly weighted summation of multiple loss terms within a single objective function, strategy that often overlooks the interdepedence among these components-resulting in suboptimal image quality and an inability to simultaneously preserve structural authenticity and color fidelity. To address this limitation, we propose a novel network architecture that follows a progressive structure, incorporating color and cell border generation logic, which enables each visual aspect to be optimized in a stage-wise and decoupled manner. To validate the effectiveness of our proposed network architecture, we build upon the Adaptive Supervised PatchNCE (ASP) framework as our baseline. We introduce additional loss functions based on 3,3'-diaminobenzidine (DAB) chromogen concentration and image gradient, enhancing color fidelity and cell boundary clarity in the generated IHC images. By reconstructing the generation pipeline using our structure-color-cell boundary progressive mechanism, experiments on HER2 and ER datasets demonstrated that the model significantly improved visual quality and achieved finer structural details.
Authors: Xin Qiao, Matteo Poggi, Xing Wei, Pengchao Deng, Yanhui Zhou, Stefano Mattoccia
Abstract: Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations-such as signal attenuation, multi-path interference (MPI), and temporal noise-that significantly compromise depth quality. To alleviate this drawback, we propose Learnable Fractional Reaction-Diffusion Dynamics (LFRD2), a hybrid framework that combines the expressive power of neural networks with the interpretability of physical modeling. Specifically, we implement a time-fractional reaction-diffusion module that enables iterative depth refinement with dynamically generated differential orders, capturing long-term dependencies. In addition, we introduce an efficient continuous convolution operator via coefficient prediction and repeated differentiation to further improve restoration quality. Experiments on four benchmark datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/wudiqx106/LFRD2.
Authors: Yi Zhang, Zheng Wang, Chen Zhen, Wenjie Ruan, Qing Guo, Siddartha Khastgir, Carsten Maple, Xingyu Zhao
Abstract: Deep learning models are notoriously vulnerable to imperceptible perturbations. Most existing research centers on adversarial robustness (AR), which evaluates models under worst-case scenarios by examining the existence of deterministic adversarial examples (AEs). In contrast, probabilistic robustness (PR) adopts a statistical perspective, measuring the probability that predictions remain correct under stochastic perturbations. While PR is widely regarded as a practical complement to AR, dedicated training methods for improving PR are still relatively underexplored, albeit with emerging progress. Among the few PR-targeted training methods, we identify three limitations: i non-comparable evaluation protocols; ii limited comparisons to strong AT baselines despite anecdotal PR gains from AT; and iii no unified framework to compare the generalization of these methods. Thus, we introduce PRBench, the first benchmark dedicated to evaluating improvements in PR achieved by different robustness training methods. PRBench empirically compares most common AT and PR-targeted training methods using a comprehensive set of metrics, including clean accuracy, PR and AR performance, training efficiency, and generalization error (GE). We also provide theoretical analysis on the GE of PR performance across different training methods. Main findings revealed by PRBench include: AT methods are more versatile than PR-targeted training methods in terms of improving both AR and PR performance across diverse hyperparameter settings, while PR-targeted training methods consistently yield lower GE and higher clean accuracy. A leaderboard comprising 222 trained models across 7 datasets and 10 model architectures is publicly available at https://tmpspace.github.io/PRBenchLeaderboard/.
Authors: Tom Odem
Abstract: This research builds on work in anticipatory human-machine interaction, a subfield of human-machine interaction where machines can facilitate advantageous interactions by anticipating a user's future state. The aim of this research is to further a machine's understanding of user knowledge, skill, and behavior in pursuit of implicit coordination. A task explorer pipeline was developed that uses clustering techniques, paired with factor analysis and string edit distance, to automatically identify key global and local strategies that are used to complete tasks. Global strategies identify generalized sets of actions used to complete tasks, while local strategies identify sequences that used those sets of actions in a similar composition. Additionally, meaningful subtasks of various lengths are identified within the tasks. The task explorer pipeline was able to automatically identify key strategies used to complete tasks and encode user runs with hierarchical subtask structures. In addition, a Task Explorer application was developed to easily review pipeline results. The task explorer pipeline can be easily modified to any action-based time-series data and the identified strategies and subtasks help to inform humans and machines on user knowledge, skill, and behavior.
Authors: Yefeng Wu, Yucheng Song, Ling Wu, Shan Wan, Yecheng Zhao
Abstract: Pneumonia remains a leading cause of morbidity and mortality worldwide, necessitating accurate and efficient automated detection systems. While recent transformer-based detectors like RT-DETR have shown promise in object detection tasks, their application to medical imaging, particularly pneumonia detection in chest X-rays, remains underexplored. This paper presents CGF-DETR, an enhanced real-time detection transformer specifically designed for pneumonia detection. We introduce XFABlock in the backbone to improve multi-scale feature extraction through convolutional attention mechanisms integrated with CSP architecture. To achieve efficient feature aggregation, we propose SPGA module that replaces standard multi-head attention with dynamic gating mechanisms and single-head self-attention. Additionally, GCFC3 is designed for the neck to enhance feature representation through multi-path convolution fusion while maintaining real-time performance via structural re-parameterization. Extensive experiments on the RSNA Pneumonia Detection dataset demonstrate that CGF-DETR achieves 82.2\% mAP@0.5, outperforming the baseline RT-DETR-l by 3.7\% while maintaining comparable inference speed at 48.1 FPS. Our ablation studies confirm that each proposed module contributes meaningfully to the overall performance improvement, with the complete model achieving 50.4\% mAP@[0.5:0.95]
Authors: Rong Li, Yuhao Dong, Tianshuai Hu, Ao Liang, Youquan Liu, Dongyue Lu, Liang Pan, Lingdong Kong, Junwei Liang, Ziwei Liu
Abstract: Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce 3EED, a multi-platform, multi-modal 3D grounding benchmark featuring RGB and LiDAR data from vehicle, drone, and quadruped platforms. We provide over 128,000 objects and 22,000 validated referring expressions across diverse outdoor scenes -- 10x larger than existing datasets. We develop a scalable annotation pipeline combining vision-language model prompting with human verification to ensure high-quality spatial grounding. To support cross-platform learning, we propose platform-aware normalization and cross-modal alignment techniques, and establish benchmark protocols for in-domain and cross-platform evaluations. Our findings reveal significant performance gaps, highlighting the challenges and opportunities of generalizable 3D grounding. The 3EED dataset and benchmark toolkit are released to advance future research in language-driven 3D embodied perception.
Authors: Kai Zhai, Ziyan Huang, Qiang Nie, Xiang Li, Bo Ouyang
Abstract: 2D-to-3D human pose lifting is a fundamental challenge for 3D human pose estimation in monocular video, where graph convolutional networks (GCNs) and attention mechanisms have proven to be inherently suitable for encoding the spatial-temporal correlations of skeletal joints. However, depth ambiguity and errors in 2D pose estimation lead to incoherence in the 3D trajectory. Previous studies have attempted to restrict jitters in the time domain, for instance, by constraining the differences between adjacent frames while neglecting the global spatial-temporal correlations of skeletal joint motion. To tackle this problem, we design HGFreNet, a novel GraphFormer architecture with hop-hybrid feature aggregation and 3D trajectory consistency in the frequency domain. Specifically, we propose a hop-hybrid graph attention (HGA) module and a Transformer encoder to model global joint spatial-temporal correlations. The HGA module groups all $k$-hop neighbors of a skeletal joint into a hybrid group to enlarge the receptive field and applies the attention mechanism to discover the latent correlations of these groups globally. We then exploit global temporal correlations by constraining trajectory consistency in the frequency domain. To provide 3D information for depth inference across frames and maintain coherence over time, a preliminary network is applied to estimate the 3D pose. Extensive experiments were conducted on two standard benchmark datasets: Human3.6M and MPI-INF-3DHP. The results demonstrate that the proposed HGFreNet outperforms state-of-the-art (SOTA) methods in terms of positional accuracy and temporal consistency.
Authors: Yuxiao Yang, Xiao-Xiao Long, Zhiyang Dou, Cheng Lin, Yuan Liu, Qingsong Yan, Yuexin Ma, Haoqian Wang, Zhiqiang Wu, Wei Yin
Abstract: In this work, we introduce \textbf{Wonder3D++}, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about $3$ minute in a coarse-to-fine manner. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works. Code available at https://github.com/xxlong0/Wonder3D/tree/Wonder3D_Plus.
URLs: https://github.com/xxlong0/Wonder3D/tree/Wonder3D_Plus.
Authors: Zhe Liu, Jinghua Hou, Xiaoqing Ye, Jingdong Wang, Hengshuang Zhao, Xiang Bai
Abstract: Although transformers have demonstrated remarkable capabilities across various domains, their quadratic attention mechanisms introduce significant computational overhead when processing long-sequence data. In this paper, we present a unified autonomous driving model, UniLION, which efficiently handles large-scale LiDAR point clouds, high-resolution multi-view images, and even temporal sequences based on the linear group RNN operator (i.e., performs linear RNN for grouped features). Remarkably, UniLION serves as a single versatile architecture that can seamlessly support multiple specialized variants (i.e., LiDAR-only, temporal LiDAR, multi-modal, and multi-modal temporal fusion configurations) without requiring explicit temporal or multi-modal fusion modules. Moreover, UniLION consistently delivers competitive and even state-of-the-art performance across a wide range of core tasks, including 3D perception (e.g., 3D object detection, 3D object tracking, 3D occupancy prediction, BEV map segmentation), prediction (e.g., motion prediction), and planning (e.g., end-to-end planning). This unified paradigm naturally simplifies the design of multi-modal and multi-task autonomous driving systems while maintaining superior performance. Ultimately, we hope UniLION offers a fresh perspective on the development of 3D foundation models in autonomous driving. Code is available at https://github.com/happinesslz/UniLION
Authors: Zhen Chen, Qing Xu, Jinlin Wu, Biao Yang, Yuhao Zhai, Geng Guo, Jing Zhang, Yinlu Ding, Nassir Navab, Jiebo Luo
Abstract: Foundation models in video generation are demonstrating remarkable capabilities as potential world models for simulating the physical world. However, their application in high-stakes domains like surgery, which demand deep, specialized causal knowledge rather than general physical rules, remains a critical unexplored gap. To systematically address this challenge, we present SurgVeo, the first expert-curated benchmark for video generation model evaluation in surgery, and the Surgical Plausibility Pyramid (SPP), a novel, four-tiered framework tailored to assess model outputs from basic appearance to complex surgical strategy. On the basis of the SurgVeo benchmark, we task the advanced Veo-3 model with a zero-shot prediction task on surgical clips from laparoscopic and neurosurgical procedures. A panel of four board-certified surgeons evaluates the generated videos according to the SPP. Our results reveal a distinct "plausibility gap": while Veo-3 achieves exceptional Visual Perceptual Plausibility, it fails critically at higher levels of the SPP, including Instrument Operation Plausibility, Environment Feedback Plausibility, and Surgical Intent Plausibility. This work provides the first quantitative evidence of the chasm between visually convincing mimicry and causal understanding in surgical AI. Our findings from SurgVeo and the SPP establish a crucial foundation and roadmap for developing future models capable of navigating the complexities of specialized, real-world healthcare domains.
Authors: Tejas Sarnaik, Manan Shah, Ravi Hegde
Abstract: Retrieval-Augmented Generation (RAG) has become a robust framework for enhancing Large Language Models (LLMs) with external knowledge. Recent advances in RAG have investigated graph based retrieval for intricate reasoning; however, the influence of prompt design on enhancing the retrieval and reasoning process is still considerably under-examined. In this paper, we present a prompt-driven GraphRAG framework that underscores the significance of prompt formulation in facilitating entity extraction, fact selection, and passage reranking for multi-hop question answering. Our approach creates a symbolic knowledge graph from text data by encoding entities and factual relationships as structured facts triples. We use LLMs selectively during online retrieval to perform semantic filtering and answer generation. We also use entity-guided graph traversal through Personalized PageRank (PPR) to support efficient, scalable retrieval based on the knowledge graph we built. Our system gets state-of-the-art performance on HotpotQA and 2WikiMultiHopQA, with F1 scores of 80.7% and 78.9%, and Recall@5 scores of 97.1% and 98.1%, respectively. These results show that prompt design is an important part of improving retrieval accuracy and response quality. This research lays the groundwork for more efficient and comprehensible multi-hop question-answering systems, highlighting the importance of prompt-aware graph reasoning.
Authors: Sagi Eppel, Alona Strugatski
Abstract: The ability to connect visual patterns with the processes that form them represents one of the deepest forms of visual understanding. Textures of clouds and waves, the growth of cities and forests, or the formation of materials and landscapes are all examples of patterns emerging from underlying mechanisms. We present the Scitextures dataset, a large-scale collection of textures and visual patterns from all domains of science, tech, and art, along with the models and code that generate these images. Covering over 1,200 different models and 100,000 images of patterns and textures from physics, chemistry, biology, sociology, technology, mathematics, and art, this dataset offers a way to explore the connection between the visual patterns that shape our world and the mechanisms that produce them. Created by an agentic AI pipeline that autonomously collects and implements models in standardized form, we use SciTextures to evaluate the ability of leading AI models to link visual patterns to the models and code that generate them, and to identify different patterns that emerged from the same process. We also test AIs ability to infer and recreate the mechanisms behind visual patterns by providing a natural image of a real-world pattern and asking the AI to identify, model, and code the mechanism that formed the pattern, then run this code to generate a simulated image that is compared to the real image. These benchmarks show that vision-language models (VLMs) can understand and simulate the physical system beyond a visual pattern. The dataset and code are available at: https://zenodo.org/records/17485502
Authors: Ming Li, Jike Zhong, Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Yuxiang Lai, Wei Chen, Konstantinos Psounis, Kaipeng Zhang
Abstract: The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as thinking-\textit{with}-images in chain-of-thought. Yet existing benchmarks fail to fully capture this advanced capability. Even Visual Search, the most common benchmark for current thinking-\textit{with}-images methods, tests only basic operations such as localization and cropping, offering little insight into more complex, dynamic, and tool-dependent reasoning. We introduce \textbf{TIR-Bench}, a comprehensive benchmark for evaluating agentic thinking-with-images across 13 diverse tasks, each requiring novel tool use for image processing and manipulation in chain-of-thought. We evaluate 22 multimodal large language models (MLLMs), from leading open-sourced and proprietary models to those with explicit tool-use augmentation. Results show that TIR-Bench is universally challenging, and strong performance requires genuine thinking-with-images capabilities. Finally, we present a pilot study comparing direct versus agentic fine-tuning.
Authors: Yurun Wu, Yousong Sun, Burkhard Wunsche, Jia Wang, Elliott Wen
Abstract: Virtual Reality (VR) has rapidly become a mainstream platform for gaming and interactive experiences, yet ensuring the quality, safety, and appropriateness of VR content remains a pressing challenge. Traditional human-based quality assurance is labor-intensive and cannot scale with the industry's rapid growth. While automated testing has been applied to traditional 2D and 3D games, extending it to VR introduces unique difficulties due to high-dimensional sensory inputs and strict real-time performance requirements. We present VRScout, a deep learning-based agent capable of autonomously navigating VR environments and interacting with virtual objects in a human-like and real-time manner. VRScout learns from human demonstrations using an enhanced Action Chunking Transformer that predicts multi-step action sequences. This enables our agent to capture higher-level strategies and generalize across diverse environments. To balance responsiveness and precision, we introduce a dynamically adjustable sliding horizon that adapts the agent's temporal context at runtime. We evaluate VRScout on commercial VR titles and show that it achieves expert-level performance with only limited training data, while maintaining real-time inference at 60 FPS on consumer-grade hardware. These results position VRScout as a practical and scalable framework for automated VR game testing, with direct applications in both quality assurance and safety auditing.
Authors: Adrian-Dinu Urse, Dumitru-Clementin Cercel, Florin Pop
Abstract: Natural disaster assessment relies on accurate and rapid access to information, with social media emerging as a valuable real-time source. However, existing datasets suffer from class imbalance and limited samples, making effective model development a challenging task. This paper explores augmentation techniques to address these issues on the CrisisMMD multimodal dataset. For visual data, we apply diffusion-based methods, namely Real Guidance and DiffuseMix. For text data, we explore back-translation, paraphrasing with transformers, and image caption-based augmentation. We evaluated these across unimodal, multimodal, and multi-view learning setups. Results show that selected augmentations improve classification performance, particularly for underrepresented classes, while multi-view learning introduces potential but requires further refinement. This study highlights effective augmentation strategies for building more robust disaster assessment systems.
Authors: Suhasnadh Reddy Veluru, Sai Teja Erukude, Viswa Chaitanya Marella
Abstract: In the current digital commerce landscape, user-generated reviews play a critical role in shaping consumer behavior, product reputation, and platform credibility. However, the proliferation of fake or misleading reviews often generated by bots, paid agents, or AI models poses a significant threat to trust and transparency within review ecosystems. Existing detection models primarily rely on unimodal, typically textual, data and therefore fail to capture semantic inconsistencies across different modalities. To address this gap, a robust multimodal fake review detection framework is proposed, integrating textual features encoded with BERT and visual features extracted using ResNet-50. These representations are fused through a classification head to jointly predict review authenticity. To support this approach, a curated dataset comprising 21,142 user-uploaded images across food delivery, hospitality, and e-commerce domains was utilized. Experimental results indicate that the multimodal model outperforms unimodal baselines, achieving an F1-score of 0.934 on the test set. Additionally, the confusion matrix and qualitative analysis highlight the model's ability to detect subtle inconsistencies, such as exaggerated textual praise paired with unrelated or low-quality images, commonly found in deceptive content. This study demonstrates the critical role of multimodal learning in safeguarding digital trust and offers a scalable solution for content moderation across various online platforms.
Authors: Pradeep M, Ritesh Pallod, Satyen Abrol, Muthu Raman, Ian Anderson
Abstract: Generative AI is reshaping fashion by enabling virtual looks and avatars making it essential to find real products that best match AI-generated styles. We propose an end-to-end product search system that has been deployed in a real-world, internet scale which ensures that AI-generated looks presented to users are matched with the most visually and semantically similar products from the indexed vector space. The search pipeline is composed of four key components: query generation, vectorization, candidate retrieval, and reranking based on AI-generated looks. Recommendation quality is evaluated using human-judged accuracy scores. The system currently serves more than 350,000 AI Looks in production per day, covering diverse product categories across global markets of over 12 million products. In our experiments, we observed that across multiple annotators and categories, CLIP outperformed alternative models by a small relative margin of 3--7\% in mean opinion scores. These improvements, though modest in absolute numbers, resulted in noticeably better user perception matches, establishing CLIP as the most reliable backbone for production deployment.
Authors: Marios Impraimakis, Evangelia Nektaria Palkanoglou
Abstract: The optimization-based damage detection and damage state digital twinning capabilities are examined here of a novel conditional-labeled generative adversarial network methodology. The framework outperforms current approaches for fault anomaly detection as no prior information is required for the health state of the system: a topic of high significance for real-world applications. Specifically, current artificial intelligence-based digital twinning approaches suffer from the uncertainty related to obtaining poor predictions when a low number of measurements is available, physics knowledge is missing, or when the damage state is unknown. To this end, an unsupervised framework is examined and validated rigorously on the benchmark structural health monitoring measurements of Z24 Bridge: a post-tensioned concrete highway bridge in Switzerland. In implementing the approach, firstly, different same damage-level measurements are used as inputs, while the model is forced to converge conditionally to two different damage states. Secondly, the process is repeated for a different group of measurements. Finally, the convergence scores are compared to identify which one belongs to a different damage state. The process for both healthy-to-healthy and damage-to-healthy input data creates, simultaneously, measurements for digital twinning purposes at different damage states, capable of pattern recognition and machine learning data generation. Further to this process, a support vector machine classifier and a principal component analysis procedure is developed to assess the generated and real measurements of each damage category, serving as a secondary new dynamics learning indicator in damage scenarios. Importantly, the approach is shown to capture accurately damage over healthy measurements, providing a powerful tool for vibration-based system-level monitoring and scalable infrastructure resilience.
Authors: Marios Impraimakis
Abstract: The dynamic structural load identification capabilities of the gated recurrent unit, long short-term memory, and convolutional neural networks are examined herein. The examination is on realistic small dataset training conditions and on a comparative view to the physics-based residual Kalman filter (RKF). The dynamic load identification suffers from the uncertainty related to obtaining poor predictions when in civil engineering applications only a low number of tests are performed or are available, or when the structural model is unidentifiable. In considering the methods, first, a simulated structure is investigated under a shaker excitation at the top floor. Second, a building in California is investigated under seismic base excitation, which results in loading for all degrees of freedom. Finally, the International Association for Structural Control-American Society of Civil Engineers (IASC-ASCE) structural health monitoring benchmark problem is examined for impact and instant loading conditions. Importantly, the methods are shown to outperform each other on different loading scenarios, while the RKF is shown to outperform the networks in physically parametrized identifiable cases.
Authors: Mengbo Wang, Shourya Verma, Aditya Malusare, Luopin Wang, Yiyang Lu, Vaneet Aggarwal, Mario Sola, Ananth Grama, Nadia Atallah Lanman
Abstract: Spatial transcriptomics (ST) technologies can be used to align transcriptomes with histopathological morphology, presenting exciting new opportunities for biomolecular discovery. Using ST data, we construct a novel framework, GeneFlow, to map transcriptomics onto paired cellular images. By combining an attention-based RNA encoder with a conditional UNet guided by rectified flow, we generate high-resolution images with different staining methods (e.g. H&E, DAPI) to highlight various cellular/tissue structures. Rectified flow with high-order ODE solvers creates a continuous, bijective mapping between transcriptomics and image manifolds, addressing the many-to-one relationship inherent in this problem. Our method enables the generation of realistic cellular morphology features and spatially resolved intercellular interactions from observational gene expression profiles, provides potential to incorporate genetic/chemical perturbations, and enables disease diagnosis by revealing dysregulated patterns in imaging phenotypes. Our rectified flow-based method outperforms diffusion-based baseline method in all experiments. Code can be found at https://github.com/wangmengbo/GeneFlow.
Authors: Wadduwage Shanika Perera, ABM Islam, Van Vung Pham, Min Kyung An
Abstract: Melanoma is one of the most aggressive and deadliest skin cancers, leading to mortality if not detected and treated in the early stages. Artificial intelligence techniques have recently been developed to help dermatologists in the early detection of melanoma, and systems based on deep learning (DL) have been able to detect these lesions with high accuracy. However, the entire community must overcome the explainability limit to get the maximum benefit from DL for diagnostics in the healthcare domain. Because of the black box operation's shortcomings in DL models' decisions, there is a lack of reliability and trust in the outcomes. However, Explainable Artificial Intelligence (XAI) can solve this problem by interpreting the predictions of AI systems. This paper proposes a machine learning model using ensemble learning of three state-of-the-art deep transfer Learning networks, along with an approach to ensure the reliability of the predictions by utilizing XAI techniques to explain the basis of the predictions.
Authors: Abhinav Joshi, Vaibhav Sharma, Sanjeet Singh, Ashutosh Modi
Abstract: Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.
Authors: Lingpeng Chen, Jiakun Tang, Apple Pui-Yi Chui, Ziyang Hong, Junfeng Wu
Abstract: Accurate 3D reconstruction in visually-degraded underwater environments remains a formidable challenge. Single-modality approaches are insufficient: vision-based methods fail due to poor visibility and geometric constraints, while sonar is crippled by inherent elevation ambiguity and low resolution. Consequently, prior fusion technique relies on heuristics and flawed geometric assumptions, leading to significant artifacts and an inability to model complex scenes. In this paper, we introduce SonarSweep, a novel, end-to-end deep learning framework that overcomes these limitations by adapting the principled plane sweep algorithm for cross-modal fusion between sonar and visual data. Extensive experiments in both high-fidelity simulation and real-world environments demonstrate that SonarSweep consistently generates dense and accurate depth maps, significantly outperforming state-of-the-art methods across challenging conditions, particularly in high turbidity. To foster further research, we will publicly release our code and a novel dataset featuring synchronized stereo-camera and sonar data, the first of its kind.
Authors: Zenghao Niu, Weicheng Xie, Siyang Song, Zitong Yu, Feng Liu, Linlin Shen
Abstract: Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma between Exploitation (maximizing attack potency) and Exploration (enhancing cross-model generalization). Traditional momentum-based methods over-prioritize Exploitation, i.e., higher loss maxima for attack potency but weakened generalization (narrow loss surface). Conversely, recent methods with inner-iteration sampling over-prioritize Exploration, i.e., flatter loss surfaces for cross-model generalization but weakened attack potency (suboptimal local maxima). To resolve this dilemma, we propose a simple yet effective Gradient-Guided Sampling (GGS), which harmonizes both objectives through guiding sampling along the gradient ascent direction to improve both sampling efficiency and stability. Specifically, based on MI-FGSM, GGS introduces inner-iteration random sampling and guides the sampling direction using the gradient from the previous inner-iteration (the sampling's magnitude is determined by a random distribution). This mechanism encourages adversarial examples to reside in balanced regions with both flatness for cross-model generalization and higher local maxima for strong attack potency. Comprehensive experiments across multiple DNN architectures and multimodal large language models (MLLMs) demonstrate the superiority of our method over state-of-the-art transfer attacks. Code is made available at https://github.com/anuin-cat/GGS.
Authors: Ruthwik Reddy Doodipala, Pankaj Pandey, Carolina Torres Rojas, Manob Jyoti Saikia, Ranganatha Sitaram
Abstract: The emergence of foundation models in neuroimaging is driven by the increasing availability of large-scale and heterogeneous brain imaging datasets. Recent advances in self-supervised learning, particularly reconstruction-based objectives, have demonstrated strong potential for pretraining models that generalize effectively across diverse downstream functional MRI (fMRI) tasks. In this study, we explore region-aware reconstruction strategies for a foundation model in resting-state fMRI, moving beyond approaches that rely on random region masking. Specifically, we introduce an ROI-guided masking strategy using the Automated Anatomical Labelling Atlas (AAL3), applied directly to full 4D fMRI volumes to selectively mask semantically coherent brain regions during self-supervised pretraining. Using the ADHD-200 dataset comprising 973 subjects with resting-state fMRI scans, we show that our method achieves a 4.23% improvement in classification accuracy for distinguishing healthy controls from individuals diagnosed with ADHD, compared to conventional random masking. Region-level attribution analysis reveals that brain volumes within the limbic region and cerebellum contribute most significantly to reconstruction fidelity and model representation. Our results demonstrate that masking anatomical regions during model pretraining not only enhances interpretability but also yields more robust and discriminative representations. In future work, we plan to extend this approach by evaluating it on additional neuroimaging datasets, and developing new loss functions explicitly derived from region-aware reconstruction objectives. These directions aim to further improve the robustness and interpretability of foundation models for functional neuroimaging.
Authors: Xiaolong Li, Zhi-Qin John Xu, Yan Ren, Tianming Qiu, Xiaowen Wang
Abstract: Accurate segmentation of pediatric brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is critical for diagnosis, treatment planning, and monitoring, yet faces unique challenges due to limited data, high anatomical variability, and heterogeneous imaging across institutions. In this work, we present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest public dataset of pre-treatment pediatric high-grade gliomas. Our contributions include: (1) a widened residual encoder with squeeze-and-excitation (SE) attention; (2) 3D depthwise separable convolutions; (3) a specificity-driven regularization term; and (4) small-scale Gaussian weight initialization. We further refine predictions with two postprocessing steps. Our models achieved first place on the Task-6 validation leaderboard, attaining lesion-wise Dice scores of 0.759 (CC), 0.967 (ED), 0.826 (ET), 0.910 (NET), 0.928 (TC) and 0.928 (WT).
Authors: Aditya Parikh, Sneha Das, Aasa Feragen
Abstract: Algorithmic bias in medical imaging can perpetuate health disparities, yet its causes remain poorly understood in segmentation tasks. While fairness has been extensively studied in classification, segmentation remains underexplored despite its clinical importance. In breast cancer segmentation, models exhibit significant performance disparities against younger patients, commonly attributed to physiological differences in breast density. We audit the MAMA-MIA dataset, establishing a quantitative baseline of age-related bias in its automated labels, and reveal a critical Biased Ruler effect where systematically flawed labels for validation misrepresent a model's actual bias. However, whether this bias originates from lower-quality annotations (label bias) or from fundamentally more challenging image characteristics remains unclear. Through controlled experiments, we systematically refute hypotheses that the bias stems from label quality sensitivity or quantitative case difficulty imbalance. Balancing training data by difficulty fails to mitigate the disparity, revealing that younger patient cases are intrinsically harder to learn. We provide direct evidence that systemic bias is learned and amplified when training on biased, machine-generated labels, a critical finding for automated annotation pipelines. This work introduces a systematic framework for diagnosing algorithmic bias in medical segmentation and demonstrates that achieving fairness requires addressing qualitative distributional differences rather than merely balancing case counts.
Authors: Renjun Gao, Xiangjie Kong, Dongting Cai, Boyi Fu, Junxiang Yang
Abstract: Reconstruction of an object from points cloud is essential in prosthetics, medical imaging, computer vision, etc. We present an effective algorithm for an Allen--Cahn-type model of reconstruction, employing the Lagrange multiplier approach. Utilizing scattered data points from an object, we reconstruct a narrow shell by solving the governing equation enhanced with an edge detection function derived from the unsigned distance function. The specifically designed edge detection function ensures the energy stability. By reformulating the governing equation through the Lagrange multiplier technique and implementing a Crank--Nicolson time discretization, we can update the solutions in a stable and decoupled manner. The spatial operations are approximated using the finite difference method, and we analytically demonstrate the unconditional stability of the fully discrete scheme. Comprehensive numerical experiments, including reconstructions of complex 3D volumes such as characters from \textit{Star Wars}, validate the algorithm's accuracy, stability, and effectiveness. Additionally, we analyze how specific parameter selections influence the level of detail and refinement in the reconstructed volumes. To facilitate the interested readers to understand our algorithm, we share the computational codes and data in https://github.com/cfdyang521/C-3PO/tree/main.
Authors: Yunchuan Guan, Yu Liu, Ke Zhou, Hui Li, Sen Jia, Zhiqi Shen, Ziyang Wang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li
Abstract: Recent advances in generative modeling enable neural networks to generate weights without relying on gradient-based optimization. However, current methods are limited by issues of over-coupling and long-horizon. The former tightly binds weight generation with task-specific objectives, thereby limiting the flexibility of the learned optimizer. The latter leads to inefficiency and low accuracy during inference, caused by the lack of local constraints. In this paper, we propose Lo-Hp, a decoupled two-stage weight generation framework that enhances flexibility through learning various optimization policies. It adopts a hybrid-policy sub-trajectory balance objective, which integrates on-policy and off-policy learning to capture local optimization policies. Theoretically, we demonstrate that learning solely local optimization policies can address the long-horizon issue while enhancing the generation of global optimal weights. In addition, we validate Lo-Hp's superior accuracy and inference efficiency in tasks that require frequent weight updates, such as transfer learning, few-shot learning, domain generalization, and large language model adaptation.
Authors: Baochao Wang, Xingyu Zhang, Qingtao Zong, Alim Pulatov, Shuqi Shang, Dongwei Wang
Abstract: Conservation agriculture features a soil surface covered with crop residues, which brings benefits of improving soil health and saving water. However, one significant challenge in conservation agriculture lies in precisely controlling the seeding depth on the soil covered with crop residues. This is constrained by the lack of ground distance information, since current distance measurement techniques, like laser, ultrasonic, or mechanical displacement sensors, are incapable of differentiating whether the distance information comes from the residue or the soil. This paper presents an image-based method to get the ground distance information for the crop-residues-covered soil. This method is performed with 3D camera and RGB camera, obtaining depth image and color image at the same time. The color image is used to distinguish the different areas of residues and soil and finally generates a mask image. The mask image is applied to the depth image so that only the soil area depth information can be used to calculate the ground distance, and residue areas can be recognized and excluded from ground distance detection. Experimentation shows that this distance measurement method is feasible for real-time implementation, and the measurement error is within plus or minus 3mm. It can be applied in conservation agriculture machinery for precision depth seeding, as well as other depth-control-demanding applications like transplant or tillage.
Authors: Zixuan Sun, Shuaifeng Zhi, Ruize Li, Jingyuan Xia, Yongxiang Liu, Weidong Jiang
Abstract: Registration of optical and synthetic aperture radar (SAR) remote sensing images serves as a critical foundation for image fusion and visual navigation tasks. This task is particularly challenging because of their modal discrepancy, primarily manifested as severe nonlinear radiometric differences (NRD), geometric distortions, and noise variations. Under large geometric transformations, existing classical template-based and sparse keypoint-based strategies struggle to achieve reliable registration results for optical-SAR image pairs. To address these limitations, we propose GDROS, a geometry-guided dense registration framework leveraging global cross-modal image interactions. First, we extract cross-modal deep features from optical and SAR images through a CNN-Transformer hybrid feature extraction module, upon which a multi-scale 4D correlation volume is constructed and iteratively refined to establish pixel-wise dense correspondences. Subsequently, we implement a least squares regression (LSR) module to geometrically constrain the predicted dense optical flow field. Such geometry guidance mitigates prediction divergence by directly imposing an estimated affine transformation on the final flow predictions. Extensive experiments have been conducted on three representative datasets WHU-Opt-SAR dataset, OS dataset, and UBCv2 dataset with different spatial resolutions, demonstrating robust performance of our proposed method across different imaging resolutions. Qualitative and quantitative results show that GDROS significantly outperforms current state-of-the-art methods in all metrics. Our source code will be released at: https://github.com/Zi-Xuan-Sun/GDROS.
Authors: Ali Khalid, Jaiaid Mobin, Sumanth Rao Appala, Avinash Maurya, Stephany Berrio Perez, M. Mustafa Rafique, Fawad Ahmad
Abstract: An autonomous vehicle can generate several terabytes of sensor data per day. A significant portion of this data consists of 3D point clouds produced by depth sensors such as LiDARs. This data must be transferred to cloud storage, where it is utilized for training machine learning models or conducting analyses, such as forensic investigations in the event of an accident. To reduce network and storage costs, this paper introduces DejaView. Although prior work uses interframe redundancies to compress data, DejaView searches for and uses redundancies on larger temporal scales (days and months) for more effective compression. We designed DejaView with the insight that the operating area of autonomous vehicles is limited and that vehicles mostly traverse the same routes daily. Consequently, the 3D data they collect daily is likely similar to the data they have captured in the past. To capture this, the core of DejaView is a diff operation that compactly represents point clouds as delta w.r.t. 3D data from the past. Using two months of LiDAR data, an end-to-end implementation of DejaView can compress point clouds by a factor of 210 at a reconstruction error of only 15 cm.
Authors: Alberto Di Biase
Abstract: Doctors and researchers routinely use diffusion tensor imaging (DTI) and tractography to visualize the fibrous structure of tissues in the human body. This paper explores the connection of these techniques to the painterly rendering of images. Using a tractography algorithm the presented method can place brush strokes that mimic the painting process of human artists, analogously to how fibres are tracked in DTI. The analogue to the diffusion tensor for image orientation is the structural tensor, which can provide better local orientation information than the gradient alone. I demonstrate this technique in portraits and general images, and discuss the parallels between fibre tracking and brush stroke placement, and frame it in the language of tractography. This work presents an exploratory investigation into the cross-domain application of diffusion tensor imaging techniques to painterly rendering of images. All the code is available at https://github.com/tito21/st-python
Authors: Abhiram Kusumba, Maitreya Patel, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang
Abstract: Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image quality, rely on brittle adversarial losses, or demand prohibitive retraining cycles. We trace these limitations to a myopic view of the denoising trajectories that govern diffusion based generation. We introduce EraseFlow, the first framework that casts concept unlearning as exploration in the space of denoising paths and optimizes it with GFlowNets equipped with the trajectory balance objective. By sampling entire trajectories rather than single end states, EraseFlow learns a stochastic policy that steers generation away from target concepts while preserving the model's prior. EraseFlow eliminates the need for carefully crafted reward models and by doing this, it generalizes effectively to unseen concepts and avoids hackable rewards while improving the performance. Extensive empirical results demonstrate that EraseFlow outperforms existing baselines and achieves an optimal trade off between performance and prior preservation.
Authors: Shashank Nag, Alan T. L. Bacellar, Zachary Susskind, Anshul Jha, Logan Liberty, Aishwarya Sivakumar, Eugene B. John, Krishnan Kailas, Priscila M. V. Lima, Neeraja J. Yadwadkar, Felipe M. G. Franca, Lizy K. John
Abstract: Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We recognize the benefits of recent works on logic and Look Up Table (LUT) based networks, such as LogicNets, NeuraLUT, DWN, among others, in offering models that simultaneously reduce both the memory and compute footprints. However, these models natively do not perform well on common vision tasks, such as CIFAR-10/100. In this work, we propose LL-ViT, a novel edge optimized vision transformer design that integrates layers of LUT neurons within the transformer architecture. Based on our characterization that reveals that a majority of model weights and computations are from the channel mixer (MLP layer), we design an alternate LUT-based channel mixer, and simultaneously develop an FPGA-based accelerator for LL-ViT. Contrary to some attempts to replace each multiplication with a table lookup, our architecture utilizes a neural learning approach which natively learns the LUT functions. This approach allows for reduced model sizes, and a computational and energy-efficient inference solution for vision transformer models. Evaluating on edge-suitable workloads, we achieve accuracies of 95.5% on CIFAR-10, 78.8% on CIFAR-100, and 60.9% on Tiny-ImageNet datasets, comparable to the baseline transformer. LL-ViT eliminates over 60% of the model weights and 50% of the multiplications in the model, and achieves 1.9x energy efficiency and 1.3x lower latency over an integer quantized ViT accelerator, while also offering superior throughput against prior works at a 10.9W power budget.
Authors: Yoshihiro Maruyama
Abstract: Human activity recognition is challenging because sensor signals shift with context, motion, and environment; effective models must therefore remain stable as the world around them changes. We introduce a categorical symmetry-aware learning framework that captures how signals vary over time, scale, and sensor hierarchy. We build these factors into the structure of feature representations, yielding models that automatically preserve the relationships between sensors and remain stable under realistic distortions such as time shifts, amplitude drift, and device orientation changes. On the UCI Human Activity Recognition benchmark, this categorical symmetry-driven design improves out-of-distribution accuracy by approx. 46 percentage points (approx. 3.6x over the baseline), demonstrating that abstract symmetry principles can translate into concrete performance gains in everyday sensing tasks via category-equivariant representation theory.
Authors: Xiangyu Shi, Zerui Li, Yanyuan Qiao, Qi Wu
Abstract: Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations and two-stage pipelines involving waypoint predictors, which introduce significant latency and limit real-world applicability. In this work, we propose Fast-SmartWay, an end-to-end zero-shot VLN-CE framework that eliminates the need for panoramic views and waypoint predictors. Our approach uses only three frontal RGB-D images combined with natural language instructions, enabling MLLMs to directly predict actions. To enhance decision robustness, we introduce an Uncertainty-Aware Reasoning module that integrates (i) a Disambiguation Module for avoiding local optima, and (ii) a Future-Past Bidirectional Reasoning mechanism for globally coherent planning. Experiments on both simulated and real-robot environments demonstrate that our method significantly reduces per-step latency while achieving competitive or superior performance compared to panoramic-view baselines. These results demonstrate the practicality and effectiveness of Fast-SmartWay for real-world zero-shot embodied navigation.
Authors: Md Talha Mohsin, Ismail Abdulrashid
Abstract: Medical imaging relies heavily on large, labeled datasets. But, unfortunately, they are not always easily accessible in clinical settings. Additionally, many practitioners often face various structural obstacles like limited data availability, fragmented data systems, and unbalanced datasets. These barriers often lead to the increased diagnostic uncertainty, underrepresentation of certain conditions, reduced model robustness, and biased diagnostic decisions. In response to these challenges, approaches such as transfer learning, meta-learning, and multimodal fusion have made great strides. However, they still need a solid theoretical justification for why they succeed or fail in situations where data is scarce. To address this gap, we propose a unified theoretical framework that characterizes learning and inference under low-resource medical imaging conditions. We first formalize the learning objective under few-shot conditions and compute sample complexity constraints to estimate the smallest quantity of data needed to achieve clinically reliable accuracy. Then based on ideas from PAC-learning and PAC-Bayesian theory, we explain how multimodal integration encourages generalization and quantifies uncertainty under sparse supervision. We further propose a formal metric for explanation stability, offering interpretability guarantees under low-data conditions. Taken together, the proposed framework establishes a principled foundation for constructing dependable, data-efficient diagnostic systems by jointly characterizing sample efficiency, uncertainty quantification, and interpretability in a unified theoretical setting.
Authors: Lijie Wang, Lianjie Guo, Ziyi Xu, Qianhao Wang, Fei Gao, Xieyuanli Chen
Abstract: Reconstructing large-scale colored point clouds is an important task in robotics, supporting perception, navigation, and scene understanding. Despite advances in LiDAR inertial visual odometry (LIVO), its performance remains highly sensitive to extrinsic calibration. Meanwhile, 3D vision foundation models, such as VGGT, suffer from limited scalability in large environments and inherently lack metric scale. To overcome these limitations, we propose LiDAR-VGGT, a novel framework that tightly couples LiDAR inertial odometry with the state-of-the-art VGGT model through a two-stage coarse- to-fine fusion pipeline: First, a pre-fusion module with robust initialization refinement efficiently estimates VGGT poses and point clouds with coarse metric scale within each session. Then, a post-fusion module enhances cross-modal 3D similarity transformation, using bounding-box-based regularization to reduce scale distortions caused by inconsistent FOVs between LiDAR and camera sensors. Extensive experiments across multiple datasets demonstrate that LiDAR-VGGT achieves dense, globally consistent colored point clouds and outperforms both VGGT-based methods and LIVO baselines. The implementation of our proposed novel color point cloud evaluation toolkit will be released as open source.
Authors: Jiawei Wang, Dingyou Wang, Jiaming Hu, Qixuan Zhang, Jingyi Yu, Lan Xu
Abstract: A deep understanding of kinematic structures and movable components is essential for enabling robots to manipulate objects and model their own articulated forms. Such understanding is captured through articulated objects, which are essential for tasks such as physical simulation, motion planning, and policy learning. However, creating these models, particularly for complex systems like robots or objects with high degrees of freedom (DoF), remains a significant challenge. Existing methods typically rely on motion sequences or strong assumptions from hand-curated datasets, which hinders scalability. In this paper, we introduce Kinematify, an automated framework that synthesizes articulated objects directly from arbitrary RGB images or text prompts. Our method addresses two core challenges: (i) inferring kinematic topologies for high-DoF objects and (ii) estimating joint parameters from static geometry. To achieve this, we combine MCTS search for structural inference with geometry-driven optimization for joint reasoning, producing physically consistent and functionally valid descriptions. We evaluate Kinematify on diverse inputs from both synthetic and real-world environments, demonstrating improvements in registration and kinematic topology accuracy over prior work.
Authors: Yuhang Huang, Zekai Lin, Fan Zhong, Lei Liu
Abstract: Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The agent learns a policy to strategically seek external visual evidence to support its diagnostic reasoning. This policy is optimized using reinforcement learning, resulting in a model that is both efficient and generalizable. Our experiments show that this action-based reasoning process significantly improves calibrated accuracy, reducing the Brier score by 18\% compared to a non-interactive baseline. To validate the faithfulness of the agent's explanations, we introduce a causal intervention method. By masking the visual evidence the agent chooses to use, we observe a measurable degradation in its performance ($\Delta$Brier=+0.029), confirming that the evidence is integral to its decision-making process. Our work provides a practical framework for building AI systems with verifiable and faithful reasoning capabilities.
Authors: Zhicheng Wang, Chen Ju, Xu Chen, Shuai Xiao, Jinsong Lan, Xiaoyong Zhu, Ying Chen, Zhiguo Cao
Abstract: Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input, singular embedding, contrastive supervision, which collapses rich, multifaceted inputs into monolithic embeddings and fails to fully exploit MLLM capabilities. In this paper, we tailor one Parallel Decoupling Framework (PDF) for multimodal embedding learning, by utilizing the proprietary steerability of MLLMs, i.e., their ability to flexibly generate quite differentiated response under explicit instructions. Concretely, PDF conditions a shared MLLM backbone on distinct, learnable prefixes to roll out multiple parallel paths for one input, then relies on these paths to obtain parallel embeddings. To promote full parallel diversity, we employ Mutual Information Minimization (MIM) as an explicit constraint, coupled with per-path contrastive supervision to maintain semantic alignment. Such dual-objectives force PDF to yield robust semantic coverage and a generalizable embedding space. Ultimately, the remarkable embedding space are accessible at inference via one single forward pass, incurring negligible computational overhead. We instantiate PDF on multiple MLLM backbones and prove its effectiveness on MMEB benchmark. Significant gains are consistently achieved across various resolutions and model sizes, e.g., boosting the VLM2Vec-LLaVA-1.6-LR model by a remarkable +8.9% (7B), while the VLM2Vec-Qwen2VL models by +4.2% (2B) and +3.1% (7B). In terms of efficiency, our 2B model surpasses its baseline by +2.6% using only half the computational budget.
Authors: Renjun Gao, Peiyan Zhong
Abstract: Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware planning, user personalization, and grounding language plans into executable skills in cluttered homes. We introduce MARS - a Multi-Agent Robotic System powered by MLLMs for assistive intelligence and designed for smart home robots supporting people with disabilities. The system integrates four agents: a visual perception agent for extracting semantic and spatial features from environment images, a risk assessment agent for identifying and prioritizing hazards, a planning agent for generating executable action sequences, and an evaluation agent for iterative optimization. By combining multimodal perception with hierarchical multi-agent decision-making, the framework enables adaptive, risk-aware, and personalized assistance in dynamic indoor environments. Experiments on multiple datasets demonstrate the superior overall performance of the proposed system in risk-aware planning and coordinated multi-agent execution compared with state-of-the-art multimodal models. The proposed approach also highlights the potential of collaborative AI for practical assistive scenarios and provides a generalizable methodology for deploying MLLM-enabled multi-agent systems in real-world environments.
Authors: Jiayi Chen, Wenxuan Song, Pengxiang Ding, Ziyang Zhou, Han Zhao, Feilong Tang, Donglin Wang, Haoang Li
Abstract: Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.
Authors: Gabriel Nobis, Maximilian Springenberg, Arina Belova, Rembert Daems, Christoph Knochenhauer, Manfred Opper, Tolga Birdal, Wojciech Samek
Abstract: We present Fractional Diffusion Bridge Models (FDBM), a novel generative diffusion bridge framework driven by an approximation of the rich and non-Markovian fractional Brownian motion (fBM). Real stochastic processes exhibit a degree of memory effects (correlations in time), long-range dependencies, roughness and anomalous diffusion phenomena that are not captured in standard diffusion or bridge modeling due to the use of Brownian motion (BM). As a remedy, leveraging a recent Markovian approximation of fBM (MA-fBM), we construct FDBM that enable tractable inference while preserving the non-Markovian nature of fBM. We prove the existence of a coupling-preserving generative diffusion bridge and leverage it for future state prediction from paired training data. We then extend our formulation to the Schr\"{o}dinger bridge problem and derive a principled loss function to learn the unpaired data translation. We evaluate FDBM on both tasks: predicting future protein conformations from aligned data, and unpaired image translation. In both settings, FDBM achieves superior performance compared to the Brownian baselines, yielding lower root mean squared deviation (RMSD) of C$_\alpha$ atomic positions in protein structure prediction and lower Fr\'echet Inception Distance (FID) in unpaired image translation.
Authors: A. Kovnatsky, M. M. Bronstein, A. M. Bronstein, K. Glashoff, R. Kimmel
Abstract: The use of Laplacian eigenbases has been shown to be fruitful in many computer graphics applications. Today, state-of-the-art approaches to shape analysis, synthesis, and correspondence rely on these natural harmonic bases that allow using classical tools from harmonic analysis on manifolds. However, many applications involving multiple shapes are obstacled by the fact that Laplacian eigenbases computed independently on different shapes are often incompatible with each other. In this paper, we propose the construction of common approximate eigenbases for multiple shapes using approximate joint diagonalization algorithms. We illustrate the benefits of the proposed approach on tasks from shape editing, pose transfer, correspondence, and similarity.
Authors: Yanpeng Sun, Qiang Chen, Xiaofan Li, Jian Wang, Jingdong Wang, Zechao Li
Abstract: The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in computer vision. To reveal the factors influencing the performance of visual in-context learning, this paper shows that prompt selection and prompt fusion are two major factors that have a direct impact on the inference performance of visual context learning. Prompt selection is the process of identifying the most appropriate prompt or example to help the model understand new tasks. This is important because providing the model with relevant prompts can help it learn more effectively and efficiently. Prompt fusion involves combining knowledge from different positions within the large-scale visual model. By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks. Based these findings, we propose a simple framework prompt-SelF for visual in-context learning. Specifically, we first use the pixel-level retrieval method to select a suitable prompt, and then use different prompt fusion methods to activate all the knowledge stored in the large-scale model, and finally ensemble the prediction results obtained from different prompt fusion methods to obtain the final prediction results. And we conduct extensive experiments on single-object segmentation and detection tasks to demonstrate the effectiveness of prompt-SelF. Remarkably, the prompt-SelF has outperformed OSLSM based meta-learning in 1-shot segmentation for the first time. This indicated the great potential of visual in-context learning. The source code and models will be available at https://github.com/syp2ysy/prompt-SelF.
Authors: Yangyang Xu, Yibo Yang, Bernard Ghanem, Lefei Zhang, Bo Du, Jun Zhu
Abstract: Convolution neural networks and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Existing studies typically employ either CNNs (effectively capture local spatial patterns) or Transformers (capturing long-range dependencies) independently, but integrating their strengths may yield more robust models. In this work, we present an efficient MTL model that combines the adaptive capabilities of deformable CNN and query-based Transformer with shared gating for MTL of dense prediction. This combination may offer a simple and efficient solution owing to its powerful and flexible task-specific learning and the advantages of lower cost, less complexity, and smaller parameters than traditional MTL methods. We introduce an efficient multi-task dense prediction with deformable and gating mixer (DeGMix). First, the deformable mixer encoder contains two types of operators: the channel-aware mixing operator leveraged to allow communication among different channels, and the spatial-aware deformable operator with deformable convolution applied to efficiently sample more informative spatial locations. Second, the task-aware gating transformer decoder is used to perform task-specific predictions, in which task interaction block integrated with self-attention is applied to capture task interaction features, and the task query block integrated with gating attention is leveraged to dynamically select the corresponding task-specific features. Furthermore, the results of the experiment demonstrate that the proposed DeGMix uses fewer GFLOPs and significantly outperforms current Transformer-based and CNN-based competitive models on a variety of metrics on three dense prediction datasets. Our code and models are available at https://github.com/yangyangxu0/DeMTG.
Authors: Xiangyu Chen, Xintao Wang, Wenlong Zhang, Xiangtao Kong, Yu Qiao, Jiantao Zhou, Chao Dong
Abstract: Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better restoration, we propose a new Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement. Extensive experiments have demonstrated the effectiveness of the proposed modules. We further scale up the model to show that the performance of the SR task can be greatly improved. Besides, we extend HAT to more image restoration applications, including real-world image super-resolution, Gaussian image denoising and image compression artifacts reduction. Experiments on benchmark and real-world datasets demonstrate that our HAT achieves state-of-the-art performance both quantitatively and qualitatively. Codes and models are publicly available at https://github.com/XPixelGroup/HAT.
Authors: Boyang Zheng, Chumeng Liang, Xiaoyu Wu
Abstract: Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized diffusion customization, by adding protective watermarks to images and poisoning diffusion models. However, current protection, leveraging untargeted attacks, does not appear to be effective enough. In this paper, we propose a simple yet effective improvement for the protection against unauthorized diffusion customization by introducing targeted attacks. We show that by carefully selecting the target, targeted attacks significantly outperform untargeted attacks in poisoning diffusion models and degrading the customization image quality. Extensive experiments validate the superiority of our method on two mainstream customization methods of diffusion models, compared to existing protections. To explain the surprising success of targeted attacks, we delve into the mechanism of attack-based protections and propose a hypothesis based on our observation, which enhances the comprehension of attack-based protections. To the best of our knowledge, we are the first to both reveal the vulnerability of diffusion models to targeted attacks and leverage targeted attacks to enhance protection against unauthorized diffusion customization. Our code is available on GitHub: https://github.com/psyker-team/mist-v2.
Authors: Young Jae Oh, Jihun Kim, Jihoon Nam, Tae Hyun Kim
Abstract: Arbitrary-scale image super-resolution employing implicit neural functions has gained significant attention lately due to its capability to upscale images across diverse scales utilizing only a single model. Nevertheless, these methodologies have imposed substantial computational demands as they involve querying every target pixel to a single resource-intensive decoder. In this paper, we introduce a novel and efficient framework, the Mixture-of-Experts Implicit Super-Resolution (MoEISR), which enables super-resolution at arbitrary scales with significantly increased computational efficiency without sacrificing reconstruction quality. MoEISR dynamically allocates the most suitable decoding expert to each pixel using a lightweight mapper module, allowing experts with varying capacities to reconstruct pixels across regions with diverse complexities. Our experiments demonstrate that MoEISR successfully reduces significant amount of floating point operations (FLOPs) while delivering comparable or superior peak signal-to-noise ratio (PSNR).
Authors: Yanpeng Sun, Jiahui Chen, Shan Zhang, Xinyu Zhang, Xiaofan Li, Qiang Chen, Gang Zhang, Errui Ding, Jingdong Wang, Zechao Li
Abstract: In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model. In essence, VRP-SAM can utilize annotated reference images to comprehend specific objects and perform segmentation of specific objects in target image. It is note that the VRP encoder can support a variety of annotation formats for reference images, including \textbf{point}, \textbf{box}, \textbf{scribble}, and \textbf{mask}. VRP-SAM achieves a breakthrough within the SAM framework by extending its versatility and applicability while preserving SAM's inherent strengths, thus enhancing user-friendliness. To enhance the generalization ability of VRP-SAM, the VRP encoder adopts a meta-learning strategy. To validate the effectiveness of VRP-SAM, we conducted extensive empirical studies on the Pascal and COCO datasets. Remarkably, VRP-SAM achieved state-of-the-art performance in visual reference segmentation with minimal learnable parameters. Furthermore, VRP-SAM demonstrates strong generalization capabilities, allowing it to perform segmentation of unseen objects and enabling cross-domain segmentation. The source code and models will be available at https://github.com/syp2ysy/VRP-SAM
Authors: Zheng Dang, Jialu Huang, Fei Wang, Mathieu Salzmann
Abstract: Recent advances in deep learning, such as neural radiance fields and implicit neural representations, have significantly advanced 3D reconstruction. However, accurately reconstructing objects with complex optical properties, such as metals, glass, and plastics, remains challenging due to the breakdown of multi-view color consistency in the presence of specular reflections, refractions, and transparency. This limitation is further exacerbated by the lack of benchmark datasets that explicitly model material-dependent light transport. To address this, we introduce OpenMaterial, a large-scale semi-synthetic dataset for benchmarking material-aware 3D reconstruction. It comprises 1,001 objects spanning 295 distinct materials, including conductors, dielectrics, plastics, and their roughened variants, captured under 714 diverse lighting conditions. By integrating lab-measured Index of Refraction (IOR) spectra, OpenMaterial enables the generation of high-fidelity multi-view images that accurately simulate complex light-matter interactions. It provides multi-view images, 3D shape models, camera poses, depth maps, and object masks, establishing the first extensive benchmark for evaluating 3D reconstruction on challenging materials. We evaluate 11 state-of-the-art methods for 3D reconstruction and novel view synthesis, conducting ablation studies to assess the impact of material type, shape complexity, and illumination on reconstruction performance. Our results indicate that OpenMaterial provides a strong and fair basis for developing more robust, physically-informed 3D reconstruction techniques to better handle real-world optical complexities.
Authors: Sungho Chun, Boeun Kim, Hyung Jin Chang, Ju Yong Chang
Abstract: Precise six-degree-of-freedom (6DoF) head pose estimation is crucial for safety-critical applications and human-computer interaction scenarios, yet existing monocular methods still struggle with robust pose estimation. We revisit this problem by introducing TRGv2, a lightweight extension of our previous Translation, Rotation, and Geometry (TRG) network, which explicitly models the bidirectional interaction between facial geometry and head pose. TRGv2 jointly infers facial landmarks and 6DoF pose through an iterative refinement loop with landmark-to-image projection, ensuring metric consistency among face size, rotation, and depth. To further improve generalization to out-of-distribution data, TRGv2 regresses correction parameters instead of directly predicting translation, combining them with a pinhole camera model for analytic depth estimation. In addition, we identify a previously overlooked source of bias in cross-dataset evaluations due to inconsistent head center definitions across different datasets. To address this, we propose a reference system alignment strategy that quantifies and corrects translation bias, enabling fair comparisons across datasets. Extensive experiments on ARKitFace, BIWI, and the challenging DD-Pose benchmarks demonstrate that TRGv2 outperforms state-of-the-art methods in both accuracy and efficiency. Code and newly annotated landmarks for DD-Pose will be publicly available.
Authors: Aleksander Ogonowski, Micha{\l} \.Zebrowski, Arkadiusz \'Cwiek, Tobiasz Jarosiewicz, Konrad Klimaszewski, Adam Padee, Piotr Wasiuk, Micha{\l} W\'ojcik
Abstract: Most of the intrusion detection methods in computer networks are based on traffic flow characteristics. However, this approach may not fully exploit the potential of deep learning algorithms to directly extract features and patterns from raw packets. Moreover, it impedes real-time monitoring due to the necessity of waiting for the processing pipeline to complete and introduces dependencies on additional software components. In this paper, we investigate deep learning methodologies capable of detecting attacks in real-time directly from raw packet data within network traffic. We propose a novel approach where packets are stacked into windows and separately recognised, with a 2D image representation suitable for processing with computer vision models. Our investigation utilizes the CIC IDS-2017 dataset, which includes both benign traffic and prevalent real-world attacks, providing a comprehensive foundation for our research.
Authors: Haopeng Li, Jinyue Yang, Kexin Wang, Xuerui Qiu, Yuhong Chou, Xin Li, Guoqi Li
Abstract: We introduce AiM, an autoregressive (AR) image generative model based on Mamba architecture. AiM employs Mamba, a novel state-space model characterized by its exceptional performance for long-sequence modeling with linear time complexity, to supplant the commonly utilized Transformers in AR image generation models, aiming to achieve both superior generation quality and enhanced inference speed. Unlike existing methods that adapt Mamba to handle two-dimensional signals via multi-directional scan, AiM directly utilizes the next-token prediction paradigm for autoregressive image generation. This approach circumvents the need for extensive modifications to enable Mamba to learn 2D spatial representations. By implementing straightforward yet strategically targeted modifications for visual generative tasks, we preserve Mamba's core structure, fully exploiting its efficient long-sequence modeling capabilities and scalability. We provide AiM models in various scales, with parameter counts ranging from 148M to 1.3B. On the ImageNet1K 256*256 benchmark, our best AiM model achieves a FID of 2.21, surpassing all existing AR models of comparable parameter counts and demonstrating significant competitiveness against diffusion models, with 2 to 10 times faster inference speed. Code is available at https://github.com/hp-l33/AiM
Authors: Wenfeng Huang, Guoan Xu, Wenjing Jia, Stuart Perry, Guangwei Gao
Abstract: Images captured in challenging environments--such as nighttime, smoke, rainy weather, and underwater--often suffer from significant degradation, resulting in a substantial loss of visual quality. The effective restoration of these degraded images is critical for the subsequent vision tasks. While many existing approaches have successfully incorporated specific priors for individual tasks, these tailored solutions limit their applicability to other degradations. In this work, we propose a universal network architecture, dubbed ``ReviveDiff'', which can address various degradations and bring images back to life by enhancing and restoring their quality. Our approach is inspired by the observation that, unlike degradation caused by movement or electronic issues, quality degradation under adverse conditions primarily stems from natural media (such as fog, water, and low luminance), which generally preserves the original structures of objects. To restore the quality of such images, we leveraged the latest advancements in diffusion models and developed ReviveDiff to restore image quality from both macro and micro levels across some key factors determining image quality, such as sharpness, distortion, noise level, dynamic range, and color accuracy. We rigorously evaluated ReviveDiff on seven benchmark datasets covering five types of degrading conditions: Rainy, Underwater, Low-light, Smoke, and Nighttime Hazy. Our experimental results demonstrate that ReviveDiff outperforms the state-of-the-art methods both quantitatively and visually.
Authors: Manuel Benavent-Lledo, David Mulero-P\'erez, David Ortiz-Perez, Jose Garcia-Rodriguez, Antonis Argyros
Abstract: We propose a novel approach to improve action recognition by exploiting the hierarchical organization of actions and by incorporating contextualized textual information, including location and previous actions, to reflect the action's temporal context. To achieve this, we introduce a transformer architecture tailored for action recognition that employs both visual and textual features. Visual features are obtained from RGB and optical flow data, while text embeddings represent contextual information. Furthermore, we define a joint loss function to simultaneously train the model for both coarse- and fine-grained action recognition, effectively exploiting the hierarchical nature of actions. To demonstrate the effectiveness of our method, we extend the Toyota Smarthome Untrimmed (TSU) dataset by incorporating action hierarchies, resulting in the Hierarchical TSU dataset, a hierarchical dataset designed for monitoring activities of the elderly in home environments. An ablation study assesses the performance impact of different strategies for integrating contextual and hierarchical data. Experimental results demonstrate that the proposed method consistently outperforms SOTA methods on the Hierarchical TSU dataset, Assembly101 and IkeaASM, achieving over a 17% improvement in top-1 accuracy.
Authors: Sanath Budakegowdanadoddi Nagaraju, Brian Bernhard Moser, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel
Abstract: Transformer-based architectures have recently advanced the image reconstruction quality of super-resolution (SR) models. Yet, their scalability remains limited by quadratic attention costs and coarse patch embeddings that weaken pixel-level fidelity. We propose TaylorIR, a plug-and-play framework that enforces 1x1 patch embeddings for true pixel-wise reasoning and replaces conventional self-attention with TaylorShift, a Taylor-series-based attention mechanism enabling full token interactions with near-linear complexity. Across multiple SR benchmarks, TaylorIR delivers state-of-the-art performance while reducing memory consumption by up to 60%, effectively bridging the gap between fine-grained detail restoration and efficient transformer scaling.
Authors: Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo, Truong Do, Dezhen Song, Truong-Son Hy
Abstract: Scene graphs have proven to be highly effective for various scene understanding tasks due to their compact and explicit representation of relational information. However, current methods often overlook the critical importance of preserving symmetry when generating scene graphs from 3D point clouds, which can lead to reduced accuracy and robustness, particularly when dealing with noisy, multi-view data. Furthermore, a major limitation of prior approaches is the lack of temporal modeling to capture time-dependent relationships among dynamically evolving entities in a scene. To address these challenges, we propose Temporal Equivariant Scene Graph Neural Network (TESGNN), consisting of two key components: (1) an Equivariant Scene Graph Neural Network (ESGNN), which extracts information from 3D point clouds to generate scene graph while preserving crucial symmetry properties, and (2) a Temporal Graph Matching Network, which fuses scene graphs generated by ESGNN across multiple time sequences into a unified global representation using an approximate graph-matching algorithm. Our combined architecture TESGNN shown to be effective compared to existing methods in scene graph generation, achieving higher accuracy and faster training convergence. Moreover, we show that leveraging the symmetry-preserving property produces a more stable and accurate global scene representation compared to existing approaches. Finally, it is computationally efficient and easily implementable using existing frameworks, making it well-suited for real-time applications in robotics and computer vision. This approach paves the way for more robust and scalable solutions to complex multi-view scene understanding challenges. Our source code is publicly available at: https://github.com/HySonLab/TESGraph
Authors: Lei Yang, Xinyu Zhang, Jun Li, Chen Wang, Jiaqi Ma, Zhiying Song, Tong Zhao, Ziying Song, Li Wang, Mo Zhou, Yang Shen, Kai Wu, Chen Lv
Abstract: Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby enhancing the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged; however, these datasets primarily focus on cameras and LiDAR, neglecting 4D Radar, a sensor used in single-vehicle autonomous driving to provide robust perception in adverse weather conditions. In this paper, to bridge the gap created by the absence of 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large-scale, real-world multi-modal dataset featuring 4D Radar. V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data encompasses sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as various typical challenging scenarios. The dataset consists of 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, including 350K annotated boxes across five categories. To support various research domains, we have established V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. Furthermore, we provide comprehensive benchmarks across these three sub-datasets. We will release all datasets and benchmark codebase at https://huggingface.co/datasets/yanglei18/V2X-Radar and https://github.com/yanglei18/V2X-Radar.
URLs: https://huggingface.co/datasets/yanglei18/V2X-Radar, https://github.com/yanglei18/V2X-Radar.
Authors: Jiajing Lin, Zhenzhong Wang, Dejun Xu, Shu Jiang, YunPeng Gong, Min Jiang
Abstract: 4D content generation aims to create dynamically evolving 3D content that responds to specific input objects such as images or 3D representations. Current approaches typically incorporate physical priors to animate 3D representations, but these methods suffer from significant limitations: they not only require users lacking physics expertise to manually specify material properties but also struggle to effectively handle the generation of multi-material composite objects. To address these challenges, we propose Phys4DGen, a novel 4D generation framework that integrates multi-material composition perception with physical simulation. The framework achieves automated, physically plausible 4D generation through three innovative modules: first, the 3D Material Grouping module partitions heterogeneous material regions on 3D representations' surfaces via semantic segmentation; second, the Internal Physical Structure Discovery module constructs the mechanical structure of object interiors; finally, we distill physical prior knowledge from multimodal large language models to enable rapid and automatic material properties identification for both objects' surfaces and interiors. Experiments on both synthetic and real-world datasets demonstrate that Phys4DGen can generate high-fidelity 4D content with physical realism in open-world scenarios, significantly outperforming state-of-the-art methods.
Authors: Nir Mualem, Roy Amoyal, Oren Freifeld, Derya Akkaynak
Abstract: In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a result, 3D reconstruction methods robust on in-air scenes, like Neural Radiance Field methods (NeRFs) or 3D Gaussian Splatting (3DGS), fail on underwater scenes. While a recent underwater adaptation of NeRFs achieved state-of-the-art results, it is impractically slow: reconstruction takes hours and its rendering rate, in frames per second (FPS), is less than 1. Here, we present a new method that takes only a few minutes for reconstruction and renders novel underwater scenes at 140 FPS. Named Gaussian Splashing, our method unifies the strengths and speed of 3DGS with an image formation model for capturing scattering, introducing innovations in the rendering and depth estimation procedures and in the 3DGS loss function. Despite the complexities of underwater adaptation, our method produces images at unparalleled speeds with superior details. Moreover, it reveals distant scene details with far greater clarity than other methods, dramatically improving reconstructed and rendered images. We demonstrate results on existing datasets and a new dataset we have collected. Additional visual results are available at: https://bgu-cs-vil.github.io/gaussiansplashingUW.github.io/ .
URLs: https://bgu-cs-vil.github.io/gaussiansplashingUW.github.io/
Authors: Jun Nie, Yonggang Zhang, Tongliang Liu, Yiu-ming Cheung, Bo Han, Xinmei Tian
Abstract: We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key insight stems from the observation that distributional discrepancies between training and testing data manifest distinctively in the epistemic uncertainty space of machine learning models. In this context, the distribution shift between natural and generated images leads to elevated epistemic uncertainty in models trained on natural images when evaluating generated ones. Hence, we exploit this phenomenon by using epistemic uncertainty as a proxy for detecting generated images. This converts the challenge of generated image detection into the problem of uncertainty estimation, underscoring the generalization performance of the model used for uncertainty estimation. Fortunately, advanced large-scale vision models pre-trained on extensive natural images have shown excellent generalization performance for various scenarios. Thus, we utilize these pre-trained models to estimate the epistemic uncertainty of images and flag those with high uncertainty as generated. Extensive experiments demonstrate the efficacy of our method. Code is available at https://github.com/tmlr-group/WePe.
Authors: Dongyue Lu, Lingdong Kong, Gim Hee Lee, Camille Simon Chane, Wei Tsang Ooi
Abstract: Event cameras offer unparalleled advantages for real-time perception in dynamic environments, thanks to the microsecond-level temporal resolution and asynchronous operation. Existing event detectors, however, are limited by fixed-frequency paradigms and fail to fully exploit the high-temporal resolution and adaptability of event data. To address these limitations, we propose FlexEvent, a novel framework that enables detection at varying frequencies. Our approach consists of two key components: FlexFuse, an adaptive event-frame fusion module that integrates high-frequency event data with rich semantic information from RGB frames, and FlexTune, a frequency-adaptive fine-tuning mechanism that generates frequency-adjusted labels to enhance model generalization across varying operational frequencies. This combination allows our method to detect objects with high accuracy in both fast-moving and static scenarios, while adapting to dynamic environments. Extensive experiments on large-scale event camera datasets demonstrate that our approach surpasses state-of-the-art methods, achieving significant improvements in both standard and high-frequency settings. Notably, our method maintains robust performance when scaling from 20 Hz to 90 Hz and delivers accurate detection up to 180 Hz, proving its effectiveness in extreme conditions. Our framework sets a new benchmark for event-based object detection and paves the way for more adaptable, real-time vision systems.
Authors: Beilin Chu, Xuan Xu, Xin Wang, Yufei Zhang, Weike You, Linna Zhou
Abstract: The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.
Authors: Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Sara Pieri, Saeed Yahya Alseiari, Shanavas Cholakkal, Khaled Aldahmani, Fahad Khan, Rao Anwer, Salman Khan, Timothy Baldwin, Hisham Cholakkal
Abstract: We introduce BiMediX2, a bilingual (Arabic-English) Bio-Medical EXpert Large Multimodal Model that supports text-based and image-based medical interactions. It enables multi-turn conversation in Arabic and English and supports diverse medical imaging modalities, including radiology, CT, and histology. To train BiMediX2, we curate BiMed-V, an extensive Arabic-English bilingual healthcare dataset consisting of 1.6M samples of diverse medical interactions. This dataset supports a range of medical Large Language Model (LLM) and Large Multimodal Model (LMM) tasks, including multi-turn medical conversations, report generation, and visual question answering (VQA). We also introduce BiMed-MBench, the first Arabic-English medical LMM evaluation benchmark, verified by medical experts. BiMediX2 demonstrates excellent performance across multiple medical LLM and LMM benchmarks, achieving state-of-the-art results compared to other open-sourced models. On BiMed-MBench, BiMediX2 outperforms existing methods by over 9% in English and more than 20% in Arabic evaluations. Additionally, it surpasses GPT-4 by approximately 9% in UPHILL factual accuracy evaluations and excels in various medical VQA, report generation, and report summarization tasks. Our trained models, instruction set, and source code are available at https://github.com/mbzuai-oryx/BiMediX2
Authors: Bi'an Du, Wei Hu, Renjie Liao
Abstract: Consistency Models (CMs) have significantly accelerated the sampling process in diffusion models, yielding impressive results in synthesizing high-resolution images. To explore and extend these advancements to point-cloud-based 3D shape generation, we propose a novel Multi-scale Latent Point Consistency Model (MLPCM). Our MLPCM follows a latent diffusion framework and introduces hierarchical levels of latent representations, ranging from point-level to super-point levels, each corresponding to a different spatial resolution. We design a multi-scale latent integration module along with 3D spatial attention to effectively denoise the point-level latent representations conditioned on those from multiple super-point levels. Additionally, we propose a latent consistency model, learned through consistency distillation, that compresses the prior into a one-step generator. This significantly improves sampling efficiency while preserving the performance of the original teacher model. Extensive experiments on standard benchmarks ShapeNet and ShapeNet-Vol demonstrate that MLPCM achieves a 100x speedup in the generation process, while surpassing state-of-the-art diffusion models in terms of both shape quality and diversity.
Authors: Haobo Yuan, Xiangtai Li, Tao Zhang, Yueyi Sun, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang
Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction tokens that guide SAM-2 in producing precise masks, enabling a grounded, multi-modal understanding of both static and dynamic visual content. Additionally, we introduce Ref-SAV, an auto-labeled dataset containing over 72k object expressions in complex video scenes, designed to boost model performance. We also manually validate 2k video objects in the Ref-SAV datasets to benchmark referring video object segmentation in complex environments. Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications. In addition, Sa2VA can be easily extended into various VLMs, including Qwen-VL and Intern-VL, which can be updated with rapid process in current open-sourced VLMs. Code and models have been provided to the community.
Authors: Maxwell Meyer, Jack Spruyt
Abstract: Current approaches to dichotomous image segmentation (DIS) treat image matting and object segmentation as fundamentally different tasks. As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation. Inspired by the possibility of aligning these two model tasks, we propose a new architectural approach for DIS called Confidence-Guided Matting (CGM). We created the first CGM model called Background Erase Network (BEN). BEN consists of two components: BEN Base for initial segmentation and BEN Refiner for confidence-based refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset, demonstrating that matting-based refinement can significantly enhance segmentation quality. This work introduces a new paradigm for integrating matting and segmentation techniques, improving fine-grained object boundary prediction in computer vision.
Authors: Bingyi Liu, Jian Teng, Hongfei Xue, Enshu Wang, Chuanhui Zhu, Pu Wang, Libing Wu
Abstract: Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment faces challenges due to bandwidth constraints and inevitable calibration errors during information exchange. To address these issues, we propose mmCooper, a novel multi-agent, multi-stage, communication-efficient, and collaboration-robust cooperative perception framework. Our framework leverages a multi-stage collaboration strategy that dynamically and adaptively balances intermediate- and late-stage information to share among agents, enhancing perceptual performance while maintaining communication efficiency. To support robust collaboration despite potential misalignments and calibration errors, our framework prevents misleading low-confidence sensing information from transmission and refines the received detection results from collaborators to improve accuracy. The extensive evaluation results on both real-world and simulated datasets demonstrate the effectiveness of the mmCooper framework and its components.
Authors: Tobias Dietz, Brian B. Moser, Tobias Nauen, Federico Raue, Stanislav Frolov, Andreas Dengel
Abstract: Dataset distillation aims to compress large datasets into compact yet highly informative subsets that preserve the training behavior of the original data. While this concept has gained traction in classification, its potential for image Super-Resolution (SR) remains largely untapped. In this work, we conduct the first systematic study of dataset distillation for SR, evaluating both pixel- and latent-space formulations. We show that a distilled dataset, occupying only 8.88% of the original size, can train SR models that retain nearly the same reconstruction fidelity as those trained on full datasets. Furthermore, we analyze how initialization strategies and distillation objectives affect efficiency, convergence, and visual quality. Our findings highlight the feasibility of SR dataset distillation and establish foundational insights for memory- and compute-efficient generative restoration models.
Authors: Craig Myles, In Hwa Um, Craig Marshall, David Harris-Birtill, David J. Harrison
Abstract: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine. We present SurGen, a dataset comprising 1,020 H&E-stained whole-slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. We illustrate SurGen's utility with a proof-of-concept model that predicts mismatch repair status directly from WSIs, achieving a test area under the receiver operating characteristic curve of 0.8273. These preliminary results underscore the dataset's potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer and beyond. SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset's capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology. Data available online: https://doi.org/10.6019/S-BIAD1285.
Authors: Anh-Tien Nguyen, Duy Minh Ho Nguyen, Nghiem Tuong Diep, Trung Quoc Nguyen, Nhat Ho, Jacqueline Michelle Metsch, Miriam Cindy Maurer, Daniel Sonntag, Hanibal Bohnenberger, Anne-Christin Hauschild
Abstract: Whole slide pathology image classification presents challenges due to gigapixel image sizes and limited annotation labels, hindering model generalization. This paper introduces a prompt learning method to adapt large vision-language models for few-shot pathology classification. We first extend the Prov-GigaPath vision foundation model, pre-trained on 1.3 billion pathology image tiles, into a vision-language model by adding adaptors and aligning it with medical text encoders via contrastive learning on 923K image-text pairs. The model is then used to extract visual features and text embeddings from few-shot annotations and fine-tunes with learnable prompt embeddings. Unlike prior methods that combine prompts with frozen features using prefix embeddings or self-attention, we propose multi-granular attention that compares interactions between learnable prompts with individual image patches and groups of them. This approach improves the model's ability to capture both fine-grained details and broader context, enhancing its recognition of complex patterns across sub-regions. To further improve accuracy, we leverage (unbalanced) optimal transport-based visual-text distance to secure model robustness by mitigating perturbations that might occur during the data augmentation process. Empirical experiments on lung, kidney, and breast pathology modalities validate the effectiveness of our approach; thereby, we surpass several of the latest competitors and consistently improve performance across diverse architectures, including CLIP, PLIP, and Prov-GigaPath integrated PLIP.
Authors: Alex Jinpeng Wang, Dongxing Mao, Jiawei Zhang, Weiming Han, Zhuobai Dong, Linjie Li, Yiqi Lin, Zhengyuan Yang, Libo Qin, Fuwei Zhang, Lijuan Wang, Min Li
Abstract: Text-conditioned image generation has gained significant attention in recent years and are processing increasingly longer and comprehensive text prompt. In everyday life, dense and intricate text appears in contexts like advertisements, infographics, and signage, where the integration of both text and visuals is essential for conveying complex information. However, despite these advances, the generation of images containing long-form text remains a persistent challenge, largely due to the limitations of existing datasets, which often focus on shorter and simpler text. To address this gap, we introduce TextAtlas5M, a novel dataset specifically designed to evaluate long-text rendering in text-conditioned image generation. Our dataset consists of 5 million long-text generated and collected images across diverse data types, enabling comprehensive evaluation of large-scale generative models on long-text image generation. We further curate 3000 human-improved test set TextAtlasEval across 3 data domains, establishing one of the most extensive benchmarks for text-conditioned generation. Evaluations suggest that the TextAtlasEval benchmarks present significant challenges even for the most advanced proprietary models (e.g. GPT4o with DallE-3), while their open-source counterparts show an even larger performance gap. These evidences position TextAtlas5M as a valuable dataset for training and evaluating future-generation text-conditioned image generation models.
Authors: Shreya Ghosh, Yi-Huan Chen, Ching-Hsiang Huang, Abu Shafin Mohammad Mahdee Jameel, Chien Chou Ho, Aly El Gamal, Samuel Labi
Abstract: A significant challenge in racing-related research is the lack of publicly available datasets containing raw images with corresponding annotations for the downstream task. In this paper, we introduce RoRaTrack, a novel dataset that contains annotated multi-camera image data from racing scenarios for track detection. The data is collected on a Dallara AV-21 at a racing circuit in Indiana, in collaboration with the Indy Autonomous Challenge (IAC). RoRaTrack addresses common problems such as blurriness due to high speed, color inversion from the camera, and absence of lane markings on the track. Consequently, we propose RaceGAN, a baseline model based on a Generative Adversarial Network (GAN) that effectively addresses these challenges. The proposed model demonstrates superior performance compared to current state-of-the-art machine learning models in track detection. The dataset and code for this work are available at https://github.com/ghosh64/RaceGAN.
Authors: Ufaq Khan, Umair Nawaz, Adnan Qayyum, Shazad Ashraf, Yutong Xie, Muhammad Haris Khan, Muhammad Bilal, Junaid Qadir
Abstract: Recent advancements in machine learning (ML) and deep learning (DL), particularly through the introduction of Foundation Models (FMs), have significantly enhanced surgical scene understanding within minimally invasive surgery (MIS). This paper surveys the integration of state-of-the-art ML and DL technologies, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Foundation Models like the Segment Anything Model (SAM), into surgical workflows. These technologies improve segmentation accuracy, instrument tracking, and phase recognition in surgical scene understanding. The paper explores the challenges these technologies face, such as data variability and computational demands, and discusses ethical considerations and integration hurdles in clinical settings. Highlighting the roles of FMs, we bridge the technological capabilities with clinical needs and outline future research directions to enhance the adaptability, efficiency, and ethical alignment of AI applications in surgery. Our findings suggest that substantial progress has been made; however, more focused efforts are required to achieve seamless integration of these technologies into clinical workflows, ensuring they complement surgical practice by enhancing precision, reducing risks, and optimizing patient outcomes.
Authors: Joel Honkamaa, Pekka Marttinen
Abstract: The deformable registration of images of different modalities, essential in many medical imaging applications, remains challenging. The main challenge is developing a robust measure for image overlap despite the compared images capturing different aspects of the underlying tissue. Here, we explore similarity metrics based on functional dependence between intensity values of registered images. Although functional dependence is too restrictive on the global scale, earlier work has shown competitive performance in deformable registration when such measures are applied over small enough contexts. We confirm this finding and further develop the idea by modeling local functional dependence via the linear basis function model with the basis functions learned jointly with the deformation. The measure can be implemented via convolutions, making it efficient to compute on GPUs. We release the method as an easy-to-use tool and show good performance on three datasets compared to well-established baseline and earlier functional dependence-based methods.
Authors: Rahul Nair, Bhanu Tokas, Hannah Kerner
Abstract: When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias amplification metrics (e.g., BA (MALS), DPA) measure bias amplification only in classification datasets. These metrics are ineffective for image captioning datasets, as they cannot capture the language semantics of a caption. Recent work introduced Leakage in Captioning (LIC), a language-aware bias amplification metric that understands caption semantics. However, LIC has a crucial limitation: it cannot identify the source of bias amplification in captioning models. We propose Directional Bias Amplification in Captioning (DBAC), a language-aware and directional metric that can identify when captioning models amplify biases. DBAC has two more improvements over LIC: (1) it is less sensitive to sentence encoders (a hyperparameter in language-aware metrics), and (2) it provides a more accurate estimate of bias amplification in captions. Our experiments on gender and race attributes in the COCO captions dataset show that DBAC is the only reliable metric to measure bias amplification in captions.
Authors: Sudarshan Regmi
Abstract: The ability of the deep learning model to recognize when a sample falls outside its learned distribution is critical for safe and reliable deployment. Recent state-of-the-art out-of-distribution (OOD) detection methods leverage activation shaping to improve the separation between in-distribution (ID) and OOD inputs. These approaches resort to sample-specific scaling but apply a static percentile threshold across all samples regardless of their nature, resulting in suboptimal ID-OOD separability. In this work, we propose \textbf{AdaSCALE}, an adaptive scaling procedure that dynamically adjusts the percentile threshold based on a sample's estimated OOD likelihood. This estimation leverages our key observation: OOD samples exhibit significantly more pronounced activation shifts at high-magnitude activations under minor perturbation compared to ID samples. AdaSCALE enables stronger scaling for likely ID samples and weaker scaling for likely OOD samples, yielding highly separable energy scores. Our approach achieves state-of-the-art OOD detection performance, outperforming the latest rival OptFS by 14.94% in near-OOD and 21.67% in far-OOD datasets in average FPR@95 metric on the ImageNet-1k benchmark across eight diverse architectures. The code is available at: https://github.com/sudarshanregmi/AdaSCALE/
Authors: Junbin Xiao, Nanxin Huang, Hao Qiu, Zhulin Tao, Xun Yang, Richang Hong, Meng Wang, Angela Yao
Abstract: We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It also features 5,311 questions directly posed or verified by the blind to reflect their in-situation needs for visual assistance. Each question has an average of 3 manually annotated reference answers to reduce subjectiveness. Using EgoBlind, we comprehensively evaluate 16 advanced MLLMs and find that all models struggle. The best performers achieve an accuracy near 60\%, which is far behind human performance of 87.4\%. To guide future advancements, we identify and summarize major limitations of existing MLLMs in egocentric visual assistance for the blind and explore heuristic solutions for improvement. With these efforts, we hope that EgoBlind will serve as a foundation for developing effective AI assistants to enhance the independence of the blind and visually impaired. Data and code are available at https://github.com/doc-doc/EgoBlind.
Authors: Zhangyu Wang, Zeping Liu, Jielu Zhang, Zhongliang Zhou, Qian Cao, Nemin Wu, Lan Mu, Yang Song, Yiqun Xie, Ni Lao, Gengchen Mai
Abstract: Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval, whose spatial generalizability significantly suffers if the spatial distribution of test im- ages does not align with the choices of grids and galleries. Recently emerging generative approaches, while getting rid of grids and galleries, use raw geographical coordinates and suffer quality losses due to their lack of multi-scale information. To address these limitations, we propose a multi-scale latent diffusion model called LocDiff for image geolocalization. We developed a novel positional encoding-decoding framework called Spherical Harmonics Dirac Delta (SHDD) Representations, which encodes points on a spherical surface (e.g., geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking on spherical probability distributions. We also propose a novel SirenNet-based architecture (CS-UNet) to learn an image-based conditional backward process in the latent SHDD space by minimizing a latent KL-divergence loss. To the best of our knowledge, LocDiff is the first image geolocalization model that performs latent diffusion in a multi-scale location encoding space and generates geolocations under the guidance of images. Experimental results show that LocDiff can outperform all state-of-the-art grid-based, retrieval-based, and diffusion-based baselines across 5 challenging global-scale image geolocalization datasets, and demonstrates significantly stronger generalizability to unseen geolocations.
Authors: Pihai Sun, Junjun Jiang, Yuanqi Yao, Youyu Chen, Wenbo Zhao, Kui Jiang, Xianming Liu
Abstract: Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability stemming from two factors: 1) limited annotated image-event-depth datasets causing insufficient cross-modal supervision, and 2) inherent frequency mismatches between static images and dynamic event streams with distinct spatiotemporal patterns, leading to ineffective feature fusion. To address this dual challenge, we propose Frequency-decoupled Unified Self-supervised Encoder (FUSE) with two synergistic components: The Parameter-efficient Self-supervised Transfer (PST) establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity by enabling joint encoding without depth ground truth. Complementing this, we propose the Frequency-Decoupled Fusion module (FreDFuse) to explicitly decouple high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches through physics-aware fusion. This combined approach enables FUSE to construct a universal image-event encoder that only requires lightweight decoder adaptation for target datasets. Extensive experiments demonstrate state-of-the-art performance with 14% and 24.9% improvements in Abs .Rel on MVSEC and DENSE datasets. The framework exhibits remarkable zero-shot adaptability to challenging scenarios including extreme lighting and motion blur, significantly advancing real-world deployment capabilities. The source code for our method is publicly available at: https://github.com/sunpihai-up/FUSE
Authors: Yuhao Huang, Ao Chang, Haoran Dou, Xing Tao, Xinrui Zhou, Yan Cao, Ruobing Huang, Alejandro F Frangi, Lingyun Bao, Xin Yang, Dong Ni
Abstract: Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: (1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. (2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents' erasing process precisely, thereby avoiding both under- and over-segmentation. (3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms.
Authors: Advaith V. Sethuraman, Max Rucker, Onur Bagoren, Pou-Chun Kung, Nibarkavi N. B. Amutha, Katherine A. Skinner
Abstract: In this paper, we present SonarSplat, a novel Gaussian splatting framework for imaging sonar that demonstrates realistic novel view synthesis and models acoustic streaking phenomena. Our method represents the scene as a set of 3D Gaussians with acoustic reflectance and saturation properties. We develop a novel method to efficiently rasterize Gaussians to produce a range/azimuth image that is faithful to the acoustic image formation model of imaging sonar. In particular, we develop a novel approach to model azimuth streaking in a Gaussian splatting framework. We evaluate SonarSplat using real-world datasets of sonar images collected from an underwater robotic platform in a controlled test tank and in a real-world river environment. Compared to the state-of-the-art, SonarSplat offers improved image synthesis capabilities (+3.2 dB PSNR) and more accurate 3D reconstruction (77% lower Chamfer Distance). We also demonstrate that SonarSplat can be leveraged for azimuth streak removal.
Authors: Qianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun
Abstract: Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-wise redundancy in MLLMs by introducing a novel metric, Layer Contribution (LC), which quantifies the impact of a layer's transformations on visual and text tokens, respectively. The calculation of LC involves measuring the divergence in model output that results from removing the layer's transformations on the specified tokens. Our pilot experiment reveals that many layers of MLLMs exhibit minimal contribution during the processing of visual tokens. Motivated by this observation, we propose ShortV, a training-free method that leverages LC to identify ineffective layers, and freezes visual token updates in these layers. Experiments show that ShortV can freeze visual token in approximately 60\% of the MLLM layers, thereby dramatically reducing computational costs related to updating visual tokens. For example, it achieves a 50\% reduction in FLOPs on LLaVA-NeXT-13B while maintaining superior performance. The code will be publicly available at https://github.com/icip-cas/ShortV
Authors: Xiucheng Liang, Jinheng Xie, Tianhong Zhao, Rudi Stouffs, Filip Biljecki
Abstract: Building properties, such as height, usage, and material, play a crucial role in spatial data infrastructures, supporting various urban applications. Despite their importance, comprehensive building attribute data remain scarce in many urban areas. Recent advances have enabled the extraction of objective building attributes using remote sensing and street-level imagery. However, establishing a pipeline that integrates diverse open datasets, acquires holistic building imagery, and infers comprehensive building attributes at scale remains a significant challenge. Among the first, this study bridges the gaps by introducing OpenFACADES, an open framework that leverages multimodal crowdsourced data to enrich building profiles with both objective attributes and semantic descriptors through multimodal large language models. First, we integrate street-level image metadata from Mapillary with OpenStreetMap geometries via isovist analysis, identifying images that provide suitable vantage points for observing target buildings. Second, we automate the detection of building facades in panoramic imagery and tailor a reprojection approach to convert objects into holistic perspective views that approximate real-world observation. Third, we introduce an innovative approach that harnesses and investigates the capabilities of open-source large vision-language models (VLMs) for multi-attribute prediction and open-vocabulary captioning in building-level analytics, leveraging a globally sourced dataset of 31,180 labeled images from seven cities. Evaluation shows that fine-tuned VLM excel in multi-attribute inference, outperforming single-attribute computer vision models and zero-shot ChatGPT-4o. Further experiments confirm its superior generalization and robustness across culturally distinct region and varying image conditions.
Authors: Zhiqiang Wang, Pengbin Feng, Yanbin Lin, Shuzhang Cai, Zongao Bian, Jinghua Yan, Xingquan Zhu
Abstract: We propose Fuzzy Group Relative Policy Reward (FGRPR), a novel framework that integrates Group Relative Policy Optimization (GRPO) with a fuzzy reward function to enhance learning efficiency. Unlike the conventional binary 0/1 accuracy reward, our fuzzy reward model provides nuanced incentives, encouraging more precise outputs. Experimental results demonstrate that GRPO with a standard 0/1 accuracy reward underperforms compared to supervised fine-tuning (SFT). In contrast, FGRPR, applied to Qwen2.5-VL(3B and 7B), surpasses all baseline models, including GPT4o, LLaMA2(90B), and SFT, across five in-domain datasets. On an out-of-domain dataset, FGRPR achieves performance comparable to SFT but excels when target values are larger, as its fuzzy reward function assigns higher rewards to closer approximations. This approach is broadly applicable to tasks where the precision of the answer is critical. Code and data: https://github.com/yeyimilk/CrowdVLM-R1
Authors: Mert Asim Karaoglu, Wenbo Ji, Ahmed Abbas, Nassir Navab, Benjamin Busam, Alexander Ladikos
Abstract: Tissue tracking plays a critical role in various surgical navigation and extended reality (XR) applications. While current methods trained on large synthetic datasets achieve high tracking accuracy and generalize well to endoscopic scenes, their runtime performances fail to meet the low-latency requirements necessary for real-time surgical applications. To address this limitation, we propose LiteTracker, a low-latency method for tissue tracking in endoscopic video streams. LiteTracker builds on a state-of-the-art long-term point tracking method, and introduces a set of training-free runtime optimizations. These optimizations enable online, frame-by-frame tracking by leveraging a temporal memory buffer for efficient feature reuse and utilizing prior motion for accurate track initialization. LiteTracker demonstrates significant runtime improvements being around 7x faster than its predecessor and 2x than the state-of-the-art. Beyond its primary focus on efficiency, LiteTracker delivers high-accuracy tracking and occlusion prediction, performing competitively on both the STIR and SuPer datasets. We believe LiteTracker is an important step toward low-latency tissue tracking for real-time surgical applications in the operating room. Our code is publicly available at https://github.com/ImFusionGmbH/lite-tracker.
Authors: Elman Ghazaei, Erchan Aptoula
Abstract: Despite their frequent use for change detection, both ConvNets and Vision transformers (ViT) exhibit well-known limitations, namely the former struggle to model long-range dependencies while the latter are computationally inefficient, rendering them challenging to train on large-scale datasets. Vision Mamba, an architecture based on State Space Models has emerged as an alternative addressing the aforementioned deficiencies and has been already applied to remote sensing change detection, though mostly as a feature extracting backbone. In this article the Change State Space Model is introduced, that has been specifically designed for change detection by focusing on the relevant changes between bi-temporal images, effectively filtering out irrelevant information. By concentrating solely on the changed features, the number of network parameters is reduced, enhancing significantly computational efficiency while maintaining high detection performance and robustness against input degradation. The proposed model has been evaluated via three benchmark datasets, where it outperformed ConvNets, ViTs, and Mamba-based counterparts at a fraction of their computational complexity. The implementation will be made available at https://github.com/Elman295/CSSM upon acceptance.
Authors: Qianqian Sun, Jixiang Luo, Dell Zhang, Xuelong Li
Abstract: Recent advancements in image editing have utilized large-scale multimodal models to enable intuitive, natural instruction-driven interactions. However, conventional methods still face significant challenges, particularly in spatial reasoning, precise region segmentation, and maintaining semantic consistency, especially in complex scenes. To overcome these challenges, we introduce SmartFreeEdit, a novel end-to-end framework that integrates a multimodal large language model (MLLM) with a hypergraph-enhanced inpainting architecture, enabling precise, mask-free image editing guided exclusively by natural language instructions. The key innovations of SmartFreeEdit include:(1)the introduction of region aware tokens and a mask embedding paradigm that enhance the spatial understanding of complex scenes;(2) a reasoning segmentation pipeline designed to optimize the generation of editing masks based on natural language instructions;and (3) a hypergraph-augmented inpainting module that ensures the preservation of both structural integrity and semantic coherence during complex edits, overcoming the limitations of local-based image generation. Extensive experiments on the Reason-Edit benchmark demonstrate that SmartFreeEdit surpasses current state-of-the-art methods across multiple evaluation metrics, including segmentation accuracy, instruction adherence, and visual quality preservation, while addressing the issue of local information focus and improving global consistency in the edited image. Our project will be available at https://github.com/smileformylove/SmartFreeEdit.
Authors: Ole-Christian Galbo Engstr{\o}m, Michela Albano-Gaglio, Erik Schou Dreier, Yamine Bouzembrak, Maria Font-i-Furnols, Puneet Mishra, Kim Steenstrup Pedersen
Abstract: Current approaches to chemical map generation from hyperspectral images are based on models such as partial least squares (PLS) regression, generating pixel-wise predictions that do not consider spatial context and suffer from a high degree of noise. This study proposes an end-to-end deep learning approach using a modified version of U-Net and a custom loss function to directly obtain chemical maps from hyperspectral images, skipping all intermediate steps required for traditional pixel-wise analysis. This study compares the U-Net with the traditional PLS regression on a real dataset of pork belly samples with associated mean fat reference values. The U-Net obtains a test set root mean squared error that is 7% lower than that of PLS regression on the task of mean fat prediction. At the same time, U-Net generates fine detail chemical maps where 99.91% of the variance is spatially correlated. Conversely, only 2.37% of the variance in the PLS-generated chemical maps is spatially correlated, indicating that each pixel-wise prediction is largely independent of neighboring pixels. Additionally, while the PLS-generated chemical maps contain predictions far beyond the physically possible range of 0-100%, U-Net learns to stay inside this range. Thus, the findings of this study indicate that U-Net is superior to PLS for chemical map generation.
Authors: David Yan, Alexander Raistrick, Jia Deng
Abstract: Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator, and report the effects on zero-shot stereo matching performance using standard benchmarks. We validate our findings by collecting the best settings and creating a large-scale dataset. Training only on this dataset achieves better performance than training on a mixture of widely used datasets, and is competitive with training on the FoundationStereo dataset, with the additional benefit of open-source generation code and an accompanying parameter analysis to enable further research. We open-source our system at https://github.com/princeton-vl/InfinigenStereo to enable further research on procedural stereo datasets.
Authors: Kevin Lane, Morteza Karimzadeh
Abstract: Foundation models have garnered increasing attention for representation learning in remote sensing. Many such foundation models adopt approaches that have demonstrated success in computer vision with minimal domain-specific modification. However, the development and application of foundation models in this field are still burgeoning, as there are a variety of competing approaches for how to most effectively leverage remotely sensed data. This paper examines these approaches, along with their roots in the computer vision field. This is done to characterize potential advantages and pitfalls, while outlining future directions to further improve remote sensing-specific foundation models. We discuss the quality of the learned representations and methods to alleviate the need for massive compute resources. We first examine single-sensor remote foundation models to introduce concepts and provide context, and then place emphasis on incorporating the multi-sensor aspect of Earth observations into foundation models. In particular, we explore the extent to which existing approaches leverage multiple sensors in training foundation models in relation to multi-modal foundation models. Finally, we identify opportunities for further harnessing the vast amounts of unlabeled, seasonal, and multi-sensor remote sensing observations.
Authors: Yunzhong Zhang, Bo Xiong, You Zhou, Changqing Su, Zhen Cheng, Zhaofei Yu, Xun Cao, Tiejun Huang
Abstract: The need for accurate and non-intrusive flow measurement methods has led to the widespread adoption of Particle Image Velocimetry (PIV), a powerful diagnostic tool in fluid motion estimation. This study investigates the tremendous potential of spike cameras (a type of ultra-high-speed, high-dynamic-range camera) in PIV. We propose a deep learning framework, Spike Imaging Velocimetry (SIV), designed specifically for highly turbulent and intricate flow fields. To aggregate motion features from the spike stream while minimizing information loss, we incorporate a Detail-Preserving Hierarchical Transform (DPHT) module. Additionally, we introduce a Graph Encoder (GE) to extract contextual features from highly complex fluid flows. Furthermore, we present a spike-based PIV dataset, Particle Scenes with Spike and Displacement (PSSD), which provides labeled data for three challenging fluid dynamics scenarios. Our proposed method achieves superior performance compared to existing baseline methods on PSSD. The datasets and our implementation of SIV are open-sourced in the supplementary materials.
Authors: Luoting Zhuang, Seyed Mohammad Hossein Tabatabaei, Ramin Salehi-Rad, Linh M. Tran, Denise R. Aberle, Ashley E. Prosper, William Hsu
Abstract: Machine learning models have utilized semantic features, deep features, or both to assess lung nodule malignancy. However, their reliance on manual annotation during inference, limited interpretability, and sensitivity to imaging variations hinder their application in real-world clinical settings. Thus, this research aims to integrate semantic features derived from radiologists' assessments of nodules, guiding the model to learn clinically relevant, robust, and explainable imaging features for predicting lung cancer. We obtained 938 low-dose CT scans from the National Lung Screening Trial (NLST) with 1,261 nodules and semantic features. Additionally, the Lung Image Database Consortium dataset contains 1,018 CT scans, with 2,625 lesions annotated for nodule characteristics. Three external datasets were obtained from UCLA Health, the LUNGx Challenge, and the Duke Lung Cancer Screening. We fine-tuned a pretrained Contrastive Language-Image Pretraining (CLIP) model with a parameter-efficient fine-tuning approach to align imaging and semantic text features and predict the one-year lung cancer diagnosis. Our model outperformed state-of-the-art (SOTA) models in the NLST test set with an AUROC of 0.901 and AUPRC of 0.776. It also showed robust results in external datasets. Using CLIP, we also obtained predictions on semantic features through zero-shot inference, such as nodule margin (AUROC: 0.807), nodule consistency (0.812), and pleural attachment (0.840). Our approach surpasses the SOTA models in predicting lung cancer across datasets collected from diverse clinical settings, providing explainable outputs, aiding clinicians in comprehending the underlying meaning of model predictions. This approach also prevents the model from learning shortcuts and generalizes across clinical settings. The code is available at https://github.com/luotingzhuang/CLIP_nodule.
Authors: Priyank Pathak, Yogesh S Rawat
Abstract: This work focuses on Clothes Changing Re-IDentification (CC-ReID) for the real world. Existing works perform well with high-quality (HQ) images, but struggle with low-quality (LQ) where we can have artifacts like pixelation, out-of-focus blur, and motion blur. These artifacts introduce noise to not only external biometric attributes (e.g. pose, body shape, etc.) but also corrupt the model's internal feature representation. Models usually cluster LQ image features together, making it difficult to distinguish between them, leading to incorrect matches. We propose a novel framework Robustness against Low-Quality (RLQ) to improve CC-ReID model on real-world data. RLQ relies on Coarse Attributes Prediction (CAP) and Task Agnostic Distillation (TAD) operating in alternate steps in a novel training mechanism. CAP enriches the model with external fine-grained attributes via coarse predictions, thereby reducing the effect of noisy inputs. On the other hand, TAD enhances the model's internal feature representation by bridging the gap between HQ and LQ features, via an external dataset through task-agnostic self-supervision and distillation. RLQ outperforms the existing approaches by 1.6%-2.9% Top-1 on real-world datasets like LaST, and DeepChange, while showing consistent improvement of 5.3%-6% Top-1 on PRCC with competitive performance on LTCC. *The code will be made public soon.*
Authors: Qifeng Cai, Hao Liang, Hejun Dong, Meiyi Qiang, Ruichuan An, Zhaoyang Han, Zhengzhou Zhu, Bin Cui, Wentao Zhang
Abstract: Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from limited video duration, low-quality captions, and coarse annotation granularity, which hinder the evaluation of advanced video-text retrieval methods. To address these limitations, we introduce LoVR, a benchmark specifically designed for long video-text retrieval. LoVR contains 467 long videos and over 40,804 fine-grained clips with high-quality captions. To overcome the issue of poor machine-generated annotations, we propose an efficient caption generation framework that integrates VLM automatic generation, caption quality scoring, and dynamic refinement. This pipeline improves annotation accuracy while maintaining scalability. Furthermore, we introduce a semantic fusion method to generate coherent full-video captions without losing important contextual information. Our benchmark introduces longer videos, more detailed captions, and a larger-scale dataset, presenting new challenges for video understanding and retrieval. Extensive experiments on various advanced embedding models demonstrate that LoVR is a challenging benchmark, revealing the limitations of current approaches and providing valuable insights for future research. We release the code and dataset link at https://github.com/TechNomad-ds/LoVR-benchmark
Authors: Hao Jing, Anhong Wang, Yifan Zhang, Donghan Bu, Junhui Hou
Abstract: Regarding intelligent transportation systems, low-bitrate transmission via lossy point cloud compression is vital for facilitating real-time collaborative perception among connected agents, such as vehicles and infrastructures, under restricted bandwidth. In existing compression transmission systems, the sender lossily compresses point coordinates and reflectance to generate a transmission code stream, which faces transmission burdens from reflectance encoding and limited detection robustness due to information loss. To address these issues, this paper proposes a 3D object detection framework with reflectance prediction-based knowledge distillation (RPKD). We compress point coordinates while discarding reflectance during low-bitrate transmission, and feed the decoded non-reflectance compressed point clouds into a student detector. The discarded reflectance is then reconstructed by a geometry-based reflectance prediction (RP) module within the student detector for precise detection. A teacher detector with the same structure as the student detector is designed for performing reflectance knowledge distillation (RKD) and detection knowledge distillation (DKD) from raw to compressed point clouds. Our cross-source distillation training strategy (CDTS) equips the student detector with robustness to low-quality compressed data while preserving the accuracy benefits of raw data through transferred distillation knowledge. Experimental results on the KITTI and DAIR-V2X-V datasets demonstrate that our method can boost detection accuracy for compressed point clouds across multiple code rates. We will release the code publicly at https://github.com/HaoJing-SX/RPKD.
Authors: Yujin Jeong, Arnas Uselis, Seong Joon Oh, Anna Rohrbach
Abstract: Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image diffusion models excel at synthesizing complex scenes, suggesting inherent compositional capabilities. Building on this, zero-shot diffusion classifiers have been proposed to repurpose diffusion models for discriminative tasks. While prior work offered promising results in discriminative compositional scenarios, these results remain preliminary due to a small number of benchmarks and a relatively shallow analysis of conditions under which the models succeed. To address this, we present a comprehensive study of the discriminative capabilities of diffusion classifiers on a wide range of compositional tasks. Specifically, our study covers three diffusion models (SD 1.5, 2.0, and, for the first time, 3-m) spanning 10 datasets and over 30 tasks. Further, we shed light on the role that target dataset domains play in respective performance; to isolate the domain effects, we introduce a new diagnostic benchmark \textsc{Self-Bench} comprised of images created by diffusion models themselves. Finally, we explore the importance of timestep weighting and uncover a relationship between domain gap and timestep sensitivity, particularly for SD3-m. To sum up, diffusion classifiers understand compositionality, but conditions apply! Code and dataset are available at https://github.com/eugene6923/Diffusion-Classifiers-Compositionality.
URLs: https://github.com/eugene6923/Diffusion-Classifiers-Compositionality.
Authors: Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
Abstract: Long-form video understanding presents significant challenges due to extensive temporal-spatial complexity and the difficulty of question answering under such extended contexts. While Large Language Models (LLMs) have demonstrated considerable advancements in video analysis capabilities and long context handling, they continue to exhibit limitations when processing information-dense hour-long videos. To overcome such limitations, we propose the Deep Video Discovery (DVD) agent to leverage an agentic search strategy over segmented video clips. Unlike previous video agents that rely on predefined workflows applied uniformly across different queries, our approach emphasizes the autonomous and adaptive nature of agents. By providing a set of search-centric tools on multi-granular video database, our DVD agent leverages the advanced reasoning capability of LLM to plan on its current observation state, strategically selects tools to orchestrate adaptive workflow for different queries in light of the gathered information. We perform comprehensive evaluation on multiple long video understanding benchmarks that demonstrates our advantage. Our DVD agent achieves state-of-the-art performance on the challenging LVBench dataset, reaching an accuracy of 74.2%, which substantially surpasses all prior works, and further improves to 76.0% with transcripts. The code has been released at https://github.com/microsoft/DeepVideoDiscovery.
Authors: Savya Khosla, Sethuraman TV, Barnett Lee, Alexander Schwing, Derek Hoiem
Abstract: We introduce the Region Encoder Network (REN), a fast and effective model for generating region-based image representations using point prompts. Recent methods combine class-agnostic segmenters (e.g., SAM) with patch-based image encoders (e.g., DINO) to produce compact and effective region representations, but they suffer from high computational cost due to the segmentation step. REN bypasses this bottleneck using a lightweight module that directly generates region tokens, enabling 60x faster token generation with 35x less memory, while also improving token quality. It uses a few cross-attention blocks that take point prompts as queries and features from a patch-based image encoder as keys and values to produce region tokens that correspond to the prompted objects. We train REN with three popular encoders-DINO, DINOv2, and OpenCLIP-and show that it can be extended to other encoders without dedicated training. We evaluate REN on semantic segmentation and retrieval tasks, where it consistently outperforms the original encoders in both performance and compactness, and matches or exceeds SAM-based region methods while being significantly faster. Notably, REN achieves state-of-the-art results on the challenging Ego4D VQ2D benchmark and outperforms proprietary LMMs on Visual Haystacks' single-needle challenge. Code and models are available at: https://github.com/savya08/REN.
Authors: Uri Gadot, Rinon Gal, Yftah Ziser, Gal Chechik, Shie Mannor
Abstract: Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image quality. However, their effective design requires substantial expertise. Recent approaches have shown promise in automating this process through large language models (LLMs), but they suffer from two critical limitations: extensive computational requirements from generating images with hundreds of predefined pipelines, and poor generalization beyond memorized training examples. We introduce a novel reinforcement learning-based framework that addresses these inefficiencies. Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations, eliminating the need for costly image generation during training. We then implement a two-phase training strategy: initial workflow vocabulary training followed by GRPO-based optimization that guides the model toward higher-performing regions of the workflow space. Additionally, we incorporate a classifier-free guidance based enhancement technique that extrapolates along the path between the initial and GRPO-tuned models, further improving output quality. We validate our approach through a set of comparisons, showing that it can successfully create new flows with greater diversity and lead to superior image quality compared to existing baselines.
Authors: Dekai Zhu, Yixuan Hu, Youquan Liu, Dongyue Lu, Lingdong Kong, Slobodan Ilic
Abstract: Leveraging recent diffusion models, LiDAR-based large-scale 3D scene generation has achieved great success. While recent voxel-based approaches can generate both geometric structures and semantic labels, existing range-view methods are limited to producing unlabeled LiDAR scenes. Relying on pretrained segmentation models to predict the semantic maps often results in suboptimal cross-modal consistency. To address this limitation while preserving the advantages of range-view representations, such as computational efficiency and simplified network design, we propose Spiral, a novel range-view LiDAR diffusion model that simultaneously generates depth, reflectance images, and semantic maps. Furthermore, we introduce novel semantic-aware metrics to evaluate the quality of the generated labeled range-view data. Experiments on the SemanticKITTI and nuScenes datasets demonstrate that Spiral achieves state-of-the-art performance with the smallest parameter size, outperforming two-step methods that combine the generative and segmentation models. Additionally, we validate that range images generated by Spiral can be effectively used for synthetic data augmentation in the downstream segmentation training, significantly reducing the labeling effort on LiDAR data.
Authors: Zhoufaran Yang, Yan Shu, Jing Wang, Zhifei Yang, Yan Zhang, Yu Li, Keyang Lu, Gangyan Zeng, Shaohui Liu, Yu Zhou, Nicu Sebe
Abstract: Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. However, existing video understanding benchmarks largely overlook textual information, while OCR-specific benchmarks are constrained to static images, limiting their ability to capture the interaction between text and dynamic visual contexts. To address this gap, we propose VidText, a new benchmark designed for comprehensive and in-depth evaluation of video text understanding. VidText offers the following key features: 1) It covers a wide range of real-world scenarios and supports multilingual content, encompassing diverse settings where video text naturally appears. 2) It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks, enabling assessment of both global summarization and local retrieval capabilities. 3) The benchmark also introduces a set of paired perception reasoning tasks, ranging from visual text perception to cross-modal reasoning between textual and visual information. Extensive experiments on 18 state-of-the-art Large Multimodal Models (LMMs) reveal that current models struggle across most tasks, with significant room for improvement. Further analysis highlights the impact of both model-intrinsic factors, such as input resolution and OCR capability, and external factors, including the use of auxiliary information and Chain-of-Thought reasoning strategies. We hope VidText will fill the current gap in video understanding benchmarks and serve as a foundation for future research on multimodal reasoning with video text in dynamic environments.
Authors: Pedram Ghamisi, Weikang Yu, Xiaokang Zhang, Aldino Rizaldy, Jian Wang, Chufeng Zhou, Richard Gloaguen, Gustau Camps-Valls
Abstract: Foundation Models (FMs) are large-scale, pre-trained artificial intelligence (AI) systems that have revolutionized natural language processing and computer vision, and are now advancing geospatial analysis and Earth Observation (EO). They promise improved generalization across tasks, scalability, and efficient adaptation with minimal labeled data. However, despite the rapid proliferation of geospatial FMs, their real-world utility and alignment with global sustainability goals remain underexplored. We introduce SustainFM, a comprehensive benchmarking framework grounded in the 17 Sustainable Development Goals with extremely diverse tasks ranging from asset wealth prediction to environmental hazard detection. This study provides a rigorous, interdisciplinary assessment of geospatial FMs and offers critical insights into their role in attaining sustainability goals. Our findings show: (1) While not universally superior, FMs often outperform traditional approaches across diverse tasks and datasets. (2) Evaluating FMs should go beyond accuracy to include transferability, generalization, and energy efficiency as key criteria for their responsible use. (3) FMs enable scalable, SDG-grounded solutions, offering broad utility for tackling complex sustainability challenges. Critically, we advocate for a paradigm shift from model-centric development to impact-driven deployment, and emphasize metrics such as energy efficiency, robustness to domain shifts, and ethical considerations.
Authors: Hyojin Bahng, Caroline Chan, Fredo Durand, Phillip Isola
Abstract: Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and time-intensive. We propose an alternative approach that leverages cycle consistency as a supervisory signal. Given an image and generated text, we map the text back to image space using a text-to-image model and compute the similarity between the original image and its reconstruction. Analogously, for text-to-image generation, we measure the textual similarity between an input caption and its reconstruction through the cycle. We use the cycle consistency score to rank candidates and construct a preference dataset of 866K comparison pairs. The reward model trained on our dataset, CycleReward, outperforms state-of-the-art alignment metrics on detailed captioning, with superior inference-time scalability when used as a verifier for Best-of-N sampling, while maintaining speed and differentiability. Furthermore, performing DPO and Diffusion DPO using our dataset enhances performance across a wide range of vision-language tasks and text-to-image generation. Our dataset, model, and code are publicly released at https://cyclereward.github.io.
Authors: Mingzhe Li, Gehao Zhang, Zhenting Wang, Guanhong Tao, Siqi Pan, Richard Cartwright, Juan Zhai, Shiqing Ma
Abstract: Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descriptions. Prompt inversion, the task of identifying the textual prompt used to generate a specific artifact, holds significant potential for applications including data attribution, model provenance, and watermarking validation. Recent studies introduced a delayed projection scheme to optimize for prompts representative of the vocabulary space, though challenges in semantic fluency and efficiency remain. Advanced image captioning models or visual large language models can generate highly interpretable prompts, but they often lack in image similarity. In this paper, we propose a prompt inversion technique called \sys for text-to-image diffusion models, which includes initializing embeddings using a pre-trained image captioning model, refining them through reverse-engineering in the latent space, and converting them to texts using an embedding-to-text model. Our experiments on the widely-used datasets, such as MS COCO, LAION, and Flickr, show that our method outperforms existing methods in terms of image similarity, textual alignment, prompt interpretability and generalizability. We further illustrate the application of our generated prompts in tasks such as cross-concept image synthesis, concept manipulation, evolutionary multi-concept generation and unsupervised segmentation.
Authors: Hugo Porta, Emanuele Dalsasso, Jessica L. McCarty, Devis Tuia
Abstract: Canada experienced in 2023 one of the most severe wildfire seasons in recent history, causing damage across ecosystems, destroying communities, and emitting large quantities of CO2. This extreme wildfire season is symptomatic of a climate-change-induced increase in the length and severity of the fire season that affects the boreal ecosystem. Therefore, it is critical to empower wildfire management in boreal communities with better mitigation solutions. Wildfire probability maps represent an important tool for understanding the likelihood of wildfire occurrence and the potential severity of future wildfires. The massive increase in the availability of Earth observation data has enabled the development of deep learning-based wildfire forecasting models, aiming at providing precise wildfire probability maps at different spatial and temporal scales. A main limitation of such methods is their reliance on coarse-resolution environmental drivers and satellite products, leading to wildfire occurrence prediction of reduced resolution, typically around $\sim 0.1${\deg}. This paper presents a benchmark dataset: CanadaFireSat, and baseline methods for high-resolution: 100 m wildfire forecasting across Canada, leveraging multi-modal data from high-resolution multi-spectral satellite images (Sentinel-2 L1C), mid-resolution satellite products (MODIS), and environmental factors (ERA5 reanalysis data). Our experiments consider two major deep learning architectures. We observe that using multi-modal temporal inputs outperforms single-modal temporal inputs across all metrics, achieving a peak performance of 60.3% in F1 score for the 2023 wildfire season, a season never seen during model training. This demonstrates the potential of multi-modal deep learning models for wildfire forecasting at high-resolution and continental scale.
Authors: Xulin Ma, Jiankai Tang, Zhang Jiang, Songqin Cheng, Yuanchun Shi, Dong LI, Xin Liu, Daniel McDuff, Xiaojing Liu, Yuntao Wang
Abstract: Remote photoplethysmography (rPPG) enables non-contact, continuous monitoring of physiological signals and offers a practical alternative to traditional health sensing methods. Although rPPG is promising for daily health monitoring, its application in long-term personal care scenarios, such as mirror-facing routines in high-altitude environments, remains challenging due to ambient lighting variations, frequent occlusions from hand movements, and dynamic facial postures. To address these challenges, we present LADH (Long-term Altitude Daily Health), the first long-term rPPG dataset containing 240 synchronized RGB and infrared (IR) facial videos from 21 participants across five common personal care scenarios, along with ground-truth PPG, respiration, and blood oxygen signals. Our experiments demonstrate that combining RGB and IR video inputs improves the accuracy and robustness of non-contact physiological monitoring, achieving a mean absolute error (MAE) of 4.99 BPM in heart rate estimation. Furthermore, we find that multi-task learning enhances performance across multiple physiological indicators simultaneously. Dataset and code are open at https://github.com/McJackTang/FusionVitals.
Authors: Donghoon Ahn, Jiwon Kang, Sanghyun Lee, Minjae Kim, Jaewon Min, Wooseok Jang, Sangwu Lee, Sayak Paul, Susung Hong, Seungryong Kim
Abstract: Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-free guidance is not applicable. However, existing attention perturbation methods lack principled approaches for determining where perturbations should be applied, particularly in Diffusion Transformer (DiT) architectures where quality-relevant computations are distributed across layers. In this paper, we investigate the granularity of attention perturbations, ranging from the layer level down to individual attention heads, and discover that specific heads govern distinct visual concepts such as structure, style, and texture quality. Building on this insight, we propose "HeadHunter", a systematic framework for iteratively selecting attention heads that align with user-centric objectives, enabling fine-grained control over generation quality and visual attributes. In addition, we introduce SoftPAG, which linearly interpolates each selected head's attention map toward an identity matrix, providing a continuous knob to tune perturbation strength and suppress artifacts. Our approach not only mitigates the oversmoothing issues of existing layer-level perturbation but also enables targeted manipulation of specific visual styles through compositional head selection. We validate our method on modern large-scale DiT-based text-to-image models including Stable Diffusion 3 and FLUX.1, demonstrating superior performance in both general quality enhancement and style-specific guidance. Our work provides the first head-level analysis of attention perturbation in diffusion models, uncovering interpretable specialization within attention layers and enabling practical design of effective perturbation strategies.
Authors: Morris Alper, David Novotny, Filippos Kokkinos, Hadar Averbuch-Elor, Tom Monnier
Abstract: Despite recent advances in sparse novel view synthesis (NVS) applied to object-centric scenes, scene-level NVS remains a challenge. A central issue is the lack of available clean multi-view training data, beyond manually curated datasets with limited diversity, camera variation, or licensing issues. On the other hand, an abundance of diverse and permissively-licensed data exists in the wild, consisting of scenes with varying appearances (illuminations, transient occlusions, etc.) from sources such as tourist photos. To this end, we present WildCAT3D, a framework for generating novel views of scenes learned from diverse 2D scene image data captured in the wild. We unlock training on these data sources by explicitly modeling global appearance conditions in images, extending the state-of-the-art multi-view diffusion paradigm to learn from scene views of varying appearances. Our trained model generalizes to new scenes at inference time, enabling the generation of multiple consistent novel views. WildCAT3D provides state-of-the-art results on single-view NVS in object- and scene-level settings, while training on strictly less data sources than prior methods. Additionally, it enables novel applications by providing global appearance control during generation.
Authors: Eugene Vorontsov, George Shaikovski, Adam Casson, Julian Viret, Eric Zimmermann, Neil Tenenholtz, Yi Kan Wang, Jan H. Bernhard, Ran A. Godrich, Juan A. Retamero, Jinru Shia, Mithat Gonen, Martin R. Weiser, David S. Klimstra, Razik Yousfi, Nicolo Fusi, Thomas J. Fuchs, Kristen Severson, Siqi Liu
Abstract: Recent rapid progress in the field of computational pathology has been enabled by foundation models. These models are beginning to move beyond encoding image patches towards whole-slide understanding but their clinical utility remains limited. In this work, we present PRISM2, a multimodal slide-level foundation model trained on data from 700,000 diagnostic specimen-report pairs, the largest vision (2.3 million whole slide images) and language (14M question-answer pairs) histopathology dataset to date. By learning through clinical-dialogue supervision, PRISM2 aligns histomorphologic features with the language of diagnostic reasoning, producing slide-level representations that support both direct diagnostic question-answering and transferable embeddings for downstream tasks. Without additional training, PRISM2 matches or exceeds the cancer-detection performance of clinical-grade products. This is observed without loss of generality on other tasks, where PRISM2 achieves top performance. Finally, using survival prediction as the example, we show that task-specific finetuning with a large dataset can outperform task-specific models, further improving performance. These results demonstrate how language-supervised pretraining provides a scalable, clinically grounded signal for learning generalizable pathology representations, bridging human diagnostic reasoning and foundation-model performance.
Authors: Yun Xing, Yue Cao, Nhat Chung, Jie Zhang, Ivor Tsang, Ming-Ming Cheng, Yang Liu, Lei Ma, Qing Guo
Abstract: Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help reveal vulnerabilities before deployment. Previous works have shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated textures perform poorly in physical implementations, i.e., when deployed as patches, limiting their practical utility for stress-testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals among the repeated textures, creating a grid structure, significantly enhances the patch's attack performance. Through extensive experimentation, we analyze how variations of this novel structure influence the adversarial effectiveness. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the interval structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack advanced stereo depth estimation methods of different paradigms, i.e., RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems. The code is officially released at: https://github.com/WiWiN42/DepthVanish
Authors: Qi-Ying Sun, Wan-Lei Zhao, Hui-Ying Xie, Yi-Bo Miao, Chong-Wah Ngo
Abstract: Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance-level feature representation. Supervised or weakly supervised object detection methods are not the appropriate solutions due to their poor performance on the unknown object categories. In this paper, based on the feature set output from self-supervised ViT, the instance-level region discovery is modeled as detecting the compact feature subsets in a hierarchical fashion. The hierarchical decomposition results in a hierarchy of instance regions. On the one hand, this kind of hierarchical decomposition well addresses the problem of object embedding and occlusions, which are widely observed in real scenarios. On the other hand, the non-leaf nodes and leaf nodes on the hierarchy correspond to the instance regions in different granularities within an image. Therefore, features in uniform length are produced for these instance regions, which may cover across a dominant image region, an integral of multiple instances, or various individual instances. Such a collection of features allows us to unify the image retrieval, multi-instance search, and instance search into one framework. The empirical studies on three benchmarks show that such an instance-level descriptor remains effective on both the known and unknown object categories. Moreover, the superior performance is achieved on single-instance and multi-instance search, as well as image retrieval tasks.
Authors: Chenlang Yi, Zizhan Xiong, Qi Qi, Xiyuan Wei, Girish Bathla, Ching-Long Lin, Bobak Jack Mortazavi, Tianbao Yang
Abstract: Contrastive Language-Image Pre-training (CLIP) models have demonstrated superior performance across various visual tasks including medical image classification. However, fairness concerns, including demographic biases, have received limited attention for CLIP models. This oversight leads to critical issues, particularly those related to race and gender, resulting in disparities in diagnostic outcomes and reduced reliability for underrepresented groups. To address these challenges, we introduce AdFair-CLIP, a novel framework employing adversarial feature intervention to suppress sensitive attributes, thereby mitigating spurious correlations and improving prediction fairness. We conduct comprehensive experiments on chest X-ray (CXR) datasets, and show that AdFair-CLIP significantly enhances both fairness and diagnostic accuracy, while maintaining robust generalization in zero-shot and few-shot scenarios. These results establish new benchmarks for fairness-aware learning in CLIP-based medical diagnostic models, particularly for CXR analysis.
Authors: Bingfan Zhu, Biao Jiang, Sunyi Wang, Shixiang Tang, Tao Chen, Linjie Luo, Youyi Zheng, Xin Chen
Abstract: With the rapid progress of large language models (LLMs), multimodal frameworks that unify understanding and generation have become promising, yet they face increasing complexity as the number of modalities and tasks grows. We observe that motion quantization introduces approximation errors that cap motion quality, and that unifying discrete text and continuous motion within a single-stream backbone amplifies cross-modal interference. Motivated by recent multi-branch Transformer designs that separate signals from different modalities, we propose MotionGPT3, a bimodal motion-language model for both understanding and generation. MotionGPT3 encodes raw motion into a continuous latent space using a variational autoencoder (VAE), thereby avoiding quantization-induced artifacts, while leveraging the semantic prior of pretrained language models. A dual-stream Transformer with shared attention preserves modality-specific routes while enabling controlled, bidirectional information flow, which reduces interference, stabilizing optimization, and empirically accelerates convergence without degrading fidelity. For multimodal joint training, a generate-then-align three-stage schedule further improves stability and limits cross-task interference. Experiments show that MotionGPT3 achieves 2x faster convergence in training loss and up to 4x faster convergence in validation, while maintaining state-of-the-art performance on standard motion understanding and motion generation benchmarks.
Authors: Christian Intern\`o, Robert Geirhos, Markus Olhofer, Sunny Liu, Barbara Hammer, David Klindt
Abstract: The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection methods often struggle with generalization and capturing subtle temporal inconsistencies. We propose ReStraV(Representation Straightening Video), a novel approach to distinguish natural from AI-generated videos. Inspired by the "perceptual straightening" hypothesis -- which suggests real-world video trajectories become more straight in neural representation domain -- we analyze deviations from this expected geometric property. Using a pre-trained self-supervised vision transformer (DINOv2), we quantify the temporal curvature and stepwise distance in the model's representation domain. We aggregate statistics of these measures for each video and train a classifier. Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos. A lightweight classifier achieves state-of-the-art detection performance (e.g., 97.17% accuracy and 98.63% AUROC on the VidProM benchmark), substantially outperforming existing image- and video-based methods. ReStraV is computationally efficient, it is offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection.
Authors: Jizhou Han, Shaokun Wang, Yuhang He, Chenhao Ding, Qiang Wang, Xinyuan Gao, SongLin Dong, Yihong Gong
Abstract: Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods face challenges due to inconsistent optimization objectives and category confusion. This leads to feature overlap and ultimately hinders performance on novel categories. To address these issues, we propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework. By pre-assigning and fixing Equiangular Tight Frame (ETF) prototypes, our method ensures an optimal geometric structure and a consistent optimization objective for both known and novel categories. We introduce a Consistent ETF Alignment Loss that unifies supervised and unsupervised ETF alignment and enhances category separability. Additionally, a Semantic Consistency Matcher (SCM) is designed to maintain stable and consistent label assignments across clustering iterations. Our method achieves strong performance on multiple GCD benchmarks, significantly enhancing novel category accuracy and demonstrating its effectiveness.
Authors: Mohsi Jawaid, Marcus M\"artens, Tat-Jun Chin
Abstract: Spacecraft pose estimation is crucial for autonomous in-space operations, such as rendezvous, docking and on-orbit servicing. Vision-based pose estimation methods, which typically employ RGB imaging sensors, is a compelling solution for spacecraft pose estimation, but are challenged by harsh lighting conditions, which produce imaging artifacts such as glare, over-exposure, blooming and lens flare. Due to their much higher dynamic range, neuromorphic or event sensors are more resilient to extreme lighting conditions. However, event sensors generally have lower spatial resolution and suffer from reduced signal-to-noise ratio during periods of low relative motion. This work addresses these individual sensor limitations by introducing a sensor fusion approach combining RGB and event sensors. A beam-splitter prism was employed to achieve precise optical and temporal alignment. Then, a RANSAC-based technique was developed to fuse the information from the RGB and event channels to achieve pose estimation that leveraged the strengths of the two modalities. The pipeline was complemented by dropout uncertainty estimation to detect extreme conditions that affect either channel. To benchmark the performance of the proposed event-RGB fusion method, we collected a comprehensive real dataset of RGB and event data for satellite pose estimation in a laboratory setting under a variety of challenging illumination conditions. Encouraging results on the dataset demonstrate the efficacy of our event-RGB fusion approach and further supports the usage of event sensors for spacecraft pose estimation. To support community research on this topic, our dataset has been released publicly.
Authors: Hongyong Han, Wei Wang, Gaowei Zhang, Mingjie Li, Yi Wang
Abstract: Coral reefs are vital yet vulnerable ecosystems that require continuous monitoring to support conservation. While coral reef images provide essential information in coral monitoring, interpreting such images remains challenging due to the need for domain expertise. Visual Question Answering (VQA), powered by Large Vision-Language Models (LVLMs), has great potential in user-friendly interaction with coral reef images. However, applying VQA to coral imagery demands a dedicated dataset that addresses two key challenges: domain-specific annotations and multidimensional questions. In this work, we introduce CoralVQA, the first large-scale VQA dataset for coral reef analysis. It contains 12,805 real-world coral images from 67 coral genera collected from 3 oceans, along with 277,653 question-answer pairs that comprehensively assess ecological and health-related conditions. To construct this dataset, we develop a semi-automatic data construction pipeline in collaboration with marine biologists to ensure both scalability and professional-grade data quality. CoralVQA presents novel challenges and provides a comprehensive benchmark for studying vision-language reasoning in the context of coral reef images. By evaluating several state-of-the-art LVLMs, we reveal key limitations and opportunities. These insights form a foundation for future LVLM development, with a particular emphasis on supporting coral conservation efforts.
Authors: Yuncong Yang, Jiageng Liu, Zheyuan Zhang, Siyuan Zhou, Reuben Tan, Jianwei Yang, Yilun Du, Chuang Gan
Abstract: Spatial reasoning in 3D space is central to human cognition and indispensable for embodied tasks such as navigation and manipulation. However, state-of-the-art vision-language models (VLMs) struggle frequently with tasks as simple as anticipating how a scene will look after an egocentric motion: they perceive 2D images but lack an internal model of 3D dynamics. We therefore propose MindJourney, a test-time scaling framework that grants a VLM with this missing capability by coupling it to a controllable world model based on video diffusion. The VLM iteratively sketches a concise camera trajectory, while the world model synthesizes the corresponding view at each step. The VLM then reasons over this multi-view evidence gathered during the interactive exploration. Without any fine-tuning, our MindJourney achieves over an average 7.7% performance boost on the representative spatial reasoning benchmark SAT, showing that pairing VLMs with world models for test-time scaling offers a simple, plug-and-play route to robust 3D reasoning. Meanwhile, our method also improves upon the test-time inference VLMs trained through reinforcement learning, which demonstrates the potential of our method that utilizes world models for test-time scaling.
Authors: Ren-Dong Xie, Zhi-Fen He, Bo Li, Bin Liu, Jin-Yan Hu
Abstract: Multi-label image classification is a critical task in machine learning that aims to accurately assign multiple labels to a single image. While existing methods often utilize attention mechanisms or graph convolutional networks to model visual representations, their performance is still constrained by two critical limitations: the inability to learn discriminative semantic-aware features, and the lack of fine-grained alignment between visual representations and label embeddings. To tackle these issues in a unified framework, this paper proposes a novel approach named Semantic-aware representation learning via Conditional Transport for Multi-Label Image Classification (SCT). The proposed method introduces a semantic-related feature learning module that extracts discriminative label-specific features by emphasizing semantic relevance and interaction, along with a conditional transport-based alignment mechanism that enables precise visual-semantic alignment. Extensive experiments on two widely-used benchmark datasets, VOC2007 and MS-COCO, validate the effectiveness of SCT and demonstrate its superior performance compared to existing state-of-the-art methods.
Authors: Chaowei Chen, Xiang Zhang, Honglie Guo, Shunfang Wang
Abstract: Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily focus on designing and combining various perturbation schemes, overlooking the inherent potential and limitations within the framework itself. In this paper, we first identify two critical deficiencies: (1) separated training data streams, which lead to confirmation bias dominated by the labeled stream; and (2) incomplete utilization of supervisory information, which limits exploration of strong-to-weak consistency. To tackle these challenges, we propose a style-aware blending and prototype-based cross-contrast consistency learning framework. Specifically, inspired by the empirical observation that the distribution mismatch between labeled and unlabeled data can be characterized by statistical moments, we design a style-guided distribution blending module to break the independent training data streams. Meanwhile, considering the potential noise in strong pseudo-labels, we introduce a prototype-based cross-contrast strategy to encourage the model to learn informative supervisory signals from both weak-to-strong and strong-to-weak predictions, while mitigating the adverse effects of noise. Experimental results demonstrate the effectiveness and superiority of our framework across multiple medical segmentation benchmarks under various semi-supervised settings.
Authors: Martin Hermann Paul Fuchs, Behnood Rasti, Beg\"um Demir
Abstract: With the rapid growth of hyperspectral data archives in remote sensing (RS), the need for efficient storage has become essential, driving significant attention toward learning-based hyperspectral image (HSI) compression. However, a comprehensive investigation of the individual and joint effects of spectral and spatial compression on learning-based HSI compression has not been thoroughly examined yet. Conducting such an analysis is crucial for understanding how the exploitation of spectral, spatial, and joint spatio-spectral redundancies affects HSI compression. To address this issue, we propose Adjustable Spatio-Spectral Hyperspectral Image Compression Network (HyCASS), a learning-based model designed for adjustable HSI compression in both spectral and spatial dimensions. HyCASS consists of six main modules: 1) spectral encoder module; 2) spatial encoder module; 3) compression ratio (CR) adapter encoder module; 4) CR adapter decoder module; 5) spatial decoder module; and 6) spectral decoder module. The modules employ convolutional layers and transformer blocks to capture both short-range and long-range redundancies. Experimental results on three HSI benchmark datasets demonstrate the effectiveness of our proposed adjustable model compared to existing learning-based compression models, surpassing the state of the art by up to 2.36 dB in terms of PSNR. Based on our results, we establish a guideline for effectively balancing spectral and spatial compression across different CRs, taking into account the spatial resolution of the HSIs. Our code and pre-trained model weights are publicly available at https://git.tu-berlin.de/rsim/hycass .
Authors: Shiben Liu, Mingyue Xu, Huijie Fan, Qiang Wang, Yandong Tang, Zhi Han
Abstract: Lifelong person re-identification (LReID) encounters a key challenge: balancing the preservation of old knowledge with adaptation to new information. Existing LReID methods typically employ knowledge distillation to enforce representation alignment. However, these approaches ignore two crucial aspects: specific distribution awareness and cross-domain unified knowledge learning, both of which are essential for addressing this challenge. To overcome these limitations, we propose a novel distribution-aware knowledge unification and association (DKUA) framework where domain-style modeling is performed for each instance to propagate domain-specific representations, enhancing anti-forgetting and generalization capacity. Specifically, we design a distribution-aware model to transfer instance-level representations of the current domain into the domain-specific representations with the different domain styles, preserving learned knowledge without storing old samples. Next, we propose adaptive knowledge consolidation (AKC) to dynamically generate the unified representation as a cross-domain representation center. To further mitigate forgetting, we develop a unified knowledge association (UKA) mechanism, which explores the unified representation as a bridge to explicitly model inter-domain associations, reducing inter-domain gaps. Finally, distribution-based knowledge transfer (DKT) is proposed to prevent the current domain distribution from deviating from the cross-domain distribution center, improving adaptation capacity. Experimental results show our DKUA outperforms the existing methods by 7.6%/5.3% average mAP/R@1 improvement on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/LiuShiBen/DKUA.
Authors: Samuel R\"aber, Till Aczel, Andreas Plesner, Roger Wattenhofer
Abstract: Previous work has suggested that preprocessing images through lossy compression can defend against adversarial perturbations, but comprehensive attack evaluations have been lacking. In this paper, we construct strong white-box and adaptive attacks against various compression models and identify a critical challenge for attackers: high realism in reconstructed images significantly increases attack difficulty. Through rigorous evaluation across multiple attack scenarios, we demonstrate that compression models capable of producing realistic, high-fidelity reconstructions are substantially more resistant to our attacks. In contrast, low-realism compression models can be broken. Our analysis reveals that this is not due to gradient masking. Rather, realistic reconstructions maintaining distributional alignment with natural images seem to offer inherent robustness. This work highlights a significant obstacle for future adversarial attacks and suggests that developing more effective techniques to overcome realism represents an essential challenge for comprehensive security evaluation.
Authors: Yingxian Chen, Jiahui Liu, Ruidi Fan, Yanwei Li, Chirui Chang, Shizhen Zhao, Wilton W. T. Fok, Xiaojuan Qi, Yik-Chung Wu
Abstract: Understanding abnormal events in videos is a vital and challenging task that has garnered significant attention in a wide range of applications. Although current video understanding Multi-modal Large Language Models (MLLMs) are capable of analyzing general videos, they often struggle to handle anomalies due to the spatial and temporal sparsity of abnormal events, where the redundant information always leads to suboptimal outcomes. To address these challenges, exploiting the representation and generalization capabilities of Vison Language Models (VLMs) and Large Language Models (LLMs), we propose VA-GPT, a novel MLLM designed for summarizing and localizing abnormal events in various videos. Our approach efficiently aligns effective tokens between visual encoders and LLMs through two key proposed modules: Spatial Effective Token Selection (SETS) and Temporal Effective Token Generation (TETG). These modules enable our model to effectively capture and analyze both spatial and temporal information associated with abnormal events, resulting in more accurate responses and interactions. Furthermore, we construct an instruction-following dataset specifically for fine-tuning video-anomaly-aware MLLMs, and introduce a cross-domain evaluation benchmark based on XD-Violence dataset. Our proposed method outperforms existing state-of-the-art methods on various benchmarks.
Authors: Nahyuk Lee, Juhong Min, Junhong Lee, Chunghyun Park, Minsu Cho
Abstract: This paper introduces a new shape-matching methodology, combinative matching, to combine interlocking parts for geometric shape assembly. Previous methods for geometric assembly typically rely on aligning parts by finding identical surfaces between the parts as in conventional shape matching and registration. In contrast, we explicitly model two distinct properties of interlocking shapes: 'identical surface shape' and 'opposite volume occupancy.' Our method thus learns to establish correspondences across regions where their surface shapes appear identical but their volumes occupy the inverted space to each other. To facilitate this process, we also learn to align regions in rotation by estimating their shape orientations via equivariant neural networks. The proposed approach significantly reduces local ambiguities in matching and allows a robust combination of parts in assembly. Experimental results on geometric assembly benchmarks demonstrate the efficacy of our method, consistently outperforming the state of the art. Project page: https://nahyuklee.github.io/cmnet.
Authors: Shu Shen, C. L. Philip Chen, Tong Zhang
Abstract: Multimodal learning has significantly enhanced machine learning performance but still faces numerous challenges and limitations. Imbalanced multimodal learning is one of the problems extensively studied in recent works and is typically mitigated by modulating the learning of each modality. However, we find that these methods typically hinder the dominant modality's learning to promote weaker modalities, which affects overall multimodal performance. We analyze the cause of this issue and highlight a commonly overlooked problem: optimization bias within networks. To address this, we propose Adaptive Intra-Network Modulation (AIM) to improve balanced modality learning. AIM accounts for differences in optimization state across parameters and depths within the network during modulation, achieving balanced multimodal learning without hindering either dominant or weak modalities for the first time. Specifically, AIM decouples the dominant modality's under-optimized parameters into Auxiliary Blocks and encourages reliance on these performance-degraded blocks for joint training with weaker modalities. This approach effectively prevents suppression of weaker modalities while enabling targeted optimization of under-optimized parameters to improve the dominant modality. Additionally, AIM assesses modality imbalance level across network depths and adaptively adjusts modulation strength at each depth. Experimental results demonstrate that AIM outperforms state-of-the-art imbalanced modality learning methods across multiple benchmarks and exhibits strong generalizability across different backbones, fusion strategies, and optimizers.
Authors: Zhongmiao Qi, Yan Jiang, Bolin Zhang, Lijun Guo, Chong Wang, Qiangbo Qian
Abstract: With the explosive growth of video data in various complex scenarios, quickly retrieving group activities has become an urgent problem. However, many tasks can only retrieve videos focusing on an entire video, not the activity granularity. To solve this problem, we propose a new STVH (spatiotemporal interleaved video hashing) technique for the first time. Through a unified framework, the STVH simultaneously models individual object dynamics and group interactions, capturing the spatiotemporal evolution on both group visual features and positional features. Moreover, in real-life video retrieval scenarios, it may sometimes require activity features, while at other times, it may require visual features of objects. We then further propose a novel M-STVH (multi-focused spatiotemporal video hashing) as an enhanced version to handle this difficult task. The advanced method incorporates hierarchical feature integration through multi-focused representation learning, allowing the model to jointly focus on activity semantics features and object visual features. We conducted comparative experiments on publicly available datasets, and both STVH and M-STVH can achieve excellent results.
Authors: Liangjing Shao, Chenkang Du, Benshuang Chen, Xueli Liu, Xinrong Chen
Abstract: Self-supervised monocular depth estimation is a significant task for low-cost and efficient 3D scene perception and measurement in endoscopy. However, the variety of illumination conditions and scene features is still the primary challenges for depth estimation in endoscopic scenes. In this work, a novel self-supervised framework is proposed for monocular depth estimation in diverse endoscopy. Firstly, considering the diverse features in endoscopic scenes with different tissues, a novel block-wise mixture of dynamic low-rank experts is proposed to efficiently finetune the foundation model for endoscopic depth estimation. In the proposed module, based on the input feature, different experts with a small amount of trainable parameters are adaptively selected for weighted inference, from low-rank experts which are allocated based on the generalization of each block. Moreover, a novel self-supervised training framework is proposed to jointly cope with brightness inconsistency and reflectance interference. The proposed method outperforms state-of-the-art works on SCARED dataset and SimCol dataset. Furthermore, the proposed network also achieves the best generalization based on zero-shot depth estimation on C3VD, Hamlyn and SERV-CT dataset. The outstanding performance of our model is further demonstrated with 3D reconstruction and ego-motion estimation. The proposed method could contribute to accurate endoscopy for minimally invasive measurement and surgery. The evaluation codes will be released upon acceptance, while the demo videos can be found on: https://endo-gmde.netlify.app/.
Authors: Nojod M. Alotaibi, Areej M. Alhothali, Manar S. Ali
Abstract: Major depressive disorder (MDD) is a prevalent mental health condition that negatively impacts both individual well-being and global public health. Automated detection of MDD using structural magnetic resonance imaging (sMRI) and deep learning (DL) methods holds increasing promise for improving diagnostic accuracy and enabling early intervention. Most existing methods employ either voxel-level features or handcrafted regional representations built from predefined brain atlases, limiting their ability to capture complex brain patterns. This paper develops a unified pipeline that utilizes Vision Transformers (ViTs) for extracting 3D region embeddings from sMRI data and Graph Neural Network (GNN) for classification. We explore two strategies for defining regions: (1) an atlas-based approach using predefined structural and functional brain atlases, and (2) an cube-based method by which ViTs are trained directly to identify regions from uniformly extracted 3D patches. Further, cosine similarity graphs are generated to model interregional relationships, and guide GNN-based classification. Extensive experiments were conducted using the REST-meta-MDD dataset to demonstrate the effectiveness of our model. With stratified 10-fold cross-validation, the best model obtained 78.98% accuracy, 76.54% sensitivity, 81.58% specificity, 81.58% precision, and 78.98% F1-score. Further, atlas-based models consistently outperformed the cube-based approach, highlighting the importance of using domain-specific anatomical priors for MDD detection.
Authors: Xuan Deng, Xingtao Wang, Xiandong Meng, Longguang Wang, Tiange Zhang, Xiaopeng Fan, Debin Zhao
Abstract: Efficient dynamic point cloud compression (DPCC) critically depends on accurate motion estimation and compensation. However, the inherently irregular structure and substantial local variations of point clouds make this task highly challenging. Existing approaches typically rely on explicit motion estimation, whose encoded motion vectors often fail to capture complex dynamics and inadequately exploit temporal correlations. To address these limitations, we propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space. Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations, which serve as predictive context in a conditional coding pipeline, forming a unified ``Motion + Conditional'' representation. Built upon this bidirectional feature alignment, we introduce a Cross-Transformer Refinement module (CTR) at the decoder side to adaptively refine locally aligned features. By modeling cross-frame dependencies with vector attention, CRT enhances local consistency and restores fine-grained spatial details that are often lost during motion alignment. Moreover, we design a Random Access (RA) reference strategy that treats the bidirectionally aligned features as conditional context, enabling frame-level parallel compression and eliminating the sequential encoding. Extensive experiments demonstrate that Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime, achieving BD-Rate reductions of 20% (D1) and 9.4% (D1), respectively.
Authors: Guangze Zheng, Shijie Lin, Haobo Zuo, Si Si, Ming-Shan Wang, Changhong Fu, Jia Pan
Abstract: This work proposes the Lattice Boltzmann Model (LBM) to learn real-world pixel dynamicity for visual tracking. LBM decomposes visual representations into dynamic pixel lattices and solves pixel motion states through collision-streaming processes. Specifically, the high-dimensional distribution of the target pixels is acquired through a multilayer predict-update network to estimate the pixel positions and visibility. The predict stage formulates lattice collisions among the spatial neighborhood of target pixels and develops lattice streaming within the temporal visual context. The update stage rectifies the pixel distributions with online visual representations. Compared with existing methods, LBM demonstrates practical applicability in an online and real-time manner, which can efficiently adapt to real-world visual tracking tasks. Comprehensive evaluations of real-world point tracking benchmarks such as TAP-Vid and RoboTAP validate LBM's efficiency. A general evaluation of large-scale open-world object tracking benchmarks such as TAO, BFT, and OVT-B further demonstrates LBM's real-world practicality.
Authors: Bishal Adhikari, Jiajia Li, Eric S. Michel, Jacob Dykes, Te-Ming Paul Tseng, Mary Love Tagert, Dong Chen
Abstract: The escalating economic losses in agriculture due to deer intrusion, estimated to be in the hundreds of millions of dollars annually in the U.S., highlight the inadequacy of traditional mitigation strategies such as hunting, fencing, use of repellents, and scare tactics. This underscores a critical need for intelligent, autonomous solutions capable of real-time deer detection and deterrence. But the progress in this field is impeded by a significant gap in the literature, mainly the lack of a domain-specific, practical dataset and limited study on the viability of deer detection systems on edge devices. To address this gap, this study presents a comprehensive evaluation of state-of-the-art deep learning models for deer detection in challenging real-world scenarios. We introduce a curated, publicly available dataset of 3,095 annotated images with bounding box annotations of deer. Then, we provide an extensive comparative analysis of 12 model variants across four recent YOLO architectures (v8 to v11). Finally, we evaluated their performance on two representative edge computing platforms: the CPU-based Raspberry Pi 5 and the GPU-accelerated NVIDIA Jetson AGX Xavier to assess feasibility for real-world field deployment. Results show that the real-time detection performance is not feasible on Raspberry Pi without hardware-specific model optimization, while NVIDIA Jetson provides greater than 30 frames per second (FPS) with 's' and 'n' series models. This study also reveals that smaller, architecturally advanced models such as YOLOv11n, YOLOv8s, and YOLOv9s offer the optimal balance of high accuracy (Average Precision (AP) > 0.85) and computational efficiency (Inference Time < 34 milliseconds).
Authors: Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang, Chen Zhao, Adams Wai-Kin Kong
Abstract: Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image diffusion models (e.g., SD3.5, FLUX) already encode essential physical and resolution priors, yet lack a framework to unleash them without resorting to latent inversion, which often locks object poses into contextually inappropriate orientations, or brittle attention surgery. We propose SHINE, a training-free framework for Seamless, High-fidelity Insertion with Neutralized Errors. SHINE introduces manifold-steered anchor loss, leveraging pretrained customization adapters (e.g., IP-Adapter) to guide latents for faithful subject representation while preserving background integrity. Degradation-suppression guidance and adaptive background blending are proposed to further eliminate low-quality outputs and visible seams. To address the lack of rigorous benchmarks, we introduce ComplexCompo, featuring diverse resolutions and challenging conditions such as low lighting, strong illumination, intricate shadows, and reflective surfaces. Experiments on ComplexCompo and DreamEditBench show state-of-the-art performance on standard metrics (e.g., DINOv2) and human-aligned scores (e.g., DreamSim, ImageReward, VisionReward). Code and benchmark will be publicly available upon publication.
Authors: Shimaa Elbana, Ahmad Kamal, Shahd Ahmed Ali, Ahmad Al-Kabbany
Abstract: The increasing size and complexity of medical imaging datasets, particularly in 3D formats, present significant barriers to collaborative research and transferability. This study investigates whether the ZFP compression technique can mitigate these challenges without compromising the performance of automated cerebrovascular segmentation, a critical first step in intracranial aneurysm detection. We apply ZFP in both its error tolerance and fixed-rate modes to a large scale, and one of the most recent, datasets in the literature, 3D medical dataset containing ground-truth vascular segmentations. The segmentation quality on the compressed volumes is rigorously compared to the uncompressed baseline (Dice approximately equals 0.8774). Our findings reveal that ZFP can achieve substantial data reduction--up to a 22.89:1 ratio in error tolerance mode--while maintaining a high degree of fidelity, with the mean Dice coefficient remaining high at 0.87656. These results demonstrate that ZFP is a viable and powerful tool for enabling more efficient and accessible research on large-scale medical datasets, fostering broader collaboration across the community.
Authors: Yaxin Hou, Bo Han, Yuheng Jia, Hui Liu, Junhui Hou
Abstract: Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However, the distribution of the unlabeled data is generally unknown and may follow an arbitrary distribution. To tackle this challenge, we propose a Controllable Pseudo-label Generation (CPG) framework, expanding the labeled dataset with the progressively identified reliable pseudo-labels from the unlabeled dataset and training the model on the updated labeled dataset with a known distribution, making it unaffected by the unlabeled data distribution. Specifically, CPG operates through a controllable self-reinforcing optimization cycle: (i) at each training step, our dynamic controllable filtering mechanism selectively incorporates reliable pseudo-labels from the unlabeled dataset into the labeled dataset, ensuring that the updated labeled dataset follows a known distribution; (ii) we then construct a Bayes-optimal classifier using logit adjustment based on the updated labeled data distribution; (iii) this improved classifier subsequently helps identify more reliable pseudo-labels in the next training step. We further theoretically prove that this optimization cycle can significantly reduce the generalization error under some conditions. Additionally, we propose a class-aware adaptive augmentation module to further improve the representation of minority classes, and an auxiliary branch to maximize data utilization by leveraging all labeled and unlabeled samples. Comprehensive evaluations on various commonly used benchmark datasets show that CPG achieves consistent improvements, surpassing state-of-the-art methods by up to $\textbf{15.97%}$ in accuracy. The code is available at https://github.com/yaxinhou/CPG.
Authors: Viktor Koz\'ak, Jan Chudoba, Libor P\v{r}eu\v{c}il
Abstract: An accurate and up-to-date model of a photovoltaic (PV) power plant is essential for its optimal operation and maintenance. However, such a model may not be easily available. This work introduces a novel approach for PV power plant mapping based on aerial overview images. It enables the automation of the mapping process while removing the reliance on third-party data. The presented mapping method takes advantage of the structural layout of the power plants to achieve detailed modeling down to the level of individual PV modules. The approach relies on visual segmentation of PV modules in overview images and the inference of structural information in each image, assigning modules to individual benches, rows, and columns. We identify visual keypoints related to the layout and use these to merge detections from multiple images while maintaining their structural integrity. The presented method was experimentally verified and evaluated on two different power plants. The final fusion of 3D positions and semantic structures results in a compact georeferenced model suitable for power plant maintenance.
Authors: Zexin Zheng, Huangyu Dai, Lingtao Mao, Xinyu Sun, Zihan Liang, Ben Chen, Yuqing Ding, Chenyi Lei, Wenwu Ou, Han Li, Kun Gai
Abstract: Traditional vision search, similar to search and recommendation systems, follows the multi-stage cascading architecture (MCA) paradigm to balance efficiency and conversion. Specifically, the query image undergoes feature extraction, recall, pre-ranking, and ranking stages, ultimately presenting the user with semantically similar products that meet their preferences. This multi-view representation discrepancy of the same object in the query and the optimization objective collide across these stages, making it difficult to achieve Pareto optimality in both user experience and conversion. In this paper, an end-to-end generative framework, OneVision, is proposed to address these problems. OneVision builds on VRQ, a vision-aligned residual quantization encoding, which can align the vastly different representations of an object across multiple viewpoints while preserving the distinctive features of each product as much as possible. Then a multi-stage semantic alignment scheme is adopted to maintain strong visual similarity priors while effectively incorporating user-specific information for personalized preference generation. In offline evaluations, OneVision performs on par with online MCA, while improving inference efficiency by 21% through dynamic pruning. In A/B tests, it achieves significant online improvements: +2.15% item CTR, +2.27% CVR, and +3.12% order volume. These results demonstrate that a semantic ID centric, generative architecture can unify retrieval and personalization while simplifying the serving pathway.
Authors: Mert Kiray, Alican Karaomer, Benjamin Busam
Abstract: We present DropD-SLAM, a real-time monocular SLAM system that achieves RGB-D-level accuracy without relying on depth sensors. The system replaces active depth input with three pretrained vision modules: a monocular metric depth estimator, a learned keypoint detector, and an instance segmentation network. Dynamic objects are suppressed using dilated instance masks, while static keypoints are assigned predicted depth values and backprojected into 3D to form metrically scaled features. These are processed by an unmodified RGB-D SLAM back end for tracking and mapping. On the TUM RGB-D benchmark, DropD-SLAM attains 7.4 cm mean ATE on static sequences and 1.8 cm on dynamic sequences, matching or surpassing state-of-the-art RGB-D methods while operating at 22 FPS on a single GPU. These results suggest that modern pretrained vision models can replace active depth sensors as reliable, real-time sources of metric scale, marking a step toward simpler and more cost-effective SLAM systems.
Authors: Jonghyun Park, Minhyuk Seo, Jonghyun Choi
Abstract: One of the key challenges of modern AI models is ensuring that they provide helpful responses to benign queries while refusing malicious ones. But often, the models are vulnerable to multimodal queries with harmful intent embedded in images. One approach for safety alignment is training with extensive safety datasets at the significant costs in both dataset curation and training. Inference-time alignment mitigates these costs, but introduces two drawbacks: excessive refusals from misclassified benign queries and slower inference speed due to iterative output adjustments. To overcome these limitations, we propose to reformulate queries to strengthen cross-modal attention to safety-critical image regions, enabling accurate risk assessment at the query level. Using the assessed risk, it adaptively steers activations to generate responses that are safe and helpful without overhead from iterative output adjustments. We call this Risk-adaptive Activation Steering (RAS). Extensive experiments across multiple benchmarks on multimodal safety and utility demonstrate that the RAS significantly reduces attack success rates, preserves general task performance, and improves inference speed over prior inference-time defenses.
Authors: Alexander Valverde, Brian Xu, Yuyin Zhou, Meng Xu, Hongyun Wang
Abstract: Scene reconstruction has emerged as a central challenge in computer vision, with approaches such as Neural Radiance Fields (NeRF) and Gaussian Splatting achieving remarkable progress. While Gaussian Splatting demonstrates strong performance on large-scale datasets, it often struggles to capture fine details or maintain realism in regions with sparse coverage, largely due to the inherent limitations of sparse 3D training data. In this work, we propose GauSSmart, a hybrid method that effectively bridges 2D foundational models and 3D Gaussian Splatting reconstruction. Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision from foundational models such as DINO, to enhance Gaussian-based scene reconstruction. By leveraging 2D segmentation priors and high-dimensional feature embeddings, our method guides the densification and refinement of Gaussian splats, improving coverage in underrepresented areas and preserving intricate structural details. We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting in the majority of evaluated scenes. Our results demonstrate the significant potential of hybrid 2D-3D approaches, highlighting how the thoughtful combination of 2D foundational models with 3D reconstruction pipelines can overcome the limitations inherent in either approach alone.
Authors: Qi Chen, Xinze Zhou, Chen Liu, Hao Chen, Wenxuan Li, Zekun Jiang, Ziyan Huang, Yuxuan Zhao, Dexin Yu, Junjun He, Yefeng Zheng, Ling Shao, Alan Yuille, Zongwei Zhou
Abstract: AI for tumor segmentation is limited by the lack of large, voxel-wise annotated datasets, which are hard to create and require medical experts. In our proprietary JHH dataset of 3,000 annotated pancreatic tumor scans, we found that AI performance stopped improving after 1,500 scans. With synthetic data, we reached the same performance using only 500 real scans. This finding suggests that synthetic data can steepen data scaling laws, enabling more efficient model training than real data alone. Motivated by these lessons, we created AbdomenAtlas 2.0--a dataset of 10,135 CT scans with a total of 15,130 tumor instances per-voxel manually annotated in six organs (pancreas, liver, kidney, colon, esophagus, and uterus) and 5,893 control scans. Annotated by 23 expert radiologists, it is several orders of magnitude larger than existing public tumor datasets. While we continue expanding the dataset, the current version of AbdomenAtlas 2.0 already provides a strong foundation--based on lessons from the JHH dataset--for training AI to segment tumors in six organs. It achieves notable improvements over public datasets, with a +7% DSC gain on in-distribution tests and +16% on out-of-distribution tests.
Authors: Usman Afzaal, Ziyu Su, Usama Sajjad, Hao Lu, Mostafa Rezapour, Metin Nafi Gurcan, Muhammad Khalid Khan Niazi
Abstract: Reproducibility remains a critical challenge in foundation model training for histopathology, often hindered by software randomness, hardware non-determinism, and inconsistent hyperparameter reporting. To investigate these issues, we trained a CLIP model on the QUILT-1M dataset and systematically evaluated the impact of different hyperparameter settings and augmentation strategies across three downstream histopathology datasets (PatchCamelyon, LC25000-Lung, and LC25000-Colon). Despite variability across runs, we identified clear trends: RandomResizedCrop values of 0.7-0.8 outperformed more aggressive (0.6) or conservative (0.9) settings, distributed training without local loss improved stability, and learning rates below 5.0e-5 consistently degraded performance across all datasets. The LC25000 (Colon) dataset consistently provided the most reproducible benchmark. These findings highlight that reproducibility in computational pathology depends not only on transparent documentation but also on carefully chosen experimental configurations, and we provide practical rules to guide future efforts in developing reproducible foundation models for digital pathology.
Authors: Chenxu Li, Zhicai Wang, Yuan Sheng, Xingyu Zhu, Yanbin Hao, Xiang Wang
Abstract: Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether performance remains stable across varying input resolutions. To address this gap, we introduce \textbf{Res-Bench}, a comprehensive benchmark comprising 14,400 samples across 12 resolution levels and six core capability dimensions. We designed a novel evaluation framework that goes beyond traditional accuracy metrics to capture performance stability. This framework introduces multiple robustness metrics: Spearman's correlation for assessing resolution-performance trends, and Absolute/Relative Continuous Error (ACE/RCE) for measuring performance volatility. Using these metrics, we conducted a large-scale evaluation of leading MLLMs. Our analysis encompasses: (1) model-centric and task-centric robustness examination, (2) investigation of preprocessing strategies including padding and super-resolution, and (3) exploration of fine-tuning for stability enhancement.
Authors: Tianci Bi, Xiaoyi Zhang, Yan Lu, Nanning Zheng
Abstract: The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizer. While recent works have explored incorporating Vision Foundation Models (VFMs) via distillation, we identify a fundamental flaw in this approach: it inevitably weakens the robustness of alignment with the original VFM, causing the aligned latents to deviate semantically under distribution shifts. In this paper, we bypass distillation by proposing a more direct approach: Vision Foundation Model Variational Autoencoder (VFM-VAE). To resolve the inherent tension between the VFM's semantic focus and the need for pixel-level fidelity, we redesign the VFM-VAE decoder with Multi-Scale Latent Fusion and Progressive Resolution Reconstruction blocks, enabling high-quality reconstruction from spatially coarse VFM features. Furthermore, we provide a comprehensive analysis of representation dynamics during diffusion training, introducing the proposed SE-CKNNA metric as a more precise tool for this diagnosis. This analysis allows us to develop a joint tokenizer-diffusion alignment strategy that dramatically accelerates convergence. Our innovations in tokenizer design and training strategy lead to superior performance and efficiency: our system reaches a gFID (w/o CFG) of 2.20 in merely 80 epochs (a 10x speedup over prior tokenizers). With continued training to 640 epochs, it further attains a gFID (w/o CFG) of 1.62, establishing direct VFM integration as a superior paradigm for LDMs.
Authors: Xiaoqing Lan, Biqiao Xin, Bingshu Wang, Han Zhang, Rui Zhu, Laixian Zhang
Abstract: Space objects in Geostationary Earth Orbit (GEO) present significant detection challenges in optical imaging due to weak signals, complex stellar backgrounds, and environmental interference. In this paper, we enhance high-frequency features of GEO targets while suppressing background noise at the single-frame level through wavelet transform. Building on this, we propose a multi-frame temporal trajectory completion scheme centered on the Hungarian algorithm for globally optimal cross-frame matching. To effectively mitigate missing and false detections, a series of key steps including temporal matching and interpolation completion, temporal-consistency-based noise filtering, and progressive trajectory refinement are designed in the post-processing pipeline. Experimental results on the public SpotGEO dataset demonstrate the effectiveness of the proposed method, achieving an F_1 score of 90.14%.
Authors: Junfei Zhou, Penglin Dai, Quanmin Wei, Bingyi Liu, Xiao Wu, Jianping Wang
Abstract: Multi-agent collaboration enhances the perception capabilities of individual agents through information sharing. However, in real-world applications, differences in sensors and models across heterogeneous agents inevitably lead to domain gaps during collaboration. Existing approaches based on adaptation and reconstruction fail to support pragmatic heterogeneous collaboration due to two key limitations: (1) Intrusive retraining of the encoder or core modules disrupts the established semantic consistency among agents; and (2) accommodating new agents incurs high computational costs, limiting scalability. To address these challenges, we present a novel Generative Communication mechanism (GenComm) that facilitates seamless perception across heterogeneous multi-agent systems through feature generation, without altering the original network, and employs lightweight numerical alignment of spatial information to efficiently integrate new agents at minimal cost. Specifically, a tailored Deformable Message Extractor is designed to extract spatial message for each collaborator, which is then transmitted in place of intermediate features. The Spatial-Aware Feature Generator, utilizing a conditional diffusion model, generates features aligned with the ego agent's semantic space while preserving the spatial information of the collaborators. These generated features are further refined by a Channel Enhancer before fusion. Experiments conducted on the OPV2V-H, DAIR-V2X and V2X-Real datasets demonstrate that GenComm outperforms existing state-of-the-art methods, achieving an 81% reduction in both computational cost and parameter count when incorporating new agents. Our code is available at https://github.com/jeffreychou777/GenComm.
Authors: Adinath Dukre, Ankan Deria, Yutong Xie, Imran Razzak
Abstract: Atypical mitotic figures are important biomarkers of tumor aggressiveness in histopathology, yet reliable recognition remains challenging due to severe class imbalance and variability across imaging domains. We present a DenseNet-121-based framework tailored for atypical mitosis classification in the MIDOG 2025 (Track 2) setting. Our method integrates stain-aware augmentation (Macenko), geometric and intensity transformations, and imbalance-aware learning via weighted sampling with a hybrid objective combining class-weighted binary cross-entropy and focal loss. Trained end-to-end with AdamW and evaluated across multiple independent domains, the model demonstrates strong generalization under scanner and staining shifts, achieving balanced accuracy 85.0%, AUROC 0.927, sensitivity 89.2%, and specificity 80.9% on the official test set. These results indicate that combining DenseNet-121 with stain-aware augmentation and imbalance-adaptive objectives yields a robust, domain-generalizable framework for atypical mitosis classification suitable for real-world computational pathology workflows.
Authors: Ningli Xu, Rongjun Qin
Abstract: Cross-view localization and synthesis are two fundamental tasks in cross-view visual understanding, which deals with cross-view datasets: overhead (satellite or aerial) and ground-level imagery. These tasks have gained increasing attention due to their broad applications in autonomous navigation, urban planning, and augmented reality. Cross-view localization aims to estimate the geographic position of ground-level images based on information provided by overhead imagery while cross-view synthesis seeks to generate ground-level images based on information from the overhead imagery. Both tasks remain challenging due to significant differences in viewing perspective, resolution, and occlusion, which are widely embedded in cross-view datasets. Recent years have witnessed rapid progress driven by the availability of large-scale datasets and novel approaches. Typically, cross-view localization is formulated as an image retrieval problem where ground-level features are matched with tiled overhead images feature, extracted by convolutional neural networks (CNNs) or vision transformers (ViTs) for cross-view feature embedding. Cross-view synthesis, on the other hand, seeks to generate ground-level views based on information from overhead imagery, generally using generative adversarial networks (GANs) or diffusion models. This paper presents a comprehensive survey of advances in cross-view localization and synthesis, reviewing widely used datasets, highlighting key challenges, and providing an organized overview of state-of-the-art techniques. Furthermore, it discusses current limitations, offers comparative analyses, and outlines promising directions for future research. We also include the project page via https://github.com/GDAOSU/Awesome-Cross-View-Methods.
Authors: Yuqian Yuan, Wenqiao Zhang, Xin Li, Shihao Wang, Kehan Li, Wentong Li, Jun Xiao, Lei Zhang, Beng Chin Ooi
Abstract: Multimodal large language models (MLLMs) have demonstrated strong general-purpose capabilities in open-world visual comprehension. However, most existing MLLMs primarily focus on holistic, scene-level understanding, often overlooking the need for fine-grained, object-centric reasoning. In this paper, we present PixelRefer, a unified region-level MLLM framework that enables advanced fine-grained understanding over user-specified regions across both images and videos. Motivated by the observation that LLM attention predominantly focuses on object-level tokens, we propose a Scale-Adaptive Object Tokenizer (SAOT) to generate compact and semantically rich object representations from free-form regions. Our analysis reveals that global visual tokens contribute mainly in early LLM layers, inspiring the design of PixelRefer-Lite, an efficient variant that employs an Object-Centric Infusion module to pre-fuse global context into object tokens. This yields a lightweight Object-Only Framework that substantially reduces computational cost while maintaining high semantic fidelity. To facilitate fine-grained instruction tuning, we curate PixelRefer-2.2M, a high-quality object-centric instruction dataset. Extensive experiments across a range of benchmarks validate that PixelRefer achieves leading performance with fewer training samples, while PixelRefer-Lite offers competitive accuracy with notable gains in efficiency.
Authors: Forouzan Fallah, Wenwen Li, Chia-Yu Hsu, Hyunho Lee, Yezhou Yang
Abstract: Super-resolution (SR) for remote sensing imagery often fails under out-of-distribution (OOD) conditions, such as rare geomorphic features captured by diverse sensors, producing visually plausible but physically inaccurate results. We present RareFlow, a physics-aware SR framework designed for OOD robustness. RareFlow's core is a dual-conditioning architecture. A Gated ControlNet preserves fine-grained geometric fidelity from the low-resolution input, while textual prompts provide semantic guidance for synthesizing complex features. To ensure physically sound outputs, we introduce a multifaceted loss function that enforces both spectral and radiometric consistency with sensor properties. Furthermore, the framework quantifies its own predictive uncertainty by employing a stochastic forward pass approach; the resulting output variance directly identifies unfamiliar inputs, mitigating feature hallucination. We validate RareFlow on a new, curated benchmark of multi-sensor satellite imagery. In blind evaluations, geophysical experts rated our model's outputs as approaching the fidelity of ground truth imagery, significantly outperforming state-of-the-art baselines. This qualitative superiority is corroborated by quantitative gains in perceptual metrics, including a nearly 40\% reduction in FID. RareFlow provides a robust framework for high-fidelity synthesis in data-scarce scientific domains and offers a new paradigm for controlled generation under severe domain shift.
Authors: Ali Ahmad Faour, Nabil Amacha, Ali J. Ghandour
Abstract: The sustainable management of the Qaraaoun Reservoir, the largest surface water body in Lebanon located in the Bekaa Plain, depends on reliable monitoring of its storage volume despite frequent sensor malfunctions and limited maintenance capacity. This study introduces a sensor-free approach that integrates open-source satellite imagery, advanced water-extent segmentation, and machine learning to estimate the reservoir's surface area and, subsequently, its volume in near real time. Sentinel-2 and Landsat 1-9 images are processed, where surface water is delineated using a newly proposed water segmentation index. A machine learning model based on Support Vector Regression (SVR) is trained on a curated dataset that includes water surface area, water level, and water volume derived from a reservoir bathymetric survey. The model is then able to estimate the water body's volume solely from the extracted water surface, without the need for any ground-based measurements. Water segmentation using the proposed index aligns with ground truth for over 95% of the shoreline. Hyperparameter tuning with GridSearchCV yields an optimized SVR performance, with an error below 1.5% of the full reservoir capacity and coefficients of determination exceeding 0.98. These results demonstrate the method's robustness and cost-effectiveness, offering a practical solution for continuous, sensor-independent monitoring of reservoir storage. The proposed methodology is applicable to other water bodies and generates over five decades of time-series data, offering valuable insights into climate change and environmental dynamics, with an emphasis on capturing temporal trends rather than exact water volume measurements.
Authors: Reem Hammoud, Abdul karim Gizzini, Ali J. Ghandour
Abstract: Ensuring transparency and trust in artificial intelligence (AI) models is essential as they are increasingly deployed in safety-critical and high-stakes domains. Explainable AI (XAI) has emerged as a promising approach to address this challenge; however, the rigorous evaluation of XAI methods remains vital for balancing the trade-offs between model complexity, predictive performance, and interpretability. While substantial progress has been made in evaluating XAI for classification tasks, strategies tailored to semantic segmentation remain limited. Moreover, objectively assessing XAI approaches is difficult, since qualitative visual explanations provide only preliminary insights. Such qualitative methods are inherently subjective and cannot ensure the accuracy or stability of explanations. To address these limitations, this work introduces a comprehensive quantitative evaluation framework for assessing XAI in semantic segmentation, accounting for both spatial and contextual task complexities. The framework systematically integrates pixel-level evaluation strategies with carefully designed metrics to yield fine-grained interpretability insights. Simulation results using recently adapted class activation mapping (CAM)-based XAI schemes demonstrate the efficiency, robustness, and reliability of the proposed methodology. These findings advance the development of transparent, trustworthy, and accountable semantic segmentation models.
Authors: Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi, Paolo Favaro
Abstract: Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the visual domain, where models, including LLMs, continue to struggle with compositional understanding, sample efficiency, and general-purpose problem-solving. We investigate Video Diffusion Models (VDMs) as a promising direction for bridging this gap. Pretraining on spatiotemporal data endows these models with strong inductive biases for structure and dynamics, which we hypothesize can support broad task adaptability. To test this, we design a controlled evaluation in which both a pretrained LLM and a pretrained VDM are equipped with lightweight adapters and presented with tasks in their natural modalities. Across benchmarks including ARC-AGI, ConceptARC, visual games, route planning, and cellular automata, VDMs demonstrate higher data efficiency than their language counterparts. Taken together, our results indicate that video pretraining offers inductive biases that support progress toward visual foundation models.
Authors: Charles Javerliat, Pierre Raimbaud, Guillaume Lavou\'e
Abstract: Markerless multiview motion capture is often constrained by the need for precise camera calibration, limiting accessibility for non-experts and in-the-wild captures. Existing calibration-free approaches mitigate this requirement but suffer from high computational cost and reduced reconstruction accuracy. We present Kineo, a fully automatic, calibration-free pipeline for markerless motion capture from videos captured by unsynchronized, uncalibrated, consumer-grade RGB cameras. Kineo leverages 2D keypoints from off-the-shelf detectors to simultaneously calibrate cameras, including Brown-Conrady distortion coefficients, and reconstruct 3D keypoints and dense scene point maps at metric scale. A confidence-driven spatio-temporal keypoint sampling strategy, combined with graph-based global optimization, ensures robust calibration at a fixed computational cost independent of sequence length. We further introduce a pairwise reprojection consensus score to quantify 3D reconstruction reliability for downstream tasks. Evaluations on EgoHumans and Human3.6M demonstrate substantial improvements over prior calibration-free methods. Compared to previous state-of-the-art approaches, Kineo reduces camera translation error by approximately 83-85%, camera angular error by 86-92%, and world mean-per-joint error (W-MPJPE) by 83-91%. Kineo is also efficient in real-world scenarios, processing multi-view sequences faster than their duration in specific configuration (e.g., 36min to process 1h20min of footage). The full pipeline and evaluation code are openly released to promote reproducibility and practical adoption at https://liris-xr.github.io/kineo/.
Authors: Kejing Xia, Jidong Jia, Ke Jin, Yucai Bai, Li Sun, Dacheng Tao, Youjian Zhang
Abstract: Recently, Gaussian Splatting (GS) has shown great potential for urban scene reconstruction in the field of autonomous driving. However, current urban scene reconstruction methods often depend on multimodal sensors as inputs, \textit{i.e.} LiDAR and images. Though the geometry prior provided by LiDAR point clouds can largely mitigate ill-posedness in reconstruction, acquiring such accurate LiDAR data is still challenging in practice: i) precise spatiotemporal calibration between LiDAR and other sensors is required, as they may not capture data simultaneously; ii) reprojection errors arise from spatial misalignment when LiDAR and cameras are mounted at different locations. To avoid the difficulty of acquiring accurate LiDAR depth, we propose D$^2$GS, a LiDAR-free urban scene reconstruction framework. In this work, we obtain geometry priors that are as effective as LiDAR while being denser and more accurate. $\textbf{First}$, we initialize a dense point cloud by back-projecting multi-view metric depth predictions. This point cloud is then optimized by a Progressive Pruning strategy to improve the global consistency. $\textbf{Second}$, we jointly refine Gaussian geometry and predicted dense metric depth via a Depth Enhancer. Specifically, we leverage diffusion priors from a depth foundation model to enhance the depth maps rendered by Gaussians. In turn, the enhanced depths provide stronger geometric constraints during Gaussian training. $\textbf{Finally}$, we improve the accuracy of ground geometry by constraining the shape and normal attributes of Gaussians within road regions. Extensive experiments on the Waymo dataset demonstrate that our method consistently outperforms state-of-the-art methods, producing more accurate geometry even when compared with those using ground-truth LiDAR data.
Authors: Xu Zheng, Zihao Dongfang, Lutao Jiang, Boyuan Zheng, Yulong Guo, Zhenquan Zhang, Giuliano Albanese, Runyi Yang, Mengjiao Ma, Zixin Zhang, Chenfei Liao, Dingcheng Zhen, Yuanhuiyi Lyu, Yuqian Fu, Bin Ren, Linfeng Zhang, Danda Pani Paudel, Nicu Sebe, Luc Van Gool, Xuming Hu
Abstract: Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing promising performance across diverse spatial tasks. However, systematic reviews and publicly available benchmarks for these models remain limited. In this survey, we provide a comprehensive review of multimodal spatial reasoning tasks with large models, categorizing recent progress in multimodal large language models (MLLMs) and introducing open benchmarks for evaluation. We begin by outlining general spatial reasoning, focusing on post-training techniques, explainability, and architecture. Beyond classical 2D tasks, we examine spatial relationship reasoning, scene and layout understanding, as well as visual question answering and grounding in 3D space. We also review advances in embodied AI, including vision-language navigation and action models. Additionally, we consider emerging modalities such as audio and egocentric video, which contribute to novel spatial understanding through new sensors. We believe this survey establishes a solid foundation and offers insights into the growing field of multimodal spatial reasoning. Updated information about this survey, codes and implementation of the open benchmarks can be found at https://github.com/zhengxuJosh/Awesome-Spatial-Reasoning.
URLs: https://github.com/zhengxuJosh/Awesome-Spatial-Reasoning.
Authors: Pei Peng, MingKun Xie, Hang Hao, Tong Jin, ShengJun Huang
Abstract: Object-context shortcuts remain a persistent challenge in vision-language models, undermining zero-shot reliability when test-time scenes differ from familiar training co-occurrences. We recast this issue as a causal inference problem and ask: Would the prediction remain if the object appeared in a different environment? To answer this at inference time, we estimate object and background expectations within CLIP's representation space, and synthesize counterfactual embeddings by recombining object features with diverse alternative contexts sampled from external datasets, batch neighbors, or text-derived descriptions. By estimating the Total Direct Effect and simulating intervention, we further subtract background-only activation, preserving beneficial object-context interactions while mitigating hallucinated scores. Without retraining or prompt design, our method substantially improves both worst-group and average accuracy on context-sensitive benchmarks, establishing a new zero-shot state of the art. Beyond performance, our framework provides a lightweight representation-level counterfactual approach, offering a practical causal avenue for debiased and reliable multimodal reasoning.
Authors: Aniruddh Bansal, Davit Soselia, Dang Nguyen, Tianyi Zhou
Abstract: Charts play an important role in visualization, reasoning, data analysis, and the exchange of ideas among humans. However, existing vision-language models (VLMs) still lack accurate perception of details and struggle to extract fine-grained structures from charts. Such limitations in chart grounding also hinder their ability to compare multiple charts and reason over them. In this paper, we introduce a novel "ChartAlign Benchmark (ChartAB)" to provide a comprehensive evaluation of VLMs in chart grounding tasks, i.e., extracting tabular data, localizing visualization elements, and recognizing various attributes from charts of diverse types and complexities. We design a JSON template to facilitate the calculation of evaluation metrics specifically tailored for each grounding task. By incorporating a novel two-stage inference workflow, the benchmark can further evaluate VLMs capability to align and compare elements/attributes across two charts. Our analysis of evaluations on several recent VLMs reveals new insights into their perception biases, weaknesses, robustness, and hallucinations in chart understanding. These findings highlight the fine-grained discrepancies among VLMs in chart understanding tasks and point to specific skills that need to be strengthened in current models.
Authors: Guozheng Zheng, Jian Guan, Mingjie Xie, Xuanjia Zhao, Congyi Fan, Shiheng Zhang, Pengming Feng
Abstract: Cross-view geo-localization (CVGL) between drone and satellite imagery remains challenging due to severe viewpoint gaps and the presence of hard negatives, which are visually similar but geographically mismatched samples. Existing mining or reweighting strategies often use static weighting, which is sensitive to distribution shifts and prone to overemphasizing difficult samples too early, leading to noisy gradients and unstable convergence. In this paper, we present a Dual-level Progressive Hardness-aware Reweighting (DPHR) strategy. At the sample level, a Ratio-based Difficulty-Aware (RDA) module evaluates relative difficulty and assigns fine-grained weights to negatives. At the batch level, a Progressive Adaptive Loss Weighting (PALW) mechanism exploits a training-progress signal to attenuate noisy gradients during early optimization and progressively enhance hard-negative mining as training matures. Experiments on the University-1652 and SUES-200 benchmarks demonstrate the effectiveness and robustness of the proposed DPHR, achieving consistent improvements over state-of-the-art methods.
Authors: Yehna Kim, Young-Eun Kim, Seong-Whan Lee
Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action classes to provide semantic context, particularly due to the presence of multi-semantic words, which can introduce ambiguity in understanding the intended concepts of actions. To address this issue, we propose an innovative approach that harnesses web-crawled descriptions, leveraging a large-language model to extract relevant keywords. This method reduces the need for human annotators and eliminates the laborious manual process of attribute data creation. Additionally, we introduce a spatio-temporal interaction module designed to focus on objects and action units, facilitating alignment between description attributes and video content. In our zero-shot experiments, our model achieves impressive results, attaining accuracies of 81.0%, 53.1%, and 68.9% on UCF-101, HMDB-51, and Kinetics-600, respectively, underscoring the model's adaptability and effectiveness across various downstream tasks.
Authors: Ilyass Moummad, Kawtar Zaher, Herv\'e Go\"eau, Alexis Joly
Abstract: Efficient large-scale retrieval requires representations that are both compact and discriminative. Foundation models provide powerful visual and multimodal embeddings, but nearest neighbor search in these high-dimensional spaces is computationally expensive. Hashing offers an efficient alternative by enabling fast Hamming distance search with binary codes, yet existing approaches often rely on complex pipelines, multi-term objectives, designs specialized for a single learning paradigm, and long training times. We introduce CroVCA (Cross-View Code Alignment), a simple and unified principle for learning binary codes that remain consistent across semantically aligned views. A single binary cross-entropy loss enforces alignment, while coding-rate maximization serves as an anti-collapse regularizer to promote balanced and diverse codes. To implement this, we design HashCoder, a lightweight MLP hashing network with a final batch normalization layer to enforce balanced codes. HashCoder can be used as a probing head on frozen embeddings or to adapt encoders efficiently via LoRA fine-tuning. Across benchmarks, CroVCA achieves state-of-the-art results in just 5 training epochs. At 16 bits, it particularly well-for instance, unsupervised hashing on COCO completes in under 2 minutes and supervised hashing on ImageNet100 in about 3 minutes on a single GPU. These results highlight CroVCA's efficiency, adaptability, and broad applicability.
Authors: Shengming Li, Luping Liu, Runnan Li, Xu Tan
Abstract: Though denoising diffusion probabilistic models (DDPMs) have achieved remarkable generation results, the low sampling efficiency of DDPMs still limits further applications. Since DDPMs can be formulated as diffusion ordinary differential equations (ODEs), various fast sampling methods can be derived from solving diffusion ODEs. However, we notice that previous fast sampling methods with fixed analytical form are not able to robust with the various error patterns in the noise estimated from pretrained diffusion models. In this work, we construct an error-robust Adams solver (ERA-Solver), which utilizes the implicit Adams numerical method that consists of a predictor and a corrector. Different from the traditional predictor based on explicit Adams methods, we leverage a Lagrange interpolation function as the predictor, which is further enhanced with an error-robust strategy to adaptively select the Lagrange bases with lower errors in the estimated noise. The proposed solver can be directly applied to any pretrained diffusion models, without extra training. Experiments on Cifar10, CelebA, LSUN-Church, and ImageNet 64 x 64 (conditional) datasets demonstrate that our proposed ERA-Solver achieves 3.54, 5.06, 5.02, and 5.11 Frechet Inception Distance (FID) for image generation, with only 10 network evaluations.
Authors: Yuhang Hu, Judah Goldfeder, Zhizhuo Zhang, Xinyue Zhu, Ruibo Liu, Philippe Wyder, Jiong Lin, Hod Lipson
Abstract: For robots to truly collaborate and assist humans, they must understand not only logic and instructions, but also the subtle emotions, aesthetics, and feelings that define our humanity. Human art and aesthetics are among the most elusive concepts-often difficult even for people to articulate-and without grasping these fundamentals, robots will be unable to help in many spheres of daily life. Consider the long-promised robotic butler: automating domestic chores demands more than motion planning. It requires an internal model of cleanliness and tidiness-a challenge largely unexplored by AI. To bridge this gap, we propose an approach that equips domestic robots to perform simple tidying tasks via knolling, the practice of arranging scattered items into neat, space-efficient layouts. Unlike the uniformity of industrial settings, household environments feature diverse objects and highly subjective notions of tidiness. Drawing inspiration from NLP, we treat knolling as a sequential prediction problem and employ a transformer based model to forecast each object's placement. Our method learns a generalizable concept of tidiness, generates diverse solutions adaptable to varying object sets, and incorporates human preferences for personalized arrangements. This work represents a step forward in building robots that internalize human aesthetic sense and can genuinely co-create in our living spaces.
Authors: Sungho Jeon, Xinyue Ma, Kwang In Kim, Myeongjae Jeon
Abstract: Recent rehearsal-free continual learning (CL) methods guided by prompts achieve strong performance on vision tasks with non-stationary data but remain resource-intensive, hindering real-world edge deployment. We introduce resource-efficient prompting (REP), which improves the computational and memory efficiency of prompt-based rehearsal-free continual learning methods while minimizing accuracy trade-offs. Our approach employs swift prompt selection to refine input data using a carefully provisioned model and introduces adaptive token merging (AToM) and adaptive layer dropping (ALD) for efficient prompt updates. AToM and ALD selectively skip data and model layers while preserving task-specific features during the learning of new tasks. Extensive experiments on multiple image classification datasets demonstrate REP's superior resource efficiency over state-of-the-art rehearsal-free CL methods.
Authors: Manuel Haas, Thomas Grandits, Thomas Pinetz, Thomas Beiert, Simone Pezzuto, Alexander Effland
Abstract: Reconstructing cardiac electrical activity from body surface electric potential measurements results in the severely ill-posed inverse problem in electrocardiography. Many different regularization approaches have been proposed to improve numerical results and provide unique results. This work presents a novel approach for reconstructing the epicardial potential from body surface potential maps based on a space-time total variation-type regularization using finite elements, where a first-order primal-dual algorithm solves the underlying convex optimization problem. In several numerical experiments, the superior performance of this method and the benefit of space-time regularization for the reconstruction of epicardial potential on two-dimensional torso data and a three-dimensional rabbit heart compared to state-of-the-art methods are demonstrated.
Authors: Yang-Che Sun, Cheng Yu Yeo, Ernie Chu, Jun-Cheng Chen, Yu-Lun Liu
Abstract: In this work, we propose using a unified representation, termed Factorized Features, for low-level vision tasks, where we test on Single Image Super-Resolution (SISR) and \textbf{Image Compression}. Motivated by the shared principles between these tasks, they require recovering and preserving fine image details, whether by enhancing resolution for SISR or reconstructing compressed data for Image Compression. Unlike previous methods that mainly focus on network architecture, our proposed approach utilizes a basis-coefficient decomposition as well as an explicit formulation of frequencies to capture structural components and multi-scale visual features in images, which addresses the core challenges of both tasks. We replace the representation of prior models from simple feature maps with Factorized Features to validate the potential for broad generalizability. In addition, we further optimize the compression pipeline by leveraging the mergeable-basis property of our Factorized Features, which consolidates shared structures on multi-frame compression. Extensive experiments show that our unified representation delivers state-of-the-art performance, achieving an average relative improvement of 204.4% in PSNR over the baseline in Super-Resolution (SR) and 9.35% BD-rate reduction in Image Compression compared to the previous SOTA. Project page: https://jayisaking.github.io/FIPER/
Authors: Mou\"in Ben Ammar, David Brellmann, Arturo Mendoza, Antoine Manzanera, Gianni Franchi
Abstract: Out-of-distribution (OOD) detection is essential for ensuring the reliability and safety of machine learning systems. In recent years, it has received increasing attention, particularly through post-hoc detection and training-based methods. In this paper, we focus on post-hoc OOD detection, which enables identifying OOD samples without altering the model's training procedure or objective. Our primary goal is to investigate the relationship between model capacity and its OOD detection performance. Specifically, we aim to answer the following question: Does the Double Descent phenomenon manifest in post-hoc OOD detection? This question is crucial, as it can reveal whether overparameterization, which is already known to benefit generalization, can also enhance OOD detection. Despite the growing interest in these topics by the classic supervised machine learning community, this intersection remains unexplored for OOD detection. We empirically demonstrate that the Double Descent effect does indeed appear in post-hoc OOD detection. Furthermore, we provide theoretical insights to explain why this phenomenon emerges in such setting. Finally, we show that the overparameterized regime does not yield superior results consistently, and we propose a method to identify the optimal regime for OOD detection based on our observations.
Authors: Xinyu Zhang, Zewei Zhou, Zhaoyi Wang, Yangjie Ji, Yanjun Huang, Hong Chen
Abstract: Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction.
Authors: Wenda Chu, Zihui Wu, Yifan Chen, Yang Song, Yisong Yue
Abstract: We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous diffusion models have achieved remarkable progress, analogous methods for discrete diffusion models remain challenging. In this work, we introduce a principled plug-and-play discrete diffusion posterior sampling algorithm based on split Gibbs sampling, which we call SGDD. Our algorithm enables reward-guided generation and solving inverse problems in discrete-state spaces. We demonstrate the convergence of SGDD to the target posterior distribution and verify this through controlled experiments on synthetic benchmarks. Our method enjoys state-of-the-art posterior sampling performance on a range of benchmarks for discrete data, including DNA sequence design, discrete image inverse problems, and music infilling, achieving more than 30% improved performance compared to existing baselines. Our code is available at https://github.com/chuwd19/Split-Gibbs-Discrete-Diffusion-Posterior-Sampling.
URLs: https://github.com/chuwd19/Split-Gibbs-Discrete-Diffusion-Posterior-Sampling.
Authors: Patryk Marsza{\l}ek, Maciej Rut, Piotr Kawa, Przemys{\l}aw Spurek, Piotr Syga
Abstract: Implicit neural representations (INR) have gained prominence for efficiently encoding multimedia data, yet their applications in audio signals remain limited. This study introduces the Kolmogorov-Arnold Network (KAN), a novel architecture using learnable activation functions, as an effective INR model for audio representation. KAN demonstrates superior perceptual performance over previous INRs, achieving the lowest Log-SpectralDistance of 1.29 and the highest Perceptual Evaluation of Speech Quality of 3.57 for 1.5 s audio. To extend KAN's utility, we propose FewSound, a hypernetwork-based architecture that enhances INR parameter updates. FewSound outperforms the state-of-the-art HyperSound, with a 33.3% improvement in MSE and 60.87% in SI-SNR. These results show KAN as a robust and adaptable audio representation with the potential for scalability and integration into various hypernetwork frameworks. The source code can be accessed at https://github.com/gmum/fewsound.git.
Authors: Taejin Jeong, Joohyeok Kim, Jaehoon Joo, Seong Jae Hwang
Abstract: Glaucoma is a major cause of irreversible blindness, with significant diagnostic subjectivity. This inherent uncertainty, combined with the overconfidence of models optimized solely for accuracy can lead to fatal issues such as overdiagnosis or missing critical diseases. To ensure clinical trust, model calibration is essential for reliable predictions, yet study in this field remains limited. Existing calibration study have overlooked glaucoma's systemic associations and high diagnostic subjectivity. To overcome these limitations, we propose V-ViT (Voting-based ViT), a framework that enhances calibration by integrating a patient's binocular information and metadata. Furthermore, to mitigate diagnostic subjectivity, V-ViT utilizes an iterative dropout-based Voting System to maximize calibration performance. The proposed framework achieved state-of-the-art performance across all metrics, including the primary calibration metrics. Our results demonstrate that V-ViT effectively resolves the issue of overconfidence in predictions in glaucoma diagnosis, providing highly reliable predictions for clinical use. Our source code is available at https://github.com/starforTJ/V-ViT.
Authors: Xuanwen Liang, Jiayu Chen, Eric Wai Ming Lee, Wei Xie
Abstract: Data-driven crowd simulation models offer advantages in enhancing the accuracy and realism of simulations, and improving their generalizability is essential for promoting application. Current data-driven approaches are primarily designed for a single scenario, with very few models validated across more than two scenarios. It is still an open question to develop data-driven crowd simulation models with strong generalizibility. We notice that the key to addressing this challenge lies in effectively and accurately capturing the core common influential features that govern pedestrians' navigation across diverse scenarios. Particularly, we believe that visual information is one of the most dominant influencing features. In light of this, this paper proposes a data-driven model incorporating a refined visual information extraction method and exit cues to enhance generalizability. The proposed model is examined on four common fundamental modules: bottleneck, corridor, corner and T-junction. The evaluation results demonstrate that our model performs excellently across these scenarios, aligning with pedestrian movement in real-world experiments, and significantly outperforms the classical knowledge-driven model. Furthermore, we introduce a modular approach to apply our proposed model in composite scenarios, and the results regarding trajectories and fundamental diagrams indicate that our simulations closely match real-world patterns in the composite scenario. The research outcomes can provide inspiration for the development of data-driven crowd simulation models with high generalizability and advance the application of data-driven approaches.This work has been submitted to Elsevier for possible publication.
Authors: Yuwen Chen, Zafer Yildiz, Qihang Li, Yaqian Chen, Haoyu Dong, Hanxue Gu, Nicholas Konz, Maciej A. Mazurowski
Abstract: Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation, such as Segment Anything Model 2 (SAM 2), offer a potential opportunity to significantly speed up the annotation process by manually annotating one or a few slices and then propagating target masks across the entire volume. However, the performance of SAM 2 in this context varies. Our experiments show that relying on a single memory bank and attention module is prone to error propagation, particularly at boundary regions where the target is present in the previous slice but absent in the current one. To address this problem, we propose Short-Long Memory SAM 2 (SLM-SAM 2), a novel architecture that integrates distinct short-term and long-term memory banks with separate attention modules to improve segmentation accuracy. We evaluate SLM-SAM 2 on four public datasets covering organs, bones, and muscles across MRI, CT, and ultrasound videos. We show that the proposed method markedly outperforms the default SAM 2, achieving an average Dice Similarity Coefficient improvement of 0.14 and 0.10 in the scenarios when 5 volumes and 1 volume are available for the initial adaptation, respectively. SLM-SAM 2 also exhibits stronger resistance to over-propagation, reducing the time required to correct propagated masks by 60.575% per volume compared to SAM 2, making a notable step toward more accurate automated annotation of medical images for segmentation model development.
Authors: Yida Xue, Zhen Bi, Jinnan Yang, Jungang Lou, Kehai Chen, Min Zhang, Huajun Chen, Ningyu Zhang
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced their capabilities; however, their spatial perception abilities remain a notable limitation. To address this challenge, multimodal data synthesis offers a promising solution. Yet, ensuring that synthesized data adhere to spatial common sense is a non-trivial task. Our approach addresses this critical gap by providing a systematic framework for generating spatially coherent data. In this work, we introduce SKG2DATA, a novel multimodal synthesis approach guided by spatial knowledge graphs, grounded in the concept of knowledge-to-data generation. SKG2DATA employs an automated pipeline for constructing Spatial Knowledge Graph (SKG) that effectively captures human-like spatial cognition, including directional and distance relationships. These structured representations then serve as precise guidance for our integrated synthesis pipeline, where a diffusion model generates spatially-consistent images while a MLLM produces corresponding textual descriptions. The automated construction of SKG enables scalable generation of diverse yet realistic spatial configurations, overcoming the limitations of manual data collection and annotation. Extensive experiments demonstrate that data synthesized from diverse types of spatial knowledge, including direction and distance, enhance the spatial perception and reasoning abilities of MLLMs markedly, albeit with a slight cost to their general capabilities. We hope that the idea of knowledge-based data synthesis can advance the development of spatial intelligence. Code is available at https://github.com/zjunlp/Knowledge2Data.
Authors: Nicholas Summerfield, Qisheng He, Alex Kuo, Ahmed I. Ghanem, Simeng Zhu, Chase Ruff, Joshua Pan, Anudeep Kumar, Prashant Nagpal, Jiwei Zhao, Ming Dong, Carri K. Glide-Hurst
Abstract: Cardiac substructure delineation is emerging in treatment planning to minimize the risk of radiation-induced heart disease. Deep learning offers efficient methods to reduce contouring burden but currently lacks generalizability across different modalities and overlapping structures. This work introduces and validates a Modality-AGnostic Image Cascade (MAGIC) deep-learning pipeline for comprehensive and multi-modal cardiac substructure segmentation. MAGIC is implemented through replicated encoding and decoding branches of an nnU-Net backbone to handle multi-modality inputs and overlapping labels. First benchmarked on the multi-modality whole-heart segmentation (MMWHS) dataset including cardiac CT-angiography (CCTA) and MR modalities, twenty cardiac substructures (heart, chambers, great vessels (GVs), valves, coronary arteries (CAs), and conduction nodes) from clinical simulation CT (Sim-CT), low-field MR-Linac, and cardiac CT-angiography (CCTA) modalities were delineated to train semi-supervised (n=151), validate (n=15), and test (n=30) MAGIC. For comparison, fourteen single-modality comparison models (two MMWHS modalities and four subgroups across three clinical modalities) were trained. Methods were evaluated for efficiency and against reference contours through the Dice similarity coefficient (DSC) and two-tailed Wilcoxon Signed-Rank test (p<0.05). Average MMWHS DSC scores across CCTA and MR inputs were 0.88(0.08) and 0.87(0.04) respectively with significant improvement over unimodal baselines. Average 20-structure DSC scores were 0.75(0.16) for Sim-CT, 0.68(0.21) for MR-Linac, and 0.80(0.16) for CCTA. Furthermore, >80% and >70% reductions in training time and parameters were achieved, respectively. MAGIC offers an efficient, lightweight solution capable of segmenting multiple image modalities and overlapping structures in a single model without compromising segmentation accuracy.
Authors: Mae Younes, Adnane Boukhayma
Abstract: 2D Gaussian Splatting (2DGS) has recently emerged as a promising method for novel view synthesis and surface reconstruction, offering better view-consistency and geometric accuracy than volumetric 3DGS. However, 2DGS suffers from severe aliasing artifacts when rendering at different sampling rates than those used during training, limiting its practical applications in scenarios requiring camera zoom or varying fields of view. We identify that these artifacts stem from two key limitations: the lack of frequency constraints in the representation and an ineffective screen-space clamping approach. To address these issues, we present AA-2DGS, an anti-aliased formulation of 2D Gaussian Splatting that maintains its geometric benefits while significantly enhancing rendering quality across different scales. Our method introduces a world-space flat smoothing kernel that constrains the frequency content of 2D Gaussian primitives based on the maximal sampling frequency from training views, effectively eliminating high-frequency artifacts when zooming in. Additionally, we derive a novel object-space Mip filter by leveraging an affine approximation of the ray-splat intersection mapping, which allows us to efficiently apply proper anti-aliasing directly in the local space of each splat.
Authors: Tyler Ward, Meredith K. Owen, O'Kira Coleman, Brian Noehren, Abdullah-Al-Zubaer Imran
Abstract: Medical image segmentation is a key task in the imaging workflow, influencing many image-based decisions. Traditional, fully-supervised segmentation models rely on large amounts of labeled training data, typically obtained through manual annotation, which can be an expensive, time-consuming, and error-prone process. This signals a need for accurate, automatic, and annotation-efficient methods of training these models. We propose ADA-SAM (automated, domain-specific, and adaptive segment anything model), a novel multitask learning framework for medical image segmentation that leverages class activation maps from an auxiliary classifier to guide the predictions of the semi-supervised segmentation branch, which is based on the Segment Anything (SAM) framework. Additionally, our ADA-SAM model employs a novel gradient feedback mechanism to create a learnable connection between the segmentation and classification branches by using the segmentation gradients to guide and improve the classification predictions. We validate ADA-SAM on real-world clinical data collected during rehabilitation trials, and demonstrate that our proposed method outperforms both fully-supervised and semi-supervised baselines by double digits in limited label settings. Our code is available at: https://github.com/tbwa233/ADA-SAM.
Authors: Shuyang Xu, Zhiyang Dou, Mingyi Shi, Liang Pan, Leo Ho, Jingbo Wang, Yuan Liu, Cheng Lin, Yuexin Ma, Wenping Wang, Taku Komura
Abstract: Enabling virtual humans to dynamically and realistically respond to diverse auditory stimuli remains a key challenge in character animation, demanding the integration of perceptual modeling and motion synthesis. Despite its significance, this task remains largely unexplored. Most previous works have primarily focused on mapping modalities like speech, audio, and music to generate human motion. As of yet, these models typically overlook the impact of spatial features encoded in spatial audio signals on human motion. To bridge this gap and enable high-quality modeling of human movements in response to spatial audio, we introduce the first comprehensive Spatial Audio-Driven Human Motion (SAM) dataset, which contains diverse and high-quality spatial audio and motion data. For benchmarking, we develop a simple yet effective diffusion-based generative framework for human MOtion generation driven by SPatial Audio, termed MOSPA, which faithfully captures the relationship between body motion and spatial audio through an effective fusion mechanism. Once trained, MOSPA can generate diverse, realistic human motions conditioned on varying spatial audio inputs. We perform a thorough investigation of the proposed dataset and conduct extensive experiments for benchmarking, where our method achieves state-of-the-art performance on this task. Our code and model are publicly available at https://github.com/xsy27/Mospa-Acoustic-driven-Motion-Generation
URLs: https://github.com/xsy27/Mospa-Acoustic-driven-Motion-Generation
Authors: Pengcheng Zheng, Xiaorong Pu, Kecheng Chen, Jiaxin Huang, Meng Yang, Bai Feng, Yazhou Ren, Jianan Jiang
Abstract: Recently, large language models (LLMs) have driven promising progress in lossless image compression. However, directly adopting existing paradigms for medical images suffers from an unsatisfactory trade-off between compression performance and efficiency. Moreover, existing LLM-based compressors often overlook the security of the compression process, which is critical in modern medical scenarios. To this end, we propose a novel joint lossless compression and steganography framework. Inspired by bit plane slicing (BPS), we find it feasible to securely embed privacy messages into medical images in an invisible manner. Based on this insight, an adaptive modalities decomposition strategy is first devised to partition the entire image into two segments, providing global and local modalities for subsequent dual-path lossless compression. During this dual-path stage, we innovatively propose a segmented message steganography algorithm within the local modality path to ensure the security of the compression process. Coupled with the proposed anatomical priors-based low-rank adaptation (A-LoRA) fine-tuning strategy, extensive experimental results demonstrate the superiority of our proposed method in terms of compression ratios, efficiency, and security. The source code will be made publicly available.
Authors: Will Fein, Ryan J. Horwitz, John E. Brown III, Amit Misra, Felipe Oviedo, Kevin White, Juan M. Lavista Ferres, Samuel K. Wasser
Abstract: The transnational ivory trade continues to drive the decline of elephant populations across Africa, and trafficking networks remain difficult to disrupt. Tusks seized by law enforcement officials carry forensic information on the traffickers responsible for their export, including DNA evidence and handwritten markings made by traffickers. For 20 years, analyses of tusk DNA have identified where elephants were poached and established connections among shipments of ivory. While the links established using genetic evidence are extremely conclusive, genetic data is expensive and sometimes impossible to obtain. But though handwritten markings are easy to photograph, they are rarely documented or analyzed. Here, we present an AI-driven pipeline for extracting and analyzing handwritten markings on seized elephant tusks, offering a novel, scalable, and low-cost source of forensic evidence. Having collected 6,085 photographs from eight large seizures of ivory over a 6-year period (2014-2019), we used an object detection model to extract over 17,000 individual markings, which were then labeled and described using state-of-the-art AI tools. We identified 184 recurring "signature markings" that connect the tusks on which they appear. 20 signature markings were observed in multiple seizures, establishing forensic links between these seizures through traffickers involved in both shipments. This work complements other investigative techniques by filling in gaps where other data sources are unavailable. The study demonstrates the transformative potential of AI in wildlife forensics and highlights practical steps for integrating handwriting analysis into efforts to disrupt organized wildlife crime.
Authors: Weijian Mai, Jiamin Wu, Yu Zhu, Zhouheng Yao, Dongzhan Zhou, Andrew F. Luo, Qihao Zheng, Wanli Ouyang, Chunfeng Song
Abstract: Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably evoke variable hemodynamic responses across trials, contexts, and subjects. However, existing deterministic methods struggle to simultaneously model this biological variability while capturing the underlying functional consistency that encodes stimulus information. To address these limitations, we propose SynBrain, a generative framework that simulates the transformation from visual semantics to neural responses in a probabilistic and biologically interpretable manner. SynBrain introduces two key components: (i) BrainVAE models neural representations as continuous probability distributions via probabilistic learning while maintaining functional consistency through visual semantic constraints; (ii) A Semantic-to-Neural Mapper acts as a semantic transmission pathway, projecting visual semantics into the neural response manifold to facilitate high-fidelity fMRI synthesis. Experimental results demonstrate that SynBrain surpasses state-of-the-art methods in subject-specific visual-to-fMRI encoding performance. Furthermore, SynBrain adapts efficiently to new subjects with few-shot data and synthesizes high-quality fMRI signals that are effective in improving data-limited fMRI-to-image decoding performance. Beyond that, SynBrain reveals functional consistency across trials and subjects, with synthesized signals capturing interpretable patterns shaped by biological neural variability. Our code is available at https://github.com/MichaelMaiii/SynBrain.
Authors: Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, Matthieu Cord
Abstract: Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such as mean steering, rely on a single steering vector, applied independently of the input query. This paradigm faces limitations when the desired behavior is dependent on the example at hand. For example, a safe answer may consist in abstaining from answering when asked for an illegal activity, or may point to external resources or consultation with an expert when asked about medical advice. In this paper, we investigate a fine-grained steering that uses an input-specific linear shift. This shift is computed using contrastive input-specific prompting. However, the input-specific prompts required for this approach are not known at test time. Therefore, we propose to train a small auxiliary module to predict the input-specific steering vector. Our approach, dubbed as L2S (Learn-to-Steer), demonstrates that it reduces hallucinations and enforces safety in MLLMs, outperforming other static baselines. Our code is publicly available at https://jayneelparekh.github.io/learn-to-steer/
Authors: Weihuan Deng, Yaofu Huang, Luan Chen, Xun Li, Yu Gu, Yao Yao
Abstract: The high cost of acquiring rural street view images has constrained comprehensive environmental perception in rural areas. Drone photographs, with their advantages of easy acquisition, broad coverage, and high spatial resolution, offer a viable approach for large-scale rural environmental perception. However, a systematic methodology for identifying key environmental elements from drone photographs and quantifying their impact on environmental perception remains lacking. To address this gap, a Vision-Language Contrastive Ranking Framework (VLCR) is designed for rural livability assessment in China. The framework employs chain-of-thought prompting strategies to guide multimodal large language models (MLLMs) in identifying visual features related to quality of life and ecological habitability from drone photographs. Subsequently, to address the instability in pairwise village comparison, a text description-constrained drone photograph comparison strategy is proposed. Finally, to overcome the efficiency bottleneck in nationwide pairwise village comparisons, an innovation ranking algorithm based on binary search interpolation is developed, which reduces the number of comparisons through automated selection of comparison targets. The proposed framework achieves superior performance with a Spearman Footrule distance of 0.74, outperforming mainstream commercial MLLMs by approximately 0.1. Moreover, the mechanism of concurrent comparison and ranking demonstrates a threefold enhancement in computational efficiency. Our framework has achieved data innovation and methodological breakthroughs in village livability assessment, providing strong support for large-scale village livability analysis. Keywords: Drone photographs, Environmental perception, Rural livability assessment, Multimodal large language models, Chain-of-thought prompting.
Authors: Jiye Lee, Chenghui Li, Linh Tran, Shih-En Wei, Jason Saragih, Alexander Richard, Hanbyul Joo, Shaojie Bai
Abstract: We present an audio-driven real-time system for animating photorealistic 3D facial avatars with minimal latency, designed for social interactions in virtual reality for anyone. Central to our approach is an encoder model that transforms audio signals into latent facial expression sequences in real time, which are then decoded as photorealistic 3D facial avatars. Leveraging the generative capabilities of diffusion models, we capture the rich spectrum of facial expressions necessary for natural communication while achieving real-time performance (<15ms GPU time). Our novel architecture minimizes latency through two key innovations: an online transformer that eliminates dependency on future inputs and a distillation pipeline that accelerates iterative denoising into a single step. We further address critical design challenges in live scenarios for processing continuous audio signals frame-by-frame while maintaining consistent animation quality. The versatility of our framework extends to multimodal applications, including semantic modalities such as emotion conditions and multimodal sensors with head-mounted eye cameras on VR headsets. Experimental results demonstrate significant improvements in facial animation accuracy over existing offline state-of-the-art baselines, achieving 100 to 1000 times faster inference speed. We validate our approach through live VR demonstrations and across various scenarios such as multilingual speeches.
Authors: Andreas Engelhardt, Mark Boss, Vikram Voleti, Chun-Han Yao, Hendrik P. A. Lensch, Varun Jampani
Abstract: We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently. However, reflectance is still represented by simple material models or needs to be estimated in additional steps to enable relighting and controlled appearance edits. We extend a latent video diffusion model to output spatially varying PBR parameters and surface normals jointly with each generated view based on explicit camera control. This unique setup allows for relighting and generating a 3D asset using our model as neural prior. We introduce various mechanisms to this pipeline that improve quality in this ill-posed setting. We show state-of-the-art relighting and novel view synthesis performance on multiple object-centric datasets. Our method generalizes to diverse inputs, enabling the generation of relightable 3D assets useful in AR/VR, movies, games and other visual media.
Authors: Lin Lin, Jiefeng Long, Zhihe Wan, Yuchi Wang, Dingkang Yang, Shuang Yang, Yueyang Yao, Xu Chen, Zirui Guo, Shengqiang Li, Weiran Li, Hanyu Li, Yaling Mou, Yan Qiu, Haiyang Yu, Xiao Liang, Hongsheng Li, Chao Feng
Abstract: Multimodal embedding models aim to yield informative unified representations that empower diverse cross-modal tasks. Despite promising developments in the evolution from CLIP-based dual-tower architectures to large vision-language models, prior works still face unavoidable challenges in real-world applications and business scenarios, such as the limited modality support, unstable training mechanisms, and industrial domain gaps. In this work, we introduce SAIL-Embedding, an omni-modal embedding foundation model that addresses these issues through tailored training strategies and architectural design. In the optimization procedure, we propose a multi-stage training scheme to boost the multifaceted effectiveness of representation learning. Specifically, the content-aware progressive training aims to enhance the model's adaptability to diverse downstream tasks and master enriched cross-modal proficiency. The collaboration-aware recommendation enhancement training further adapts multimodal representations for recommendation scenarios by distilling knowledge from sequence-to-item and ID-to-item embeddings while mining user historical interests. Concurrently, we develop the stochastic specialization and dataset-driven pattern matching to strengthen model training flexibility and generalizability. Experimental results show that SAIL-Embedding achieves SOTA performance compared to other methods in different retrieval tasks. In online experiments across various real-world scenarios integrated with our model, we observe a significant increase in Lifetime (LT), which is a crucial indicator for the recommendation experience. For instance, the model delivers the 7-day LT gain of +0.5% in the Douyin-Selected scenario. For the Douyin feed rank model, the match features produced by SAIL-Embedding yield a +0.1% AUC gain.
Authors: Zehao Ni, Yonghao He, Lingfeng Qian, Jilei Mao, Fa Fu, Wei Sui, Hu Su, Junran Peng, Zhipeng Wang, Bin He
Abstract: In the context of imitation learning, visuomotor-based diffusion policy learning is one of the main directions in robotic manipulation. Most of these approaches rely on point clouds as observation inputs and construct scene representations through point clouds feature learning, which enables them to achieve remarkable accuracy. However, the existing literature lacks an in-depth exploration of vision-only solutions that have significant potential. In this paper, we propose a Vision-Only and single-view Diffusion Policy learning method (VO-DP) that leverages pretrained visual foundation models to achieve effective fusion of semantic and geometric features. We utilize intermediate features from VGGT incorporating semantic features from DINOv2 and geometric features from Alternating Attention blocks. Features are fused via cross-attention and spatially compressed with a CNN to form the input to the policy head. Extensive experiments demonstrate that VO-DP not only outperforms the vision-only baseline DP significantly but also exhibits distinct performance trends against the point cloud-based method DP3: in simulation tasks, VO-DP achieves an average success rate of 64.6% on par with DP3 64.0% and far higher than DP 34.8%, while in real-world tasks, it reaches 87.9%, outperforming both DP3 67.5% and DP 11.2% by a notable margin. Further robustness evaluations confirm that VO-DP remains highly stable under varying conditions including color, size, background, and lighting. Lastly, we open-source a training library for robotic manipulation. Built on Accelerate, this library supports multi-machine and multi-GPU parallel training, as well as mixed precision training. It is compatible with visuomotor policies such as DP, DP3 and VO-DP, and also supports the RoboTwin simulator.
Authors: Jiacheng Liu, Xinyu Wang, Yuqi Lin, Zhikai Wang, Peiru Wang, Peiliang Cai, Qinming Zhou, Zhengan Yan, Zexuan Yan, Zhengyi Shi, Chang Zou, Yue Ma, Linfeng Zhang
Abstract: Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to prohibitive computational overhead and generation latency, forming a major bottleneck for real-time applications. Although existing acceleration techniques have made progress, they still face challenges such as limited applicability, high training costs, or quality degradation. Against this backdrop, \textbf{Diffusion Caching} offers a promising training-free, architecture-agnostic, and efficient inference paradigm. Its core mechanism identifies and reuses intrinsic computational redundancies in the diffusion process. By enabling feature-level cross-step reuse and inter-layer scheduling, it reduces computation without modifying model parameters. This paper systematically reviews the theoretical foundations and evolution of Diffusion Caching and proposes a unified framework for its classification and analysis. Through comparative analysis of representative methods, we show that Diffusion Caching evolves from \textit{static reuse} to \textit{dynamic prediction}. This trend enhances caching flexibility across diverse tasks and enables integration with other acceleration techniques such as sampling optimization and model distillation, paving the way for a unified, efficient inference framework for future multimodal and interactive applications. We argue that this paradigm will become a key enabler of real-time and efficient generative AI, injecting new vitality into both theory and practice of \textit{Efficient Generative Intelligence}.
Authors: Anand, Umberto Cappellazzo, Stavros Petridis, Maja Pantic
Abstract: Large language models (LLMs) have recently advanced auditory speech recognition (ASR), visual speech recognition (VSR), and audio-visual speech recognition (AVSR). However, understanding of their internal dynamics under fine-tuning remains limited. In natural language processing, recent work has revealed attention sinks, tokens that attract disproportionately high attention, and associated massive activations in which some features of sink tokens exhibit huge activation in LLMs. In this work, we are the first to study these phenomena in multimodal speech recognition. Through a detailed analysis of audio-visual LLMs, we identify attention sinks and massive activations not only at the BOS token but also at intermediate low-semantic tokens across ASR, VSR, and AVSR. We show that massive activations originate in the MLP layers and correspond to fixed feature indices across all sink tokens. We further show that intermediate sink tokens exhibit high cosine similarity to the BOS token, thereby amplifying attention and activation. Building on these insights, we introduce a simple decorrelation loss that reduces cosine similarity between BOS and other tokens, effectively mitigating intermediate sinks and massive activations. Furthermore, our method improves word error rate (WER) under high audio-visual feature downsampling while remaining stable at lower downsampling rates.
Authors: Siyin Wang, Jinlan Fu, Feihong Liu, Xinzhe He, Huangxuan Wu, Junhao Shi, Kexin Huang, Zhaoye Fei, Jingjing Gong, Zuxuan Wu, Yu-Gang Jiang, See-Kiong Ng, Tat-Seng Chua, Xipeng Qiu
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have driven rapid progress in Vision-Language-Action (VLA) models for robotic manipulation. Although effective in many scenarios, current approaches largely rely on explicit instructions, whereas in real-world interactions, humans rarely issue instructions directly. Effective collaboration requires robots to infer user intentions proactively. In this work, we introduce cross-modal contextual instructions, a new setting where intent is derived from spoken dialogue, environmental sounds, and visual cues rather than explicit commands. To address this new setting, we present RoboOmni, a Perceiver-Thinker-Talker-Executor framework based on end-to-end omni-modal LLMs that unifies intention recognition, interaction confirmation, and action execution. RoboOmni fuses auditory and visual signals spatiotemporally for robust intention recognition, while supporting direct speech interaction. To address the absence of training data for proactive intention recognition in robotic manipulation, we build OmniAction, comprising 140k episodes, 5k+ speakers, 2.4k event sounds, 640 backgrounds, and six contextual instruction types. Experiments in simulation and real-world settings show that RoboOmni surpasses text- and ASR-based baselines in success rate, inference speed, intention recognition, and proactive assistance.
Authors: Bocheng Guo, Jin Wang, Yijie Li, Junyi Wang, Mingyu Gao, Puming Feng, Yuqian Chen, Jarrett Rushmore, Nikos Makris, Yogesh Rathi, Lauren J O'Donnell, Fan Zhang
Abstract: Tractography fiber clustering using diffusion MRI (dMRI) is a crucial method for white matter (WM) parcellation to enable analysis of brains structural connectivity in health and disease. Current fiber clustering strategies primarily use the fiber geometric characteristics (i.e., the spatial trajectories) to group similar fibers into clusters, while neglecting the functional and microstructural information of the fiber tracts. There is increasing evidence that neural activity in the WM can be measured using functional MRI (fMRI), providing potentially valuable multimodal information for fiber clustering to enhance its functional coherence. Furthermore, microstructural features such as fractional anisotropy (FA) can be computed from dMRI as additional information to ensure the anatomical coherence of the clusters. In this paper, we develop a novel deep learning fiber clustering framework, namely Deep Multi-view Fiber Clustering (DMVFC), which uses joint multi-modal dMRI and fMRI data to enable functionally consistent WM parcellation. DMVFC can effectively integrate the geometric and microstructural characteristics of the WM fibers with the fMRI BOLD signals along the fiber tracts. DMVFC includes two major components: (1) a multi-view pretraining module to compute embedding features from each source of information separately, including fiber geometry, microstructure measures, and functional signals, and (2) a collaborative fine-tuning module to simultaneously refine the differences of embeddings. In the experiments, we compare DMVFC with two state-of-the-art fiber clustering methods and demonstrate superior performance in achieving functionally meaningful and consistent WM parcellation results.
Authors: Meghraj Prajapat, Alankar Alankar
Abstract: Electron back-scatter diffraction (EBSD) has traditionally relied upon methods such as the Hough transform and dictionary Indexing to interpret diffraction patterns and extract crystallographic orientation. However, these methods encounter significant limitations, particularly when operating at high scanning speeds, where the exposure time per pattern is decreased beyond the operating sensitivity of CCD camera. Hence the signal to noise ratio decreases for the observed pattern which makes the pattern noisy, leading to reduced indexing accuracy. This research work aims to develop generative machine learning models for the post-processing or on-the-fly processing of Kikuchi patterns which are capable of restoring noisy EBSD patterns obtained at high scan speeds. These restored patterns can be used for the determination of crystal orientations to provide reliable indexing results. We compare the performance of such generative models in enhancing the quality of patterns captured at short exposure times (high scan speeds). An interesting observation is that the methodology is not data-hungry as typical machine learning methods.