Authors: Chimdi Walter Ndubuisi, Toni Kazic
Abstract: Leaf-lesion segmentation is topology-sensitive: small merges, splits, or false holes can be biologically meaningful descriptors of biochemical pathways, yet they are weakly penalized by standard pixel-wise losses in Euclidean latents. I explore HyperTopo-Adapters, a lightweight, parameter-efficient head trained on top of a frozen vision encoder, which embeds features on a product manifold -- hyperbolic + Euclidean + spherical (H + E + S) -- to encourage hierarchical separation (H), local linear detail (E), and global closure (S). A topology prior complements Dice/BCE in two forms: (i) persistent-homology (PH) distance for evaluation and selection, and (ii) a differentiable surrogate that combines a soft Euler-characteristic match with total variation regularization for stable training. I introduce warm-ups for both the hyperbolic contrastive term and the topology prior, per-sample evaluation of structure-aware metrics (Boundary-F1, Betti errors, PD distance), and a min-PD within top-K Dice rule for checkpoint selection. On a Kaggle leaf-lesion dataset (N=2,940), early results show consistent gains in boundary and topology metrics (reducing Delta beta_1 hole error by 9%) while Dice/IoU remain competitive. The study is diagnostic by design: I report controlled ablations (curvature learning, latent dimensions, contrastive temperature, surrogate settings), and ongoing tests varying encoder strength (ResNet-50, DeepLabV3, DINOv2/v3), input resolution, PH weight, and partial unfreezing of late blocks. The contribution is an open, reproducible train/eval suite (available at https://github.com/ChimdiWalter/HyperTopo-Adapters) that isolates geometric/topological priors and surfaces failure modes to guide stronger, topology-preserving architectures.
Authors: Yin Wang, Chunlin Gong, Zhuozhen Xu, Lehan Zhang, Xiang Wu
Abstract: Sea Surface Temperature (SST) prediction plays a vital role in climate modeling and disaster forecasting. However, it remains challenging due to its nonlinear spatiotemporal dynamics and extended prediction horizons. To address this, we propose OptFormer, a novel encoder-decoder model that integrates phase-space reconstruction with a motion-aware attention mechanism guided by optical flow. Unlike conventional attention, our approach leverages inter-frame motion cues to highlight relative changes in the spatial field, allowing the model to focus on dynamic regions and capture long-range temporal dependencies more effectively. Experiments on NOAA SST datasets across multiple spatial scales demonstrate that OptFormer achieves superior performance under a 1:1 training-to-prediction setting, significantly outperforming existing baselines in accuracy and robustness.
Authors: Aradhya Dixit, Tianxi Liang
Abstract: Long-form video question answering remains challenging for modern vision-language models, which struggle to reason over hour-scale footage without exceeding practical token and compute budgets. Existing systems typically downsample frames or feed dense visual embeddings to large-context language models, trading off temporal coverage against cost. We propose Semantic Event Graphs (SEG), a lightweight symbolic interface between video and language that replaces raw frames with compact temporal interaction logs. Our pipeline detects and tracks objects with YOLOv11, converts proximity patterns into START/END human-object events, and organizes them into a Temporal Scene Graph (TSG). At inference time, a query-aware pruning module identifies anchor entities and lexically relevant events, returning only a small subgraph which is verbalized and passed to Gemini 2.5 Flash for answer generation. On five YouTube videos (300-500 interactions each) and 120 automatically generated long-horizon questions, SEG achieves 65.0% accuracy using only 3.47k tokens per query, closely matching a full-log baseline (62.5% at 40.39k tokens) while reducing token usage by 91.4%. A short-context baseline restricted to the last 30 seconds collapses to 2.5% accuracy, underscoring the need for explicit temporal memory. These results show that symbolic temporal graphs can serve as an effective, plug-and-play memory layer for off-the-shelf vision-language models, preserving long-range reasoning ability while making long-form video question answering substantially more token- and cost-efficient. Code, logs, and event-extraction tools will be released for reproducibility.
Authors: Canming Xia, Peixi Peng, Guang Tan, Zhan Su, Haoran Xu, Zhenxian Liu, Luntong Li
Abstract: Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge distillation from the VLM to RL, overlooking the potential of RL-generated interaction data to enhance the VLM. To address this, we propose COVR, a collaborative optimization framework that enables the mutual enhancement of the VLM and RL policies. Specifically, COVR fine-tunes the VLM with RL-generated data to enhance the semantic reasoning ability consistent with the target task, and uses the enhanced VLM to further guide policy learning via action priors. To improve fine-tuning efficiency, we introduce two key modules: (1) an Exploration-Driven Dynamic Filter module that preserves valuable exploration samples using adaptive thresholds based on the degree of exploration, and (2) a Return-Aware Adaptive Loss Weight module that improves the stability of training by quantifying the inconsistency of sampling actions via return signals of RL. We further design a progressive fine-tuning strategy to reduce resource consumption. Extensive experiments show that COVR achieves strong performance across various challenging visual control tasks.
Authors: Sao Mai Nguyen (U2IS, ENSTA, IP Paris)
Abstract: To allow the development and assessment of physical rehabilitation by an intelligent tutoring system, we propose a medical dataset of clinical patients carrying out low back-pain rehabilitation exercises and benchmark on state of the art human movement analysis algorithms. This dataset is valuable because it includes rehabilitation motions in a clinical setting with patients in their rehabilitation program. This paper introduces the Keraal dataset, a clinically collected dataset to enable intelligent tutoring systems (ITS) for rehabilitation. It addresses four challenges in exercise monitoring: motion assessment, error recognition, spatial localization, temporal localization
Authors: Kaiyuan Deng, Bo Hui, Gen Li, Jie Ji, Minghai Qin, Geng Yuan, Xiaolong Ma
Abstract: The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery learned from massive training corpora. As a practical solution, machine unlearning aims to selectively erase unwanted concepts from a pre-trained model without retraining from scratch. While most existing methods are effective for single-concept unlearning, they often struggle in real-world scenarios that require removing multiple concepts, since extending them to this setting is both non-trivial and problematic, causing significant challenges in unlearning effectiveness, generation quality, and sensitivity to hyperparameters and datasets. In this paper, we take a unique perspective on multi-concept unlearning by leveraging model sparsity and propose the Forget It All (FIA) framework. FIA first introduces Contrastive Concept Saliency to quantify each weight connection's contribution to a target concept. It then identifies Concept-Sensitive Neurons by combining temporal and spatial information, ensuring that only neurons consistently responsive to the target concept are selected. Finally, FIA constructs masks from the identified neurons and fuses them into a unified multi-concept mask, where Concept-Agnostic Neurons that broadly support general content generation are preserved while concept-specific neurons are pruned to remove the targets. FIA is training-free and requires only minimal hyperparameter tuning for new tasks, thereby promoting a plug-and-play paradigm. Extensive experiments across three distinct unlearning tasks demonstrate that FIA achieves more reliable multi-concept unlearning, improving forgetting effectiveness while maintaining semantic fidelity and image quality.
Authors: Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Ahn Eungyeol, Jungwhan Kim, Seunghyeok Hong, Youngsook Song
Abstract: Current vision-language benchmarks predominantly feature well-structured questions with clear, explicit prompts. However, real user queries are often informal and underspecified. Users naturally leave much unsaid, relying on images to convey context. We introduce HAERAE-Vision, a benchmark of 653 real-world visual questions from Korean online communities (0.76% survival from 86K candidates), each paired with an explicit rewrite, yielding 1,306 query variants in total. Evaluating 39 VLMs, we find that even state-of-the-art models (GPT-5, Gemini 2.5 Pro) achieve under 50% on the original queries. Crucially, query explicitation alone yields 8 to 22 point improvements, with smaller models benefiting most. We further show that even with web search, under-specified queries underperform explicit queries without search, revealing that current retrieval cannot compensate for what users leave unsaid. Our findings demonstrate that a substantial portion of VLM difficulty stem from natural query under-specification instead of model capability, highlighting a critical gap between benchmark evaluation and real-world deployment.
Authors: Di Xu, Hengjie Liu, Yang Yang, Mary Feng, Jin Ning, Xin Miao, Jessica E. Scholey, Alexandra E. Hotca-cho, William C. Chen, Michael Ohliger, Martina Descovich, Huiming Dong, Wensha Yang, Ke Sheng
Abstract: Accelerated dynamic volumetric magnetic resonance imaging (4DMRI) is essential for applications relying on motion resolution. Existing 4DMRI produces acceptable artifacts of averaged breathing phases, which can blur and misrepresent instantaneous dynamic information. Recovery of such information requires a new paradigm to reconstruct extremely undersampled non-Cartesian k-space data. We propose B-FIRE, a binning-free diffusion implicit neural representation framework for hyper-accelerated MR reconstruction capable of reflecting instantaneous 3D abdominal anatomy. B-FIRE employs a CNN-INR encoder-decoder backbone optimized using diffusion with a comprehensive loss that enforces image-domain fidelity and frequency-aware constraints. Motion binned image pairs were used as training references, while inference was performed on binning-free undersampled data. Experiments were conducted on a T1-weighted StarVIBE liver MRI cohort, with accelerations ranging from 8 spokes per frame (RV8) to RV1. B-FIRE was compared against direct NuFFT, GRASP-CS, and an unrolled CNN method. Reconstruction fidelity, motion trajectory consistency, and inference latency were evaluated.
Authors: Jyotiraditya Gupta
Abstract: Handwritten digit images lie in a high-dimensional pixel space but exhibit strong geometric and statistical structure. This paper investigates the latent organization of handwritten digits in the MNIST dataset using three complementary dimensionality reduction techniques: Principal Component Analysis (PCA), Factor Analysis (FA), and Uniform Manifold Approximation and Projection (UMAP). Rather than focusing on classification accuracy, we study how each method characterizes intrinsic dimensionality, shared variation, and nonlinear geometry. PCA reveals dominant global variance directions and enables high-fidelity reconstructions using a small number of components. FA decomposes digits into interpretable latent handwriting primitives corresponding to strokes, loops, and symmetry. UMAP uncovers nonlinear manifolds that reflect smooth stylistic transitions between digit classes. Together, these results demonstrate that handwritten digits occupy a structured low-dimensional manifold and that different statistical frameworks expose complementary aspects of this structure.
Authors: Zhiyong Ma, Zhenpeng Li, Yuanjie Shi, Zhengping Li, Jiahao Chen, Qingyuan Chuai
Abstract: Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failure and prior-dominated hallucination, that form a vicious cycle degrading generation quality. Existing methods rely on tailored training, which limits flexibility and raises deployment costs. To address these challenges effectively, we propose TBDN, a training-free framework integrating two complementary closed-loop mechanisms: Hint Instruction (HI) and Query Contrastive Decoding (QCD). HI injects task-aware inductive bias via lightweight prompt engineering to anchor models on contextual mapping rules, thereby mitigating compliance failure. QCD adjusts the decoding distributions of language models by contrasting full-input and query-omitted distributions, suppressing prior-dominated hallucination. TBDN achieves State-of-the-Art performance on CoBSAT and Text-to-Image Fast Mini-ImageNet, with robust generalization across model backbones, prompt designs, and hyperparameters. It also maintains promising performance in concept preservation and prompt following on Dreambench++. By breaking the two bottlenecks, TBDN establishes a simple yet effective framework for efficient and reliable T2I-ICL.
Authors: Hongbo Jin, Siyi Xie, Jiayu Ding, Kuanwei Lin, Ge Li
Abstract: While Large Video-Language Models (Video-LLMs) have achieved remarkable progress in perception, their reasoning capabilities remain a bottleneck. Existing solutions typically resort to a heavy "data engineering" paradigm-synthesizing large-scale Chain-of-Thought (CoT) datasets followed by Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). This pipeline primarily optimizes probability sampling efficiency and aligns output distributions, but fails to activate the intrinsic intelligence required for dynamic visual exploration. In this work, we propose TIR-Flow, a novel framework that shifts the paradigm from passive processing to active video searching and reasoning without additional data or parameter updating. Concretely, our framework operates through three synergistic modules: HDD decomposes complex queries into a set of verifiable sub-tasks; HAP actively directs visual attention to gather high-resolution evidence for hypothesis validation; EBA maintains a persistent workspace to accumulate and update the discovered clues for logical reasoning. Extensive experiments on seven benchmarks demonstrate that TIR-Flow significantly outperforms recent strong baselines, delivering an average performance boost of 5.9%, with gains reaching 10.5% on Egoschema. Our analysis confirms that empowering frozen VLMs with System-2-like active perception is a scalable path toward solving long-horizon video reasoning.
Authors: Nishan Rai, Pushpa R. Dahal
Abstract: This study presents a unified Attention U-Net architecture trained jointly on MRI (BraTS 2021) and CT (LIDC-IDRI) datasets to investigate the generalizability of a single model across diverse imaging modalities and anatomical sites. Our proposed pipeline incorporates modality-harmonized preprocessing, attention-gated skip connections, and a modality-aware Focal Tversky loss function. To the best of our knowledge, this study is among the first to evaluate a single Attention U-Net trained simultaneously on separate MRI (BraTS) and CT (LIDC-IDRI) tumor datasets, without relying on modality-specific encoders or domain adaptation. The unified model demonstrates competitive performance in terms of Dice coefficient, IoU, and AUC on both domains, thereby establishing a robust and reproducible baseline for future research in cross-modality tumor segmentation.
Authors: Shubham Goel, Farzana S, C V Rishi, Aditya Arun, C V Jawahar
Abstract: Biryani, one of India's most celebrated dishes, exhibits remarkable regional diversity in its preparation, ingredients, and presentation. With the growing availability of online cooking videos, there is unprecedented potential to study such culinary variations using computational tools systematically. However, existing video understanding methods fail to capture the fine-grained, multimodal, and culturally grounded differences in procedural cooking videos. This work presents the first large-scale, curated dataset of biryani preparation videos, comprising 120 high-quality YouTube recordings across 12 distinct regional styles. We propose a multi-stage framework leveraging recent advances in vision-language models (VLMs) to segment videos into fine-grained procedural units and align them with audio transcripts and canonical recipe text. Building on these aligned representations, we introduce a video comparison pipeline that automatically identifies and explains procedural differences between regional variants. We construct a comprehensive question-answer (QA) benchmark spanning multiple reasoning levels to evaluate procedural understanding in VLMs. Our approach employs multiple VLMs in complementary roles, incorporates human-in-the-loop verification for high-precision tasks, and benchmarks several state-of-the-art models under zero-shot and fine-tuned settings. The resulting dataset, comparison methodology, and QA benchmark provide a new testbed for evaluating VLMs on structured, multimodal reasoning tasks and open new directions for computational analysis of cultural heritage through cooking videos. We release all data, code, and the project website at https://farzanashaju.github.io/how-does-india-cook-biryani/.
URLs: https://farzanashaju.github.io/how-does-india-cook-biryani/.
Authors: Shiwen Zhang, Haibin Huang, Chi Zhang, Xuelong Li
Abstract: Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to its internal entangled content and style features. In this technical report, we propose the first content-preserving style transfer model trained on Qwen-Image-Edit, which activates Qwen-Image-Edit's strong content preservation and style customization capability. We collected and filtered high quality data of limited specific styles and synthesized triplets with thousands categories of style images in-the-wild. We introduce the Curriculum Continual Learning framework to train QwenStyle with such mixture of clean and noisy triplets, which enables QwenStyle to generalize to unseen styles without degradation of the precise content preservation capability. Our QwenStyle V1 achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.
Authors: Tayyab Rehman, Giovanni De Gasperis, Aly Shmahell
Abstract: Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture low-level deviations without contextual reasoning, object detectors provide speed but limited semantics, and large vision-language systems deliver interpretability at prohibitive computational cost. This work introduces a cascading multi-agent framework that unifies these complementary paradigms into a coherent and interpretable architecture. Early modules perform reconstruction-gated filtering and object-level assessment, while higher-level reasoning agents are selectively invoked to interpret semantically ambiguous events. The system employs adaptive escalation thresholds and a publish-subscribe communication backbone, enabling asynchronous coordination and scalable deployment across heterogeneous hardware. Extensive evaluation on large-scale monitoring data demonstrates that the proposed cascade achieves a threefold reduction in latency compared to direct vision-language inference, while maintaining high perceptual fidelity (PSNR = 38.3 dB, SSIM = 0.965) and consistent semantic labeling. The framework advances beyond conventional detection pipelines by combining early-exit efficiency, adaptive multi-agent reasoning, and explainable anomaly attribution, establishing a reproducible and energy-efficient foundation for scalable intelligent visual monitoring.
Authors: Julien Combes (SVH), Alexandre Derville (Michelin), Jean-Fran\c{c}ois Coeurjolly (SVH)
Abstract: The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two particularities of machine vision are first, that most of the images produced are free of defects, and second, that the amount of images produced is so big that we cannot store all acquired images. This results, on the one hand, in a strong class imbalance in defect distribution and, on the other hand, in a potential label shift caused by limited storage. To understand how these two forms of imbalance affect active learning algorithms, we propose a simulation study based on two open-source datasets. We artificially create datasets for which we control the levels of class imbalance and label shift. Three standard active learning selection strategies are compared: random sampling, entropy-based selection, and core-set selection. We demonstrate that active learning strategies, and in particular the entropy-based and core-set selections, remain interesting and efficient even for highly imbalanced datasets. We also illustrate and measure the loss of efficiency that occurs in the situation a strong label shift.
Authors: Yani Meziani
Abstract: We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA). The system leverages the Mamba-3 Selective State Space Model (SSM) augmented by a Sparse Mixture of Hamiltonian Experts (SMoE-HE) that enforces latent physical conservation laws through symplectic integration. For visual synthesis, we introduce Hamiltonian Flow Matching (HFM) and persistent 3D Gaussian Splatting (3DGS), enabling ultra-low latency (<50ms) on mobile hardware. This work establishes a new paradigm in latent world models, achieving unprecedented spatiotemporal coherence through a holographic memory architecture. Our approach demonstrates that incorporating physics-inspired inductive biases into neural architectures yields significant improvements: state-of-the-art video prediction (FVD: 287), 4x faster visual synthesis than diffusion models, and 3-18x inference speedup over transformer baselines while maintaining energy conservation over extended horizons.
Authors: Kuan Wei Chen, Ting Yi Lin, Wen Ren Yang, Aryan Kesarwani, Riya Singh
Abstract: We present a cost-effective two-step authentication system that integrates face identification and speaker verification using only a camera and microphone available on common devices. The pipeline first performs face recognition to identify a candidate user from a small enrolled group, then performs voice recognition only against the matched identity to reduce computation and improve robustness. For face recognition, a pruned VGG-16 based classifier is trained on an augmented dataset of 924 images from five subjects, with faces localized by MTCNN; it achieves 95.1% accuracy. For voice recognition, a CNN speaker-verification model trained on LibriSpeech (train-other-360) attains 98.9% accuracy and 3.456% EER on test-clean. Source code and trained models are available at https://github.com/NCUE-EE-AIAL/Two-step-Authentication-Multi-biometric-System.
URLs: https://github.com/NCUE-EE-AIAL/Two-step-Authentication-Multi-biometric-System.
Authors: Xinghao Wang, Changtao Miao, Dianmo Sheng, Tao Gong, Qi Chu, Nenghai Yu, Quanchen Zou, Deyue Zhang, Xiangzheng Zhang
Abstract: Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised methods rely only on image-level binary labels and focus on global classification, often overlooking local edge cues that are critical for precise localization. We observe that feature variations at manipulated boundaries are substantially larger than in interior regions. To address this gap, we propose Semantic-Agnostic Prompt Learning (SAPL) in CLIP, which learns text prompts that intentionally encode non-semantic, boundary-centric cues so that CLIPs multimodal similarity highlights manipulation edges rather than high-level object semantics. SAPL combines two complementary modules Edge-aware Contextual Prompt Learning (ECPL) and Hierarchical Edge Contrastive Learning (HECL) to exploit edge information in both textual and visual spaces. The proposed ECPL leverages edge-enhanced image features to generate learnable textual prompts via an attention mechanism, embedding semantic-irrelevant information into text features, to guide CLIP focusing on manipulation edges. The proposed HECL extract genuine and manipulated edge patches, and utilize contrastive learning to boost the discrimination between genuine edge patches and manipulated edge patches. Finally, we predict the manipulated regions from the similarity map after processing. Extensive experiments on multiple public benchmarks demonstrate that SAPL significantly outperforms existing approaches, achieving state-of-the-art localization performance.
Authors: Miao Pan, Wangjie Gan, Jintao Chen, Wenqi Zhang, Bing Sun, Jianwei Yin, Xuhong Zhang
Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse tasks, their practical deployment is severely hindered by hallucination issues, which become particularly acute during Reinforcement Learning (RL) optimization. This paper systematically analyzes the root causes of hallucinations in MLLMs under RL training, identifying three critical factors: (1) an over-reliance on chained visual reasoning, where inaccurate initial descriptions or redundant information anchor subsequent inferences to incorrect premises; (2) insufficient exploration diversity during policy optimization, leading the model to generate overly confident but erroneous outputs; and (3) destructive conflicts between training samples, where Neural Tangent Kernel (NTK) similarity causes false associations and unstable parameter updates. To address these challenges, we propose a comprehensive framework comprising three core modules. First, we enhance visual localization by introducing dedicated planning and captioning stages before the reasoning phase, employing a quality-based caption reward to ensure accurate initial anchoring. Second, to improve exploration, we categorize samples based on the mean and variance of their reward distributions, prioritizing samples with high variance to focus the model on diverse and informative data. Finally, to mitigate sample interference, we regulate NTK similarity by grouping sample pairs and applying an InfoNCE loss to push overly similar pairs apart and pull dissimilar ones closer, thereby guiding gradient interactions toward a balanced range. Experimental results demonstrate that our proposed method significantly reduces hallucination rates and effectively enhances the inference accuracy of MLLMs.
Authors: Zhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm, Yi Jin, Claas Tebruegge, Ernst Warsitz, Markus Gardill
Abstract: The scarcity and low diversity of well-annotated automotive radar datasets often limit the performance of deep-learning-based environmental perception. To overcome these challenges, we propose a conditional generative framework for synthesizing realistic Frequency-Modulated Continuous-Wave radar Range-Azimuth Maps. Our approach leverages a generative diffusion model to generate radar data for multiple object categories, including pedestrians, cars, and cyclists. Specifically, conditioning is achieved via Confidence Maps, where each channel represents a semantic class and encodes Gaussian-distributed annotations at target locations. To address radar-specific characteristics, we incorporate Geometry Aware Conditioning and Temporal Consistency Regularization into the generative process. Experiments on the ROD2021 dataset demonstrate that signal reconstruction quality improves by \SI{3.6}{dB} in Peak Signal-to-Noise Ratio over baseline methods, while training with a combination of real and synthetic datasets improves overall mean Average Precision by 4.15% compared with conventional image-processing-based augmentation. These results indicate that our generative framework not only produces physically plausible and diverse radar spectrum but also substantially improves model generalization in downstream tasks.
Authors: Aya Kaysan Bahjat
Abstract: As multimedia content is quickly growing, the field of facial recognition has become one of the major research fields, particularly in the recent years. The most problematic area to researchers in image processing and computer vision is the human face which is a complex object with myriads of distinctive features that can be used to identify the face. The survey of this survey is particularly focused on most challenging facial characteristics, including differences in the light, ageing, variation in poses, partial occlusion, and facial expression and presents methodological solutions. The factors, therefore, are inevitable in the creation of effective facial recognition mechanisms used on facial images. This paper reviews the most sophisticated methods of facial detection which are Hidden Markov Models, Principal Component Analysis (PCA), Elastic Cluster Plot Matching, Support Vector Machine (SVM), Gabor Waves, Artificial Neural Networks (ANN), Eigenfaces, Independent Component Analysis (ICA), and 3D Morphable Model. Alongside the works mentioned above, we have also analyzed the images of a number of facial databases, namely JAFEE, FEI, Yale, LFW, AT&T (then called ORL), and AR (created by Martinez and Benavente), to analyze the results. However, this survey is aimed at giving a thorough literature review of face recognition, and its applications, and some experimental results are provided at the end after a detailed discussion.
Authors: Stevenson Pather, Niels Martign\`ene, Arnaud Bugnet, Fouad Boutaleb, Fabien D'Hondt, Deise Santana Maia
Abstract: We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left-right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available.
Authors: Shida Xu, Jingqi Jiang, Jonatan Scharff Willners, Sen Wang
Abstract: Underwater sonar imaging plays a crucial role in various applications, including autonomous navigation in murky water, marine archaeology, and environmental monitoring. However, the unique characteristics of sonar images, such as complex noise patterns and the lack of elevation information, pose significant challenges for 3D reconstruction and novel view synthesis. In this paper, we present NAS-GS, a novel Noise-Aware Sonar Gaussian Splatting framework specifically designed to address these challenges. Our approach introduces a Two-Ways Splatting technique that accurately models the dual directions for intensity accumulation and transmittance calculation inherent in sonar imaging, significantly improving rendering speed without sacrificing quality. Moreover, we propose a Gaussian Mixture Model (GMM) based noise model that captures complex sonar noise patterns, including side-lobes, speckle, and multi-path noise. This model enhances the realism of synthesized images while preventing 3D Gaussian overfitting to noise, thereby improving reconstruction accuracy. We demonstrate state-of-the-art performance on both simulated and real-world large-scale offshore sonar scenarios, achieving superior results in novel view synthesis and 3D reconstruction.
Authors: Joseph Heyward, Nikhil Pathasarathy, Tyler Zhu, Aravindh Mahendran, Jo\~ao Carreira, Dima Damen, Andrew Zisserman, Viorica P\u{a}tr\u{a}ucean
Abstract: The Third Perception Test challenge was organised as a full-day workshop alongside the IEEE/CVF International Conference on Computer Vision (ICCV) 2025. Its primary goal is to benchmark state-of-the-art video models and measure the progress in multimodal perception. This year, the workshop featured 2 guest tracks as well: KiVA (an image understanding challenge) and Physic-IQ (a video generation challenge). In this report, we summarise the results from the main Perception Test challenge, detailing both the existing tasks as well as novel additions to the benchmark. In this iteration, we placed an emphasis on task unification, as this poses a more challenging test for current SOTA multimodal models. The challenge included five consolidated tracks: unified video QA, unified object and point tracking, unified action and sound localisation, grounded video QA, and hour-long video QA, alongside an analysis and interpretability track that is still open for submissions. Notably, the unified video QA track introduced a novel subset that reformulates traditional perception tasks (such as point tracking and temporal action localisation) as multiple-choice video QA questions that video-language models can natively tackle. The unified object and point tracking merged the original object tracking and point tracking tasks, whereas the unified action and sound localisation merged the original temporal action localisation and temporal sound localisation tracks. Accordingly, we required competitors to use unified approaches rather than engineered pipelines with task-specific models. By proposing such a unified challenge, Perception Test 2025 highlights the significant difficulties existing models face when tackling diverse perception tasks through unified interfaces.
Authors: Zane Durante, Silky Singh, Arpandeep Khatua, Shobhit Agarwal, Reuben Tan, Yong Jae Lee, Jianfeng Gao, Ehsan Adeli, Li Fei-Fei
Abstract: Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples that splice together short, captioned videos from existing datasets. Rather than modifying model architectures or optimization objectives, VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute. We systematically study how different data composition strategies like random versus visually clustered splicing and caption enrichment affect downstream performance on downstream video question answering. Under identical compute constraints, models trained with VideoWeave achieve higher accuracy than conventional video finetuning. Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models. We link our code for all experiments here.
Authors: Saksham Singh Kushwaha, Sayan Nag, Yapeng Tian, Kuldeep Kulkarni
Abstract: In this paper, we introduce Object-WIPER, a training-free framework for removing dynamic objects and their associated visual effects from videos, and inpainting them with semantically consistent and temporally coherent content. Our approach leverages a pre-trained text-to-video diffusion transformer (DiT). Given an input video, a user-provided object mask, and query tokens describing the target object and its effects, we localize relevant visual tokens via visual-text cross-attention and visual self-attention. This produces an intermediate effect mask that we fuse with the user mask to obtain a final foreground token mask to replace. We first invert the video through the DiT to obtain structured noise, then reinitialize the masked tokens with Gaussian noise while preserving background tokens. During denoising, we copy values for the background tokens saved during inversion to maintain scene fidelity. To address the lack of suitable evaluation, we introduce a new object removal metric that rewards temporal consistency among foreground tokens across consecutive frames, coherence between foreground and background tokens within each frame, and dissimilarity between the input and output foreground tokens. Experiments on DAVIS and a newly curated real-world associated effect benchmark (WIPER-Bench) show that Object-WIPER surpasses both training-based and training-free baselines in terms of the metric, achieving clean removal and temporally stable reconstruction without any retraining. Our new benchmark, source code, and pre-trained models will be publicly available.
Authors: Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre
Abstract: Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to model the diversity of student behaviors, yet privacy concerns often restrict researchers to their own proprietary datasets. Moreover, the classroom context, represented in peers' actions, is ignored. To address the aforementioned limitation, we propose a novel three-stage framework for video-based student engagement measurement. First, we explore the few-shot adaptation of the vision-language model for student action recognition, which is fine-tuned to distinguish among action categories with a few training samples. Second, to handle continuous and unpredictable student actions, we utilize the sliding temporal window technique to divide each student's 2-minute-long video into non-overlapping segments. Each segment is assigned an action category via the fine-tuned VLM model, generating a sequence of action predictions. Finally, we leverage the large language model to classify this entire sequence of actions, together with the classroom context, as belonging to an engaged or disengaged student. The experimental results demonstrate the effectiveness of the proposed approach in identifying student engagement.
Authors: Yueming Pan, Ruoyu Feng, Jianmin Bao, Chong Luo, Nanning Zheng
Abstract: Video outpainting extends a video beyond its original boundaries by synthesizing missing border content. Compared with image outpainting, it requires not only per-frame spatial plausibility but also long-range temporal coherence, especially when outpainted content becomes visible across time under camera or object motion. We propose GlobalPaint, a diffusion-based framework for spatiotemporal coherent video outpainting. Our approach adopts a hierarchical pipeline that first outpaints key frames and then completes intermediate frames via an interpolation model conditioned on the completed boundaries, reducing error accumulation in sequential processing. At the model level, we augment a pretrained image inpainting backbone with (i) an Enhanced Spatial-Temporal module featuring 3D windowed attention for stronger spatiotemporal interaction, and (ii) global feature guidance that distills OpenCLIP features from observed regions across all frames into compact global tokens using a dedicated extractor. Comprehensive evaluations on benchmark datasets demonstrate improved reconstruction quality and more natural motion compared to prior methods. Our demo page is https://yuemingpan.github.io/GlobalPaint/
Authors: Xianghong Zou, Jianping Li, Yandi Yang, Weitong Wu, Yuan Wang, Qiegen Liu, Zhen Dong
Abstract: Point Cloud-based Place Recognition (PCPR) demonstrates considerable potential in applications such as autonomous driving, robot localization and navigation, and map update. In practical applications, point clouds used for place recognition are often acquired from different platforms and LiDARs across varying scene. However, existing PCPR datasets lack diversity in scenes, platforms, and sensors, which limits the effective development of related research. To address this gap, we establish WHU-PCPR, a cross-platform heterogeneous point cloud dataset designed for place recognition. The dataset differentiates itself from existing datasets through its distinctive characteristics: 1) cross-platform heterogeneous point clouds: collected from survey-grade vehicle-mounted Mobile Laser Scanning (MLS) systems and low-cost Portable helmet-mounted Laser Scanning (PLS) systems, each equipped with distinct mechanical and solid-state LiDAR sensors. 2) Complex localization scenes: encompassing real-time and long-term changes in both urban and campus road scenes. 3) Large-scale spatial coverage: featuring 82.3 km of trajectory over a 60-month period and an unrepeated route of approximately 30 km. Based on WHU-PCPR, we conduct extensive evaluation and in-depth analysis of several representative PCPR methods, and provide a concise discussion of key challenges and future research directions. The dataset and benchmark code are available at https://github.com/zouxianghong/WHU-PCPR.
Authors: Xiaoya Tang, Xiaohe Yue, Heran Mane, Dapeng Li, Quynh Nguyen, Tolga Tasdizen
Abstract: A substantial body of health research demonstrates a strong link between neighborhood environments and health outcomes. Recently, there has been increasing interest in leveraging advances in computer vision to enable large-scale, systematic characterization of neighborhood built environments. However, the generalizability of vision models across fundamentally different domains remains uncertain, for example, transferring knowledge from ImageNet to the distinct visual characteristics of Google Street View (GSV) imagery. In applied fields such as social health research, several critical questions arise: which models are most appropriate, whether to adopt unsupervised training strategies, what training scale is feasible under computational constraints, and how much such strategies benefit downstream performance. These decisions are often costly and require specialized expertise. In this paper, we answer these questions through empirical analysis and provide practical insights into how to select and adapt foundation models for datasets with limited size and labels, while leveraging larger, unlabeled datasets through unsupervised training. Our study includes comprehensive quantitative and visual analyses comparing model performance before and after unsupervised adaptation.
Authors: Weihao Hong, Zhiyuan Jiang, Bingyu Shen, Xinlei Guan, Yangyi Feng, Meng Xu, Boyang Li
Abstract: Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are not present in the image to satisfy user prompts. While recent datasets and benchmarks have been introduced to evaluate systematic hallucinations in VLMs, many hallucination behaviors remain insufficiently characterized. In particular, prior work primarily focuses on object presence or absence, leaving it unclear how prompt phrasing and structural constraints can systematically induce hallucinations. In this paper, we investigate how different forms of prompt pressure influence hallucination behavior. We introduce Ghost-100, a procedurally generated dataset of synthetic scenes in which key visual details are deliberately removed, enabling controlled analysis of absence-based hallucinations. Using a structured 5-Level Prompt Intensity Framework, we vary prompts from neutral queries to toxic demands and rigid formatting constraints. We evaluate three representative open-weight VLMs: MiniCPM-V 2.6-8B, Qwen2-VL-7B, and Qwen3-VL-8B. Across all three models, hallucination rates do not increase monotonically with prompt intensity. All models exhibit reductions at higher intensity levels at different thresholds, though not all show sustained reduction under maximum coercion. These results suggest that current safety alignment is more effective at detecting semantic hostility than structural coercion, revealing model-specific limitations in handling compliance pressure. Our dataset is available at: https://github.com/bli1/tone-matters
Authors: Chao Liu, Ngai-Man Cheung
Abstract: 3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs has shown that the integration of visual inputs significantly increases vulnerability to adversarial attacks, making these models easier to manipulate into generating toxic or misleading outputs. In this paper, we investigate whether incorporating 3D vision similarly compromises the robustness of 3D VLMs. To this end, we present the first systematic study of adversarial robustness in point-based 3D VLMs. We propose two complementary attack strategies: \textit{Vision Attack}, which perturbs the visual token features produced by the 3D encoder and projector to assess the robustness of vision-language alignment; and \textit{Caption Attack}, which directly manipulates output token sequences to evaluate end-to-end system robustness. Each attack includes both untargeted and targeted variants to measure general vulnerability and susceptibility to controlled manipulation. Our experiments reveal that 3D VLMs exhibit significant adversarial vulnerabilities under untargeted attacks, while demonstrating greater resilience against targeted attacks aimed at forcing specific harmful outputs, compared to their 2D counterparts. These findings highlight the importance of improving the adversarial robustness of 3D VLMs, especially as they are deployed in safety-critical applications.
Authors: Chenxu Dang, Jie Wang, Guang Li, Zhiwen Hou, Zihan You, Hangjun Ye, Jie Ma, Long Chen, Yan Wang
Abstract: In autonomous driving, Vision Language Models (VLMs) excel at high-level reasoning , whereas semantic occupancy provides fine-grained details. Despite significant progress in individual fields, there is still no method that can effectively integrate both paradigms. Conventional VLMs struggle with token explosion and limited spatiotemporal reasoning, while semantic occupancy provides a unified, explicit spatial representation but is too dense to integrate efficiently with VLMs. To address these challenges and bridge the gap between VLMs and occupancy, we propose SparseOccVLA, a novel vision-language-action model that unifies scene understanding, occupancy forecasting, and trajectory planning powered by sparse occupancy queries. Starting with a lightweight Sparse Occupancy Encoder, SparseOccVLA generates compact yet highly informative sparse occupancy queries that serve as the single bridge between vision and language. These queries are aligned into the language space and reasoned by the LLM for unified scene understanding and future occupancy forecasting. Furthermore, we introduce an LLM-guided Anchor-Diffusion Planner featuring decoupled anchor scoring and denoising, as well as cross-model trajectory-condition fusion. SparseOccVLA achieves a 7% relative improvement in CIDEr over the state-of-the-art on OmniDrive-nuScenes, a 0.5 increase in mIoU score on Occ3D-nuScenes, and sets state-of-the-art open-loop planning metric on nuScenes benchmark, demonstrating its strong holistic capability.
Authors: Kai Cheng, Ruoqi Wang, Qiong Luo
Abstract: Radio astronomy is an indispensable discipline for observing distant celestial objects. Measurements of wave signals from radio telescopes, called visibility, need to be transformed into images for astronomical observations. These dirty images blend information from real sources and artifacts. Therefore, astronomers usually perform reconstruction before imaging to obtain cleaner images. Existing methods consider only a single modality of sparse visibility data, resulting in images with remaining artifacts and insufficient modeling of correlation. To enhance the extraction of visibility information and emphasize output quality in the image domain, we propose VVTRec, a multimodal radio interferometric data reconstruction method with visibility-guided visual and textual modality enrichment. In our VVTRec, sparse visibility is transformed into image-form and text-form features to obtain enhancements in terms of spatial and semantic information, improving the structural integrity and accuracy of images. Also, we leverage Vision-Language Models (VLMs) to achieve additional training-free performance improvements. VVTRec enables sparse visibility, as a foreign modality unseen by VLMs, to accurately extract pre-trained knowledge as a supplement. Our experiments demonstrate that VVTRec effectively enhances imaging results by exploiting multimodal information without introducing excessive computational overhead.
Authors: JiaLin Zhang, Dong Li
Abstract: Facial optical flow supports a wide range of tasks in facial motion analysis. However, the lack of high-resolution facial optical flow datasets has hindered progress in this area. In this paper, we introduce Splatting Rasterization Flow (SRFlow), a high-resolution facial optical flow dataset, and Splatting Rasterization Guided FlowNet (SRFlowNet), a facial optical flow model with tailored regularization losses. These losses constrain flow predictions using masks and gradients computed via difference or Sobel operator. This effectively suppresses high-frequency noise and large-scale errors in texture-less or repetitive-pattern regions, enabling SRFlowNet to be the first model explicitly capable of capturing high-resolution skin motion guided by Gaussian splatting rasterization. Experiments show that training with the SRFlow dataset improves facial optical flow estimation across various optical flow models, reducing end-point error (EPE) by up to 42% (from 0.5081 to 0.2953). Furthermore, when coupled with the SRFlow dataset, SRFlowNet achieves up to a 48% improvement in F1-score (from 0.4733 to 0.6947) on a composite of three micro-expression datasets. These results demonstrate the value of advancing both facial optical flow estimation and micro-expression recognition.
Authors: Yue Wang, Lawrence Amadi, Xiang Gao, Yazheng Chen, Yuanpeng Liu, Ning Lu, Xianfeng Gu
Abstract: We present a zero-shot framework for transferring human facial expressions to 3D animal face meshes. Our method combines intrinsic geometric descriptors (HKS/WKS) with a mesh-agnostic latent embedding that disentangles facial identity and expression. The ID latent space captures species-independent facial structure, while the expression latent space encodes deformation patterns that generalize across humans and animals. Trained only with human expression pairs, the model learns the embeddings, decoupling, and recoupling of cross-identity expressions, enabling expression transfer without requiring animal expression data. To enforce geometric consistency, we employ Jacobian loss together with vertex-position and Laplacian losses. Experiments show that our approach achieves plausible cross-species expression transfer, effectively narrowing the geometric gap between human and animal facial shapes.
Authors: Hao Tang, Ting Huang, Zeyu Zhang
Abstract: Spatial intelligence refers to the ability to perceive, reason about, and describe objects and their relationships within three-dimensional environments, forming a foundation for embodied perception and scene understanding. 3D captioning aims to describe 3D scenes in natural language; however, it remains challenging due to the sparsity and irregularity of point clouds and, more critically, the weak grounding and limited out-of-distribution (OOD) generalization of existing captioners across drastically different environments, including indoor and outdoor 3D scenes. To address this challenge, we propose 3D CoCa v2, a generalizable 3D captioning framework that unifies contrastive vision-language learning with 3D caption generation and further improves robustness via test-time search (TTS) without updating the captioner parameters. 3D CoCa v2 builds on a frozen CLIP-based semantic prior, a spatially-aware 3D scene encoder for geometry, and a multimodal decoder jointly optimized with contrastive and captioning objectives, avoiding external detectors or handcrafted proposals. At inference, TTS produces diverse caption candidates and performs reward-guided selection using a compact scene summary. Experiments show improvements over 3D CoCa of +1.50 CIDEr@0.5IoU on ScanRefer and +1.61 CIDEr@0.5IoU on Nr3D, and +3.8 CIDEr@0.25 in zero-shot OOD evaluation on TOD3Cap. Code will be released at https://github.com/AIGeeksGroup/3DCoCav2.
Authors: Yash Thesia, Meera Suthar
Abstract: Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per image). Conversely, traditional CNN-based baselines offer real-time inference but struggle with "over-smoothing," failing to recover fine structural details in extreme low-light conditions. This creates a practical gap in the literature: the lack of a model that provides generative-level texture recovery at edge-deployable speeds. In this paper, we address this trade-off by proposing a hybrid Attention U-Net GAN. We demonstrate that the heavy iterative sampling of diffusion models is not strictly necessary for texture recovery. Instead, by integrating Attention Gates into a lightweight U-Net backbone and training within a conditional adversarial framework, we can approximate the high-frequency fidelity of generative models in a single forward pass. Extensive experiments on the SID dataset show that our method achieves a best-in-class LPIPS score of 0.112 among efficient models, significantly outperforming efficient baselines (SID, EnlightenGAN) while maintaining an inference latency of 0.06s. This represents a 40x speedup over latent diffusion models, making our approach suitable for near real-time applications.
Authors: Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li
Abstract: While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.
Authors: Yuanting Gao, Shuo Cao, Xiaohui Li, Yuandong Pu, Yihao Liu, Kai Zhang
Abstract: Image deblurring has advanced rapidly with deep learning, yet most methods exhibit poor generalization beyond their training datasets, with performance dropping significantly in real-world scenarios. Our analysis shows this limitation stems from two factors: datasets face an inherent trade-off between realism and coverage of diverse blur patterns, and algorithmic designs remain restrictive, as pixel-wise losses drive models toward local detail recovery while overlooking structural and semantic consistency, whereas diffusion-based approaches, though perceptually strong, still fail to generalize when trained on narrow datasets with simplistic strategies. Through systematic investigation, we identify blur pattern diversity as the decisive factor for robust generalization and propose Blur Pattern Pretraining (BPP), which acquires blur priors from simulation datasets and transfers them through joint fine-tuning on real data. We further introduce Motion and Semantic Guidance (MoSeG) to strengthen blur priors under severe degradation, and integrate it into GLOWDeblur, a Generalizable reaL-wOrld lightWeight Deblur model that combines convolution-based pre-reconstruction & domain alignment module with a lightweight diffusion backbone. Extensive experiments on six widely-used benchmarks and two real-world datasets validate our approach, confirming the importance of blur priors for robust generalization and demonstrating that the lightweight design of GLOWDeblur ensures practicality in real-world applications. The project page is available at https://vegdog007.github.io/GLOWDeblur_Website/.
Authors: Wiktor Mucha, Michael Wray, Martin Kampel
Abstract: We present V-HPOT, a novel approach for improving the cross-domain performance of 3D hand pose estimation from egocentric images across diverse, unseen domains. State-of-the-art methods demonstrate strong performance when trained and tested within the same domain. However, they struggle to generalise to new environments due to limited training data and depth perception -- overfitting to specific camera intrinsics. Our method addresses this by estimating keypoint z-coordinates in a virtual camera space, normalised by focal length and image size, enabling camera-agnostic depth prediction. We further leverage this invariance to camera intrinsics to propose a self-supervised test-time optimisation strategy that refines the model's depth perception during inference. This is achieved by applying a 3D consistency loss between predicted and in-space scale-transformed hand poses, allowing the model to adapt to target domain characteristics without requiring ground truth annotations. V-HPOT significantly improves 3D hand pose estimation performance in cross-domain scenarios, achieving a 71% reduction in mean pose error on the H2O dataset and a 41% reduction on the AssemblyHands dataset. Compared to state-of-the-art methods, V-HPOT outperforms all single-stage approaches across all datasets and competes closely with two-stage methods, despite needing approximately x3.5 to x14 less data.
Authors: Pan Liao, Feng Yang, Di Wu, Jinwen Yu, Yuhua Zhu, Wenhui Zhao
Abstract: Traditional Multi-Object Tracking (MOT) systems have achieved remarkable precision in localization and association, effectively answering \textit{where} and \textit{who}. However, they often function as autistic observers, capable of tracing geometric paths but blind to the semantic \textit{what} and \textit{why} behind object behaviors. To bridge the gap between geometric perception and cognitive reasoning, we propose \textbf{LLMTrack}, a novel end-to-end framework for Semantic Multi-Object Tracking (SMOT). We adopt a bionic design philosophy that decouples strong localization from deep understanding, utilizing Grounding DINO as the eyes and the LLaVA-OneVision multimodal large model as the brain. We introduce a Spatio-Temporal Fusion Module that aggregates instance-level interaction features and video-level contexts, enabling the Large Language Model (LLM) to comprehend complex trajectories. Furthermore, we design a progressive three-stage training strategy, Visual Alignment, Temporal Fine-tuning, and Semantic Injection via LoRA to efficiently adapt the massive model to the tracking domain. Extensive experiments on the BenSMOT benchmark demonstrate that LLMTrack achieves state-of-the-art performance, significantly outperforming existing methods in instance description, interaction recognition, and video summarization while maintaining robust tracking stability.
Authors: Fangxu Yu, Ziyao Lu, Liqiang Niu, Fandong Meng, Jie Zhou
Abstract: Grounding events in videos serves as a fundamental capability in video analysis. While Vision-Language Models (VLMs) are increasingly employed for this task, existing approaches predominantly train models to associate events with timestamps in the forward video only. This paradigm hinders VLMs from capturing the inherent temporal structure and directionality of events, thereby limiting robustness and generalization. To address this limitation, inspired by the arrow of time in physics, which characterizes the intrinsic directionality of temporal processes, we propose ArrowGEV, a reinforcement learning framework that explicitly models temporal directionality in events to improve both event grounding and temporal directionality understanding in VLMs. Specifically, we categorize events into time-sensitive (e.g., putting down a bag) and time-insensitive (e.g., holding a towel in the left hand). The former denote events whose reversal substantially alters their meaning, while the latter remain semantically unchanged under reversal. For time-sensitive events, ArrowGEV introduces a reward that encourages VLMs to discriminate between forward and backward videos, whereas for time-insensitive events, it enforces consistent grounding across both directions. Extensive experiments demonstrate that ArrowGEV not only improves grounding precision and temporal directionality recognition, but also enhances general video understanding and reasoning ability.
Authors: Jiale Wang, Gee Wah Ng, Lee Onn Mak, Randall Cher, Ng Ding Hei Ryan, Davis Wang
Abstract: This paper introduces QCaption, a novel video captioning and Q&A pipeline that enhances video analytics by fusing three models: key frame extraction, a Large Multimodal Model (LMM) for image-text analysis, and a Large Language Model (LLM) for text analysis. This approach enables integrated analysis of text, images, and video, achieving performance improvements over existing video captioning and Q&A models; all while remaining fully self-contained, adept for on-premises deployment. Experimental results using QCaption demonstrated up to 44.2% and 48.9% improvements in video captioning and Q&A tasks, respectively. Ablation studies were also performed to assess the role of LLM on the fusion on the results. Moreover, the paper proposes and evaluates additional video captioning approaches, benchmarking them against QCaption and existing methodologies. QCaption demonstrate the potential of adopting a model fusion approach in advancing video analytics.
Authors: Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian
Abstract: Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance, high-responsiveness objectives (e.g., OCR) while under-optimizing perceptual goals. We identify two mechanistic causes: variance hijacking, where reward dispersion induces implicit reweighting that dominates the normalized training signal, and gradient conflicts, where competing objectives produce opposing update directions and trigger seesaw-like oscillations. We propose APEX (Adaptive Priority-based Efficient X-objective Alignment), which stabilizes heterogeneous rewards with Dual-Stage Adaptive Normalization and dynamically schedules objectives via P^3 Adaptive Priorities that combine learning potential, conflict penalty, and progress need. On Stable Diffusion 3.5, APEX achieves improved Pareto trade-offs across four heterogeneous objectives, with balanced gains of +1.31 PickScore, +0.35 DeQA, and +0.53 Aesthetics while maintaining competitive OCR accuracy, mitigating the instability of multi-objective alignment.
Authors: Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong, Xucheng Yin
Abstract: Text-guided image generation has advanced rapidly with large-scale diffusion models, yet achieving precise stylization with visual exemplars remains difficult. Existing approaches often depend on task-specific retraining or expensive inversion procedures, which can compromise content integrity, reduce style fidelity, and lead to an unsatisfactory trade-off between semantic prompt adherence and style alignment. In this work, we introduce a training-free framework that reformulates style-guided synthesis as an in-context learning task. Guided by textual semantic prompts, our method concatenates a reference style image with a masked target image, leveraging a pretrained ReFlow-based inpainting model to seamlessly integrate semantic content with the desired style through multimodal attention fusion. We further analyze the imbalance and noise sensitivity inherent in multimodal attention fusion and propose a Dynamic Semantic-Style Integration (DSSI) mechanism that reweights attention between textual semantic and style visual tokens, effectively resolving guidance conflicts and enhancing output coherence. Experiments show that our approach achieves high-fidelity stylization with superior semantic-style balance and visual quality, offering a simple yet powerful alternative to complex, artifact-prone prior methods.
Authors: Gui Huang, Kangyuan Zheng, Xuan Cai, Jiaqi Wang, Jianjia Zhang, Kaida Ning, Wenbo Wei, Yujuan Zhu, Jiong Zhang, Mengting Liu
Abstract: Organoids, sophisticated in vitro models of human tissues, are crucial for medical research due to their ability to simulate organ functions and assess drug responses accurately. Accurate organoid instance segmentation is critical for quantifying their dynamic behaviors, yet remains profoundly limited by high-quality annotated datasets and pervasive overlap in microscopy imaging. While semi-supervised learning (SSL) offers a solution to alleviate reliance on scarce labeled data, conventional SSL frameworks suffer from biases induced by noisy pseudo-labels, particularly in overlapping regions. Synthesis-assisted SSL (SA-SSL) has been proposed for mitigating training biases in semi-supervised semantic segmentation. We present the first adaptation of SA-SSL to organoid instance segmentation and reveal that SA-SSL struggles to disentangle intertwined organoids, often misrepresenting overlapping instances as a single entity. To overcome this, we propose Pseudo-Label Unmixing (PLU), which identifies erroneous pseudo-labels for overlapping instances and then regenerates organoid labels through instance decomposition. For image synthesis, we apply a contour-based approach to synthesize organoid instances efficiently, particularly for overlapping cases. Instance-level augmentations (IA) on pseudo-labels before image synthesis further enhances the effect of synthetic data (SD). Rigorous experiments on two organoid datasets demonstrate our method's effectiveness, achieving performance comparable to fully supervised models using only 10% labeled data, and state-of-the-art results. Ablation studies validate the contributions of PLU, contour-based synthesis, and augmentation-aware training. By addressing overlap at both pseudo-label and synthesis levels, our work advances scalable, label-efficient organoid analysis, unlocking new potential for high-throughput applications in precision medicine.
Authors: Krishna Vinod, Joseph Raj Vishal, Kaustav Chanda, Prithvi Jai Ramesh, Yezhou Yang, Bharatesh Chakravarthi
Abstract: Tracking skiers in RGB broadcast footage is challenging due to motion blur, static overlays, and clutter that obscure the fast-moving athlete. Event cameras, with their asynchronous contrast sensing, offer natural robustness to such artifacts, yet a controlled benchmark for winter-sport tracking has been missing. We introduce event SkiTB (eSkiTB), a synthetic event-based ski tracking dataset generated from SkiTB using direct video-to-event conversion without neural interpolation, enabling an iso-informational comparison between RGB and event modalities. Benchmarking SDTrack (spiking transformer) against STARK (RGB transformer), we find that event-based tracking is substantially resilient to broadcast clutter in scenes dominated by static overlays, achieving 0.685 IoU, outperforming RGB by +20.0 points. Across the dataset, SDTrack attains a mean IoU of 0.711, demonstrating that temporal contrast is a reliable cue for tracking ballistic motion in visually congested environments. eSkiTB establishes the first controlled setting for event-based tracking in winter sports and highlights the promise of event cameras for ski tracking. The dataset and code will be released at https://github.com/eventbasedvision/eSkiTB.
Authors: Sanjay Pradeep, Chen Wang, Matthew M. Dahm, Jeff D. Eldredge, Candace S. J. Tsai
Abstract: Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a unified framework leveraging vision foundation models to automate the quantification and classification of CNTs in electron microscopy images. First, we introduce an interactive quantification tool built on the Segment Anything Model (SAM) that segments particles with near-perfect accuracy using minimal user input. Second, we propose a novel classification pipeline that utilizes these segmentation masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise. Evaluated on a dataset of 1,800 TEM images, this architecture achieves 95.5% accuracy in distinguishing between four different CNT morphologies, significantly outperforming the current baseline despite using a fraction of the training data. Crucially, this instance-level processing allows the framework to resolve mixed samples, correctly classifying distinct particle types co-existing within a single field of view. These results demonstrate that integrating zero-shot segmentation with self-supervised feature learning enables high-throughput, reproducible nanomaterial analysis, transforming a labor-intensive bottleneck into a scalable, data-driven process.
Authors: Mahsa Mitcheff, Adam Czajka
Abstract: Iris recognition is a mature biometric technology offering remarkable precision and speed, and allowing for large-scale deployments to populations exceeding a billion enrolled users (e.g., AADHAAR in India). However, in forensic applications, a human expert may be needed to review and confirm a positive identification before an iris matching result can be presented as evidence in court, especially in cases where processed samples are degraded (e.g., in post-mortem cases) or where there is a need to judge whether the sample is authentic, rather than a result of a presentation attack. This paper presents a study that examines human performance in iris verification in two controlled scenarios: (a) under varying pupil sizes, with and without a linear/nonlinear alignment of the pupil size between compared images, and (b) when both genuine and impostor iris image pairs are synthetically generated. The results demonstrate that pupil size normalization carried out by a modern autoencoder-based identity-preserving image-to-image translation model significantly improves verification accuracy. Participants were also able to determine whether iris pairs corresponded to the same or different eyes when both images were either authentic or synthetic. However, accuracy declined when subjects were comparing authentic irises against high-quality, same-eye synthetic counterparts. These findings (a) demonstrate the importance of pupil-size alignment for iris matching tasks in which humans are involved, and (b) indicate that despite the high fidelity of modern generative models, same-eye synthetic iris images are more often judged by humans as different-eye images, compared to same-eye authentic image pairs. We offer data and human judgments along with this paper to allow full replicability of this study and future works.
Authors: Shaonan Liu, Guo Yu, Xiaoling Luo, Shiyi Zheng, Wenting Chen, Jie Liu, Linlin Shen
Abstract: Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this critical capability. To address these challenges, we introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation. Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical workflows, and implicit adherence to safety protocols. We propose a Three-Dimensional Clinical Intent Framework evaluating: (1) Spatial Intent: discriminating precise targets amid visual noise, (2) Temporal Intent: inferring causal rationale through retrospective and prospective reasoning, and (3) Standard Intent: verifying protocol compliance through safety checks. Beyond accuracy metrics, we introduce Trap QA mechanisms to stress-test clinical reliability by penalizing hallucinations and cognitive sycophancy. Experiments reveal current MLLMs struggle with egocentric intent due to over-reliance on global features, leading to fabricated observations and uncritical acceptance of invalid instructions.
Authors: Ali Lotfi, Adam Carter, Mohammad Meysami, Thuan Ha, Kwabena Nketia, Steve Shirtliffe
Abstract: Normalized difference indices have been a staple in remote sensing for decades. They stay reliable under lighting changes produce bounded values and connect well to biophysical signals. Even so, they are usually treated as a fixed pre processing step with coefficients set to one, which limits how well they can adapt to a specific learning task. In this study, we introduce the Normalized Difference Layer that is a differentiable neural network module. The proposed method keeps the classical idea but learns the band coefficients from data. We present a complete mathematical framework for integrating this layer into deep learning architectures that uses softplus reparameterization to ensure positive coefficients and bounded denominators. We describe forward and backward pass algorithms enabling end to end training through backpropagation. This approach preserves the key benefits of normalized differences, namely illumination invariance and outputs bounded to $[-1,1]$ while allowing gradient descent to discover task specific band weightings. We extend the method to work with signed inputs, so the layer can be stacked inside larger architectures. Experiments show that models using this layer reach similar classification accuracy to standard multilayer perceptrons while using about 75\% fewer parameters. They also handle multiplicative noise well, at 10\% noise accuracy drops only 0.17\% versus 3.03\% for baseline MLPs. The learned coefficient patterns stay consistent across different depths.
Authors: Zhongping Ji
Abstract: Modern computer vision architectures, from CNNs to Transformers, predominantly rely on the stacking of heuristic modules: spatial mixers (Attention/Conv) followed by channel mixers (FFNs). In this work, we challenge this paradigm by returning to mathematical first principles. We propose the \textbf{Clifford Algebra Network (CAN)}, also referred to as CliffordNet, a vision backbone grounded purely in Geometric Algebra. Instead of engineering separate modules for mixing and memory, we derive a unified interaction mechanism based on the \textbf{Clifford Geometric Product} ($uv = u \cdot v + u \wedge v$). This operation ensures algebraic completeness regarding the Geometric Product by simultaneously capturing feature coherence (via the generalized inner product) and structural variation (via the exterior wedge product). Implemented via an efficient sparse rolling mechanism with \textbf{strict linear complexity $\mathcal{O}(N)$}, our model reveals a surprising emergent property: the geometric interaction is so representationally dense that standard Feed-Forward Networks (FFNs) become redundant. Empirically, CliffordNet establishes a new Pareto frontier: our \textbf{Nano} variant achieves \textbf{76.41\%} accuracy on CIFAR-100 with only \textbf{1.4M} parameters, effectively matching the heavy-weight ResNet-18 (11.2M) with \textbf{$8\times$ fewer parameters}, while our \textbf{Base} variant sets a new SOTA for tiny models at \textbf{78.05\%}. Our results suggest that global understanding can emerge solely from rigorous, algebraically complete local interactions, potentially signaling a shift where \textit{geometry is all you need}. Code is available at https://github.com/ParaMind2025/CAN.
Authors: Jiwen Zhang, Zejun Li, Siyuan Wang, Xiangyu Shi, Zhongyu Wei, Qi Wu
Abstract: Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation.
Authors: Jee Won Lee, Hansol Lim, Minhyeok Im, Dohyeon Lee, Jongseong Brad Choi
Abstract: We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces geometry-first pair selection by scoring reconstruction informativeness - the product of overlap and parallax - before expensive matching. A lightweight pre-matching stage uses mutual nearest neighbors and RANSAC to estimate these cues, then constructs an Information-Weighted Spanning Tree (IWST) augmented with targeted edges for loop closure, long-baseline anchors, and weak-view reinforcement. Compared to exhaustive matching, SARA reduces rotation errors by 46.5+-5.5% and translation errors by 12.5+-6.5% across modern learned detectors, while achieving at most 50x speedup through 98% pair reduction (from 30,848 to 580 pairs). This reduces matching complexity from quadratic to quasi-linear, maintaining within +-3% of baseline reconstruction metrics for 3D Gaussian Splatting and SVRaster.
Authors: Chenglong Bao, Tongyao Pang, Zuowei Shen, Dihan Zheng, Yihang Zou
Abstract: Low-resolution image representation is a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various image processing tasks. However, a key challenge is to preserve essential visual content while maintaining the ability to accurately reconstruct the original images. This work proposes LR2Flow, a nonlinear framework that learns low-resolution image representations by integrating wavelet tight frame blocks with normalizing flows. We conduct a reconstruction error analysis of the proposed network, which demonstrates the necessity of designing invertible neural networks in the wavelet tight frame domain. Experimental results on various tasks, including image rescaling, compression, and denoising, demonstrate the effectiveness of the learned representations and the robustness of the proposed framework.
Authors: Hyunseo Lee, Sang Min Kim, Ho Kyung Shin, Taeheon Kim, Woo-Jeoung Nam
Abstract: Synthetic Aperture Radar (SAR) provides robust all-weather imaging capabilities; however, translating SAR observations into photo-realistic optical images remains a fundamentally ill-posed problem. Current approaches are often hindered by the inherent speckle noise and geometric distortions of SAR data, which frequently result in semantic misinterpretation, ambiguous texture synthesis, and structural hallucinations. To address these limitations, a novel SAR-to-Optical (S2O) translation framework is proposed, integrating three core technical contributions: (i) Cross-Modal Semantic Alignment, which establishes an Optical-Aware SAR Encoder by distilling robust semantic priors from an Optical Teacher into a SAR Student (ii) Semantically-Grounded Generative Guidance, realized by a Semantically-Grounded ControlNet that integrates class-aware text prompts for global context with hierarchical visual prompts for local spatial guidance; and (iii) an Uncertainty-Aware Objective, which explicitly models aleatoric uncertainty to dynamically modulate the reconstruction focus, effectively mitigating artifacts caused by speckle-induced ambiguity. Extensive experiments demonstrate that the proposed method achieves superior perceptual quality and semantic consistency compared to state-of-the-art approaches.
Authors: Hansol Lim, Minhyeok Im, Jongseong Brad Choi
Abstract: We present PRISM, a novel color-guided stratified sampling method for RGB-LiDAR point clouds. Our approach is motivated by the observation that unique scene features often exhibit chromatic diversity while repetitive, redundant features are homogeneous in color. Conventional downsampling methods (Random Sampling, Voxel Grid, Normal Space Sampling) enforce spatial uniformity while ignoring this photometric content. In contrast, PRISM allocates sampling density proportional to chormatic diversity. By treating RGB color space as the stratification domain and imposing a maximum capacity k per color bin, the method preserves texture-rich regions with high color variation while substantially reducing visually homogeneous surfaces. This shifts the sampling space from spatial coverage to visual complexity to produce sparser point clouds that retain essential features for 3D reconstruction tasks.
Authors: Junyan Lin, Junlong Tong, Hao Wu, Jialiang Zhang, Jinming Liu, Xin Jin, Xiaoyu Shen
Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before generating outputs. Recent streaming methods reduce latency by interleaving perception and generation, but still enforce a sequential perception-generation cycle, limiting real-time interaction. In this work, we target a fundamental bottleneck that arises when extending MLLMs to real-time video understanding: the global positional continuity constraint imposed by standard positional encoding schemes. While natural in offline inference, this constraint tightly couples perception and generation, preventing effective input-output parallelism. To address this limitation, we propose a parallel streaming framework that relaxes positional continuity through three designs: Overlapped, Group-Decoupled, and Gap-Isolated. These designs enable simultaneous perception and generation, allowing the model to process incoming inputs while producing responses in real time. Extensive experiments reveal that Group-Decoupled achieves the best efficiency-performance balance, maintaining high fluency and accuracy while significantly reducing latency. We further show that the proposed framework yields up to 2x acceleration under balanced perception-generation workloads, establishing a principled pathway toward speak-while-watching real-time systems. We make all our code publicly available: https://github.com/EIT-NLP/Speak-While-Watching.
Authors: Mengmeng Zhang, Xiaoping Wu, Hao Luo, Fan Wang, Yisheng Lv
Abstract: Vision-Language Models (VLMs) can generate convincing clinical narratives, yet frequently struggle to visually ground their statements. We posit this limitation arises from the scarcity of high-quality, large-scale clinical referring-localization pairs. To address this, we introduce MedGround, an automated pipeline that transforms segmentation resources into high-quality medical referring grounding data. Leveraging expert masks as spatial anchors, MedGround precisely derives localization targets, extracts shape and spatial cues, and guides VLMs to synthesize natural, clinically grounded queries that reflect morphology and location. To ensure data rigor, a multi-stage verification system integrates strict formatting checks, geometry- and medical-prior rules, and image-based visual judging to filter out ambiguous or visually unsupported samples. Finally, we present MedGround-35K, a novel multimodal medical dataset. Extensive experiments demonstrate that VLMs trained with MedGround-35K consistently achieve improved referring grounding performance, enhance multi-object semantic disambiguation, and exhibit strong generalization to unseen grounding settings. This work highlights MedGround as a scalable, data-driven approach to anchor medical language to verifiable visual evidence. Dataset and code will be released publicly upon acceptance.
Authors: Changli Wu, Haodong Wang, Jiayi Ji, Yutian Yao, Chunsai Du, Jihua Kang, Yanwei Fu, Liujuan Cao
Abstract: Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints. We introduce Multi-view 3D Referring Expression Segmentation (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images. Traditional two-stage pipelines, which first reconstruct a point cloud and then perform segmentation, often yield low-quality geometry, produce coarse or degraded target regions, and run slowly. We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning through a dual-branch design. Training in this setting exposes a critical optimization barrier, termed Foreground Gradient Dilution (FGD), where sparse 3D signals lead to weak supervision. To resolve this, we introduce Per-view No-target Suppression Optimization (PVSO), which provides stronger and more balanced gradients across views, enabling stable and efficient learning. To support consistent evaluation, we build MVRefer, a benchmark that defines standardized settings and metrics for MV-3DRES. Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives. Code and models are publicly available at https://mvggt.github.io.
URLs: https://mvggt.github.io.
Authors: Dillan Imans, Phuoc-Nguyen Bui, Duc-Tai Le, Hyunseung Choo
Abstract: Unsupervised Domain Adaptation with SAM-RefiSeR for Enhanced Brain Tumor Segmentation
Authors: Xinhang Liu, Jiawei Shi, Zheng Dang, Yuchao Dai
Abstract: We present MixRI, a lightweight network that solves the CAD-based novel object pose estimation problem in RGB images. It can be instantly applied to a novel object at test time without finetuning. We design our network to meet the demands of real-world applications, emphasizing reduced memory requirements and fast inference time. Unlike existing works that utilize many reference images and have large network parameters, we directly match points based on the multi-view information between the query and reference images with a lightweight network. Thanks to our reference image fusion strategy, we significantly decrease the number of reference images, thus decreasing the time needed to process these images and the memory required to store them. Furthermore, with our lightweight network, our method requires less inference time. Though with fewer reference images, experiments on seven core datasets in the BOP challenge show that our method achieves comparable results with other methods that require more reference images and larger network parameters.
Authors: Nimrod Shabtay, Itamar Zimerman, Eli Schwartz, Raja Giryes
Abstract: Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.
Authors: Zengyuan Zuo, Junjun Jiang, Gang Wu, Xianming Liu
Abstract: Image dehazing has witnessed significant advancements with the development of deep learning models. However, a few methods predominantly focus on single-modal RGB features, neglecting the inherent correlation between scene depth and haze distribution. Even those that jointly optimize depth estimation and image dehazing often suffer from suboptimal performance due to inadequate utilization of accurate depth information. In this paper, we present UDPNet, a general framework that leverages depth-based priors from large-scale pretrained depth estimation model DepthAnything V2 to boost existing image dehazing models. Specifically, our architecture comprises two typical components: the Depth-Guided Attention Module (DGAM) adaptively modulates features via lightweight depth-guided channel attention, and the Depth Prior Fusion Module (DPFM) enables hierarchical fusion of multi-scale depth map features by dual sliding-window multi-head cross-attention mechanism. These modules ensure both computational efficiency and effective integration of depth priors. Moreover, the intrinsic robustness of depth priors empowers the network to dynamically adapt to varying haze densities, illumination conditions, and domain gaps across synthetic and real-world data. Extensive experimental results demonstrate the effectiveness of our UDPNet, outperforming the state-of-the-art methods on popular dehazing datasets, such as 0.85 dB PSNR improvement on the SOTS dataset, 1.19 dB on the Haze4K dataset and 1.79 dB PSNR on the NHR dataset. Our proposed solution establishes a new benchmark for depth-aware dehazing across various scenarios. Pretrained models and codes will be released at our project https://github.com/Harbinzzy/UDPNet.
Authors: Shenghao Zhang, Runtao Liu, Christopher Schroers, Yang Zhang
Abstract: Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry buffers (G-buffers) to produce visually compelling results without explicit scene geometry or light simulation, they remain constrained by two major limitations. First, the iterative nature of the diffusion process introduces substantial latency. Second, the inherent stochasticity of these generative models compromises physical accuracy and temporal consistency. In response to these challenges, we propose a novel, end-to-end, deterministic, single-step neural rendering framework, RenderFlow, built upon a flow matching paradigm. To further strengthen both rendering quality and generalization, we propose an efficient and effective module for sparse keyframe guidance. Our method significantly accelerates the rendering process and, by optionally incorporating sparsely rendered keyframes as guidance, enhances both the physical plausibility and overall visual quality of the output. The resulting pipeline achieves near real-time performance with photorealistic rendering quality, effectively bridging the gap between the efficiency of modern generative models and the precision of traditional physically based rendering. Furthermore, we demonstrate the versatility of our framework by introducing a lightweight, adapter-based module that efficiently repurposes the pretrained forward model for the inverse rendering task of intrinsic decomposition.
Authors: Haodong Chen, Qiang Huang, Jiaqi Zhao, Qiuping Jiang, Xiaojun Chang, Jun Yu
Abstract: Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings, raising concerns about social bias driven by demographic cues. A central challenge in measuring such social bias is attribution under visual confounding: real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution. We propose a \textbf{face-only counterfactual evaluation paradigm} that isolates demographic effects while preserving real-image realism. Starting from real photographs, we generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed. Based on this paradigm, we construct \textbf{FOCUS}, a dataset of 480 scene-matched counterfactual images across six occupations and ten demographic groups, and propose \textbf{REFLECT}, a benchmark comprising three decision-oriented tasks: two-alternative forced choice, multiple-choice socioeconomic inference, and numeric salary recommendation. Experiments on five state-of-the-art VLMs reveal that demographic disparities persist under strict visual control and vary substantially across task formulations. These findings underscore the necessity of controlled, counterfactual audits and highlight task design as a critical factor in evaluating social bias in multimodal models.
Authors: Chengwen Liu, Xiaomin Yu, Zhuoyue Chang, Zhe Huang, Shuo Zhang, Heng Lian, Kunyi Wang, Rui Xu, Sen Hu, Jianheng Hou, Hao Peng, Chengwei Qin, Xiaobin Hu, Hong Peng, Ronghao Chen, Huacan Wang
Abstract: In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.
Authors: Yuhang Su, Mei Wang, Yaoyao Zhong, Guozhang Li, Shixing Li, Yihan Feng, Hua Huang
Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual understanding, they often struggle when faced with the unstructured and ambiguous nature of human-generated sketches. This limitation is particularly pronounced in the underexplored task of visual grading, where models should not only solve a problem but also diagnose errors in hand-drawn diagrams. Such diagnostic capabilities depend on complex structural, semantic, and metacognitive reasoning. To bridge this gap, we introduce SketchJudge, a novel benchmark tailored for evaluating MLLMs as graders of hand-drawn STEM diagrams. SketchJudge encompasses 1,015 hand-drawn student responses across four domains: geometry, physics, charts, and flowcharts, featuring diverse stylistic variations and distinct error types. Evaluations on SketchJudge demonstrate that even advanced MLLMs lag significantly behind humans, validating the benchmark's effectiveness in exposing the fragility of current vision-language alignment in symbolic and noisy contexts. All data, code, and evaluation scripts are publicly available at https://github.com/yuhangsu82/SketchJudge.
Authors: Yu Zhong, Tianwei Lin, Ruike Zhu, Yuqian Yuan, Haoyu Zheng, Liang Liang, Wenqiao Zhang, Feifei Shao, Haoyuan Li, Wanggui He, Hao Jiang, Yueting Zhuang
Abstract: Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-fits-all'' paradigm and struggle to model user-specific concepts (e.g., generate a photo of \texttt{
Authors: Jie Zhu, Yiyang Su, Xiaoming Liu
Abstract: Multi-modal large language models (MLLMs) exhibit strong general-purpose capabilities, yet still struggle on Fine-Grained Visual Classification (FGVC), a core perception task that requires subtle visual discrimination and is crucial for many real-world applications. A widely adopted strategy for boosting performance on challenging tasks such as math and coding is Chain-of-Thought (CoT) reasoning. However, several prior works have reported that CoT can actually harm performance on visual perception tasks. These studies, though, examine the issue from relatively narrow angles and leave open why CoT degrades perception-heavy performance. We systematically re-examine the role of CoT in FGVC through the lenses of zero-shot evaluation and multiple training paradigms. Across these settings, we uncover a central paradox: the degradation induced by CoT is largely driven by the reasoning length, in which longer textual reasoning consistently lowers classification accuracy. We term this phenomenon the ``Cost of Thinking''. Building on this finding, we make two key contributions: (1) \alg, a simple and general plug-and-play normalization method for multi-reward optimization that balances heterogeneous reward signals, and (2) ReFine-RFT, a framework that combines ensemble rewards with \alg to constrain reasoning length while providing dense accuracy-oriented feedback. Extensive experiments demonstrate the effectiveness of our findings and the proposed ReFine-RFT, achieving state-of-the-art performance across FGVC benchmarks. Code and models are available at \href{https://github.com/jiezhu23/ReFine-RFT}{Project Link}.
Authors: Sen Zeng, Hong Zhou, Zheng Zhu, Yang Liu
Abstract: Accurate molecular subtype classification is essential for personalized breast cancer treatment, yet conventional immunohistochemical analysis relies on invasive biopsies and is prone to sampling bias. Although dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) enables non-invasive tumor characterization, clinical workflows typically acquire only single-phase post-contrast images to reduce scan time and contrast agent dose. In this study, we propose a spatial multi-task learning framework for breast cancer molecular subtype prediction from clinically practical single-phase DCE-MRI. The framework simultaneously predicts estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2) status, and the Ki-67 proliferation index -- biomarkers that collectively define molecular subtypes. The architecture integrates a deep feature extraction network with multi-scale spatial attention to capture intratumoral and peritumoral characteristics, together with a region-of-interest weighting module that emphasizes the tumor core, rim, and surrounding tissue. Multi-task learning exploits biological correlations among biomarkers through shared representations with task-specific prediction branches. Experiments on a dataset of 960 cases (886 internal cases split 7:1:2 for training/validation/testing, and 74 external cases evaluated via five-fold cross-validation) demonstrate that the proposed method achieves an AUC of 0.893, 0.824, and 0.857 for ER, PR, and HER2 classification, respectively, and a mean absolute error of 8.2\% for Ki-67 regression, significantly outperforming radiomics and single-task deep learning baselines. These results indicate the feasibility of accurate, non-invasive molecular subtype prediction using standard imaging protocols.
Authors: Yunrui Gu, Zhenzhe Gao, Cong Kong, Zhaoxia Yin
Abstract: Medical hyperspectral imaging (HSI) enables accurate disease diagnosis by capturing rich spectral-spatial tissue information, but recent advances in deep learning have exposed its vulnerability to adversarial attacks. In this work, we identify two fundamental causes of this fragility: the reliance on local pixel dependencies for preserving tissue structure and the dependence on multiscale spectral-spatial representations for hierarchical feature encoding. Building on these insights, we propose a targeted adversarial attack framework for medical HSI, consisting of a Local Pixel Dependency Attack that exploits spatial correlations among neighboring pixels, and a Multiscale Information Attack that perturbs features across hierarchical spectral-spatial scales. Experiments on the Brain and MDC datasets demonstrate that our attacks significantly degrade classification performance, especially in tumor regions, while remaining visually imperceptible. Compared with existing methods, our approach reveals the unique vulnerabilities of medical HSI models and underscores the need for robust, structure-aware defenses in clinical applications.
Authors: Carlos Pizarroso, Zuzana Berger Haladov\'a, Zuzana \v{C}ernekov\'a, Viktor Kocur
Abstract: Roadside billboards represent a central element of outdoor advertising, yet their presence may contribute to driver distraction and accident risk. This study introduces a fully automated pipeline for billboard detection and driver gaze duration estimation, aiming to evaluate billboard relevance without reliance on manual annotations or eye-tracking devices. Our pipeline operates in two stages: (1) a YOLO-based object detection model trained on Mapillary Vistas and fine-tuned on BillboardLamac images achieved 94% mAP@50 in the billboard detection task (2) a classifier based on the detected bounding box positions and DINOv2 features. The proposed pipeline enables estimation of billboard driver gaze duration from individual frames. We show that our method is able to achieve 68.1% accuracy on BillboardLamac when considering individual frames. These results are further validated using images collected from Google Street View.
Authors: Yuliang Cai, Dongqiangzi Ye, Zitian Chen, Chongruo Wu
Abstract: Autonomous driving increasingly relies on Visual Question Answering (VQA) to enable vehicles to understand complex surroundings by analyzing visual inputs and textual queries. Currently, a paramount concern for VQA in this domain is the stringent requirement for fast latency and real-time processing, as delays directly impact real-world safety in this safety-critical application. However, current state-of-the-art VQA models, particularly large vision-language models (VLMs), often prioritize performance over computational efficiency. These models typically process dense patch tokens for every frame, leading to prohibitive computational costs (FLOPs) and significant inference latency, especially with long video sequences. This focus limits their practical deployment in real-time autonomous driving scenarios. To tackle this issue, we propose an efficient VLM framework for autonomous driving VQA tasks, SRC-Pipeline. It learns to compress early frame tokens into a small number of high-level tokens while retaining full patch tokens for recent frames. Experiments on autonomous driving video question answering tasks show that our approach achieves 66% FLOPs reduction while maintaining comparable performance, enabling VLMs to operate more effectively in real-time, safety-critical autonomous driving settings.
Authors: Peiyuan Jing, Yue Tang, Chun-Wun Cheng, Zhenxuan Zhang, Liutao Yang, Thiago V. Lima, Klaus Strobel, Antoine Leimgruber, Angelica Aviles-Rivero, Guang Yang, Javier Montoya
Abstract: Low-dose Positron Emission Tomography (PET) imaging reduces patient radiation exposure but suffers from increased noise that degrades image quality and diagnostic reliability. Although diffusion models have demonstrated strong denoising capability, their stochastic nature makes it challenging to enforce anatomically consistent structures, particularly in low signal-to-noise regimes and volumetric whole-body imaging. We propose Wavelet-Conditioned ControlNet (WCC-Net), a fully 3D diffusion-based framework that introduces explicit frequency-domain structural priors via wavelet representations to guide volumetric PET denoising. By injecting wavelet-based structural guidance into a frozen pretrained diffusion backbone through a lightweight control branch, WCC-Net decouples anatomical structure from noise while preserving generative expressiveness and 3D structural continuity. Extensive experiments demonstrate that WCC-Net consistently outperforms CNN-, GAN-, and diffusion-based baselines. On the internal 1/20-dose test set, WCC-Net improves PSNR by +1.21 dB and SSIM by +0.008 over a strong diffusion baseline, while reducing structural distortion (GMSD) and intensity error (NMAE). Moreover, WCC-Net generalizes robustly to unseen dose levels (1/50 and 1/4), achieving superior quantitative performance and improved volumetric anatomical consistency.
Authors: Meng Lu, Yuxing Lu, Yuchen Zhuang, Megan Mullins, Yang Xie, Guanghua Xiao, Charles Fleming, Wenqi Shi, Xuan Wang
Abstract: Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely on static visual embeddings and single-pass inference, preventing models from re-examining, verifying, or refining visual evidence during reasoning. While tool-integrated reasoning offers a promising path forward, open-source VLMs lack the training infrastructure to learn effective tool selection, invocation, and coordination in multi-modal medical reasoning. We introduce MedVistaGym, a scalable and interactive training environment that incentivizes tool-integrated visual reasoning for medical image analysis. MedVistaGym equips VLMs to determine when and which tools to invoke, localize task-relevant image regions, and integrate single or multiple sub-image evidence into interleaved multimodal reasoning within a unified, executable interface for agentic training. Using MedVistaGym, we train MedVistaGym-R1 to interleave tool use with agentic reasoning through trajectory sampling and end-to-end reinforcement learning. Across six medical VQA benchmarks, MedVistaGym-R1-8B exceeds comparably sized tool-augmented baselines by 19.10% to 24.21%, demonstrating that structured agentic training--not tool access alone--unlocks effective tool-integrated reasoning for medical image analysis.
Authors: Kexin Bao, Yong Li, Dan Zeng, Shiming Ge
Abstract: Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid catastrophic forgetting on old classes and overfitting to novel classes. This work proposes a generative co-memory regularization approach to facilitate FSCIL. In the approach, the base learning leverages generative domain adaptation finetuning to finetune a pretrained generative encoder on a few examples of base classes by jointly incorporating a masked autoencoder (MAE) decoder for feature reconstruction and a fully-connected classifier for feature classification, which enables the model to efficiently capture general and adaptable representations. Using the finetuned encoder and learned classifier, we construct two class-wise memories: representation memory for storing the mean features for each class, and weight memory for storing the classifier weights. After that, the memory-regularized incremental learning is performed to train the classifier dynamically on the examples of few-shot classes in each incremental session by simultaneously optimizing feature classification and co-memory regularization. The memories are updated in a class-incremental manner and they collaboratively regularize the incremental learning. In this way, the learned models improve recognition accuracy, while mitigating catastrophic forgetting over old classes and overfitting to novel classes. Extensive experiments on popular benchmarks clearly demonstrate that our approach outperforms the state-of-the-arts.
Authors: Daniel Hong, James Tribble, Hao Wang, Chaoyi Zhou, Ashish Bastola, Siyu Huang, Abolfazl Razi
Abstract: From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of motion analysis in sports and other fast-movement scenarios. To bridge this gap, we propose a real-time motion focus recognition method that estimates the subject's locomotion intention from any egocentric video. Our approach leverages the foundation model for camera pose estimation and introduces system-level optimizations to enable efficient and scalable inference. Evaluated on a collected egocentric action dataset, our method achieves real-time performance with manageable memory consumption through a sliding batch inference strategy. This work makes motion-centric analysis practical for edge deployment and offers a complementary perspective to existing egocentric studies on sports and fast-movement activities.
Authors: Shu Shen, C. L. Philip Chen, Tong Zhang
Abstract: Reliable learning on low-quality multimodal data is a widely concerning issue, especially in safety-critical applications. However, multimodal noise poses a major challenge in this domain and leads existing methods to suffer from two key limitations. First, they struggle to reliably remove heterogeneous data noise, hindering robust multimodal representation learning. Second, they exhibit limited adaptability and generalization when encountering previously unseen noise. To address these issues, we propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD). On one hand, TAHCD introduces the Adaptive Stable Subspace Alignment and Sample-Adaptive Confidence Alignment to reliably remove heterogeneous noise. They account for noise at both global and instance levels and enable jointly removal of modality-specific and cross-modality noise, achieving robust learning. On the other hand, TAHCD introduces test-time cooperative enhancement, which adaptively updates the model in response to input noise in a label-free manner, improving adaptability and generalization. This is achieved by collaboratively enhancing the joint removal process of modality-specific and cross-modality noise across global and instance levels according to sample noise. Experiments on multiple benchmarks demonstrate that the proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
Authors: Weilin Zhou, Zonghao Ying, Chunlei Meng, Jiahui Liu, Hengyang Zhou, Quanchen Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang
Abstract: Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this, we propose DIVER (Dynamic Iterative Visual Evidence Reasoning), a framework grounded in a progressive, evidence-driven reasoning paradigm. DIVER first establishes a strong text-based baseline through language analysis, leveraging intra-modal consistency to filter unreliable or hallucinated claims. Only when textual evidence is insufficient does the framework introduce visual information, where inter-modal alignment verification adaptively determines whether deeper visual inspection is necessary. For samples exhibiting significant cross-modal semantic discrepancies, DIVER selectively invokes fine-grained visual tools (e.g., OCR and dense captioning) to extract task-relevant evidence, which is iteratively aggregated via uncertainty-aware fusion to refine multimodal reasoning. Experiments on Weibo, Weibo21, and GossipCop demonstrate that DIVER outperforms state-of-the-art baselines by an average of 2.72\%, while optimizing inference efficiency with a reduced latency of 4.12 s.
Authors: Yichun Zhang, Xiangwu Guo, Yauhong Goh, Jessica Hu, Zhiheng Chen, Xin Wang, Difei Gao, Mike Zheng Shou
Abstract: Graphical User Interfaces (GUIs) are central to human-computer interaction, yet automating complex GUI tasks remains a major challenge for autonomous agents, largely due to a lack of scalable, high-quality training data. While recordings of human demonstrations offer a rich data source, they are typically long, unstructured, and lack annotations, making them difficult for agents to learn from.To address this, we introduce ShowUI-Aloha, a comprehensive pipeline that transforms unstructured, in-the-wild human screen recordings from desktop environments into structured, actionable tasks. Our framework includes four key components: A recorder that captures screen video along with precise user interactions like mouse clicks, keystrokes, and scrolls. A learner that semantically interprets these raw interactions and the surrounding visual context, translating them into descriptive natural language captions. A planner that reads the parsed demonstrations, maintains task states, and dynamically formulates the next high-level action plan based on contextual reasoning. An executor that faithfully carries out these action plans at the OS level, performing precise clicks, drags, text inputs, and window operations with safety checks and real-time feedback. Together, these components provide a scalable solution for collecting and parsing real-world human data, demonstrating a viable path toward building general-purpose GUI agents that can learn effectively from simply observing humans.
Authors: Yu Guo, Zhiqiang Lao, Xiyun Song, Yubin Zhou, Heather Yu
Abstract: Glass surfaces create complex interactions of reflected and transmitted light, making single-image reflection removal (SIRR) challenging. Existing datasets suffer from limited physical realism in synthetic data or insufficient scale in real captures. We introduce a synthetic dataset generation framework that path-traces 3D glass models over real background imagery to create physically accurate reflection scenarios with varied glass properties, camera settings, and post-processing effects. To leverage the capabilities of Large Multimodal Model (LMM), we concatenate the image layers into a single composite input, apply joint captioning, and fine-tune the model using task-specific LoRA rather than full-parameter training. This enables our approach to achieve improved reflection removal and separation performance compared to state-of-the-art methods.
Authors: Jeongjun Choi, Yeonsoo Park, H. Jin Kim
Abstract: We present SceneNAT, a single-stage masked non-autoregressive Transformer that synthesizes complete 3D indoor scenes from natural language instructions through only a few parallel decoding passes, offering improved performance and efficiency compared to prior state-of-the-art approaches. SceneNAT is trained via masked modeling over fully discretized representations of both semantic and spatial attributes. By applying a masking strategy at both the attribute level and the instance level, the model can better capture intra-object and inter-object structure. To boost relational reasoning, SceneNAT employs a dedicated triplet predictor for modeling the scene's layout and object relationships by mapping a set of learnable relation queries to a sparse set of symbolic triplets (subject, predicate, object). Extensive experiments on the 3D-FRONT dataset demonstrate that SceneNAT achieves superior performance compared to state-of-the-art autoregressive and diffusion baselines in both semantic compliance and spatial arrangement accuracy, while operating with substantially lower computational cost.
Authors: Thanh-Nhan Vo, Trong-Thuan Nguyen, Tam V. Nguyen, Minh-Triet Tran
Abstract: State-of-the-art text-based image editing models often struggle to balance background preservation with semantic consistency, frequently resulting either in the synthesis of entirely new images or in outputs that fail to realize the intended edits. In contrast, scene graph-based image editing addresses this limitation by providing a structured representation of semantic entities and their relations, thereby offering improved controllability. However, existing scene graph editing methods typically depend on model fine-tuning, which incurs high computational cost and limits scalability. To this end, we introduce VENUS (Visual Editing with Noise inversion Using Scene graphs), a training-free framework for scene graph-guided image editing. Specifically, VENUS employs a split prompt conditioning strategy that disentangles the target object of the edit from its background context, while simultaneously leveraging noise inversion to preserve fidelity in unedited regions. Moreover, our proposed approach integrates scene graphs extracted from multimodal large language models with diffusion backbones, without requiring any additional training. Empirically, VENUS substantially improves both background preservation and semantic alignment on PIE-Bench, increasing PSNR from 22.45 to 24.80, SSIM from 0.79 to 0.84, and reducing LPIPS from 0.100 to 0.070 relative to the state-of-the-art scene graph editing model (SGEdit). In addition, VENUS enhances semantic consistency as measured by CLIP similarity (24.97 vs. 24.19). On EditVal, VENUS achieves the highest fidelity with a 0.87 DINO score and, crucially, reduces per-image runtime from 6-10 minutes to only 20-30 seconds. Beyond scene graph-based editing, VENUS also surpasses strong text-based editing baselines such as LEDIT++ and P2P+DirInv, thereby demonstrating consistent improvements across both paradigms.
Authors: Jongwon Ryu, Joonhyung Park, Jaeho Han, Yeong-Seok Kim, Hye-rin Kim, Sunjae Yoon, Junyeong Kim
Abstract: Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations, while preserving unrelated structural and seman tic content. Existing methods struggle to maintain structural integrity and provide fine grained, attribute-specific control, especially when multiple domains are involved. We propose LACE (Language-grounded Attribute Controllable Translation), built on two compo nents: (1) a GLIP-Adapter that fuses global semantics with local structural features to pre serve consistency, and (2) a Multi-Domain Control Guidance mechanism that explicitly grounds the semantic delta between source and target prompts into per-attribute translation vec tors, aligning linguistic semantics with domain level visual changes. Together, these modules enable compositional multi-domain control with independent strength modulation for each attribute. Experiments on CelebA(Dialog) and BDD100K demonstrate that LACE achieves high visual fidelity, structural preservation, and interpretable domain-specific control, surpass ing prior baselines. This positions LACE as a cross-modal content generation framework bridging language semantics and controllable visual translation.
Authors: Li Zheng, Liangbin Xie, Jiantao Zhou, He YiMin
Abstract: Stable Diffusion (SD) often produces degraded outputs when the training dataset contains adversarial noise. Adversarial purification offers a promising solution by removing adversarial noise from contaminated data. However, existing purification methods are primarily designed for classification tasks and fail to address SD-specific adversarial strategies, such as attacks targeting the VAE encoder, UNet denoiser, or both. To address the gap in SD security, we propose Universal Diffusion Adversarial Purification (UDAP), a novel framework tailored for defending adversarial attacks targeting SD models. UDAP leverages the distinct reconstruction behaviors of clean and adversarial images during Denoising Diffusion Implicit Models (DDIM) inversion to optimize the purification process. By minimizing the DDIM metric loss, UDAP can effectively remove adversarial noise. Additionally, we introduce a dynamic epoch adjustment strategy that adapts optimization iterations based on reconstruction errors, significantly improving efficiency without sacrificing purification quality. Experiments demonstrate UDAP's robustness against diverse adversarial methods, including PID (VAE-targeted), Anti-DreamBooth (UNet-targeted), MIST (hybrid), and robustness-enhanced variants like Anti-Diffusion (Anti-DF) and MetaCloak. UDAP also generalizes well across SD versions and text prompts, showcasing its practical applicability in real-world scenarios.
Authors: Yusen Cheng, Qinfeng Zhu, Lei Fan
Abstract: Data-driven landslide susceptibility mapping (LSM) typically relies on landslide conditioning factors (LCFs), whose availability, heterogeneity, and preprocessing-related uncertainties can constrain mapping reliability. Recently, Google AlphaEarth (AE) embeddings, derived from multi-source geospatial observations, have emerged as a unified representation of Earth surface conditions. This study evaluated the potential of AE embeddings as alternative predictors for LSM. Two AE representations, including retained principal components and the full set of 64 embedding bands, were systematically compared with conventional LCFs across three study areas (Nantou County, Taiwan; Hong Kong; and part of Emilia-Romagna, Italy) using three deep learning models (CNN1D, CNN2D, and Vision Transformer). Performance was assessed using multiple evaluation metrics, ROC-AUC analysis, error statistics, and spatial pattern assessment. Results showed that AE-based models consistently outperformed LCFs across all regions and models, yielding higher F1-scores, AUC values, and more stable error distributions. Such improvement was most pronounced when using the full 64-band AE representation, with F1-score improvements of approximately 4% to 15% and AUC increased ranging from 0.04 to 0.11, depending on the study area and model. AE-based susceptibility maps also exhibited clearer spatial correspondence with observed landslide occurrences and enhanced sensitivity to localised landslide-prone conditions. Performance improvements were more evident in Nantou and Emilia than in Hong Kong, revealing that closer temporal alignment between AE embeddings and landslide inventories may lead to more effective LSM outcomes. These findings highlight the strong potential of AE embeddings as a standardised and information-rich alternative to conventional LCFs for LSM.
Authors: Siqi Liu, Maoyu Wang, Bo Dai, Cewu Lu
Abstract: Retargeting motion between characters with different skeleton structures is a fundamental challenge in computer animation. When source and target characters have vastly different bone arrangements, maintaining the original motion's semantics and quality becomes increasingly difficult. We present PALUM, a novel approach that learns common motion representations across diverse skeleton topologies by partitioning joints into semantic body parts and applying attention mechanisms to capture spatio-temporal relationships. Our method transfers motion to target skeletons by leveraging these skeleton-agnostic representations alongside target-specific structural information. To ensure robust learning and preserve motion fidelity, we introduce a cycle consistency mechanism that maintains semantic coherence throughout the retargeting process. Extensive experiments demonstrate superior performance in handling diverse skeletal structures while maintaining motion realism and semantic fidelity, even when generalizing to previously unseen skeleton-motion combinations. We will make our implementation publicly available to support future research.
Authors: Chen Min, Chengyang Li, Fanjie Kong, Qi Zhu, Dawei Zhao, Liang Xiao
Abstract: This paper presents GenDet, a novel framework that redefines object detection as an image generation task. In contrast to traditional approaches, GenDet adopts a pioneering approach by leveraging generative modeling: it conditions on the input image and directly generates bounding boxes with semantic annotations in the original image space. GenDet establishes a conditional generation architecture built upon the large-scale pre-trained Stable Diffusion model, formulating the detection task as semantic constraints within the latent space. It enables precise control over bounding box positions and category attributes, while preserving the flexibility of the generative model. This novel methodology effectively bridges the gap between generative models and discriminative tasks, providing a fresh perspective for constructing unified visual understanding systems. Systematic experiments demonstrate that GenDet achieves competitive accuracy compared to discriminative detectors, while retaining the flexibility characteristic of generative methods.
Authors: Yuanyang Yin, Yufan Deng, Shenghai Yuan, Kaipeng Zhang, Xiao Yang, Feng Zhao
Abstract: The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual constraints and low-frequency textual guidance during the denoising process. However, while existing I2V models prioritize visual consistency, how to effectively couple this dual guidance to ensure strong adherence to the text prompt remains underexplored. In this work, we observe that in Diffusion Transformer (DiT)-based I2V models, certain intermediate layers exhibit weak semantic responses (termed Semantic-Weak Layers), as indicated by a measurable drop in text-visual similarity. We attribute this to a phenomenon called Condition Isolation, where attention to visual features becomes partially detached from text guidance and overly relies on learned visual priors. To address this, we propose Focal Guidance (FG), which enhances the controllability from Semantic-Weak Layers. FG comprises two mechanisms: (1) Fine-grained Semantic Guidance (FSG) leverages CLIP to identify key regions in the reference frame and uses them as anchors to guide Semantic-Weak Layers. (2) Attention Cache transfers attention maps from semantically responsive layers to Semantic-Weak Layers, injecting explicit semantic signals and alleviating their over-reliance on the model's learned visual priors, thereby enhancing adherence to textual instructions. To further validate our approach and address the lack of evaluation in this direction, we introduce a benchmark for assessing instruction following in I2V models. On this benchmark, Focal Guidance proves its effectiveness and generalizability, raising the total score on Wan2.1-I2V to 0.7250 (+3.97\%) and boosting the MMDiT-based HunyuanVideo-I2V to 0.5571 (+7.44\%).
Authors: Jiapeng Shi, Junke Wang, Zuyao You, Bo He, Zuxuan Wu
Abstract: This paper presents VideoLoom, a unified Video Large Language Model (Video LLM) for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k, a human-centric video dataset with temporally grounded and spatially localized captions. With this, VideoLoom achieves state-of-the-art or highly competitive performance across a variety of spatial and temporal benchmarks (e.g., 63.1 J&F on ReVOS for referring video object segmentation, and 48.3 R1@0.7 on Charades-STA for temporal grounding). In addition, we introduce LoomBench, a novel benchmark consisting of temporal, spatial, and compositional video-question pairs, enabling a comprehensive evaluation of Video LLMs from diverse aspects. Collectively, these contributions offer a universal and effective suite for joint spatial-temporal video understanding, setting a new standard in multimodal intelligence.
Authors: Qi Zheng, Shuliang Liu, Yu Huang, Sihang Jia, Jungang Li, Lyuhao Chen, Junhao Chen, Hanqian Li, Aiwei Liu, Yibo Yan, Xuming Hu
Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic watermarks introduce visually irrelevant tokens and disrupt visual grounding by enforcing indiscriminate pseudo-random biases, while some semantic-aware methods incur prohibitive inference latency due to rejection sampling. In this paper, we propose the VIsual Semantic Adaptive Watermark (VISA-Mark), a novel framework that embeds detectable signals while strictly preserving visual fidelity. Our approach employs a lightweight, efficiently trained prefix-tuner to extract dynamic Visual-Evidence Weights, which quantify the evidentiary support for candidate tokens based on the visual input. These weights guide an adaptive vocabulary partitioning and logits perturbation mechanism, concentrating watermark strength specifically on visually-supported tokens. By actively aligning the watermark with visual evidence, VISA-Mark effectively maintains visual fidelity. Empirical results confirm that VISA-Mark outperforms conventional methods with a 7.8% improvement in visual consistency (Chair-I) and superior semantic fidelity. The framework maintains highly competitive detection accuracy (96.88% AUC) and robust attack resilience (99.3%) without sacrificing inference efficiency, effectively establishing a new standard for reliability-preserving multimodal watermarking.
Authors: Weidong Tang, Xinyan Wan, Siyu Li, Xiumei Wang
Abstract: While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive modeling (VAR) remains unexplored. We introduce VAR-Scaling, the first general framework for inference-time scaling in VAR, addressing the critical challenge of discrete latent spaces that prohibit continuous path search. We find that VAR scales exhibit two distinct pattern types: general patterns and specific patterns, where later-stage specific patterns conditionally optimize early-stage general patterns. To overcome the discrete latent space barrier in VQ models, we map sampling spaces to quasi-continuous feature spaces via kernel density estimation (KDE), where high-density samples approximate stable, high-quality solutions. This transformation enables effective navigation of sampling distributions. We propose a density-adaptive hybrid sampling strategy: Top-k sampling focuses on high-density regions to preserve quality near distribution modes, while Random-k sampling explores low-density areas to maintain diversity and prevent premature convergence. Consequently, VAR-Scaling optimizes sample fidelity at critical scales to enhance output quality. Experiments in class-conditional and text-to-image evaluations demonstrate significant improvements in inference process. The code is available at https://github.com/WD7ang/VAR-Scaling.
Authors: Jianghao Yin, Qingbin Li, Kun Sun, Cheng Ding, Jie Wang, Qin Chen, Jie Zhou, Nan Wang, Changqing Li, Pei Wu, Jian Xu, Zheming Yang, Liang He
Abstract: While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose the Cognition-Inspired Meta-Action Framework (CINEMA), a novel approach that decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer which explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 57k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.
Authors: Zhongming Liu, Bingbing Jiang
Abstract: Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into sequential and parallel paradigms, yet the selection process remains largely empirical, lacking systematic analysis and unified principles. We systematically compare channel-spatial attention combinations under a unified framework, building an evaluation suite of 18 topologies across four classes: sequential, parallel, multi-scale, and residual. Across two vision and nine medical datasets, we uncover a "data scale-method-performance" coupling law: (1) in few-shot tasks, the "Channel-Multi-scale Spatial" cascaded structure achieves optimal performance; (2) in medium-scale tasks, parallel learnable fusion architectures demonstrate superior results; (3) in large-scale tasks, parallel structures with dynamic gating yield the best performance. Additionally, experiments indicate that the "Spatial-Channel" order is more stable and effective for fine-grained classification, while residual connections mitigate vanishing gradient problems across varying data scales. We thus propose scenario-based guidelines for building future attention modules. Code is open-sourced at https://github.com/DWlzm.
Authors: Tessa Pulli, Jean-Baptiste Weibel, Peter H\"onig, Matthias Hirschmanner, Markus Vincze, Andreas Holzinger
Abstract: 6D object pose estimation plays a crucial role in scene understanding for applications such as robotics and augmented reality. To support the needs of ever-changing object sets in such context, modern zero-shot object pose estimators were developed to not require object-specific training but only rely on CAD models. Such models are hard to obtain once deployed, and a continuously changing and growing set of objects makes it harder to reliably identify the instance model of interest. To address this challenge, we introduce an Open-Set CAD Retrieval from a Language Prompt and a Single Image (OSCAR), a novel training-free method that retrieves a matching object model from an unlabeled 3D object database. During onboarding, OSCAR generates multi-view renderings of database models and annotates them with descriptive captions using an image captioning model. At inference, GroundedSAM detects the queried object in the input image, and multi-modal embeddings are computed for both the Region-of-Interest and the database captions. OSCAR employs a two-stage retrieval: text-based filtering using CLIP identifies candidate models, followed by image-based refinement using DINOv2 to select the most visually similar object. In our experiments we demonstrate that OSCAR outperforms all state-of-the-art methods on the cross-domain 3D model retrieval benchmark MI3DOR. Furthermore, we demonstrate OSCAR's direct applicability in automating object model sourcing for 6D object pose estimation. We propose using the most similar object model for pose estimation if the exact instance is not available and show that OSCAR achieves an average precision of 90.48\% during object retrieval on the YCB-V object dataset. Moreover, we demonstrate that the most similar object model can be utilized for pose estimation using Megapose achieving better results than a reconstruction-based approach.
Authors: Mohit Jaiswal, Naman Jain, Shivani Pathak, Mainak Singha, Nikunja Bihari Kar, Ankit Jha, Biplab Banerjee
Abstract: Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS.
Authors: Jiao Xu, Junwei Liu, Jiangwei Lao, Qi Zhu, Yunpeng Zhao, Congyun Jin, Shinan Liu, Zhihong Lu, Lihe Zhang, Xin Chen, Jian Wang, Ping Wang
Abstract: Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional com-parisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.
Authors: Shezheng Song, Shasha Li, Jie Yu
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a variety of vision-language tasks. However, their internal reasoning often exhibits a critical inconsistency: although deeper layers may attend to the correct visual regions, final predictions are frequently misled by noisy attention from earlier layers. This results in a disconnect between what the model internally understands and what it ultimately expresses, a phenomenon we describe as seeing it right but saying it wrong. To address this issue, we propose DualPD, a dual-perspective decoding refinement strategy that enhances the visual understanding without any additional training. DualPD consists of two components. (1) The layer-wise attention-guided contrastive logits module captures how the belief in the correct answer evolves by comparing output logits between layers that exhibit the largest attention shift. (2) The head-wise information filtering module suppresses low-contribution attention heads that focus on irrelevant regions, thereby improving attention quality within each layer. Experiments conducted on both the LLaVA and Qwen-VL model families across multiple multimodal benchmarks demonstrate that DualPD consistently improves accuracy without training, confirming its effectiveness and generalizability. The code will be released upon publication.
Authors: Haoxuan Li, Mengyan Li, Junjun Zheng
Abstract: Generating structured narrations for real-world e-commerce videos requires models to perceive fine-grained visual details and organize them into coherent, high-level stories--capabilities that existing approaches struggle to unify. We introduce the E-commerce Hierarchical Video Captioning (E-HVC) dataset with dual-granularity, temporally grounded annotations: a Temporal Chain-of-Thought that anchors event-level observations and Chapter Summary that compose them into concise, story-centric summaries. Rather than directly prompting chapters, we adopt a staged construction that first gathers reliable linguistic and visual evidence via curated ASR and frame-level descriptions, then refines coarse annotations into precise chapter boundaries and titles conditioned on the Temporal Chain-of-Thought, yielding fact-grounded, time-aligned narratives. We also observe that e-commerce videos are fast-paced and information-dense, with visual tokens dominating the input sequence. To enable efficient training while reducing input tokens, we propose the Scene-Primed ASR-anchored Compressor (SPA-Compressor), which compresses multimodal tokens into hierarchical scene and event representations guided by ASR semantic cues. Built upon these designs, our HiVid-Narrator framework achieves superior narrative quality with fewer input tokens compared to existing methods.
Authors: Jiao Xu, Xin Chen, Lihe Zhang
Abstract: In this paper, we present a new dynamic collaborative network for semi-supervised 3D vessel segmentation, termed DiCo. Conventional mean teacher (MT) methods typically employ a static approach, where the roles of the teacher and student models are fixed. However, due to the complexity of 3D vessel data, the teacher model may not always outperform the student model, leading to cognitive biases that can limit performance. To address this issue, we propose a dynamic collaborative network that allows the two models to dynamically switch their teacher-student roles. Additionally, we introduce a multi-view integration module to capture various perspectives of the inputs, mirroring the way doctors conduct medical analysis. We also incorporate adversarial supervision to constrain the shape of the segmented vessels in unlabeled data. In this process, the 3D volume is projected into 2D views to mitigate the impact of label inconsistencies. Experiments demonstrate that our DiCo method sets new state-of-the-art performance on three 3D vessel segmentation benchmarks. The code repository address is https://github.com/xujiaommcome/DiCo
Authors: Guantao Chen, Shikang Zheng, Yuqi Lin, Linfeng Zhang
Abstract: Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by reusing intermediate representations across timesteps. However, existing caching approaches treat all feature components uniformly. We reveal that DiT feature spaces contain distinct principal and residual subspaces with divergent temporal behavior: the principal subspace evolves smoothly and predictably, while the residual subspace exhibits volatile, low-energy oscillations that resist accurate prediction. Building on this insight, we propose SVD-Cache, a subspace-aware caching framework that decomposes diffusion features via Singular Value Decomposition (SVD), applies exponential moving average (EMA) prediction to the dominant low-rank components, and directly reuses the residual subspace. Extensive experiments demonstrate that SVD-Cache achieves near-lossless across diverse models and methods, including 5.55$\times$ speedup on FLUX and HunyuanVideo, and compatibility with model acceleration techniques including distillation, quantization and sparse attention. Our code is in supplementary material and will be released on Github.
Authors: Prachet Dev Singh, Shyamsundar Paramasivam, Sneha Barman, Mainak Singha, Ankit Jha, Girish Mishra, Biplab Banerjee
Abstract: Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.
Authors: Mahdi Chamseddine, Didier Stricker, Jason Rambach
Abstract: Existing image foundation models are not optimized for spherical images having been trained primarily on perspective images. PanoSAMic integrates the pre-trained Segment Anything (SAM) encoder to make use of its extensive training and integrate it into a semantic segmentation model for panoramic images using multiple modalities. We modify the SAM encoder to output multi-stage features and introduce a novel spatio-modal fusion module that allows the model to select the relevant modalities and best features from each modality for different areas of the input. Furthermore, our semantic decoder uses spherical attention and dual view fusion to overcome the distortions and edge discontinuity often associated with panoramic images. PanoSAMic achieves state-of-the-art (SotA) results on Stanford2D3DS for RGB, RGB-D, and RGB-D-N modalities and on Matterport3D for RGB and RGB-D modalities. https://github.com/dfki-av/PanoSAMic
Authors: Himanshu Patil, Geo Jolly, Ramana Raja Buddala, Ganesh Ramakrishnan, Rohit Saluja
Abstract: Video Question Answering (VideoQA) models enhance understanding and interaction with audiovisual content, making it more accessible, searchable, and useful for a wide range of fields such as education, surveillance, entertainment, and content creation. Due to heavy compute requirements, most large visual language models (VLMs) for VideoQA rely on a fixed number of frames by uniformly sampling the video. However, this process does not pick important frames or capture the context of the video. We present a novel query-based selection of frames relevant to the questions based on the submodular mutual Information (SMI) functions. By replacing uniform frame sampling with query-based selection, our method ensures that the chosen frames provide complementary and essential visual information for accurate VideoQA. We evaluate our approach on the MVBench dataset, which spans a diverse set of multi-action video tasks. VideoQA accuracy on this dataset was assessed using two VLMs, namely Video-LLaVA and LLaVA-NeXT, both of which originally employed uniform frame sampling. Experiments were conducted using both uniform and query-based sampling strategies. An accuracy improvement of up to \textbf{4\%} was observed when using query-based frame selection over uniform sampling. Qualitative analysis further highlights that query-based selection, using SMI functions, consistently picks frames better aligned with the question. We opine that such query-based frame selection can enhance accuracy in a wide range of tasks that rely on only a subset of video frames.
Authors: Shikang Zheng, Guantao Chen, Lixuan He, Jiacheng Liu, Yuqi Lin, Chang Zou, Linfeng Zhang
Abstract: Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution of early sampling steps. However, existing methods rely on heuristic re-noising at every resolution transition, injecting noise that breaks cross-stage consistency and forces the model to relearn global structure. In addition, these methods indiscriminately upsample the entire latent space at once without checking which regions have actually converged, causing accumulated errors, and visible artifacts. Therefore, we propose \textbf{Fresco}, a dynamic resolution framework that unifies re-noise and global structure across stages with progressive upsampling, preserving both the efficiency of low-resolution drafting and the fidelity of high-resolution refinement, with all stages aligned toward the same final target. Fresco achieves near-lossless acceleration across diverse domains and models, including 10$\times$ speedup on FLUX, and 5$\times$ on HunyuanVideo, while remaining orthogonal to distillation, quantization and feature caching, reaching 22$\times$ speedup when combined with distilled models. Our code is in supplementary material and will be released on Github.
Authors: Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Jiaen Liang, Wei Huang, Yining Wang, Junnan Zhu
Abstract: Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: \textbf{Positional Disparity}, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections. This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts. To address this, we propose \textbf{FocalOrder}, a framework driven by \textbf{Focal Preference Optimization (FPO)}. Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while introducing a difficulty-calibrated pairwise ranking objective to enforce global logical consistency. Extensive experiments demonstrate that FocalOrder establishes new state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc. Our compact model not only outperforms competitive specialized baselines but also significantly surpasses large-scale general VLMs. These results demonstrate that aligning the optimization with intrinsic structural ambiguity of documents is critical for mastering complex document structures.
Authors: Bing Yu, Liu Shi, Haitao Wang, Deran Qi, Xiang Cai, Wei Zhong, Qiegen Liu
Abstract: Accurate three-dimensional (3D) tooth segmentation from Cone-Beam Computed Tomography (CBCT) is a prerequisite for digital dental workflows. However, achieving high-fidelity segmentation remains challenging due to adhesion artifacts in naturally occluded scans, which are caused by low contrast and indistinct inter-arch boundaries. To address these limitations, we propose the Anatomy Aware Cascade Network (AACNet), a coarse-to-fine framework designed to resolve boundary ambiguity while maintaining global structural consistency. Specifically, we introduce two mechanisms: the Ambiguity Gated Boundary Refiner (AGBR) and the Signed Distance Map guided Anatomical Attention (SDMAA). The AGBR employs an entropy based gating mechanism to perform targeted feature rectification in high uncertainty transition zones. Meanwhile, the SDMAA integrates implicit geometric constraints via signed distance map to enforce topological consistency, preventing the loss of spatial details associated with standard pooling. Experimental results on a dataset of 125 CBCT volumes demonstrate that AACNet achieves a Dice Similarity Coefficient of 90.17 \% and a 95\% Hausdorff Distance of 3.63 mm, significantly outperforming state-of-the-art methods. Furthermore, the model exhibits strong generalization on an external dataset with an HD95 of 2.19 mm, validating its reliability for downstream clinical applications such as surgical planning. Code for AACNet is available at https://github.com/shiliu0114/AACNet.
Authors: Fangyu Lin, Yingdong Hu, Zhening Liu, Yufan Zhuang, Zehong Lin, Jun Zhang
Abstract: Immersive telepresence aims to transform human interaction in AR/VR applications by enabling lifelike full-body holographic representations for enhanced remote collaboration. However, existing systems rely on hardware-intensive multi-camera setups and demand high bandwidth for volumetric streaming, limiting their real-time performance on mobile devices. To overcome these challenges, we propose Mon3tr, a novel Monocular 3D telepresence framework that integrates 3D Gaussian splatting (3DGS) based parametric human modeling into telepresence for the first time. Mon3tr adopts an amortized computation strategy, dividing the process into a one-time offline multi-view reconstruction phase to build a user-specific avatar and a monocular online inference phase during live telepresence sessions. A single monocular RGB camera is used to capture body motions and facial expressions in real time to drive the 3DGS-based parametric human model, significantly reducing system complexity and cost. The extracted motion and appearance features are transmitted at < 0.2 Mbps over WebRTC's data channel, allowing robust adaptation to network fluctuations. On the receiver side, e.g., Meta Quest 3, we develop a lightweight 3DGS attribute deformation network to dynamically generate corrective 3DGS attribute adjustments on the pre-built avatar, synthesizing photorealistic motion and appearance at ~ 60 FPS. Extensive experiments demonstrate the state-of-the-art performance of our method, achieving a PSNR of > 28 dB for novel poses, an end-to-end latency of ~ 80 ms, and > 1000x bandwidth reduction compared to point-cloud streaming, while supporting real-time operation from monocular inputs across diverse scenarios. Our demos can be found at https://mon3tr3d.github.io.
Authors: Farhad G. Zanjani, Hong Cai, Amirhossein Habibian
Abstract: Autonomous driving systems rely heavily on multi-view images to ensure accurate perception and robust decision-making. To effectively develop and evaluate perception stacks and planning algorithms, realistic closed-loop simulators are indispensable. While 3D reconstruction techniques such as Gaussian Splatting offer promising avenues for simulator construction, the rendered novel views often exhibit artifacts, particularly in extrapolated perspectives or when available observations are sparse. We introduce ViewMorpher3D, a multi-view image enhancement framework based on image diffusion models, designed to elevate photorealism and multi-view coherence in driving scenes. Unlike single-view approaches, ViewMorpher3D jointly processes a set of rendered views conditioned on camera poses, 3D geometric priors, and temporally adjacent or spatially overlapping reference views. This enables the model to infer missing details, suppress rendering artifacts, and enforce cross-view consistency. Our framework accommodates variable numbers of cameras and flexible reference/target view configurations, making it adaptable to diverse sensor setups. Experiments on real-world driving datasets demonstrate substantial improvements in image quality metrics, effectively reducing artifacts while preserving geometric fidelity.
Authors: Ahmad AlMughrabi, Guillermo Rivo, Carlos Jim\'enez-Farf\'an, Umair Haroon, Farid Al-Areqi, Hyunjun Jung, Benjamin Busam, Ricardo Marques, Petia Radeva
Abstract: Food image segmentation is a critical task for dietary analysis, enabling accurate estimation of food volume and nutrients. However, current methods suffer from limited multi-view data and poor generalization to new viewpoints. We introduce BenchSeg, a novel multi-view food video segmentation dataset and benchmark. BenchSeg aggregates 55 dish scenes (from Nutrition5k, Vegetables & Fruits, MetaFood3D, and FoodKit) with 25,284 meticulously annotated frames, capturing each dish under free 360{\deg} camera motion. We evaluate a diverse set of 20 state-of-the-art segmentation models (e.g., SAM-based, transformer, CNN, and large multimodal) on the existing FoodSeg103 dataset and evaluate them (alone and combined with video-memory modules) on BenchSeg. Quantitative and qualitative results demonstrate that while standard image segmenters degrade sharply under novel viewpoints, memory-augmented methods maintain temporal consistency across frames. Our best model based on a combination of SeTR-MLA+XMem2 outperforms prior work (e.g., improving over FoodMem by ~2.63% mAP), offering new insights into food segmentation and tracking for dietary analysis. We release BenchSeg to foster future research. The project page including the dataset annotations and the food segmentation models can be found at https://amughrabi.github.io/benchseg.
Authors: Shruti Atul Mali (on behalf of EUCanImage working group), Zohaib Salahuddin (on behalf of EUCanImage working group), Yumeng Zhang (on behalf of EUCanImage working group), Andre Aichert (on behalf of EUCanImage working group), Xian Zhong (on behalf of EUCanImage working group), Henry C. Woodruff (on behalf of EUCanImage working group), Maciej Bobowicz (on behalf of EUCanImage working group), Katrine Riklund (on behalf of EUCanImage working group), Juozas Kup\v{c}inskas (on behalf of EUCanImage working group), Lorenzo Faggioni (on behalf of EUCanImage working group), Roberto Francischello (on behalf of EUCanImage working group), Razvan L Miclea (on behalf of EUCanImage working group), Philippe Lambin (on behalf of EUCanImage working group)
Abstract: Colorectal liver metastases (CRLM) are a major cause of cancer-related mortality, and reliable detection on CT remains challenging in multi-centre settings. We developed a foundation model-based AI pipeline for patient-level classification and lesion-level detection of CRLM on contrast-enhanced CT, integrating uncertainty quantification and explainability. CT data from the EuCanImage consortium (n=2437) and an external TCIA cohort (n=197) were used. Among several pretrained models, UMedPT achieved the best performance and was fine-tuned with an MLP head for classification and an FCOS-based head for lesion detection. The classification model achieved an AUC of 0.90 and a sensitivity of 0.82 on the combined test set, with a sensitivity of 0.85 on the external cohort. Excluding the most uncertain 20 percent of cases improved AUC to 0.91 and balanced accuracy to 0.86. Decision curve analysis showed clinical benefit for threshold probabilities between 0.30 and 0.40. The detection model identified 69.1 percent of lesions overall, increasing from 30 percent to 98 percent across lesion size quartiles. Grad-CAM highlighted lesion-corresponding regions in high-confidence cases. These results demonstrate that foundation model-based pipelines can support robust and interpretable CRLM detection and classification across heterogeneous CT data.
Authors: Lior Dvir, Nadav Torem, Yoav Y. Schechner
Abstract: We derive the likelihood of a raw signal in a single photon avalanche diode (SPAD), given a fixed photon flux. The raw signal comprises timing of detection events, which are nonlinearly related to the flux. Moreover, they are naturally stochastic. We then derive a score function of the signal. This is a key for solving inverse problems based on SPAD signals. We focus on deriving solutions involving a diffusion model, to express image priors. We demonstrate the effect of low or high photon counts, and the consequence of exploiting timing of detection events.
Authors: Zijian Wu, Boyao Zhou, Liangxiao Hu, Hongyu Liu, Yuan Sun, Xuan Wang, Xun Cao, Yujun Shen, Hao Zhu
Abstract: We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of unposed inputs, including a single image, multi-view captures, and smartphone-captured videos. Unlike the traditional avatar method, which requires a studio-level multi-view capture system and reconstructs a human-specific model through a long-time optimization process, we rethink the task through the lenses of model representation, network design, and data preparation. First, we introduce a UV-guided avatar modeling strategy, in which each input image is associated with a pixel-wise facial correspondence estimation. Such correspondence estimation allows us to reproject each valid pixel color from screen space to UV space, which is independent of camera pose and character expression. Furthermore, we design learnable UV tokens on which the attention mechanism can be applied at both the screen and UV levels. The learned UV tokens can be decoded into canonical Gaussian attributes using aggregated UV information from all input views. To train our large avatar model, we additionally prepare a large-scale, identity-rich synthetic training dataset. Our method significantly outperforms existing approaches in both monocular and multi-view settings. Project page: https://zijian-wu.github.io/uika-page/
Authors: Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Jiaen Liang, Wei Huang, Yining Wang, Junnan Zhu
Abstract: Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual features with extracted text. This dependency introduces two major drawbacks: propagation of text recognition errors and substantial computational overhead, limiting the robustness and practical applicability of multimodal approaches. In contrast to the prevailing multimodal trend, we argue that effective layout analysis depends not on text-visual fusion, but on a deep understanding of documents' intrinsic visual structure. To this end, we propose PARL (Position-Aware Relation Learning Network), a novel OCR-free, vision-only framework that models layout through positional sensitivity and relational structure. Specifically, we first introduce a Bidirectional Spatial Position-Guided Deformable Attention module to embed explicit positional dependencies among layout elements directly into visual features. Second, we design a Graph Refinement Classifier (GRC) to refine predictions by modeling contextual relationships through a dynamically constructed layout graph. Extensive experiments show PARL achieves state-of-the-art results. It establishes a new benchmark for vision-only methods on DocLayNet and, notably, surpasses even strong multimodal models on M6Doc. Crucially, PARL (65M) is highly efficient, using roughly four times fewer parameters than large multimodal models (256M), demonstrating that sophisticated visual structure modeling can be both more efficient and robust than multimodal fusion.
Authors: Zhankai Ye, Bofan Li, Yukai Jin, Shuoqiu Li, Wei Wang, Yanfu Zhang, Shangqian Gao, Xin Liu
Abstract: Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, existing pipelines typically decouple motion quantization from semantic embedding learning, linking them solely via token IDs. This approach fails to effectively align the intrinsic geometry of the motion space with the embedding space, thereby hindering the LLM's capacity for nuanced motion reasoning. We argue that alignment is most effective when both modalities share a unified geometric basis. Therefore, instead of forcing the LLM to reconstruct the complex geometry among motion tokens from scratch, we present a novel framework that explicitly enforces orthogonality on both the motion codebook and the LLM embedding space, ensuring that their relational structures naturally mirror each other. Specifically, we employ a decoder-only quantizer with Gumbel-Softmax for differentiable training and balanced codebook usage. To bridge the modalities, we use a sparse projection that maps motion codes into the LLM embedding space while preserving orthogonality. Finally, a two-stage orthonormal regularization schedule enforces soft constraints during tokenizer training and LLM fine-tuning to maintain geometric alignment without hindering semantic adaptation. Extensive experiments on HumanML3D demonstrate that our framework achieves a 20% performance improvement over current state-of-the-art methods, validating that a unified geometric basis effectively empowers the LLM for nuanced motion reasoning.
Authors: Yuze He, Yanning Zhou, Wang Zhao, Jingwen Ye, Zhongkai Wu, Ran Yi, Yong-Jin Liu
Abstract: We present StdGEN++, a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs. Existing 3D generative methods often produce monolithic meshes that lack the structural flexibility required by industrial pipelines in gaming and animation. Addressing this gap, StdGEN++ is built upon a Dual-branch Semantic-aware Large Reconstruction Model (Dual-Branch S-LRM), which jointly reconstructs geometry, color, and per-component semantics in a feed-forward manner. To achieve production-level fidelity, we introduce a novel semantic surface extraction formalism compatible with hybrid implicit fields. This mechanism is accelerated by a coarse-to-fine proposal scheme, which significantly reduces memory footprint and enables high-resolution mesh generation. Furthermore, we propose a video-diffusion-based texture decomposition module that disentangles appearance into editable layers (e.g., separated iris and skin), resolving semantic confusion in facial regions. Experiments demonstrate that StdGEN++ achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement. Crucially, the resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking, making it a robust solution for automated character asset production.
Authors: Dang Dinh Nguyen, Decky Aspandi Latif, Titus Zaharia
Abstract: In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often struggle to capture the variability and uncertainty intrinsic to human motion. To address this issue, we propose a variational contrastive learning framework that integrates probabilistic latent modeling with contrastive self-supervised learning. This formulation enables the learning of structured and semantically meaningful representations that generalize across different datasets and supervision levels. Extensive experiments on three widely used skeleton-based action recognition benchmarks show that our proposed method consistently outperforms existing approaches, particularly in low-label regimes. Moreover, qualitative analyses show that the features provided by our method are more relevant given the motion and sample characteristics, with more focus on important skeleton joints, when compared to the other methods.
Authors: Rayson Laroca, Valter Estevam, Gladston J. P. Moreira, Rodrigo Minetto, David Menotti
Abstract: Automatic License Plate Recognition is a frequent research topic due to its wide-ranging practical applications. While recent studies use synthetic images to improve License Plate Recognition (LPR) results, there remain several limitations in these efforts. This work addresses these constraints by comprehensively exploring the integration of real and synthetic data to enhance LPR performance. We subject 16 Optical Character Recognition (OCR) models to a benchmarking process involving 12 public datasets acquired from various regions. Several key findings emerge from our investigation. Primarily, the massive incorporation of synthetic data substantially boosts model performance in both intra- and cross-dataset scenarios. We examine three distinct methodologies for generating synthetic data: template-based generation, character permutation, and utilizing a Generative Adversarial Network (GAN) model, each contributing significantly to performance enhancement. The combined use of these methodologies demonstrates a notable synergistic effect, leading to end-to-end results that surpass those reached by state-of-the-art methods and established commercial systems. Our experiments also underscore the efficacy of synthetic data in mitigating challenges posed by limited training data, enabling remarkable results to be achieved even with small fractions of the original training data. Finally, we investigate the trade-off between accuracy and speed among different models, identifying those that strike the optimal balance in each intra-dataset and cross-dataset settings.
Authors: Nicolas Sereyjol-Garros, Ellington Kirby, Victor Besnier, Nermin Samet
Abstract: LiDAR scene synthesis is an emerging solution to scarcity in 3D data for robotic tasks such as autonomous driving. Recent approaches employ diffusion or flow matching models to generate realistic scenes, but 3D data remains limited compared to RGB datasets with millions of samples. We introduce R3DPA, the first LiDAR scene generation method to unlock image-pretrained priors for LiDAR point clouds, and leverage self-supervised 3D representations for state-of-the-art results. Specifically, we (i) align intermediate features of our generative model with self-supervised 3D features, which substantially improves generation quality; (ii) transfer knowledge from large-scale image-pretrained generative models to LiDAR generation, mitigating limited LiDAR datasets; and (iii) enable point cloud control at inference for object inpainting and scene mixing with solely an unconditional model. On the KITTI-360 benchmark R3DPA achieves state of the art performance. Code and pretrained models are available at https://github.com/valeoai/R3DPA.
Authors: Siwen Jiao, Tianxiong Lv, Kangan Qian, Chenxu Zhao, Xiuyuan Zhu, Tianlun Li, Xiaolong Cheng, Jinyu Li, Zhihao Liao, Yang Cai
Abstract: Vision-Language Models (VLMs) face a critical bottleneck in achieving precise numerical prediction for 3D scene understanding. Traditional reinforcement learning (RL) approaches, primarily based on relative ranking, often suffer from severe reward sparsity and gradient instability, failing to effectively exploit the verifiable signals provided by 3D physical constraints. Notably, in standard GRPO frameworks, relative normalization causes "near-miss" samples (characterized by small but non-zero errors) to suffer from advantage collapse. This leads to a severe data utilization bottleneck where valuable boundary samples are discarded during optimization. To address this, we introduce the Smooth Numerical Reward Activation (SNRA) operator and the Absolute-Preserving GRPO (AP-GRPO) framework. SNRA employs a dynamically parameterized Sigmoid function to transform raw feedback into a dense, continuous reward continuum. Concurrently, AP-GRPO integrates absolute scalar gradients to mitigate the numerical information loss inherent in conventional relative-ranking mechanisms. By leveraging this approach, we constructed Numerical3D-50k, a dataset comprising 50,000 verifiable 3D subtasks. Empirical results indicate that AP-GRPO achieves performance parity with large-scale supervised methods while maintaining higher data efficiency, effectively activating latent 3D reasoning in VLMs without requiring architectural modifications.
Authors: Jakob Paul Zimmermann, Georg Loho
Abstract: It has been demonstrated in various contexts that monotonicity leads to better explainability in neural networks. However, not every function can be well approximated by a monotone neural network. We demonstrate that monotonicity can still be used in two ways to boost explainability. First, we use an adaptation of the decomposition of a trained ReLU network into two monotone and convex parts, thereby overcoming numerical obstacles from an inherent blowup of the weights in this procedure. Our proposed saliency methods -- SplitCAM and SplitLRP -- improve on state of the art results on both VGG16 and Resnet18 networks on ImageNet-S across all Quantus saliency metric categories. Second, we exhibit that training a model as the difference between two monotone neural networks results in a system with strong self-explainability properties.
Authors: Guillaume J. Laurent, Patrick Sandoz
Abstract: This paper presents a method for carrying fair comparisons of the accuracy of pose estimation using fiducial markers. These comparisons rely on large sets of high-fidelity synthetic images enabling deep exploration of the 6 degrees of freedom. A low-discrepancy sampling of the space allows to check the correlations between each degree of freedom and the pose errors by plotting the 36 pairs of combinations. The images are rendered using a physically based ray tracing code that has been specifically developed to use the standard calibration coefficients of any camera directly. The software reproduces image distortions, defocus and diffraction blur. Furthermore, sub-pixel sampling is applied to sharp edges to enhance the fidelity of the rendered image. After introducing the rendering algorithm and its experimental validation, the paper proposes a method for evaluating the pose accuracy. This method is applied to well-known markers, revealing their strengths and weaknesses for pose estimation. The code is open source and available on GitHub.
Authors: Chen Ling, Nai Ding
Abstract: We propose UAIT (Uncommon-sense Action Image-Text) dataset, a new evaluation benchmark designed to test the semantic understanding ability of visual language models (VLMs) in uncommon-sense action scenes. Unlike previous datasets that focus on common visual scenes with statistical frequency advantages, UAIT challenges models with grammatically reasonable but semantically counter-common sense image-text pairs. Such tasks require models to go beyond superficial pattern recognition and demonstrate a deep understanding of agent-patient relationships and physical feasibility. To build UAIT, we designed a semi-automated process to synthesize high-quality uncommon-sense image-text samples using large language models, few-shot prompt engineering, and text-to-image generation. Each sample is accompanied by a carefully designed multiple-choice question to test the model's competence in fine-grained reasoning. We evaluate multiple state-of-the-art visual language models and compare them with models based on contrastive learning. Experiments show that all models perform significantly worse than humans in semantic judgment, especially in distinguishing grammatical correctness from semantic rationality. Further experiments show that even the lightweight model can improve its accuracy after fine-tuning, demonstrating the great potential of directional adaptation. This study not only reveals the key weaknesses of VLMs, but also provides diagnostic tools and research directions for the development of robust models with real visual semantic reasoning capabilities.
Authors: Agnieszka Kaliszewska, Monika Syga
Abstract: In this work we analyse a number of variants of the Wasserstein distance which allow to focus the classification on the prescribed parts (fragments) of classified 2D curves. These variants are based on the use of a number of discrete probability measures which reflect the importance of given fragments of curves. The performance of this approach is tested through a series of experiments related to the clustering analysis of 2D curves performed on data coming from the field of archaeology.
Authors: Yanxiang Huang, Guohua Gao, Zhaoyang Wei, Jianyuan Ni
Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches. To resolve this, we introduce the Chain of Evidence (CoE), a novel framework that architecturally decouples and co-optimizes perceptual grounding and reasoning efficiency. CoE incorporates two core innovations: (1) A lightweight Evidence Grounding Module (EGM) that acts as a query-guided filter, dynamically identifying and extracting a compact set of high-fidelity visual evidence; and (2) An Evidence-Anchoring Protocol optimized via Reinforcement Learning. Crucially, we design a composite reward mechanism that enforces process alignment, compelling the model to strictly reference identified temporal anchors during deduction, thereby mitigating hallucinations. To enable this, we construct CoE-Instruct, a large-scale dataset (164k samples) featuring a novel dual-annotation schema for separate perception and reasoning supervision. Extensive experiments on five benchmarks, including Video-MME, MVBench, and VSI-Bench, demonstrate that CoE-enhanced models establish a new state-of-the-art. They significantly outperform existing methods in accuracy, proving CoE to be a powerful and practical paradigm for reliable video understanding.
Authors: Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang, Ruibin Li, Yujing Sun, Shuaizheng Liu, Lei Zhang
Abstract: Recent works such as REPA have shown that guiding diffusion models with external semantic features (e.g., DINO) can significantly accelerate the training of diffusion transformers (DiTs). However, this requires the use of pretrained external networks, introducing additional dependencies and reducing flexibility. In this work, we argue that DiTs actually have the power to guide the training of themselves, and propose \textbf{Self-Transcendence}, a simple yet effective method that achieves fast convergence using internal feature supervision only. It is found that the slow convergence in DiT training primarily stems from the difficulty of representation learning in shallow layers. To address this, we initially train the DiT model by aligning its shallow features with the latent representations from the pretrained VAE for a short phase (e.g., 40 epochs), then apply classifier-free guidance to the intermediate features, enhancing their discriminative capability and semantic expressiveness. These enriched internal features, learned entirely within the model, are used as supervision signals to guide a new DiT training. Compared to existing self-contained methods, our approach brings a significant performance boost. It can even surpass REPA in terms of generation quality and convergence speed, but without the need for any external pretrained models. Our method is not only more flexible for different backbones but also has the potential to be adopted for a wider range of diffusion-based generative tasks. The source code of our method can be found at https://github.com/csslc/Self-Transcendence.
Authors: Patrick Bauer, Marius Schwinning, Florian Renk, Andreas Weinmann, Hichem Snoussi
Abstract: The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable crater detection, since craters pose a risk to safe lunar landings. This task is usually addressed with automated crater detection algorithms (CDA) based on deep learning techniques. It is non-trivial due to the vast amount of craters of various sizes and shapes, as well as challenging conditions such as varying illumination and rugged terrain. Therefore, we propose a deep-learning CDA based on the OWLv2 model, which is built on a Vision Transformer, that has proven highly effective in various computer vision tasks. For fine-tuning, we utilize a manually labeled dataset fom the IMPACT project, that provides crater annotations on high-resolution Lunar Reconnaissance Orbiter Camera Calibrated Data Record images. We insert trainable parameters using a parameter-efficient fine-tuning strategy with Low-Rank Adaptation, and optimize a combined loss function consisting of Complete Intersection over Union (CIoU) for localization and a contrastive loss for classification. We achieve satisfactory visual results, along with a maximum recall of 94.0% and a maximum precision of 73.1% on a test dataset from IMPACT. Our method achieves reliable crater detection across challenging lunar imaging conditions, paving the way for robust crater analysis in future lunar exploration.
Authors: Sijun Dong, Siming Fu, Kaiyu Li, Xiangyong Cao, Xiaoliang Meng, Bo Du
Abstract: Remote sensing change detection fundamentally relies on the effective fusion and discrimination of bi-temporal features. Prevailing paradigms typically utilize Siamese encoders bridged by explicit difference computation modules, such as subtraction or concatenation, to identify changes. In this work, we challenge this complexity with SEED (Siamese Encoder-Exchange-Decoder), a streamlined paradigm that replaces explicit differencing with parameter-free feature exchange. By sharing weights across both Siamese encoders and decoders, SEED effectively operates as a single parameter set model. Theoretically, we formalize feature exchange as an orthogonal permutation operator and prove that, under pixel consistency, this mechanism preserves mutual information and Bayes optimal risk, whereas common arithmetic fusion methods often introduce information loss. Extensive experiments across five benchmarks, including SYSU-CD, LEVIR-CD, PX-CLCD, WaterCD, and CDD, and three backbones, namely SwinT, EfficientNet, and ResNet, demonstrate that SEED matches or surpasses state of the art methods despite its simplicity. Furthermore, we reveal that standard semantic segmentation models can be transformed into competitive change detectors solely by inserting this exchange mechanism, referred to as SEG2CD. The proposed paradigm offers a robust, unified, and interpretable framework for change detection, demonstrating that simple feature exchange is sufficient for high performance information fusion. Code and full training and evaluation protocols will be released at https://github.com/dyzy41/open-rscd.
Authors: Anurag Das, Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas, Bernt Schiele, Georgios Tzimiropoulos, Brais Martinez
Abstract: Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored. While existing benchmarks have initiated the evaluation of multi-image models, a comprehensive analysis of their core weaknesses and their causes is still lacking. In this work, we introduce MIMIC (Multi-Image Model Insights and Challenges), a new benchmark designed to rigorously evaluate the multi-image capabilities of LVLMs. Using MIMIC, we conduct a series of diagnostic experiments that reveal pervasive issues: LVLMs often fail to aggregate information across images and struggle to track or attend to multiple concepts simultaneously. To address these failures, we propose two novel complementary remedies. On the data side, we present a procedural data-generation strategy that composes single-image annotations into rich, targeted multi-image training examples. On the optimization side, we analyze layer-wise attention patterns and derive an attention-masking scheme tailored for multi-image inputs. Experiments substantially improved cross-image aggregation, while also enhancing performance on existing multi-image benchmarks, outperforming prior state of the art across tasks. Data and code will be made available at https://github.com/anurag-198/MIMIC.
Authors: Kewei Zhang, Ye Huang, Yufan Deng, Jincheng Yu, Junsong Chen, Huan Ling, Enze Xie, Daquan Zhou
Abstract: While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades performance, with existing fixes typically re-introducing computational overhead through extra modules (e.g., depthwise separable convolution) that defeat the original purpose. In this work, we identify a key failure mode in these methods: global context collapse, where the model loses representational diversity. To address this, we propose Multi-Head Linear Attention (MHLA), which preserves this diversity by computing attention within divided heads along the token dimension. We prove that MHLA maintains linear complexity while recovering much of the expressive power of softmax attention, and verify its effectiveness across multiple domains, achieving a 3.6\% improvement on ImageNet classification, a 6.3\% gain on NLP, a 12.6\% improvement on image generation, and a 41\% enhancement on video generation under the same time complexity.
Authors: Maxwell Jones, Rameen Abdal, Or Patashnik, Ruslan Salakhutdinov, Sergey Tulyakov, Jun-Yan Zhu, Kuan-Chieh Jackson Wang
Abstract: We present RefVFX, a new framework that transfers complex temporal effects from a reference video onto a target video or image in a feed-forward manner. While existing methods excel at prompt-based or keyframe-conditioned editing, they struggle with dynamic temporal effects such as dynamic lighting changes or character transformations, which are difficult to describe via text or static conditions. Transferring a video effect is challenging, as the model must integrate the new temporal dynamics with the input video's existing motion and appearance. % To address this, we introduce a large-scale dataset of triplets, where each triplet consists of a reference effect video, an input image or video, and a corresponding output video depicting the transferred effect. Creating this data is non-trivial, especially the video-to-video effect triplets, which do not exist naturally. To generate these, we propose a scalable automated pipeline that creates high-quality paired videos designed to preserve the input's motion and structure while transforming it based on some fixed, repeatable effect. We then augment this data with image-to-video effects derived from LoRA adapters and code-based temporal effects generated through programmatic composition. Building on our new dataset, we train our reference-conditioned model using recent text-to-video backbones. Experimental results demonstrate that RefVFX produces visually consistent and temporally coherent edits, generalizes across unseen effect categories, and outperforms prompt-only baselines in both quantitative metrics and human preference. See our website $\href{https://tuningfreevisualeffects-maker.github.io/Tuning-free-Visual-Effect-Transfer-across-Videos-Project-Page/}{at\ this\ URL}$.
Authors: Aizierjiang Aiersilan, Ruting Cheng, James Hahn
Abstract: The recent release of SAM 3D Body \cite{sam3dbody2025} marks a significant milestone in human mesh recovery, demonstrating state-of-the-art performance in producing clean, topologically coherent meshes from single images. By leveraging the novel Momentum Human Rig (MHR), it achieves remarkable robustness to occlusion and diverse poses. However, our evaluation reveals a specific and consistent limitation: the model struggles to reconstruct detailed anthropometric deviations, especially on populations with special body shape alters such as geriatric muscle atrophy, scoliosis, or pregnancy, even when these features are prominent in the input image. In this paper, we investigate this phenomenon not as a failure of the model's capacity, but as a byproduct of the \textit{perception-distortion trade-off}. We posit that the architectural reliance on the low-dimensional parametric MHR representation, combined with semantic-invariant conditioning (DINOv3) and annotation-based alignment, creates a \enquote{regression to the mean} effect. We analyze these mechanisms to understand why individual biological details are smoothed out and propose specific, constructive pathways for future work to extend the impressive baseline performance of SAM 3D Body into the medical domain.
Authors: Chunliang Chen, Ming Guan, Xiao Lin, Jiaxu Li, Qiyi Wang, Xiangyu Chen, Jixiang Luo, Changzhi Sun, Dell Zhang, Xuelong Li
Abstract: Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable mechanisms for updating or refining stored memories, leading to schema-driven hallucinations, inefficient write operations, and minimal support for multimodal reasoning.To address these challenges, we propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction, ensuring that only dialogue-grounded information is preserved. TeleMem further introduces a structured writing pipeline that batches, retrieves, clusters, and consolidates memory entries, substantially improving storage efficiency, reducing token usage, and accelerating memory operations. Additionally, a multimodal memory module combined with ReAct-style reasoning equips the system with a closed-loop observe, think, and act process that enables accurate understanding of complex video content in long-term contexts. Experimental results show that TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark.
Authors: Tim Johansson, Mikael Mangold, Kristina Dabrock, Anna Donarelli, Ingrid Campo-Ruiz
Abstract: During 2025 and 2026, the Energy Performance of Buildings Directive is being implemented in the European Union member states, requiring all member states to have National Building Renovation Plans. In Sweden, there is a lack of a national register of buildings with heritage values. This is seen as a barrier for the analyses underlying the development of Building Renovation Plans by the involved Swedish authorities. The purpose of this research was to assist Swedish authorities in assigning heritage values to building in the Swedish building stock. As part of the analyses, buildings in street view images from all over Sweden (N=154 710) have been analysed using multimodal Large Language Models (LLM) to assess aspects of heritage value. Zero-shot predictions by LLMs were used as a basis to for identifying buildings with potential heritage values for 5.0 million square meters of heated floor area for the Swedish Building Renovation Plan. In this paper, the results of the predictions and lessons learnt are presented and related to the development of Swedish Building Renovation Plan as part of governance. Potential risks for authorities using LLM-based data are addressed, with a focus on issues of transparency, error detection and sycophancy.
Authors: Min-Han Shih, Yu-Hsin Wu, Yu-Wei Chen
Abstract: We propose a dedicated multimodal Judge Model designed to provide reliable, explainable evaluation across a diverse suite of tasks. Our benchmark spans text, audio, image, and video modalities, drawing from carefully sampled public datasets with fixed seeds to ensure reproducibility and minimize train test leakage. Instead of simple scoring, our framework aggregates multimodal judgments, analyzes the quality and reasoning consistency of model outputs, and generates diagnostic feedback. We evaluate several MLLMs, including Gemini 2.5, Phi 4, and Qwen 2.5, across 280 multimodal samples and compare judge model assessments with human annotators. Results show strong alignment between the Judge Model and human scores, demonstrating its potential as a scalable, interpretable evaluation pipeline for future multimodal AI research.
Authors: Zhaowen Fan
Abstract: This work introduces Adaptive Density Fields (ADF), a geometric attention framework that formulates spatial aggregation as a query-conditioned, metric-induced attention operator in continuous space. By reinterpreting spatial influence as geometry-preserving attention grounded in physical distance, ADF bridges concepts from adaptive kernel methods and attention mechanisms. Scalability is achieved via FAISS-accelerated inverted file indices, treating approximate nearest-neighbor search as an intrinsic component of the attention mechanism. We demonstrate the framework through a case study on aircraft trajectory analysis in the Chengdu region, extracting trajectory-conditioned Zones of Influence (ZOI) to reveal recurrent airspace structures and localized deviations.
Authors: Kaiyuan Deng, Gen Li, Yang Xiao, Bo Hui, Xiaolong Ma
Abstract: Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight updates that hinder unlearning or degrade generation; (ii) imprecise mechanisms that cause collateral damage to similar content; and (iii) reliance on additional data or modules, creating scalability bottlenecks. To address these, we propose Scalable-Precise Concept Unlearning (ScaPre), a unified framework tailored for large-scale unlearning. ScaPre introduces a conflict-aware stable design, integrating spectral trace regularization and geometry alignment to stabilize optimization, suppress conflicts, and preserve global structure. Furthermore, an Informax Decoupler identifies concept-relevant parameters and adaptively reweights updates, strictly confining unlearning to the target subspace. ScaPre yields an efficient closed-form solution without requiring auxiliary data or sub-models. Comprehensive experiments on objects, styles, and explicit content demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It forgets up to $\times \mathbf{5}$ more concepts than the best baseline within acceptable quality limits, achieving state-of-the-art precision and efficiency for large-scale unlearning.
Authors: Xuechen Chen, Junting Li, Chuang Chen, Hairong Lin, Yishen Li
Abstract: In this paper, we propose a high-efficiency deep joint source-channel coding (JSCC) method for video transmission based on conditional coding with asymmetric context. The conditional coding-based neural video compression requires to predict the encoding and decoding conditions from the same context which includes the same reconstructed frames. However in JSCC schemes which fall into pseudo-analog transmission, the encoder cannot infer the same reconstructed frames as the decoder even a pipeline of the simulated transmission is constructed at the encoder. In the proposed method, without such a pipeline, we guide and design neural networks to learn encoding and decoding conditions from asymmetric contexts. Additionally, we introduce feature propagation, which allows intermediate features to be independently propagated at the encoder and decoder and help to generate conditions, enabling the framework to greatly leverage temporal correlation while mitigating the problem of error accumulation. To further exploit the performance of the proposed transmission framework, we implement content-adaptive coding which achieves variable bandwidth transmission using entropy models and masking mechanisms. Experimental results demonstrate that our method outperforms existing deep video transmission frameworks in terms of performance and effectively mitigates the error accumulation. By mitigating the error accumulation, our schemes can reduce the frequency of inserting intra-frame coding modes, further enhancing performance.
Authors: Anh-Kiet Duong, Petra Gomez-Kr\"amer, Ho\`ang-\^An L\^e, Minh-Tan Pham
Abstract: Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak sensitive information through their outputs, motivating the need for rigorous privacy evaluation. In this paper, we leverage membership inference attacks (MIA) as a quantitative privacy measurement framework for FL applied to remote sensing image classification. We evaluate multiple black-box MIA techniques, including entropy-based attacks, modified entropy attacks, and the likelihood ratio attack, across different FL algorithms and communication strategies. Experiments conducted on two public scene classification datasets demonstrate that MIA effectively reveals privacy leakage not captured by accuracy alone. Our results show that communication-efficient FL strategies reduce MIA success rates while maintaining competitive performance. These findings confirm MIA as a practical metric and highlight the importance of integrating privacy measurement into FL system design for remote sensing applications.
Authors: Soundes Oumaima Boufaida, Abdemadjid Benmachiche, Majda Maatallah
Abstract: Embedded vision systems need efficient and robust image processing algorithms to perform real-time, with resource-constrained hardware. This research investigates image processing algorithms, specifically edge detection, corner detection, and blob detection, that are implemented on embedded processors, including DSPs and FPGAs. To address latency, accuracy and power consumption noted in the image processing literature, optimized algorithm architectures and quantization techniques are employed. In addition, optimal techniques for inter-frame redundancy removal and adaptive frame averaging are used to improve throughput with reasonable image quality. Simulations and hardware trials of the proposed approaches show marked improvements in the speed and energy efficiency of processing as compared to conventional implementations. The advances of this research facilitate a path for scalable and inexpensive embedded imaging systems for the automotive, surveillance, and robotics sectors, and underscore the benefit of co-designing algorithms and hardware architectures for practical real-time embedded vision applications.
Authors: Sobhana Jahan, Saydul Akbar Murad, Nick Rahimi, Noorbakhsh Amiri Golilarz
Abstract: Deep cognitive attention is characterized by heightened gamma oscillations and coordinated visual behavior. Despite the physiological importance of these mechanisms, computational studies rarely synthesize these modalities or identify the neural regions most responsible for sustained focus. To address this gap, this work introduces Gamma2Patterns, a multimodal framework that characterizes deep cognitive attention by leveraging complementary Gamma and Alpha band EEG activity alongside Eye-tracking measurements. Using the SEED-IV dataset [1], we extract spectral power, burst-based temporal dynamics, and fixation-saccade-pupil signals across 62 channels or electrodes to analyze how neural activation differs between high-focus (Gamma-dominant) and low-focus (Alpha-dominant) states. Our findings reveal that frontopolar, temporal, anterior frontal, and parieto-occipital regions exhibit the strongest Gamma power and burst rates, indicating their dominant role in deep attentional engagement, while Eye-tracking signals confirm complementary contributions from frontal, frontopolar, and frontotemporal regions. Furthermore, we show that Gamma power and burst duration provide more discriminative markers of deep focus than Alpha power alone, demonstrating their value for attention decoding. Collectively, these results establish a multimodal, evidence-based map of cortical regions and oscillatory signatures underlying deep focus, providing a neurophysiological foundation for future brain-inspired attention mechanisms in AI systems.
Authors: Yashika Ahlawat
Abstract: Block based image compression relies on transform coding to concentrate signal energy into a small number of coefficients. While classical codecs use fixed transforms such as the Discrete Cosine Transform (DCT), data driven methods such as Principal Component Analysis (PCA) are theoretically optimal for decorrelation. This paper presents an experimental comparison of DCT, Hadamard, and PCA across multiple block sizes and compression rates. Using rate distortion and energy compaction analysis, we show that PCA outperforms fixed transforms only when block dimensionality is sufficiently large, while DCT remains near optimal for standard block sizes such as $8\times8$ and at low bit rates. These results explain the robustness of DCT in practical codecs and highlight the limitations of block wise learned transforms.
Authors: Binxu Wang, Jingxuan Fan, Xu Pan
Abstract: Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic interpretability approach to investigate how a DiT can generate correct spatial relations between objects. We train, from scratch, DiTs of different sizes with different text encoders to learn to generate images containing two objects whose attributes and spatial relations are specified in the text prompt. We find that, although all the models can learn this task to near-perfect accuracy, the underlying mechanisms differ drastically depending on the choice of text encoder. When using random text embeddings, we find that the spatial-relation information is passed to image tokens through a two-stage circuit, involving two cross-attention heads that separately read the spatial relation and single-object attributes in the text prompt. When using a pretrained text encoder (T5), we find that the DiT uses a different circuit that leverages information fusion in the text tokens, reading spatial-relation and single-object information together from a single text token. We further show that, although the in-domain performance is similar for the two settings, their robustness to out-of-domain perturbations differs, potentially suggesting the difficulty of generating correct relations in real-world scenarios.
Authors: Nusrat Jahan Prottasha, Md Kowsher, Chun-Nam Yu, Chen Chen, Ozlem Garibay
Abstract: Mixture-of-experts variants of parameter-efficient fine-tuning enable per-token specialization, but they introduce additional trainable routers and expert parameters, increasing memory usage and training cost. This undermines the core goal of parameter-efficient fine-tuning. We propose Monkey Jump, a method that brings mixture-of-experts-style specialization to parameter-efficient fine-tuning without introducing extra trainable parameters for experts or routers. Instead of adding new adapters as experts, Monkey Jump treats the adapters already present in each Transformer block (such as query, key, value, up, and down projections) as implicit experts and routes tokens among them. Routing is performed using k-means clustering with exponentially moving averaged cluster centers, requiring no gradients and no learned parameters. We theoretically show that token-wise routing increases expressivity and can outperform shared adapters by avoiding cancellation effects. Across multi-task experiments covering 14 text, 14 image, and 19 video benchmarks, Monkey Jump achieves competitive performance with mixture-of-experts-based parameter-efficient fine-tuning methods while using 7 to 29 times fewer trainable parameters, up to 48 percent lower memory consumption, and 1.5 to 2 times faster training. Monkey Jump is architecture-agnostic and can be applied to any adapter-based parameter-efficient fine-tuning method.
Authors: Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
Abstract: To improve the quality of Differentially private (DP) synthetic images, most studies have focused on improving the core optimization techniques (e.g., DP-SGD). Recently, we have witnessed a paradigm shift that takes these techniques off the shelf and studies how to use them together to achieve the best results. One notable work is DP-FETA, which proposes using `central images' for `warming up' the DP training and then using traditional DP-SGD. Inspired by DP-FETA, we are curious whether there are other such tools we can use together with DP-SGD. We first observe that using `central images' mainly works for datasets where there are many samples that look similar. To handle scenarios where images could vary significantly, we propose FETA-Pro, which introduces frequency features as `training shortcuts.' The complexity of frequency features lies between that of spatial features (captured by `central images') and full images, allowing for a finer-grained curriculum for DP training. To incorporate these two types of shortcuts together, one challenge is to handle the training discrepancy between spatial and frequency features. To address it, we leverage the pipeline generation property of generative models (instead of having one model trained with multiple features/objectives, we can have multiple models working on different features, then feed the generated results from one model into another) and use a more flexible design. Specifically, FETA-Pro introduces an auxiliary generator to produce images aligned with noisy frequency features. Then, another model is trained with these images, together with spatial features and DP-SGD. Evaluated across five sensitive image datasets, FETA-Pro shows an average of 25.7% higher fidelity and 4.1% greater utility than the best-performing baseline, under a privacy budget $\epsilon = 1$.
Authors: Nathan Pascal Walus, Ranulfo Bezerra, Shotaro Kojima, Tsige Tadesse Alemayoh, Satoshi Tadokoro, Kazunori Ohno
Abstract: Utilizing functional elements in an industrial environment, such as displays and interactive valves, provide effective possibilities for robot training. When preparing simulations for robots or applications that involve high-level scene understanding, the simulation environment must be equally detailed. Although CAD files for such environments deliver an exact description of the geometry and visuals, they usually lack semantic, relational and functional information, thus limiting the simulation and training possibilities. A 3D scene graph can organize semantic, spatial and functional information by enriching the environment through a Large Vision-Language Model (LVLM). In this paper we present an offline approach to creating detailed 3D scene graphs from CAD environments. This will serve as a foundation to include the relations of functional and actionable elements, which then can be used for dynamic simulation and reasoning. Key results of this research include both quantitative results of the generated semantic labels as well as qualitative results of the scene graph, especially in hindsight of pipe structures and identified functional relations. All code, results and the environment will be made available at https://cad-scenegraph.github.io
Authors: Hyunseo Koh, Chang-Yong Song, Youngjae Choi, Misa Viveiros, David Hyde, Heewon Kim
Abstract: Food cutting is a highly practical yet underexplored application at the intersection of vision and robotic manipulation. The task remains challenging because interactions between the knife and deformable materials are highly nonlinear and often entail large deformations, frequent contact, and topological change, which in turn hinder stable and safe large-scale data collection. To address these challenges, we propose a unified framework that couples a vision-language-action (VLA) dataset with a physically realistic cutting simulator built on the material point method (MPM). Our simulator adopts MLS-MPM as its computational core, reducing numerical dissipation and energy drift while preserving rotational and shear responses even under topology-changing cuts. During cutting, forces and stress distributions are estimated from impulse exchanges between particles and the grid, enabling stable tracking of transient contact forces and energy transfer. We also provide a benchmark dataset that integrates diverse cutting trajectories, multi-view visual observations, and fine-grained language instructions, together with force--torque and tool--pose labels to provide physically consistent training signals. These components realize a learning--evaluation loop that respects the core physics of cutting and establishes a safe, reproducible, and scalable foundation for advancing VLA models in deformable object manipulation.
Authors: Sayak Chakrabarty, Souradip Pal
Abstract: Large Language Models (LLMs) have recently shown strong potential for usage in sequential recommendation tasks through text-only models, which combine advanced prompt design, contrastive alignment, and fine-tuning on downstream domain-specific data. While effective, these approaches overlook the rich visual information present in many real-world recommendation scenarios, particularly in e-commerce. This paper proposes PixRec - a vision-language framework that incorporates both textual attributes and product images into the recommendation pipeline. Our architecture leverages a vision-language model backbone capable of jointly processing image-text sequences, maintaining a dual-tower structure and mixed training objective while aligning multi-modal feature projections for both item-item and user-item interactions. Using the Amazon Reviews dataset augmented with product images, our experiments demonstrate $3\times$ and 40% improvements in top-rank and top-10 rank accuracy over text-only recommenders respectively, indicating that visual features can help distinguish items with similar textual descriptions. Our work outlines future directions for scaling multi-modal recommenders training, enhancing visual-text feature fusion, and evaluating inference-time performance. This work takes a step toward building software systems utilizing visual information in sequential recommendation for real-world applications like e-commerce.
Authors: Minfeng Qi, Dongyang He, Qin Wang, Lefeng Zhang
Abstract: Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are increasingly deployed as a primary defense against automated bots. Existing solvers fall into two paradigms: vision-centric, which rely on template-specific detectors but fail on novel layouts, and reasoning-centric, which leverage LLMs but struggle with fine-grained visual perception. Both lack the generality needed to handle heterogeneous VRC deployments. We present ViPer, a unified attack framework that integrates structured multi-object visual perception with adaptive LLM-based reasoning. ViPer parses visual layouts, grounds attributes to question semantics, and infers target coordinates within a modular pipeline. Evaluated on six major VRC providers (VTT, Geetest, NetEase, Dingxiang, Shumei, Xiaodun), ViPer achieves up to 93.2% success, approaching human-level performance across multiple benchmarks. Compared to prior solvers, GraphNet (83.2%), Oedipus (65.8%), and the Holistic approach (89.5%), ViPer consistently outperforms all baselines. The framework further maintains robustness across alternative LLM backbones (GPT, Grok, DeepSeek, Kimi), sustaining accuracy above 90%. To anticipate defense, we further introduce Template-Space Randomization (TSR), a lightweight strategy that perturbs linguistic templates without altering task semantics. TSR measurably reduces solver (i.e., attacker) performance. Our proposed design suggests directions for human-solvable but machine-resistant CAPTCHAs.
Authors: Hao Li, Xinqi Liu, Yaoqing Jin
Abstract: Millimeter-wave radar enables robust environment perception in autonomous systems under adverse conditions yet suffers from sparse, noisy point clouds with low angular resolution. Existing diffusion-based radar enhancement methods either incur high learning complexity by modeling full LiDAR distributions or fail to prioritize critical structures due to uniform regional processing. To address these issues, we propose R3D, a regional-guided residual radar diffusion framework that integrates residual diffusion modeling-focusing on the concentrated LiDAR-radar residual encoding complementary high-frequency details to reduce learning difficulty-and sigma-adaptive regional guidance-leveraging radar-specific signal properties to generate attention maps and applying lightweight guidance only in low-noise stages to avoid gradient imbalance while refining key regions. Extensive experiments on the ColoRadar dataset demonstrate that R3D outperforms state-of-the-art methods, providing a practical solution for radar perception enhancement. Our anonymous code and pretrained models are released here: https://anonymous.4open.science/r/r3d-F836
Authors: Andrei A. Korigodskii, Artem E. Vasiunik, Georgii A. Varin, Adilia M. Zukhurova, Matvei V. Urvantsev, Semen A. Osipenkov, Igor S. Efremov, Georgii E. Bondar
Abstract: The integration of autonomous unmanned aerial vehicles (UAVs) into large-scale artistic projects has emerged as a new application in robotics. This paper presents the design, deployment, and testing of a novel multi-drone system for automated mural painting in outdoor settings. This technology makes use of new software that coordinates multiple drones simultaneously, utilizing state-machine algorithms for task execution. Key advancements are the complex positioning system that combines 2D localization using a single motion tracking camera with onboard LiDAR for precise positioning, and a novel flight control algorithm, which works differently along the trajectory and normally to it, ensuring smoothness and high precision of the drawings at the same time. A 100 square meters mural was created using the developed multi-drone system, validating the system's efficacy. Compared to single-drone approaches, our multi-UAV solution significantly improves scalability and operational speed while maintaining high stability even in harsh weather conditions. The findings highlight the potential of autonomous robotic swarms in creative applications, paving the way for further advancements in large-scale robotic art.
Authors: Jiao Xu, Peng Li, Bing Zheng
Abstract: Least absolute deviations (LAD) is a statistical optimality criterion widely utilized in scenarios where a minority of measurements are contaminated by outliers of arbitrary magnitudes. In this paper, we delve into the robustness of the variant of adaptive iterative hard thresholding to outliers, known as graded fast hard thresholding pursuit (GFHTP$_1$) algorithm. Unlike the majority of the state-of-the-art algorithms in this field, GFHTP$_1$ does not require prior information about the signal's sparsity. Moreover, its design is parameterless, which not only simplifies the implementation process but also removes the intricacies of parameter optimization. Numerical experiments reveal that the GFHTP$_1$ algorithm consistently outperforms competing algorithms in terms of both robustness and computational efficiency.
Authors: Dushan N. Wadduwage, Dineth Jayakody, Leonidas Zimianitis
Abstract: Machine learning (ML) models show strong promise for new biomedical prediction tasks, but concerns about trustworthiness have hindered their clinical adoption. In particular, it is often unclear whether a model relies on true clinical cues or on spurious hierarchical correlations in the data. This paper introduces a simple yet broadly applicable trustworthiness test grounded in stochastic proof-by-contradiction. Instead of just showing high test performance, our approach trains and tests on spurious labels carefully permuted based on a potential outcomes framework. A truly trustworthy model should fail under such label permutation; comparable accuracy across real and permuted labels indicates overfitting, shortcut learning, or data leakage. Our approach quantifies this behavior through interpretable Fisher-style p-values, which are well understood by domain experts across medical and life sciences. We evaluate our approach on multiple new bacterial diagnostics to separate tasks and models learning genuine causal relationships from those driven by dataset artifacts or statistical coincidences. Our work establishes a foundation to build rigor and trust between ML and life-science research communities, moving ML models one step closer to clinical adoption.
Authors: Mohammad Khateri, Morteza Ghahremani, Sergio Valencia, Camilo Jaimes, Alejandra Sierra, Jussi Tohka, P. Ellen Grant, Davood Karimi
Abstract: Ultrasound offers a safe, cost-effective, and widely accessible technology for fetal brain imaging, making it especially suitable for routine clinical use. However, it suffers from view-dependent artifacts, operator variability, and a limited field of view, which make interpretation and quantitative evaluation challenging. Ultrasound compounding aims to overcome these limitations by integrating complementary information from multiple 3D acquisitions into a single, coherent volumetric representation. This work provides four main contributions: (1) We present the first systematic categorization of computational strategies for fetal brain ultrasound compounding, including both classical techniques and modern learning-based frameworks. (2) We implement and compare representative methods across four key categories - multi-scale, transformation-based, variational, and deep learning approaches - emphasizing their core principles and practical advantages. (3) Motivated by the lack of full-view, artifact-free ground truth required for supervised learning, we focus on unsupervised and self-supervised strategies and introduce two new deep learning based approaches: a self-supervised compounding framework and an adaptation of unsupervised deep plug-and-play priors for compounding. (4) We conduct a comprehensive evaluation on ten multi-view fetal brain ultrasound datasets, using both expert radiologist scoring and standard quantitative image-quality metrics. We also release the USFetal Compounding Toolbox, publicly available to support benchmarking and future research. Keywords: Ultrasound compounding, fetal brain, deep learning, self-supervised, unsupervised.
Authors: Huatao Xu, Zihe Liu, Zilin Zeng, Baichuan Li, Mo Li
Abstract: We present AutoTour, a system that enhances user exploration by automatically generating fine-grained landmark annotations and descriptive narratives for photos captured by users. The key idea of AutoTour is to fuse visual features extracted from photos with nearby geospatial features queried from open matching databases. Unlike existing tour applications that rely on pre-defined content or proprietary datasets, AutoTour leverages open and extensible data sources to provide scalable and context-aware photo-based guidance. To achieve this, we design a training-free pipeline that first extracts and filters relevant geospatial features around the user's GPS location. It then detects major landmarks in user photos through VLM-based feature detection and projects them into the horizontal spatial plane. A geometric matching algorithm aligns photo features with corresponding geospatial entities based on their estimated distance and direction. The matched features are subsequently grounded and annotated directly on the original photo, accompanied by large language model-generated textual and audio descriptions to provide an informative, tour-like experience. We demonstrate that AutoTour can deliver rich, interpretable annotations for both iconic and lesser-known landmarks, enabling a new form of interactive, context-aware exploration that bridges visual perception and geospatial understanding.
Authors: Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu
Abstract: While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.
Authors: Michael Sidorov, Ofer Hadar
Abstract: The rapid growth of multimedia consumption, driven by major advances in mobile devices since the mid-2000s, has led to widespread use of video conferencing applications (VCAs) such as Zoom and Google Meet, as well as instant messaging applications (IMAs) like WhatsApp and Telegram, which increasingly support video conferencing as a core feature. Many of these systems rely on the Web Real-Time Communication (WebRTC) protocol, enabling direct peer-to-peer media streaming without requiring a third-party server to relay data, reducing the latency and facilitating a real-time communication. Despite WebRTC's potential, adverse network conditions can degrade streaming quality and consequently reduce users' Quality of Experience (QoE). Maintaining high QoE therefore requires continuous monitoring and timely intervention when QoE begins to deteriorate. While content providers can often estimate QoE by directly comparing transmitted and received media, this task is significantly more challenging for internet service providers (ISPs). End-to-end encryption, commonly used by modern VCAs and IMAs, prevent ISPs from accessing the original media stream, leaving only Quality of Service (QoS) and routing information available. To address this limitation, we propose the QoE Attention Convolutional Neural Network (qAttCNN), a model that leverages packet size parameter of the traffic to infer two no-reference QoE metrics viz. BRISQUE and frames per second (FPS). We evaluate qAttCNN on a custom dataset collected from WhatsApp video calls and compare it against existing QoE models. Using mean absolute error percentage (MAEP), our approach achieves 2.14% error for BRISQUE and 7.39% for FPS prediction.
Authors: Yuetao Li, Zhizhou Jia, Yu Zhang, Qun Hao, Shaohui Zhang
Abstract: Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .
Authors: Hasan M Jamil
Abstract: Glioblastoma (GBM) is a highly aggressive primary brain tumor with limited therapeutic options and poor prognosis. The methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) gene promoter is a critical molecular biomarker that influences patient response to temozolomide chemotherapy. Traditional methods for determining MGMT status rely on invasive biopsies and are limited by intratumoral heterogeneity and procedural risks. This study presents a radiogenomic molecular imaging analysis framework for the non-invasive prediction of MGMT promoter methylation using multi-parametric magnetic resonance imaging (mpMRI). Our approach integrates radiomics, deep learning, and explainable artificial intelligence (XAI) to analyze MRI-derived imaging phenotypes and correlate them with molecular labels. Radiomic features are extracted from FLAIR, T1-weighted, T1-contrast-enhanced, and T2-weighted MRI sequences, while a 3D convolutional neural network learns deep representations from the same modalities. These complementary features are fused using both early fusion and attention-based strategies and classified to predict MGMT methylation status. To enhance clinical interpretability, we apply XAI methods such as Grad-CAM and SHAP to visualize and explain model decisions. The proposed framework is trained on the RSNA-MICCAI Radiogenomic Classification dataset and externally validated on the BraTS 2021 dataset. This work advances the field of molecular imaging by demonstrating the potential of AI-driven radiogenomics for precision oncology, supporting non-invasive, accurate, and interpretable prediction of clinically actionable molecular biomarkers in GBM.
Authors: Taisuke Noguchi, Takayuki Nishio, Takuya Azumi
Abstract: 3D object detection using LiDAR-based point cloud data and deep neural networks is essential in autonomous driving technology. However, deploying state-of-the-art models on edge devices present challenges due to high computational demands and energy consumption. Additionally, single LiDAR setups suffer from blind spots. This paper proposes SC-MII, multiple infrastructure LiDAR-based 3D object detection on edge devices for Split Computing with Multiple Intermediate outputs Integration. In SC-MII, edge devices process local point clouds through the initial DNN layers and send intermediate outputs to an edge server. The server integrates these features and completes inference, reducing both latency and device load while improving privacy. Experimental results on a real-world dataset show a 2.19x speed-up and a 71.6% reduction in edge device processing time, with at most a 1.09% drop in accuracy.
Authors: Sungguk Cha, DongWook Kim, Mintae Kim, Youngsub Han, Byoung-Ki Jeon, Sangyeob Lee
Abstract: Multi-vector embedding models have emerged as a powerful paradigm for document retrieval, preserving fine-grained visual and textual details through token-level representations. However, this expressiveness comes at a staggering cost: storing embeddings for every token inflates index sizes by over $1000\times$ compared to single-vector approaches, severely limiting scalability. We introduce \textbf{ReinPool}, a reinforcement learning framework that learns to dynamically filter and pool multi-vector embeddings into compact, retrieval-optimized representations. By training with an inverse retrieval objective and NDCG-based rewards, ReinPool identifies and retains only the most discriminative vectors without requiring manual importance annotations. On the Vidore V2 benchmark across three vision-language embedding models, ReinPool compresses multi-vector representations by $746$--$1249\times$ into single vectors while recovering 76--81\% of full multi-vector retrieval performance. Compared to static mean pooling baselines, ReinPool achieves 22--33\% absolute NDCG@3 improvement, demonstrating that learned selection significantly outperforms heuristic aggregation.
Authors: James Calo, Benny Lo
Abstract: Consensus mechanisms are the core of any blockchain system. However, the majority of these mechanisms do not target federated learning directly nor do they aid in the aggregation step. This paper introduces Proof of Reasoning (PoR), a novel consensus mechanism specifically designed for federated learning using blockchain, aimed at preserving data privacy, defending against malicious attacks, and enhancing the validation of participating networks. Unlike generic blockchain consensus mechanisms commonly found in the literature, PoR integrates three distinct processes tailored for federated learning. Firstly, a masked autoencoder (MAE) is trained to generate an encoder that functions as a feature map and obfuscates input data, rendering it resistant to human reconstruction and model inversion attacks. Secondly, a downstream classifier is trained at the edge, receiving input from the trained encoder. The downstream network's weights, a single encoded datapoint, the network's output and the ground truth are then added to a block for federated aggregation. Lastly, this data facilitates the aggregation of all participating networks, enabling more complex and verifiable aggregation methods than previously possible. This three-stage process results in more robust networks with significantly reduced computational complexity, maintaining high accuracy by training only the downstream classifier at the edge. PoR scales to large IoT networks with low latency and storage growth, and adapts to evolving data, regulations, and network conditions.
Authors: Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Shui Yu
Abstract: Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to firstly upload their data to the server as a prerequisite for unlearning. These methods are infeasible in many privacy-preserving scenarios where servers are prohibited from accessing users' data, such as federated learning (FL). In this paper, we explore how to implement unlearning under the condition of not uncovering the erasing data to the server. We propose \textbf{Blind Unlearning (BlindU)}, which carries out unlearning using compressed representations instead of original inputs. BlindU only involves the server and the unlearning user: the user locally generates privacy-preserving representations, and the server performs unlearning solely on these representations and their labels. For the FL model training, we employ the information bottleneck (IB) mechanism. The encoder of the IB-based FL model learns representations that distort maximum task-irrelevant information from inputs, allowing FL users to generate compressed representations locally. For effective unlearning using compressed representation, BlindU integrates two dedicated unlearning modules tailored explicitly for IB-based models and uses a multiple gradient descent algorithm to balance forgetting and utility retaining. While IB compression already provides protection for task-irrelevant information of inputs, to further enhance the privacy protection, we introduce a noise-free differential privacy (DP) masking method to deal with the raw erasing data before compressing. Theoretical analysis and extensive experimental results illustrate the superiority of BlindU in privacy protection and unlearning effectiveness compared with the best existing privacy-preserving unlearning benchmarks.
Authors: Taekbeom Lee, Dabin Kim, Youngseok Jang, H. Jin Kim
Abstract: We present HERE, an active 3D scene reconstruction framework based on neural radiance fields, enabling high-fidelity implicit mapping. Our approach centers around an active learning strategy for camera trajectory generation, driven by accurate identification of unseen regions, which supports efficient data acquisition and precise scene reconstruction. The key to our approach is epistemic uncertainty quantification based on evidential deep learning, which directly captures data insufficiency and exhibits a strong correlation with reconstruction errors. This allows our framework to more reliably identify unexplored or poorly reconstructed regions compared to existing methods, leading to more informed and targeted exploration. Additionally, we design a hierarchical exploration strategy that leverages learned epistemic uncertainty, where local planning extracts target viewpoints from high-uncertainty voxels based on visibility for trajectory generation, and global planning uses uncertainty to guide large-scale coverage for efficient and comprehensive reconstruction. The effectiveness of the proposed method in active 3D reconstruction is demonstrated by achieving higher reconstruction completeness compared to previous approaches on photorealistic simulated scenes across varying scales, while a hardware demonstration further validates its real-world applicability.
Authors: Alexandre Tuel, Thomas Kerdreux, Quentin Febvre, Alexis Mouche, Antoine Grouazel, Jean-Renaud Miadana, Antoine Audras, Chen Wang, Bertrand Chapron
Abstract: We present OceanSAR-2, the second generation of our foundation model for SAR-based ocean observation. Building on our earlier release, which pioneered self-supervised learning on Sentinel-1 Wave Mode data, OceanSAR-2 relies on improved SSL training and dynamic data curation strategies, which enhances performance while reducing training cost. OceanSAR-2 demonstrates strong transfer performance across downstream tasks, including geophysical pattern classification, ocean surface wind vector and significant wave height estimation, and iceberg detection. We release standardized benchmark datasets, providing a foundation for systematic evaluation and advancement of SAR models for ocean applications.
Authors: Youngmin Oh, Hyung-Il Kim, Jung Uk Kim
Abstract: Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully annotated data for all tasks is impractical due to labeling costs. Existing methods for partially labeled MTL typically rely on predictions from unlabeled tasks, making it difficult to establish reliable task associations and potentially leading to negative transfer and suboptimal performance. To address these issues, we propose a prototype-based knowledge retrieval framework that achieves robust MTL instead of relying on predictions from unlabeled tasks. Our framework consists of two key components: (1) a task prototype embedding task-specific characteristics and quantifying task associations, and (2) a knowledge retrieval transformer that adaptively refines feature representations based on these associations. To achieve this, we introduce an association knowledge generating (AKG) loss to ensure the task prototype consistently captures task-specific characteristics. Extensive experiments demonstrate the effectiveness of our framework, highlighting its potential for robust multi-task learning, even when only a subset of tasks is annotated.
Authors: Margherita Firenze, Sean I. Young, Clinton J. Wang, Hyuk Jin Yun, Elfar Adalsteinsson, Kiho Im, P. Ellen Grant, Polina Golland
Abstract: Fully convolutional networks have become the backbone of modern medical imaging due to their ability to learn multi-scale representations and perform end-to-end inference. Yet their potential for slice-to-volume reconstruction (SVR), the task of jointly estimating 3D anatomy and slice poses from misaligned 2D acquisitions, remains underexplored. We introduce a fast convolutional framework that fuses multiple orthogonal 2D slice stacks to recover coherent 3D structure and refines slice alignment through lightweight model-based optimization. Applied to fetal brain MRI, our approach reconstructs high-quality 3D volumes in under 10s, with 1s slice registration and accuracy on par with state-of-the-art iterative SVR pipelines, offering more than speedup. The framework uses non-rigid displacement fields to represent transformations, generalizing to other SVR problems like fetal body and placental MRI. Additionally, the fast inference time paves the way for real-time, scanner-side volumetric feedback during MRI acquisition.
Authors: Alvaro Becerra, Ruth Cobos, Roberto Daza
Abstract: Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance across multiple modalities remain scarce. To address this gap, we present SOPHIAS (Student Oral Presentation monitoring for Holistic Insights & Analytics using Sensors), a 12-hour multimodal dataset containing recordings of 50 oral presentations (10-15-minute presentation followed by 5-15-minute Q&A) delivered by 65 undergraduate and master's students at the Universidad Autonoma de Madrid. SOPHIAS integrates eight synchronized sensor streams from high-definition webcams, ambient and webcam audio, eye-tracking glasses, smartwatch physiological sensors, and clicker, keyboard, and mouse interactions. In addition, the dataset includes slides and rubric-based evaluations from teachers, peers, and self-assessments, along with timestamped contextual annotations. The dataset captures presentations conducted in real classroom settings, preserving authentic student behaviors, interactions, and physiological responses. SOPHIAS enables the exploration of relationships between multimodal behavioral and physiological signals and presentation performance, supports the study of peer assessment, and provides a benchmark for developing automated feedback and Multimodal Learning Analytics tools. The dataset is publicly available for research through GitHub and Science Data Bank.
Authors: Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Qingyun Li, Yian Wang, Yu Qiao, Zun Wang, Zichen Ding
Abstract: While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of granular control over historical visual context curation and the absence of visual-aware tutorial retrieval. To bridge these gaps, we introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation: (1) a Reflection-Memory Agent that utilizes milestone-driven long-term memory to enable trajectory-level self-correction, effectively mitigating visual context loss in long-horizon tasks; (2) Versatile Tool Agents featuring a Multimodal Searcher that adopts a SeeAct paradigm to navigate a browser-based sandbox to synthesize live, visually aligned tutorials, thereby resolving fidelity issues in unseen scenarios. Experimental results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales, establishing new state-of-the-art results on three online benchmarks, notably achieving 65.84% on OSWorld.
Authors: Mohammed Himayath Ali, Mohammed Aqib Abdullah, Mohammed Mudassir Uddin, Shahnawaz Alam
Abstract: Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where malicious instructions embedded in security artifacts manipulate model behavior. This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails, adaptive constitution evolution, and Direct Preference Optimization for unlearning unsafe response patterns, addressing the unique challenges of high-stakes security contexts where traditional safety mechanisms prove insufficient against sophisticated adversarial manipulation. Experimental evaluation demonstrates that SecureCAI reduces attack success rates by 94.7% compared to baseline models while maintaining 95.1% accuracy on benign security analysis tasks, with the framework incorporating continuous red-teaming feedback loops enabling dynamic adaptation to emerging attack strategies and achieving constitution adherence scores exceeding 0.92 under sustained adversarial pressure, thereby establishing a foundation for trustworthy integration of language model capabilities into operational cybersecurity workflows and addressing a critical gap in current approaches to AI safety within adversarial domains.
Authors: Viraj Shah, Svetlana Lazebnik, Julien Philip
Abstract: Intrinsic Image Decomposition (IID) is a challenging inverse problem that seeks to decompose a natural image into its underlying intrinsic components such as albedo and shading. While recent image decomposition methods rely on learning-based priors on these components, they often suffer from component cross-contamination owing to joint training of priors; or from Sim-to-Real gap since the priors trained on synthetic data are kept frozen during the inference on real images. In this work, we propose to solve the intrinsic image decomposition problem using a bank of Generative Adversarial Networks (GANs) as priors where each GAN is independently trained only on a single intrinsic component, providing stronger and more disentangled priors. At the core of our approach is the idea that the latent space of a GAN is a well-suited optimization domain to solve inverse problems. Given an input image, we propose to jointly invert the latent codes of a set of GANs and combine their outputs to reproduce the input. Contrary to all existing GAN inversion methods that are limited to inverting only a single GAN, our proposed approach, JoIN, is able to jointly invert multiple GANs using only a single image as supervision while still maintaining distribution priors of each intrinsic component. We show that our approach is modular, allowing various forward imaging models, and that it can successfully decompose both synthetic and real images. Further, taking inspiration from existing GAN inversion approaches, we allow for careful fine-tuning of the generator priors during the inference on real images. This way, our method is able to achieve excellent generalization on real images even though it uses only synthetic data to train the GAN priors. We demonstrate the success of our approach through exhaustive qualitative and quantitative evaluations and ablation studies on various datasets.
Authors: Fadhil Muhammad, Alif Bintang Elfandra, Iqbal Pahlevi Amin, Alfan Farizki Wicaksono
Abstract: The rich biodiversity of coral reefs in Indonesian waters represents a valuable asset that must be preserved. Rapid climate change and uncontrolled human activities have caused significant degradation of coral reef ecosystems, including coral bleaching, which is a critical indicator of declining reef health. Therefore, this study aims to develop an accurate classification model to distinguish between healthy corals and bleached corals. This research utilizes a specialized dataset consisting of 923 images collected from Flickr using the Flickr API. The dataset comprises two distinct classes: healthy corals (438 images) and bleached corals (485 images). All images were resized so that the maximum width or height does not exceed 300 pixels, ensuring consistent image dimensions across the dataset. The proposed approach employs machine learning techniques, particularly convolutional neural networks (CNNs), to identify and differentiate visual patterns associated with healthy and bleached corals. The dataset can be used to train and evaluate various classification models in order to achieve optimal performance. Using the ResNet architecture, the results indicate that a ResNet model trained from scratch outperforms pretrained models in terms of both precision and accuracy. The successful development of an accurate classification model provides substantial benefits for researchers and marine biologists by enabling a deeper understanding of coral reef health. Furthermore, these models can be applied to monitor environmental changes in coral reef ecosystems, thereby contributing meaningfully to conservation and restoration efforts that are vital to sustaining marine life.
Authors: Philipp Liznerski, Saurabh Varshneya, Ece Calikus, Puyu Wang, Alexander Bartscher, Sebastian Josef Vollmer, Sophie Fellenz, Marius Kloft
Abstract: Deep learning-based methods have achieved a breakthrough in image anomaly detection, but their complexity introduces a considerable challenge to understanding why an instance is predicted to be anomalous. We introduce a novel explanation method that generates multiple alternative modifications for each anomaly, capturing diverse concepts of anomalousness. Each modification is trained to be perceived as normal by the anomaly detector. The method provides a semantic explanation of the mechanism that triggered the detector, allowing users to explore ``what-if scenarios.'' Qualitative and quantitative analyses across various image datasets demonstrate that applying this method to state-of-the-art detectors provides high-quality semantic explanations.
Authors: Zhaoxu Li, Wei An, Gaowei Guo, Longguang Wang, Yingqian Wang, Zaiping Lin
Abstract: Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However, existing HTD methods are developed based on per-pixel binary classification, neglecting the three-dimensional cube structure of hyperspectral images (HSIs) that integrates both spatial and spectral dimensions. The synergistic existence of spatial and spectral features in HSIs enable objects to simultaneously exhibit both, yet the per-pixel HTD framework limits the joint expression of these features. In this paper, we rethink HTD from the perspective of spatial-spectral synergistic representation and propose hyperspectral point object detection as an innovative task framework. We introduce SpecDETR, the first specialized network for hyperspectral multi-class point object detection, which eliminates dependence on pre-trained backbone networks commonly required by vision-based object detectors. SpecDETR uses a multi-layer Transformer encoder with self-excited subpixel-scale attention modules to directly extract deep spatial-spectral joint features from hyperspectral cubes. We develop a simulated hyperspectral point object detection benchmark termed SPOD, and for the first time, evaluate and compare the performance of visual object detection networks and HTD methods on hyperspectral point object detection. Extensive experiments demonstrate that our proposed SpecDETR outperforms SOTA visual object detection networks and HTD methods. Our code and dataset are available at https://github.com/ZhaoxuLi123/SpecDETR.
Authors: Shuo Xu, Sai Wang, Xinyue Hu, Yutian Lin, Sibei Yang, Yu Wu
Abstract: Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attributes, neglecting the fact that objects naturally exhibit multiple interrelated attributes. Their narrow attribute scope and single attribute labeling introduce annotation biases, misleading the learning of attributes and causing inaccurate evaluation. To address these issues, we introduce the Multi-Attribute Composition (MAC) dataset, encompassing 22,838 images and 17,627 compositions with comprehensive and representative attribute annotations. MAC shows complex relationship between attributes and objects, with each attribute type linked to an average of 82.2 object types, and each object type associated with 31.4 attribute types. Based on MAC, we propose multi-attribute compositional zero-shot learning that requires deeper semantic understanding and advanced attribute associations, establishing a more realistic and challenging benchmark for CZSL. We also propose Multi-attribute Visual-Primitive Integrator (MVP-Integrator), a robust baseline for multi-attribute CZSL, which disentangles semantic primitives and performs effective visual-primitive association. Experimental results demonstrate that MVP-Integrator significantly outperforms existing CZSL methods on MAC with improved inference efficiency.
Authors: Yanheng Wang, Xiaohan Yu, Yongsheng Gao, Jianjun Sha, Jian Wang, Shiyong Yan, Kai Qin, Yonggang Zhang, Lianru Gao
Abstract: Kolmogorov-Arnold networks (KANs) represent data features by learning the activation functions and demonstrate superior accuracy with fewer parameters, FLOPs, GPU memory usage (Memory), shorter training time (TraT), and testing time (TesT) when handling low-dimensional data. However, when applied to high-dimensional data, which contains significant redundant information, the current activation mechanism of KANs leads to unnecessary computations, thereby reducing computational efficiency. KANs require reshaping high-dimensional data into a one-dimensional tensor as input, which inevitably results in the loss of dimensional information. To address these limitations, we propose weighted activation distribution KANs (WKANs), which reduce the frequency of activations per node and distribute node information into different output nodes through weights to avoid extracting redundant information. Furthermore, we introduce a multilevel tensor splitting framework (MTSF), which decomposes high-dimensional data to extract features from each dimension independently and leverages tensor-parallel computation to significantly improve the computational efficiency of WKANs on high-dimensional data. In this paper, we design SpectralKAN for hyperspectral image change detection using the proposed MTSF. SpectralKAN demonstrates outstanding performance across five datasets, achieving an overall accuracy (OA) of 0.9801 and a Kappa coefficient (K) of 0.9514 on the Farmland dataset, with only 8 k parameters, 0.07 M FLOPs, 911 MB Memory, 13.26 S TraT, and 2.52 S TesT, underscoring its superior accuracy-efficiency trade-off. The source code is publicly available at https://github.com/yanhengwang-heu/SpectralKAN.
Authors: Runhui Huang, Xinpeng Ding, Chunwei Wang, Jianhua Han, Yulong Liu, Hengshuang Zhao, Hang Xu, Lu Hou, Wei Zhang, Xiaodan Liang
Abstract: High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising direction is to use sliding windows to slice the input into uniform patches, each matching the input size of the well-trained vision encoder. Although efficient, this slicing strategy leads to the fragmentation of original input, i.e., the continuity of contextual information and spatial geometry is lost across patches, adversely affecting performance in cross-patch context perception and position-specific tasks. To overcome these shortcomings, we introduce HiRes-LLaVA, a novel framework designed to efficiently process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compresses the vision tokens based on themselves, preserving the original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related and position-related tasks. Our comprehensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and on EntityGrid-QA, particularly on document-oriented tasks, establishing new standards for handling high-resolution inputs.
Authors: Nian Wu, Jiarui Xing, Miaomiao Zhang
Abstract: This paper presents a novel approach, termed {\em Temporal Latent Residual Network (TLRN)}, to predict a sequence of deformation fields in time-series image registration. The challenge of registering time-series images often lies in the occurrence of large motions, especially when images differ significantly from a reference (e.g., the start of a cardiac cycle compared to the peak stretching phase). To achieve accurate and robust registration results, we leverage the nature of motion continuity and exploit the temporal smoothness in consecutive image frames. Our proposed TLRN highlights a temporal residual network with residual blocks carefully designed in latent deformation spaces, which are parameterized by time-sequential initial velocity fields. We treat a sequence of residual blocks over time as a dynamic training system, where each block is designed to learn the residual function between desired deformation features and current input accumulated from previous time frames. We validate the effectivenss of TLRN on both synthetic data and real-world cine cardiac magnetic resonance (CMR) image videos. Our experimental results shows that TLRN is able to achieve substantially improved registration accuracy compared to the state-of-the-art. Our code is publicly available at https://github.com/nellie689/TLRN.
Authors: Yanlin Jin, Rui-Yang Ju, Haojun Liu, Yuzhong Zhong
Abstract: Deep visual odometry, despite extensive research, still faces limitations in accuracy and generalizability that prevent its broader application. To address these challenges, we propose an Oriented FAST and Rotated BRIEF (ORB)-guided visual odometry with selective online adaptation named ORB-SfMLearner. We present a novel use of ORB features for learning-based ego-motion estimation, leading to more robust and accurate results. We also introduce the cross-attention mechanism to enhance the explainability of PoseNet and have revealed that driving direction of the vehicle can be explained through the attention weights. To improve generalizability, our selective online adaptation allows the network to rapidly and selectively adjust to the optimal parameters across different domains. Experimental results on KITTI and vKITTI datasets show that our method outperforms previous state-of-the-art deep visual odometry methods in terms of ego-motion accuracy and generalizability. Code is available at https://github.com/PeaceNeil/ORB-SfMLearner
Authors: Chen Hu, Yian Huang, Kexuan Li, Luping Zhang, Chang Long, Yiming Zhu, Tian Pu, Zhenming Peng
Abstract: Infrared small target detection (ISTD) is widely used in civilian and military applications. However, ISTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Dynamic Attention Transformer Network (DATransNet), which aims to extract and preserve detailed information vital for small targets. DATransNet employs the Dynamic Attention Transformer (DATrans), simulating central difference convolutions (CDC) to extract gradient features. Furthermore, we propose a global feature extraction module (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the global information. We compare the network with state-of-the-art (SOTA) approaches and demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/DATransNet.
Authors: Yun-Jin Li, Mariia Gladkova, Yan Xia, Daniel Cremers
Abstract: Understanding dynamic 3D scenes is crucial for extended reality (XR) and autonomous driving. Incorporating semantic information into 3D reconstruction enables holistic scene representations, unlocking immersive and interactive applications. To this end, we introduce TRASE, a novel tracking-free 4D segmentation method for dynamic scene understanding. TRASE learns a 4D segmentation feature field in a weakly-supervised manner, leveraging a soft-mined contrastive learning objective guided by SAM masks. The resulting feature space is semantically coherent and well-separated, and final object-level segmentation is obtained via unsupervised clustering. This enables fast editing, such as object removal, composition, and style transfer, by directly manipulating the scene's Gaussians. We evaluate TRASE on five dynamic benchmarks, demonstrating state-of-the-art segmentation performance from unseen viewpoints and its effectiveness across various interactive editing tasks. Our project page is available at: https://yunjinli.github.io/project-sadg/
Authors: Siyun Liang, Sen Wang, Kunyi Li, Michael Niemeyer, Stefano Gasperini, Nassir Navab, Federico Tombari
Abstract: 3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While the vanilla Gaussian Splatting representation is mainly designed for view synthesis, more recent works investigated how to extend it with scene understanding and language features. However, existing methods lack a detailed comprehension of scenes, limiting their ability to segment and interpret complex structures. To this end, We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural Gaussians to learn instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of what we call Super-Gaussians. Super-Gaussians facilitate the distillation of 2D language features into 3D space. Through Super-Gaussians, our method enables high-dimensional language feature rendering without extreme increases in GPU memory. Extensive experiments demonstrate that SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks.
Authors: Siyu Jiao, Haoye Dong, Yuyang Yin, Zequn Jie, Yinlong Qian, Yao Zhao, Humphrey Shi, Yunchao Wei
Abstract: Recent works in 3D multimodal learning have made remarkable progress. However, typically 3D multimodal models are only capable of handling point clouds. Compared to the emerging 3D representation technique, 3D Gaussian Splatting (3DGS), the spatially sparse point cloud cannot depict the texture information of 3D objects, resulting in inferior reconstruction capabilities. This limitation constrains the potential of point cloud-based 3D multimodal representation learning. In this paper, we present CLIP-GS, a novel multimodal representation learning framework grounded in 3DGS. We introduce the GS Tokenizer to generate serialized gaussian tokens, which are then processed through transformer layers pre-initialized with weights from point cloud models, resulting in the 3DGS embeddings. CLIP-GS leverages contrastive loss between 3DGS and the visual-text embeddings of CLIP, and we introduce an image voting loss to guide the directionality and convergence of gradient optimization. Furthermore, we develop an efficient way to generate triplets of 3DGS, images, and text, facilitating CLIP-GS in learning unified multimodal representations. Leveraging the well-aligned multimodal representations, CLIP-GS demonstrates versatility and outperforms point cloud-based models on various 3D tasks, including multimodal retrieval, zero-shot, and few-shot classification.
Authors: Hongbo Zhao, Fei Zhu, Bolin Ni, Feng Zhu, Gaofeng Meng, Zhaoxiang Zhang
Abstract: For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners, and these requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify three key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. (iii) In real-world scenarios, the training samples may be scarce or partially missing during the process of forgetting. To address them, we first propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we introduce Low-Rank Adaptation (LoRA) modules to fine-tune the Feed-Forward Network (FFN) layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. To further extend GS-LoRA to more practical scenarios, we incorporate prototype information as additional supervision and introduce a more practical approach, GS-LoRA++. For each forgotten class, we move the logits away from its original prototype. For the remaining classes, we pull the logits closer to their respective prototypes. We conduct extensive experiments on face recognition, object detection, and image classification and demonstrate that our method manages to forget specific classes with minimal impact on other classes. Codes have been released on https://github.com/bjzhb666/GS-LoRA.
Authors: Huaying Yuan, Jian Ni, Zheng Liu, Yueze Wang, Junjie Zhou, Zhengyang Liang, Bo Zhao, Zhao Cao, Zhicheng Dou, Ji-Rong Wen
Abstract: Accurately locating key moments within long videos is crucial for solving long video understanding (LVU) tasks. However, existing benchmarks are either severely limited in terms of video length and task diversity, or they focus solely on the end-to-end LVU performance, making them inappropriate for evaluating whether key moments can be accurately accessed. To address this challenge, we propose MomentSeeker, a novel benchmark for long-video moment retrieval (LMVR), distinguished by the following features. First, it is created based on long and diverse videos, averaging over 1200 seconds in duration and collected from various domains, e.g., movie, anomaly, egocentric, and sports. Second, it covers a variety of real-world scenarios in three levels: global-level, event-level, object-level, covering common tasks like action recognition, object localization, and causal reasoning, etc. Third, it incorporates rich forms of queries, including text-only queries, image-conditioned queries, and video-conditioned queries. On top of MomentSeeker, we conduct comprehensive experiments for both generation-based approaches (directly using MLLMs) and retrieval-based approaches (leveraging video retrievers). Our results reveal the significant challenges in long-video moment retrieval in terms of accuracy and efficiency, despite improvements from the latest long-video MLLMs and task-specific fine-tuning. We have publicly released MomentSeeker(https://yhy-2000.github.io/MomentSeeker/) to facilitate future research in this area.
Authors: Siyu Jiao, Gengwei Zhang, Yinlong Qian, Jiancheng Huang, Yao Zhao, Humphrey Shi, Lin Ma, Yunchao Wei, Zequn Jie
Abstract: This work challenges the residual prediction paradigm in visual autoregressive modeling and presents FlexVAR, a new Flexible Visual AutoRegressive image generation paradigm. FlexVAR facilitates autoregressive learning with ground-truth prediction, enabling each step to independently produce plausible images. This simple, intuitive approach swiftly learns visual distributions and makes the generation process more flexible and adaptable. Trained solely on low-resolution images ($\leq$ 256px), FlexVAR can: (1) Generate images of various resolutions and aspect ratios, even exceeding the resolution of the training images. (2) Support various image-to-image tasks, including image refinement, in/out-painting, and image expansion. (3) Adapt to various autoregressive steps, allowing for faster inference with fewer steps or enhancing image quality with more steps. Our 1.0B model outperforms its VAR counterpart on the ImageNet 256$\times$256 benchmark. Moreover, when zero-shot transfer the image generation process with 13 steps, the performance further improves to 2.08 FID, outperforming state-of-the-art autoregressive models AiM/VAR by 0.25/0.28 FID and popular diffusion models LDM/DiT by 1.52/0.19 FID, respectively. When transferring our 1.0B model to the ImageNet 512$\times$512 benchmark in a zero-shot manner, FlexVAR achieves competitive results compared to the VAR 2.3B model, which is a fully supervised model trained at 512$\times$512 resolution.
Authors: Minwen Liao, Hao Bo Dong, Xinyi Wang, Kurban Ubul, Yihua Shao, Ziyang Yan
Abstract: Low-light enhancement has wide applications in autonomous driving, 3D reconstruction, remote sensing, surveillance, and so on, which can significantly improve information utilization. However, most existing methods lack generalization and are limited to specific tasks such as image recovery. To address these issues, we propose Gated-Mechanism Mixture-of-Experts (GM-MoE), the first framework to introduce a mixture-of-experts network for low-light image enhancement. GM-MoE comprises a dynamic gated weight conditioning network and three sub-expert networks, each specializing in a distinct enhancement task. Combining a self-designed gated mechanism that dynamically adjusts the weights of the sub-expert networks for different data domains. Additionally, we integrate local and global feature fusion within sub-expert networks to enhance image quality by capturing multi-scale features. Experimental results demonstrate that the GM-MoE achieves superior generalization with respect to 25 compared approaches, reaching state-of-the-art performance on PSNR on 5 benchmarks and SSIM on 4 benchmarks, respectively.
Authors: Moreno D'Inc\`a, Elia Peruzzo, Xingqian Xu, Humphrey Shi, Nicu Sebe, Massimiliano Mancini
Abstract: Vision-language models (VLMs) often inherit the biases and unsafe associations present within their large-scale training dataset. While recent approaches mitigate unsafe behaviors, their evaluation focuses on how safe the model is on unsafe inputs, ignoring potential shortcomings on safe ones. In this paper, we first revise safety evaluation by introducing SafeGround, a new set of metrics that evaluate safety at different levels of granularity. With this metric, we uncover a surprising issue of training-based methods: they make the model less safe on safe inputs. From this finding, we take a different direction and explore whether it is possible to make a model safer without training, introducing Unsafe Weights Manipulation (UWM). UWM uses a calibration set of safe and unsafe instances to compare activations between safe and unsafe content, identifying the most important parameters for processing the latter. Their values are then manipulated via negation. Experiments show that UWM achieves the best tradeoff between safety and knowledge preservation, consistently improving VLMs on unsafe queries while outperforming even training-based state-of-the-art methods on safe ones.
Authors: Yishai Lavi, Leo Segre, Shai Avidan
Abstract: 3D Gaussian Splatting (3D-GS) enables efficient novel view synthesis, but treats all frequencies uniformly, making it difficult to separate coarse structure from fine detail. Recent works have started to exploit frequency signals, but lack explicit frequency decomposition of the 3D representation itself. We propose a frequency-aware decomposition that organizes 3D Gaussians into groups corresponding to Laplacian-pyramid subbands of the input images. Each group is trained with spatial frequency regularization to confine it to its target frequency, while higher-frequency bands use signed residual colors to capture fine details that may be missed by lower-frequency reconstructions. A progressive coarse-to-fine training schedule stabilizes the decomposition. Our method achieves state-of-the-art reconstruction quality and rendering speed among all LOD-capable methods. In addition to improved interpretability, our method enables dynamic level-of-detail rendering, progressive streaming, foveated rendering, promptable 3D focus, and artistic filtering. Our code will be made publicly available.
Authors: Patrice Bechard, Chao Wang, Amirhossein Abaskohi, Juan Rodriguez, Christopher Pal, David Vazquez, Spandana Gella, Sai Rajeswar, Perouz Taslakian
Abstract: Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and system integrations. Despite being widely used, building workflows can be complex, often requiring manual configuration through low-code platforms or visual programming tools. To simplify this process, we explore the use of generative foundation models, particularly vision-language models (VLMs), to automatically generate structured workflows from visual inputs. Translating hand-drawn sketches or computer-generated diagrams into executable workflows is challenging due to the ambiguity of free-form drawings, variations in diagram styles, and the difficulty of inferring execution logic from visual elements. To address this, we introduce StarFlow, a framework for generating structured workflow outputs from sketches using vision-language models. We curate a diverse dataset of workflow diagrams -- including synthetic, manually annotated, and real-world samples -- to enable robust training and evaluation. We finetune and benchmark multiple vision-language models, conducting a series of ablation studies to analyze the strengths and limitations of our approach. Our results show that finetuning significantly enhances structured workflow generation, outperforming large vision-language models on this task.
Authors: Wangbo Zhao, Yizeng Han, Jiasheng Tang, Kai Wang, Hao Luo, Yibing Song, Gao Huang, Fan Wang, Yang You
Abstract: Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the static inference paradigm, which inevitably introduces redundant computation in certain diffusion timesteps and spatial regions. To overcome this inefficiency, we propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its computation along both timestep and spatial dimensions. Building on these designs, we present an extended version, DyDiT++, with improvements in three key aspects. First, it extends the generation mechanism of DyDiT beyond diffusion to flow matching, demonstrating that our method can also accelerate flow-matching-based generation, enhancing its versatility. Furthermore, we enhance DyDiT to tackle more complex visual generation tasks, including video generation and text-to-image generation, thereby broadening its real-world applications. Finally, to address the high cost of full fine-tuning and democratize technology access, we investigate the feasibility of training DyDiT in a parameter-efficient manner and introduce timestep-based dynamic LoRA (TD-LoRA). Extensive experiments on diverse visual generation models, including DiT, SiT, Latte, and FLUX, demonstrate the effectiveness of DyDiT++. Remarkably, with <3% additional fine-tuning iterations, our approach reduces the FLOPs of DiT-XL by 51%, yielding 1.73x realistic speedup on hardware, and achieves a competitive FID score of 2.07 on ImageNet. The code is available at https://github.com/alibaba-damo-academy/DyDiT.
Authors: Dileepa Pitawela, Gustavo Carneiro, Hsiang-Ting Chen
Abstract: In ordinal classification, misclassifying neighboring ranks is common, yet the consequences of these errors are not the same. For example, misclassifying benign tumor categories is less consequential, compared to an error at the pre-cancerous to cancerous threshold, which could profoundly influence treatment choices. Despite this, existing ordinal classification methods do not account for the varying importance of these margins, treating all neighboring classes as equally significant. To address this limitation, we propose CLOC, a new margin-based contrastive learning method for ordinal classification that learns an ordered representation based on the optimization of multiple margins with a novel multi-margin n-pair loss (MMNP). CLOC enables flexible decision boundaries across key adjacent categories, facilitating smooth transitions between classes and reducing the risk of overfitting to biases present in the training data. We provide empirical discussion regarding the properties of MMNP and show experimental results on five real-world image datasets (Adience, Historical Colour Image Dating, Knee Osteoarthritis, Indian Diabetic Retinopathy Image, and Breast Carcinoma Subtyping) and one synthetic dataset simulating clinical decision bias. Our results demonstrate that CLOC outperforms existing ordinal classification methods and show the interpretability and controllability of CLOC in learning meaningful, ordered representations that align with clinical and practical needs.
Authors: Giyeong Oh, Woohyun Cho, Siyeol Kim, Suhwan Choi, Youngjae Yu
Abstract: Residual connections are pivotal for deep neural networks, enabling greater depth by mitigating vanishing gradients. However, in standard residual updates, the module's output is directly added to the input stream. This can lead to updates that predominantly reinforce or modulate the existing stream direction, potentially underutilizing the module's capacity for learning entirely novel features. In this work, we introduce Orthogonal Residual Update: we decompose the module's output relative to the input stream and add only the component orthogonal to this stream. This design aims to guide modules to contribute primarily new representational directions, fostering richer feature learning while promoting more efficient training. We demonstrate that our orthogonal update strategy improves generalization accuracy and training stability across diverse architectures (ResNetV2, Vision Transformers) and datasets (CIFARs, TinyImageNet, ImageNet-1k), achieving, for instance, a +3.78 pp top-1 accuracy gain for ViT-B on ImageNet-1k.
Authors: Arjhun Swaminathan, Mete Akg\"un
Abstract: Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting targeted attacks that aim to misclassify into a specific target class is particularly challenging due to narrow decision regions. Current state-of-the-art methods often exploit the geometric properties of the decision boundary separating a source image and a target image rather than incorporating information from the images themselves. In contrast, we propose Targeted Edge-informed Attack (TEA), a novel attack that utilizes edge information from the target image to carefully perturb it, thereby producing an adversarial image that is closer to the source image while still achieving the desired target classification. Our approach consistently outperforms current state-of-the-art methods across different models in low query settings (nearly 70% fewer queries are used), a scenario especially relevant in real-world applications with limited queries and black-box access. Furthermore, by efficiently generating a suitable adversarial example, TEA provides an improved target initialization for established geometry-based attacks.
Authors: Shruti Atul Mali, Zohaib Salahuddin, Danial Khan, Yumeng Zhang, Henry C. Woodruff, Eduardo Ibor-Crespo, Ana Jimenez-Pastor, Luis Marti-Bonmati, Gloria Ribas, Silvia Flor-Arnal, Marta Zerunian, Damiano Caruso, Christophe Aube, Florence Longueville, Caroline Caramella, Philippe Lambin
Abstract: Purpose: This study evaluates the impact of harmonization and multi-region feature integration on survival prediction in non-small cell lung cancer (NSCLC) patients. We assess the prognostic utility of handcrafted radiomics and pretrained deep features from thoracic CT images, integrating them with clinical data using a multicentre dataset. Methods: Survival models were built using handcrafted radiomic and deep features from lung, tumor, mediastinal nodes, coronary arteries, and coronary artery calcium (CAC) scores from 876 patients across five centres. CT features were harmonized using ComBat, reconstruction kernel normalization (RKN), and RKN-ComBat. Models were constructed at the region of interest (ROI) level and through ensemble strategies. Regularized Cox models estimated overall survival, with performance assessed via the concordance index (C-index), 5-year time-dependent area under the curve (t-AUC), and hazard ratios. SHAP values interpreted feature contributions, while consensus analysis categorized predicted survival probabilities at fixed time points. Results: TNM staging showed prognostic value (C-index = 0.67; hazard ratio = 2.70; t-AUC = 0.85). The clinical and tumor texture radiomics model with ComBat yielded high performance (C-index = 0.76; t-AUC = 0.88). FM deep features from 50 voxel cubes also showed predictive value (C-index = 0.76; t-AUC = 0.89). An ensemble model combining tumor, lung, mediastinal node, CAC, and FM features achieved a C-index of 0.71 and t-AUC of 0.79. Consensus analysis identified a high-confidence patient subset, resulting in a model with a 5-year t-AUC of 0.92, sensitivity of 96.8%, and specificity of 70.0%. Conclusion: Harmonization and multi-region feature integration enhance survival prediction in NSCLC patients using CT imaging, supporting individualized risk stratification in multicentre settings.
Authors: Tianchen Deng, Wenhua Wu, Junjie He, Yue Pan, Shenghai Yuan, Danwei Wang, Hesheng Wang
Abstract: 3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle with memory explosion in large-scale scenes and long sequences. To this end, we propose VPGS-SLAM, the first 3DGS-based large-scale RGBD SLAM framework for both indoor and outdoor scenarios. We design a novel voxel-based progressive 3D Gaussian mapping method with multiple submaps for compact and accurate scene representation in large-scale and long-sequence scenes. This allows us to scale up to arbitrary scenes and improves robustness (even under pose drifts). In addition, we propose a 2D-3D fusion camera tracking method to achieve robust and accurate camera tracking in both indoor and outdoor large-scale scenes. Furthermore, we design a 2D-3D Gaussian loop closure method to eliminate pose drift. We further propose a submap fusion method with online distillation to achieve global consistency in large-scale scenes when detecting a loop. Experiments on various indoor and outdoor datasets demonstrate the superiority and generalizability of the proposed framework. The code will be open source on https://github.com/dtc111111/vpgs-slam.
Authors: Robin Bruneau, Baptiste Brument, Yvain Qu\'eau, Jean M\'elou, Fran\c{c}ois Bernard Lauze, Jean-Denis Durou, Lilian Calvet
Abstract: Achieving high-fidelity 3D surface reconstruction while preserving fine details remains challenging, especially in the presence of materials with complex reflectance properties and without a dense-view setup. In this paper, we introduce a versatile framework that incorporates multi-view normal and optionally reflectance maps into radiance-based surface reconstruction. Our approach employs a pixel-wise joint re-parametrization of reflectance and surface normals, representing them as a vector of radiances under simulated, varying illumination. This formulation enables seamless incorporation into standard surface reconstruction pipelines, such as traditional multi-view stereo (MVS) frameworks or modern neural volume rendering (NVR) ones. Combined with the latter, our approach achieves state-of-the-art performance on multi-view photometric stereo (MVPS) benchmark datasets, including DiLiGenT-MV, LUCES-MV and Skoltech3D. In particular, our method excels in reconstructing fine-grained details and handling challenging visibility conditions. The present paper is an extended version of the earlier conference paper by Brument et al. (in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024), featuring an accelerated and more robust algorithm as well as a broader empirical evaluation. The code and data relative to this article is available at https://github.com/RobinBruneau/RNb-NeuS2.
Authors: Junjian Li, Jin Liu, Hulin Kuang, Hailin Yue, Mengshen He, Jianxin Wang
Abstract: Multiple instance learning (MIL) has shown significant promise in histopathology whole slide image (WSI) analysis for cancer diagnosis and prognosis. However, the inherent spatial heterogeneity of WSIs presents critical challenges, as morphologically similar tissue types are often dispersed across distant anatomical regions. Conventional MIL methods struggle to model these scattered tissue distributions and capture cross-regional spatial interactions effectively. To address these limitations, we propose a novel Multiple instance learning framework with Context-Aware Clustering (MiCo), designed to enhance cross-regional intra-tissue correlations and strengthen inter-tissue semantic associations in WSIs. MiCo begins by clustering instances to distill discriminative morphological patterns, with cluster centroids serving as semantic anchors. To enhance cross-regional intra-tissue correlations, MiCo employs a Cluster Route module, which dynamically links instances of the same tissue type across distant regions via feature similarity. These semantic anchors act as contextual hubs, propagating semantic relationships to refine instance-level representations. To eliminate semantic fragmentation and strengthen inter-tissue semantic associations, MiCo integrates a Cluster Reducer module, which consolidates redundant anchors while enhancing information exchange between distinct semantic groups. Extensive experiments on two challenging tasks across nine large-scale public cancer datasets demonstrate the effectiveness of MiCo, showcasing its superiority over state-of-the-art methods. The code is available at https://github.com/junjianli106/MiCo.
Authors: Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Ruiping Liu, Fei Teng, Kai Luo, Zhiyong Li, Kailun Yang
Abstract: 3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution (OoD) objects and long-tail distributions, which increases the risk of undetected anomalies and misinterpretations, posing safety hazards. To address these challenges, we introduce Out-of-Distribution Semantic Occupancy Prediction, targeting OoD detection in 3D voxel space. To fill dataset gaps, we propose a Realistic Anomaly Augmentation that injects synthetic anomalies while preserving realistic spatial and occlusion patterns, enabling the creation of two datasets: VAA-KITTI and VAA-KITTI-360. Then, a novel framework that integrates OoD detection into 3D semantic occupancy prediction, OccOoD, is proposed, which uses Cross-Space Semantic Refinement (CSSR) to refine semantic predictions from complementary voxel and BEV representations, improving OoD detection. Experimental results demonstrate that OccOoD achieves state-of-the-art OoD detection with an AuROC of 65.50% and an AuPRCr of 31.83 within a 1.2m region, while maintaining competitive semantic occupancy prediction performance and generalization in real-world urban driving scenes. The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD.
Authors: Junjie Hu, Tianyang Han, Kai Ma, Jialin Gao, Song Yang, Xianhua He, Junfeng Luo, Xiaoming Wei, Wenqiang Zhang
Abstract: Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity and layout by global attention mechanisms. To this end, we introduce \modelname{}, a unified framework for high-fidelity, spatially controllable multi-subject customization. First, we present BMPDS, the first automatic data-synthesis pipeline for position-annotated multi-subject datasets, effectively providing crucial spatial supervision. Second, we design a lightweight, layout-aware diffusion framework that integrates a novel visibility-aware attention mechanism. This mechanism explicitly models spatial relationships via an NeRF-inspired volumetric weight regulation to effectively decouple instance-level spatial embeddings from semantic identity features, enabling precise, occlusion-aware placement of multiple subjects. Extensive experiments demonstrate \modelname{} achieves state-of-the-art performance on public benchmarks, setting new records for spatial precision and identity consistency. Our work represents a significant step towards truly controllable, high-fidelity image customization in multi-entity scenarios. Code and data will be publicly released.
Authors: Saeid Ghafouri, Mohsen Fayyaz, Xiangchen Li, Deepu John, Bo Ji, Dimitrios Nikolopoulos, Hans Vandierendonck
Abstract: Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines on the TAO dataset. Polymorph is open source at https://github.com/inference-serving/polymorph/.
Authors: Zhiyuan Chen (State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Yuecong Min (State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Jie Zhang (State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Bei Yan (State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Jiahao Wang (Trustworthy Technology and Engineering Laboratory, Huawei), Xiaozhen Wang (Trustworthy Technology and Engineering Laboratory, Huawei), Shiguang Shan (State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences)
Abstract: Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However, these models often suffer from hallucination, producing content that appears plausible but contradicts the input content or established world knowledge. This survey offers an in-depth review of hallucination evaluation benchmarks and detection methods across Image-to-Text (I2T) and Text-to-image (T2I) generation tasks. Specifically, we first propose a taxonomy of hallucination based on faithfulness and factuality, incorporating the common types of hallucinations observed in practice. Then we provide an overview of existing hallucination evaluation benchmarks for both T2I and I2T tasks, highlighting their construction process, evaluation objectives, and employed metrics. Furthermore, we summarize recent advances in hallucination detection methods, which aims to identify hallucinated content at the instance level and serve as a practical complement of benchmark-based evaluation. Finally, we highlight key limitations in current benchmarks and detection methods, and outline potential directions for future research.
Authors: Anubhav Kataria, Surbhi Madan, Shreya Ghosh, Tom Gedeon, Abhinav Dhall
Abstract: Understanding individual, group and event level emotions along with contextual information is crucial for analyzing a multi-person social situation. To achieve this, we frame emotion comprehension as the task of predicting fine-grained individual emotion to coarse grained group and event level emotion. We introduce GEMS that leverages a multimodal swin-transformer and S3Attention based architecture, which processes an input scene, group members, and context information to generate joint predictions. Existing multi-person emotion related benchmarks mainly focus on atomic interactions primarily based on emotion perception over time and group level. To this end, we extend and propose VGAF-GEMS to provide more fine grained and holistic analysis on top of existing group level annotation of VGAF dataset. GEMS aims to predict basic discrete and continuous emotions (including valence and arousal) as well as individual, group and event level perceived emotions. Our benchmarking effort links individual, group and situational emotional responses holistically. The quantitative and qualitative comparisons with adapted state-of-the-art models demonstrate the effectiveness of GEMS framework on VGAF-GEMS benchmarking. We believe that it will pave the way of further research. The code and data is available at: https://github.com/katariaak579/GEMS
Authors: Ke Liu, Xuanhan Wang, Qilong Zhang, Lianli Gao, Jingkuan Song
Abstract: Deep image watermarking, which refers to enabling imperceptible watermark embedding and reliable extraction in cover images, has been shown to be effective for copyright protection of image assets. However, existing methods face limitations in simultaneously satisfying three essential criteria for generalizable watermarking: (1) invisibility (imperceptible hiding of watermarks), (2) robustness (reliable watermark recovery under diverse conditions), and (3) broad applicability (low latency in the watermarking process). To address these limitations, we propose a Hierarchical Watermark Learning (HiWL) framework, a two-stage optimization that enables a watermarking model to simultaneously achieve all three criteria. In the first stage, distribution alignment learning is designed to establish a common latent space with two constraints: (1) visual consistency between watermarked and non-watermarked images, and (2) information invariance across watermark latent representations. In this way, multimodal inputs -- including watermark messages (binary codes) and cover images (RGB pixels) -- can be effectively represented, ensuring both the invisibility of watermarks and robustness in the watermarking process. In the second stage, we employ generalized watermark representation learning to separate a unique representation of the watermark from the marked image in RGB space. Once trained, the HiWL model effectively learns generalizable watermark representations while maintaining broad applicability. Extensive experiments demonstrate the effectiveness of the proposed method. Specifically, it achieves 7.6% higher accuracy in watermark extraction compared to existing methods, while maintaining extremely low latency (processing 1000 images in 1 second).
Authors: Haoyang Li, Jiaqing Li, Jialun Cao, Zongyuan Yang, Yongping Xiong
Abstract: Large foundation models have achieved significant performance gains through scalable training on massive datasets. However, the field of \textbf{H}andwritten \textbf{M}athematical \textbf{E}xpression \textbf{R}ecognition (HMER) has been impeded by the scarcity of data, primarily due to the arduous and costly process of manual annotation. To bridge this gap, we propose a novel method integrating limited handwritten formulas with large-scale LaTeX-rendered formulas by developing a scalable data engine to generate complex and consistent LaTeX sequences. With this engine, we built the largest formula dataset to date, termed \texttt{Tex80M}, comprising over 80 million high-quality training instances. Then we propose \texttt{TexTeller}, the first HMER model trained at scale, by mix-training \texttt{Tex80M} with a relatively small HME dataset. The expansive training dataset and our refined pipeline have equipped \texttt{TexTeller} with state-of-the-art (SOTA) performance across nearly all benchmarks. To advance the field, we will openly release our complete model, entire dataset, and full codebase, enabling further research building upon our contributions.
Authors: Alexandre Brown, Glen Berseth
Abstract: Visual reinforcement learning (RL) is challenging due to the need to extract useful representations from high-dimensional inputs while learning effective control from sparse and noisy rewards. Although large perception models exist, integrating them effectively into RL for visual generalization and improved sample efficiency remains difficult. We propose SegDAC, a Segmentation-Driven Actor-Critic method. SegDAC uses Segment Anything (SAM) for object-centric decomposition and YOLO-World to ground the image segmentation process via text inputs. It includes a novel transformer-based architecture that supports a dynamic number of segments at each time step and effectively learns which segments to focus on using online RL, without using human labels. By evaluating SegDAC over a challenging visual generalization benchmark using Maniskill3, which covers diverse manipulation tasks under strong visual perturbations, we demonstrate that SegDAC achieves significantly better visual generalization, doubling prior performance on the hardest setting and matching or surpassing prior methods in sample efficiency across all evaluated tasks. Project Page: https://segdac.github.io/
Authors: Vincenzo Polizzi, Stephen Yang, Quentin Clark, Jonathan Kelly, Igor Gilitschenski, David B. Lindell
Abstract: Event cameras are a bio-inspired class of sensors that asynchronously measure per-pixel intensity changes. Under fixed illumination conditions in static or low-motion scenes, rigidly mounted event cameras are unable to generate any events and become unsuitable for most computer vision tasks. To address this limitation, recent work has investigated motion-induced event stimulation, which often requires complex hardware or additional optical components. In contrast, we introduce a lightweight approach to sustain persistent event generation by employing a simple rotating unbalanced mass to induce periodic vibrational motion. This is combined with a motion-compensation pipeline that removes the injected motion and yields clean, motion-corrected events for downstream perception tasks. We develop a hardware prototype to demonstrate our approach and evaluate it on real-world datasets. Our method reliably recovers motion parameters and improves both image reconstruction and edge detection compared to event-based sensing without motion induction.
Authors: Che Liu, Yinda Chen, Haoyuan Shi, Jinpeng Lu, Bailiang Jian, Jiazhen Pan, Linghan Cai, Jiayi Wang, Jieming Yu, Ziqi Gao, Xiaoran Zhang, Long Bai, Yundi Zhang, Jun Li, Cosmin I. Bercea, Cheng Ouyang, Chen Chen, Zhiwei Xiong, Benedikt Wiestler, Christian Wachinger, James S. Duncan, Daniel Rueckert, Wenjia Bai, Rossella Arcucci
Abstract: The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.
Authors: Diego Eustachio Farchione, Ramzi Idoughi, Peter Wonka
Abstract: Accurate estimation of object volume and surface area from visual data is an open challenge with broad implications across various domains. We propose a unified framework that predicts volumetric and surface metrics directly from a set of 2D multi-view images. Our approach first generates a point cloud from the captured multi-view images using recent 3D reconstruction techniques, while a parallel 2D encoder aggregates view-aligned features. A fusion module then aligns and merges 3D geometry with 2D visual embeddings, followed by a graph-based decoder that regresses volume, surface area, and their corresponding uncertainties. This proposed architecture maintains robustness against sparse or noisy data. We evaluate the framework across multiple application domains: corals, where precise geometric measurements support growth monitoring; food items, where volume prediction relates to dietary tracking and portion analysis; and human bodies, where volumetric cues are crucial for anthropometric and medical applications. Experimental results demonstrate the reliable performance of our framework across diverse scenarios, highlighting its versatility and adaptability. Furthermore, by coupling 3D reconstruction with neural regression and 2D features, our model provides a scalable and fast solution for quantitative shape analysis from visual data.
Authors: Shubhashis Roy Dipta, Tz-Ying Wu, Subarna Tripathi
Abstract: We propose VC-Inspector, a lightweight, open-source large multimodal model (LMM) for reference-free evaluation of video captions, with a focus on factual accuracy. Unlike existing metrics that suffer from limited context handling, weak factuality assessment, or reliance on proprietary services, VC-Inspector offers a reproducible, fact-aware alternative that aligns closely with human judgments. To enable robust training and interpretable evaluation, we introduce a systematic approach for generating captions with controllable errors, paired with graded quality scores and explanatory annotations. Experiments show that VC-Inspector achieves state-of-the-art correlation with human judgments, generalizing across diverse domains (e.g., VATEX-Eval, Flickr8K-Expert, and Flickr8K-CF benchmarks) and revealing the potential for caption improvement.
Authors: Xin Lei Lin, Soroush Mehraban, Abhishek Moturu, Babak Taati
Abstract: Automated pain assessment from facial expressions is crucial for non-communicative patients, such as those with dementia. Progress has been limited by two challenges: (i) existing datasets exhibit severe demographic and label imbalance due to ethical constraints, and (ii) current generative models cannot precisely control facial action units (AUs), facial structure, or clinically validated pain levels. We present 3DPain, a large-scale synthetic dataset specifically designed for automated pain assessment, featuring unprecedented annotation richness and demographic diversity. Our three-stage framework generates diverse 3D meshes, textures them with diffusion models, and applies AU-driven face rigging to synthesize multi-view faces with paired neutral and pain images, AU configurations, PSPI scores, and the first dataset-level annotations of pain-region heatmaps. The dataset comprises 82,500 samples across 25,000 pain expression heatmaps and 2,500 synthetic identities balanced by age, gender, and ethnicity. We further introduce ViTPain, a Vision Transformer based cross-modal distillation framework in which a heatmap-trained teacher guides a student trained on RGB images, enhancing accuracy, interpretability, and clinical reliability. Together, 3DPain and ViTPain establish a controllable, diverse, and clinically grounded foundation for generalizable automated pain assessment.
Authors: Lavish Ramchandani, Gunjan Deotale, Dev Kumar Das
Abstract: Atypical mitotic figures (AMFs) are rare abnormal cell divisions associated with tumor aggressiveness and poor prognosis. Their detection remains a significant challenge due to subtle morphological cues, class imbalance, and inter-observer variability among pathologists. The MIDOG 2025 challenge introduced a dedicated track for atypical mitosis classification, enabling systematic evaluation of deep learning methods. In this study, we investigated the use of large vision foundation models, including Virchow, Virchow2, and UNI, with Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We conducted extensive experiments with different LoRA ranks, as well as random and group-based data splits, to analyze robustness under varied conditions. Our best approach, Virchow with LoRA rank 8 and ensemble of three-fold cross-validation, achieved a balanced accuracy of 88.37% on the preliminary test set, ranking joint 9th in the challenge leaderboard. These results highlight the promise of foundation models with efficient adaptation strategies for the classification of atypical mitosis, while underscoring the need for improvements in specificity and domain generalization.
Authors: Yu Li, Da Chang, Xi Xiao
Abstract: While the Segment Anything Model (SAM) has achieved remarkable success in image segmentation, its direct application to medical imaging remains hindered by fundamental challenges, including ambiguous boundaries, insufficient modeling of anatomical relationships, and the absence of uncertainty quantification. To address these limitations, we introduce KG-SAM, a knowledge-guided framework that synergistically integrates anatomical priors with boundary refinement and uncertainty estimation. Specifically, KG-SAM incorporates (i) a medical knowledge graph to encode fine-grained anatomical relationships, (ii) an energy-based Conditional Random Field (CRF) to enforce anatomically consistent predictions, and (iii) an uncertainty-aware fusion module to enhance reliability in high-stakes clinical scenarios. Extensive experiments across multi-center medical datasets demonstrate the effectiveness of our approach: KG-SAM achieves an average Dice score of 82.69% on prostate segmentation and delivers substantial gains in abdominal segmentation, reaching 78.05% on MRI and 79.68% on CT. These results establish KG-SAM as a robust and generalizable framework for advancing medical image segmentation.
Authors: Odin Kohler, Rahul Vijaykumar, Masudul H. Imtiaz
Abstract: With recent advancements in deepfake technology, it is now possible to generate convincing deepfakes in real-time. Unfortunately, malicious actors have started to use this new technology to perform real-time phishing attacks during video meetings. The nature of a video call allows access to what the deepfake is ``seeing,'' that is, the screen displayed to the malicious actor. Using this with the estimated gaze from the malicious actors streamed video enables us to estimate where the deepfake is looking on screen, the point of gaze. Because the point of gaze during conversations is not random and is instead used as a subtle nonverbal communicator, it can be used to detect deepfakes, which are not capable of mimicking this subtle nonverbal communication. This paper proposes a real-time deepfake detection method adapted to this genre of attack, utilizing previously unavailable biometric information. We built our model based on explainable features selected after careful review of research on gaze patterns during dyadic conversations. We then test our model on a novel dataset of our creation, achieving an accuracy of 82\%. This is the first reported method to utilize point-of-gaze tracking for deepfake detection.
Authors: Alec K. Peltekian, Halil Ertugrul Aktas, Gorkem Durak, Kevin Grudzinski, Bradford C. Bemiss, Carrie Richardson, Jane E. Dematte, G. R. Scott Budinger, Anthony J. Esposito, Alexander Misharin, Alok Choudhary, Ankit Agrawal, Ulas Bagci
Abstract: Mixture-of-Experts (MoE) architectures have significantly contributed to scalable machine learning by enabling specialized subnetworks to tackle complex tasks efficiently. However, traditional MoE systems lack domain-specific constraints essential for medical imaging, where anatomical structure and regional disease heterogeneity strongly influence pathological patterns. Here, we introduce \textit{Regional Expert Networks (REN)}, the first anatomically-informed MoE framework tailored specifically for medical image classification. REN leverages anatomical priors to train seven specialized experts, each dedicated to distinct lung lobes and bilateral lung combinations, enabling precise modeling of region-specific pathological variations. Multi-modal gating mechanisms dynamically integrate radiomics biomarkers and deep learning (DL) features (CNN, ViT, Mamba) to weight expert contributions optimally. Applied to interstitial lung disease (ILD) classification, REN achieves consistently superior performance: the radiomics-guided ensemble reached an average AUC of 0.8646 +- 0.0467, a +12.5\% improvement over the SwinUNETR baseline (AUC 0.7685, p=0.031). Region-specific experts further revealed that lower-lobe models achieved AUCs of 0.88-0.90, surpassing DL counterparts (CNN: 0.76-0.79) and aligning with known disease progression patterns. Through rigorous patient-level cross-validation, REN demonstrates strong generalizability and clinical interpretability, presenting a scalable, anatomically-guided approach readily extensible to other structured medical imaging applications. Code is available on our GitHub: https://github.com/NUBagciLab/MoE-REN.
Authors: Jinxuan Li, Chaolei Tan, Haoxuan Chen, Jianxin Ma, Jian-Fang Hu, Wei-Shi Zheng, Jianhuang Lai
Abstract: Image-Language Foundation Models (ILFMs) have demonstrated remarkable success in vision-language understanding, providing transferable multimodal representations that generalize across diverse downstream image-based tasks. The advancement of video-text research has spurred growing interest in extending image-based models to the video domain. This paradigm, termed as image-to-video transfer learning, effectively mitigates the substantial data and computational demands compared to training video-language models from scratch while achieves comparable or even stronger model performance. This survey provides the first comprehensive review of this emerging field, which begins by summarizing the widely used ILFMs and their capabilities. We then systematically classify existing image-to-video transfer learning techniques into two broad root categories (frozen features and adapted features), along with numerous fine-grained subcategories, based on the paradigm for transferring image understanding capability to video tasks. Building upon the task-specific nature of image-to-video transfer, this survey methodically elaborates these strategies and details their applications across a spectrum of video-text learning tasks, ranging from fine-grained settings (e.g., spatio-temporal video grounding) to coarse-grained ones (e.g., video question answering). We further present a detailed experimental analysis to investigate the efficacy of different image-to-video transfer learning paradigms on a range of downstream video understanding tasks. Finally, we identify prevailing challenges and highlight promising directions for future research. By offering a comprehensive and structured overview, this survey aims to establish a structured roadmap for advancing video-text learning based on existing ILFM, and to inspire future research directions in this rapidly evolving domain. Github repository is available.
Authors: Daniele L. V. dos Santos, Thiago B. Pereira, Carlos Eduardo G. R. Alves, Richard J. M. G. Tello, Francisco de A. Boldt, Thiago M. Paix\~ao
Abstract: This paper investigates the feasibility of using lightweight body landmark detection for the recognition of isolated signs in Brazilian Sign Language (LIBRAS). Although the skeleton-based approach by Alves et al. (2024) enabled substantial improvements in recognition performance, the use of OpenPose for landmark extraction hindered time performance. In a preliminary investigation, we observed that simply replacing OpenPose with the lightweight MediaPipe, while improving processing speed, significantly reduced accuracy. To overcome this limitation, we explored landmark subset selection strategies aimed at optimizing recognition performance. Experimental results showed that a proper landmark subset achieves comparable or superior performance to state-of-the-art methods while reducing processing time by more than 5X compared to Alves et al. (2024). As an additional contribution, we demonstrated that spline-based imputation effectively mitigates missing landmark issues, leading to substantial accuracy gains. These findings highlight that careful landmark selection, combined with simple imputation techniques, enables efficient and accurate isolated sign recognition, paving the way for scalable Sign Language Recognition systems.
Authors: Fahimeh Orvati Nia, Amirmohammad Mohammadi, Salim Al Kharsa, Pragati Naikare, Zigfried Hampel-Arias, Joshua Peeples
Abstract: In this work, we introduce Neighborhood Feature Pooling (NFP), a novel pooling layer designed to enhance texture-aware representation learning for remote sensing image classification. The proposed NFP layer captures relationships between neighboring spatial features by aggregating local similarity patterns across feature dimensions. Implemented using standard convolutional operations, NFP can be seamlessly integrated into existing neural network architectures with minimal additional parameters. Extensive experiments across multiple benchmark datasets and backbone models demonstrate that NFP consistently improves classification performance compared to conventional pooling strategies, while maintaining computational efficiency. These results highlight the effectiveness of neighborhood-based feature aggregation for capturing discriminative texture information in remote sensing imagery.
Authors: Yang Miao, Jan-Nico Zaech, Xi Wang, Fabien Despinoy, Danda Pani Paudel, Luc Van Gool
Abstract: We propose LangHOPS, the first Multimodal Large Language Model (MLLM) based framework for open-vocabulary object-part instance segmentation. Given an image, LangHOPS can jointly detect and segment hierarchical object and part instances from open-vocabulary candidate categories. Unlike prior approaches that rely on heuristic or learnable visual grouping, our approach grounds object-part hierarchies in language space. It integrates the MLLM into the object-part parsing pipeline to leverage its rich knowledge and reasoning capabilities, and link multi-granularity concepts within the hierarchies. We evaluate LangHOPS across multiple challenging scenarios, including in-domain and cross-dataset object-part instance segmentation, and zero-shot semantic segmentation. LangHOPS achieves state-of-the-art results, surpassing previous methods by 5.5% Average Precision (AP) (in-domain) and 4.8% (cross-dataset) on the PartImageNet dataset and by 2.5% mIOU on unseen object parts in ADE20K (zero-shot). Ablation studies further validate the effectiveness of the language-grounded hierarchy and MLLM driven part query refinement strategy. The code will be released here.
Authors: Yuhao Shen, Jiahe Qian, Shuping Zhang, Zhangtianyi Chen, Tao Lu, Juexiao Zhou
Abstract: Multimodal large language models (LLMs) are increasingly used to generate dermatology diagnostic narratives directly from images. However, reliable evaluation remains the primary bottleneck for responsible clinical deployment. We introduce a novel evaluation framework that combines DermBench, a meticulously curated benchmark, with DermEval, a robust automatic evaluator, to enable clinically meaningful, reproducible, and scalable assessment. We build DermBench, which pairs 4,000 real-world dermatology images with expert-certified diagnostic narratives and uses an LLM-based judge to score candidate narratives across clinically grounded dimensions, enabling consistent and comprehensive evaluation of multimodal models. For individual case assessment, we train DermEval, a reference-free multimodal evaluator. Given an image and a generated narrative, DermEval produces a structured critique along with an overall score and per-dimension ratings. This capability enables fine-grained, per-case analysis, which is critical for identifying model limitations and biases. Experiments on a diverse dataset of 4,500 cases demonstrate that DermBench and DermEval achieve close alignment with expert ratings, with mean deviations of 0.251 and 0.117 (out of 5), respectively, providing reliable measurement of diagnostic ability and trustworthiness across different multimodal LLMs.
Authors: Pooja P Jain, Pietro Mascagni, Giuseppe Massimiani, Nabani Banik, Marta Goglia, Lorenzo Arboit, Britty Baby, Andrea Balla, Ludovica Baldari, Gianfranco Silecchia, Claudio Fiorillo, CompSurg Colorectal Experts Group, Sergio Alfieri, Salvador Morales-Conde, Deborah S Keller, Luigi Boni, Nicolas Padoy
Abstract: Minimally invasive colorectal surgery is characterized by procedural variability, a difficult learning curve, and complications that impact quality and outcomes. Video-based assessment (VBA) offers an opportunity to generate data-driven insights to reduce variability, optimize training, and improve surgical performance. However, existing tools for workflow analysis remain difficult to standardize and implement. This study aims to develop and validate a VBA tool for workflow analysis across minimally invasive colorectal procedures. A Delphi process was conducted to achieve consensus on generalizable workflow descriptors. The resulting framework informed the development of a new VBA tool, ColoWorkflow. Independent raters then applied ColoWorkflow to a multicentre video dataset of laparoscopic and robotic colorectal surgery (CRS). Applicability and inter-rater reliability were evaluated. Consensus was achieved for 10 procedure-agnostic phases and 34 procedure-specific steps describing CRS workflows. ColoWorkflow was developed and applied to 54 colorectal operative videos (left and right hemicolectomies, sigmoid and rectosigmoid resections, and total proctocolectomies) from five centres. The tool demonstrated broad applicability, with all but one label utilized. Inter-rater reliability was moderate, with mean Cohen's K of 0.71 for phases and 0.66 for steps. Most discrepancies arose at phase transitions and step boundary definitions. ColoWorkflow is the first consensus-based, validated VBA tool for comprehensive workflow analysis in minimally invasive CRS. It establishes a reproducible framework for video-based performance assessment, enabling benchmarking across institutions and supporting the development of artificial intelligence-driven workflow recognition. Its adoption may standardize training, accelerate competency acquisition, and advance data-informed surgical quality improvement.
Authors: Rong Zhang, Jinxiao Li, Jingnan Wang, Zhiwen Zuo, Jianfeng Dong, Wei Li, Chi Wang, Weiwei Xu, Xun Wang
Abstract: Garment-centric fashion image generation aims to synthesize realistic and controllable human models dressing a given garment, which has attracted growing interest due to its practical applications in e-commerce. The key challenges of the task lie in two aspects: (1) faithfully preserving the garment details, and (2) gaining fine-grained controllability over the model's appearance. Existing methods typically require performing garment deformation in the generation process, which often leads to garment texture distortions. Also, they fail to control the fine-grained attributes of the generated models, due to the lack of specifically designed mechanisms. To address these issues, we propose FashionMAC, a novel diffusion-based deformation-free framework that achieves high-quality and controllable fashion showcase image generation. The core idea of our framework is to eliminate the need for performing garment deformation and directly outpaint the garment segmented from a dressed person, which enables faithful preservation of the intricate garment details. Moreover, we propose a novel region-adaptive decoupled attention (RADA) mechanism along with a chained mask injection strategy to achieve fine-grained appearance controllability over the synthesized human models. Specifically, RADA adaptively predicts the generated regions for each fine-grained text attribute and enforces the text attribute to focus on the predicted regions by a chained mask injection strategy, significantly enhancing the visual fidelity and the controllability. Extensive experiments validate the superior performance of our framework compared to existing state-of-the-art methods.
Authors: Junming Liu, Yifei Sun, Weihua Cheng, Yujin Kang, Yirong Chen, Ding Wang, Guosun Zeng
Abstract: Magnetic Resonance Imaging (MRI) plays a crucial role in brain disease diagnosis, but it is not always feasible for certain patients due to physical or clinical constraints. Recent studies attempt to synthesize MRI from Computed Tomography (CT) scans; however, low-dose protocols often result in highly sparse CT volumes with poor through-plane resolution, making accurate reconstruction of the full brain MRI volume particularly challenging. To address this, we propose ReBrain, a retrieval-augmented diffusion framework for brain MRI reconstruction. Given any 3D CT scan with limited slices, we first employ a Brownian Bridge Diffusion Model (BBDM) to synthesize MRI slices along the 2D dimension. Simultaneously, we retrieve structurally and pathologically similar CT slices from a comprehensive prior database via a fine-tuned retrieval model. These retrieved slices are used as references, incorporated through a ControlNet branch to guide the generation of intermediate MRI slices and ensure structural continuity. We further account for rare retrieval failures when the database lacks suitable references and apply spherical linear interpolation to provide supplementary guidance. Extensive experiments on SynthRAD2023 and BraTS demonstrate that ReBrain achieves state-of-the-art performance in cross-modal reconstruction under sparse conditions.
Authors: Ryoma Yataka, Pu Perry Wang, Petros Boufounos, Ryuhei Takahashi
Abstract: Multi-view indoor radar perception has drawn attention due to its cost-effectiveness and low privacy risks. Existing methods often rely on {implicit} cross-view radar feature association, such as proposal pairing in RFMask or query-to-feature cross-attention in RETR, which can lead to ambiguous feature matches and degraded detection in complex indoor scenes. To address these limitations, we propose \textbf{REXO} (multi-view Radar object dEtection with 3D bounding boX diffusiOn), which lifts the 2D bounding box (BBox) diffusion process of DiffusionDet into the 3D radar space. REXO utilizes these noisy 3D BBoxes to guide an {explicit} cross-view radar feature association, enhancing the cross-view radar-conditioned denoising process. By accounting for prior knowledge that the person is in contact with the ground, REXO reduces the number of diffusion parameters by determining them from this prior. Evaluated on two open indoor radar datasets, our approach surpasses state-of-the-art methods by a margin of +4.22 AP on the HIBER dataset and +11.02 AP on the MMVR dataset. The REXO implementation is available at https://github.com/merlresearch/radar-bbox-diffusion.
Authors: Kuan Wei Huang, Brandon Li, Bharath Hariharan, Noah Snavely
Abstract: Geometric models like DUSt3R have shown great advances in understanding the geometry of a scene from pairs of photos. However, they fail when the inputs are from vastly different viewpoints (e.g., aerial vs. ground) or modalities (e.g., photos vs. abstract drawings) compared to what was observed during training. This paper addresses a challenging version of this problem: predicting correspondences between ground-level photos and floor plans. Current datasets for joint photo-floor plan reasoning are limited, either lacking in varying modalities (VIGOR) or lacking in correspondences (WAFFLE). To address these limitations, we introduce a new dataset, C3, created by first reconstructing a number of scenes in 3D from Internet photo collections via structure-from-motion, then manually registering the reconstructions to floor plans gathered from the Internet, from which we can derive correspondences between images and floor plans. C3 contains 90K paired floor plans and photos across 597 scenes with 153M pixel-level correspondences and 85K camera poses. We find that state-of-the-art correspondence models struggle on this task. By training on our new data, we can improve on the best performing method by 34% in RMSE. We also use the predicted correspondences to estimate camera poses and evaluate performance using recall metrics. Lastly, we identify open challenges in cross-modal geometric reasoning that our dataset aims to help address.
Authors: Yongqi Zhu, Morui Zhu, Qi Chen, Deyuan Qu, Isabella Luo, Song Fu, Qing Yang
Abstract: We present RefPtsFusion, a lightweight and interpretable framework for cooperative autonomous driving. Instead of sharing large feature maps or query embeddings, vehicles exchange compact reference points, e.g., objects' positions, velocities, and size information. This approach shifts the focus from "what is seen" to "where to see", creating a sensor- and model-independent interface that works well across vehicles with heterogeneous perception models while greatly reducing communication bandwidth. To enhance the richness of shared information, we further develop a selective Top-K query fusion that selectively adds high-confidence queries from the sender. It thus achieves a strong balance between accuracy and communication cost. Experiments on the M3CAD dataset show that RefPtsFusion maintains stable perception performance while reducing communication overhead by five orders of magnitude, dropping from hundreds of MB/s to only a few KB/s at 5 FPS (frame per second), compared to traditional feature-level fusion methods. Extensive experiments also demonstrate RefPtsFusion's strong robustness and consistent transmission behavior, highlighting its potential for scalable, real-time cooperative driving systems.
Authors: Gil Goldman, Raja Giryes, Mahadev Satyanarayanan
Abstract: We propose a smooth regularization technique that instills a strong temporal inductive bias in video recognition models, particularly benefiting lightweight architectures. Our method encourages smoothness in the intermediate-layer embeddings of consecutive frames by modeling their changes as a Gaussian Random Walk (GRW). This penalizes abrupt representational shifts, thereby promoting low-acceleration solutions that better align with the natural temporal coherence inherent in videos. By leveraging this enforced smoothness, lightweight models can more effectively capture complex temporal dynamics. Applied to such models, our technique yields a 3.8% to 6.4% accuracy improvement on Kinetics-600. Notably, the MoViNets model family trained with our smooth regularization improves the current state of the art by 3.8% to 6.1% within their respective FLOP constraints, while MobileNetV3 and the MoViNets-Stream family achieve gains of 4.9% to 6.4% over prior state-of-the-art models with comparable memory footprints. Our code and models are available at https://github.com/cmusatyalab/grw-smoothing.
Authors: Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu Zhang
Abstract: Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at https://github.com/Woof6/ECOCSeg.
Authors: Alexander Goslin
Abstract: For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. We introduce Terrain Diffusion, a generative framework that bridges the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. At its core is InfiniteDiffusion, a novel algorithm for infinite generation that reformulates standard diffusion sampling for unbounded domains. While noise functions remain near-instant, our framework outpaces orbital velocity by 9 times on a consumer GPU, enabling realistic terrain generation at interactive rates. We integrate a hierarchical stack of diffusion models to couple planetary context with local detail, a compact Laplacian encoding to stabilize outputs across Earth-scale dynamic ranges, and an open-source infinite-tensor framework for constant-memory manipulation of unbounded tensors. Together, these components position diffusion models as a practical, scalable foundation for the next generation of infinite virtual worlds.
Authors: Zizhang Li, Cheng Zhang, Zhengqin Li, Henry Howard-Jenkins, Zhaoyang Lv, Chen Geng, Jiajun Wu, Richard Newcombe, Jakob Engel, Zhao Dong
Abstract: We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state RGB images. Previous methods for articulated object reconstruction either rely on slow optimization with fragile cross-state correspondences or use feed-forward models limited to specific object categories. In contrast, ART treats articulated objects as assemblies of rigid parts, formulating reconstruction as part-based prediction. Our newly designed transformer architecture maps sparse image inputs to a set of learnable part slots, from which ART jointly decodes unified representations for individual parts, including their 3D geometry, texture, and explicit articulation parameters. The resulting reconstructions are physically interpretable and readily exportable for simulation. Trained on a large-scale, diverse dataset with per-part supervision, and evaluated across diverse benchmarks, ART achieves significant improvements over existing baselines and establishes a new state of the art for articulated object reconstruction from image inputs.
Authors: Ditmar Hadera, Jan Cech, Miroslav Purkrabek, Matej Hoffmann
Abstract: Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consisTency), a novel approach designed to anonymize infant faces in video recordings while preserving essential facial attributes. Our method comprises two stages. First, a new random face, compatible with the original identity, is generated via inpainting using a diffusion model. Second, the new identity is seamlessly incorporated into each video frame through temporally consistent face swapping with authentic expression transfer. The method is evaluated on a dataset of short video recordings of babies and is compared to the popular anonymization method, DeepPrivacy2. Key metrics assessed include the level of de-identification, preservation of facial attributes, impact on human pose estimation (as an example of a downstream task), and presence of artifacts. Both methods alter the identity, and our method outperforms DeepPrivacy2 in all other respects. The code is available as an easy-to-use anonymization demo at https://github.com/ctu-vras/blanket-infant-face-anonym.
URLs: https://github.com/ctu-vras/blanket-infant-face-anonym.
Authors: Zehui Lin, Luyi Han, Xin Wang, Ying Zhou, Yanming Zhang, Tianyu Zhang, Lingyun Bao, Jiarui Zhou, Yue Sun, Jieyun Bai, Shuo Li, Shandong Wu, Dong Ni, Ritse Mann, Wendie Berg, Dong Xu, Tao Tan, the UUSIC25 Challenge Consortium
Abstract: IMPORTANCE: Modern ultrasound systems are universal diagnostic tools capable of imaging the entire body. However, current AI solutions remain fragmented into single-task tools. This critical gap between hardware versatility and software specificity limits workflow integration and clinical utility. OBJECTIVE: To evaluate the diagnostic accuracy, versatility, and efficiency of single general-purpose deep learning models for multi-organ classification and segmentation. DESIGN: The Universal UltraSound Image Challenge 2025 (UUSIC25) involved developing algorithms on 11,644 images aggregated from 12 sources (9 public, 3 private). Evaluation used an independent, multi-center private test set of 2,479 images, including data from a center completely unseen during training to assess generalization. OUTCOMES: Diagnostic performance (Dice Similarity Coefficient [DSC]; Area Under the Receiver Operating Characteristic Curve [AUC]) and computational efficiency (inference time, GPU memory). RESULTS: Of 15 valid algorithms, the top model (SMART) achieved a macro-averaged DSC of 0.854 across 5 segmentation tasks and AUC of 0.766 for binary classification. Models demonstrated high capability in anatomical segmentation (e.g., fetal head DSC: 0.942) but variability in complex diagnostic tasks subject to domain shift. Specifically, in breast cancer molecular subtyping, the top model's performance dropped from an AUC of 0.571 (internal) to 0.508 (unseen external center), highlighting the challenge of generalization. CONCLUSIONS: General-purpose AI models can achieve high accuracy and efficiency across multiple tasks using a single architecture. However, significant performance degradation on unseen data suggests domain generalization is critical for future clinical deployment.
Authors: Kaijie Chen, Zhiyang Xu, Ying Shen, Zihao Lin, Yuguang Yao, Lifu Huang
Abstract: Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt group sizes ignore variation in sampling importance across prompts, which leads to inefficient sampling and slower training; and (ii) trajectory-level advantages are reused as per-step estimates, which biases credit assignment along the flow. We propose SuperFlow, an RL training framework for flow-based models that adjusts group sizes with variance-aware sampling and computes step-level advantages in a way that is consistent with continuous-time flow dynamics. Empirically, SuperFlow reaches promising performance while using only 5.4% to 56.3% of the original training steps and reduces training time by 5.2% to 16.7% without any architectural changes. On standard text-to-image (T2I) tasks, including text rendering, compositional image generation, and human preference alignment, SuperFlow improves over SD3.5-M by 4.6% to 47.2%, and over Flow-GRPO by 1.7% to 16.0%.
Authors: Chunyuan Chen, Yunuo Cai, Shujuan Li, Weiyun Liang, Bin Wang, Jing Xu
Abstract: Camouflaged image generation (CIG) has recently emerged as an efficient alternative for acquiring high-quality training data for camouflaged object detection (COD). However, existing CIG methods still suffer from a substantial gap to real camouflaged imagery: generated images either lack sufficient camouflage due to weak visual similarity, or exhibit cluttered backgrounds that are semantically inconsistent with foreground targets. To address these limitations, we propose RealCamo, a novel out-painting-based framework for controllable realistic camouflaged image generation. RealCamo explicitly introduces additional layout controls to regulate global image structure, thereby improving semantic coherence between foreground objects and generated backgrounds. Moreover, we construct a multimodal textual-visual condition by combining a unified fine-grained textual task description with texture-oriented background retrieval, which jointly guides the generation process to enhance visual fidelity and realism. To quantitatively assess camouflage quality, we further introduce a background-foreground distribution divergence metric that measures the effectiveness of camouflage in generated images. Extensive experiments and visualizations demonstrate the effectiveness of our proposed framework.
Authors: Yi Zhou, Xuechao Zou, Shun Zhang, Kai Li, Shiying Wang, Jingming Chen, Congyan Lang, Tengfei Cao, Pin Tao, Yuanchun Shi
Abstract: Semi-supervised remote sensing (RS) image semantic segmentation offers a promising solution to alleviate the burden of exhaustive annotation, yet it fundamentally struggles with pseudo-label drift, a phenomenon where confirmation bias leads to the accumulation of errors during training. In this work, we propose Co2S, a stable semi-supervised RS segmentation framework that synergistically fuses priors from vision-language models and self-supervised models. Specifically, we construct a heterogeneous dual-student architecture comprising two distinct ViT-based vision foundation models initialized with pretrained CLIP and DINOv3 to mitigate error accumulation and pseudo-label drift. To effectively incorporate these distinct priors, an explicit-implicit semantic co-guidance mechanism is introduced that utilizes text embeddings and learnable queries to provide explicit and implicit class-level guidance, respectively, thereby jointly enhancing semantic consistency. Furthermore, a global-local feature collaborative fusion strategy is developed to effectively fuse the global contextual information captured by CLIP with the local details produced by DINOv3, enabling the model to generate highly precise segmentation results. Extensive experiments on six popular datasets demonstrate the superiority of the proposed method, which consistently achieves leading performance across various partition protocols and diverse scenarios. Project page is available at https://xavierjiezou.github.io/Co2S/.
Authors: Tianchen Deng, Xuefeng Chen, Yi Chen, Qu Chen, Yuyao Xu, Lijin Yang, Le Xu, Yu Zhang, Bo Zhang, Wuxiong Huang, Hesheng Wang
Abstract: Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover, current approaches represent 3D spatial information with point cloud or BEV features do not accurately align textual information with the underlying 3D scene. To address these limitations, we propose a novel unified DWM framework based on 3D Gaussian scene representation, which enables both 3D scene understanding and multi-modal scene generation, while also enabling contextual enrichment for understanding and generation tasks. Our approach directly aligns textual information with the 3D scene by embedding rich linguistic features into each Gaussian primitive, thereby achieving early modality alignment. In addition, we design a novel task-aware language-guided sampling strategy that removes redundant 3D Gaussians and injects accurate and compact 3D tokens into LLM. Furthermore, we design a dual-condition multi-modal generation model, where the information captured by our vision-language model is leveraged as a high-level language condition in combination with a low-level image condition, jointly guiding the multi-modal generation process. We conduct comprehensive studies on the nuScenes, and NuInteract datasets to validate the effectiveness of our framework. Our method achieves state-of-the-art performance. We will release the code publicly on GitHub https://github.com/dtc111111/GaussianDWM.
Authors: Dongsheng Li, Tianli Ma, Siling Wang, Beibei Duan, Song Gao
Abstract: Detecting infrared gas leaks is critical for environmental monitoring and industrial safety, yet remains difficult because plumes are faint, small, semitransparent, and have weak, diffuse boundaries. We present physics-edge hybrid gas dynamic routing network (PEG-DRNet). First, we introduce the Gas Block, a diffusion-convection unit modeling gas transport: a local branch captures short-range variations, while a large-kernel branch captures long-range propagation. An edge-gated learnable fusion module balances local detail and global context, strengthening weak-contrast plume and contour cues. Second, we propose the adaptive gradient and phase edge operator (AGPEO), computing reliable edge priors from multi-directional gradients and phase-consistent responses. These are transformed by a multi-scale edge perception module (MSEPM) into hierarchical edge features that reinforce boundaries. Finally, the content-adaptive sparse routing path aggregation network (CASR-PAN), with adaptive information modulation modules for fusion and self, selectively propagates informative features across scales based on edge and content cues, improving cross-scale discriminability while reducing redundancy. Experiments on the IIG dataset show that PEG-DRNet achieves an overall AP of 29.8\%, an AP$_{50}$ of 84.3\%, and a small-object AP of 25.3\%, surpassing the RT-DETR-R18 baseline by 3.0\%, 6.5\%, and 5.3\%, respectively, while requiring only 43.7 Gflops and 14.9 M parameters. The proposed PEG-DRNet achieves superior overall performance with the best balance of accuracy and computational efficiency, outperforming existing CNN and Transformer detectors in AP and AP$_{50}$ on the IIG and LangGas dataset.
Authors: Mustafa Demetgul, Sanja Lazarova Molnar
Abstract: Monitoring states of road surfaces provides valuable information for the planning and controlling vehicles and active vehicle control systems. Classical road monitoring methods are expensive and unsystematic because they require time for measurements. This article proposes an real time system based on weather conditional data and road surface condition data. For this purpose, we collected data with a mobile phone camera on the roads around the campus of the Karlsruhe Institute of Technology. We tested a large number of different image-based deep learning algorithms for road classification. In addition, we used road acceleration data along with road image data for training by using them as images. We compared the performances of acceleration-based and camera image-based approaches. The performances of the simple Alexnet, LeNet, VGG, and Resnet algorithms were compared as deep learning algorithms. For road condition classification, 5 classes were considered: asphalt, damaged asphalt, gravel road, damaged gravel road, pavement road and over 95% accuracy performance was achieved. It is also proposed to use the acceleration or the camera image to classify the road surface according to the weather and the time of day using fuzzy logic.
Authors: TsaiChing Ni, ZhenQi Chen, YuanFu Yang
Abstract: We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution real-world defects spanning over 60 material categories and more than 400 defect types, each accompanied by expert-verified annotations and fine-grained textual descriptions detailing defect location, severity, and contextual attributes. This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling. Building upon IMDD-1M, we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios. The model serves as a generalizable foundation that can be efficiently adapted to specialized domains through lightweight fine-tuning. With less than 5% of the task-specific data required by dedicated expert models, it achieves comparable performance, highlighting the potential of data-efficient foundation model adaptation for industrial inspection and generation, paving the way for scalable, domain-adaptive, and knowledge-grounded manufacturing intelligence. Additional details and resources can be found in this URL: https://ninaneon.github.io/projectpage/
Authors: Duoxun Tang, Xueyi Zhang, Chak Hin Wang, Xi Xiao, Dasen Dai, Xinhang Jiang, Wentao Shi, Rui Li, Qing Li
Abstract: Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Directly regressing clean videos from adversarial inputs often fails to recover faithful content due to the subtle nature of perturbations; this necessitates physically shattering the adversarial structure. Therefore, we propose Flow Matching for Adversarial Video Purification FMVP. FMVP physically shatters global adversarial structures via a masking strategy and reconstructs clean video dynamics using Conditional Flow Matching (CFM) with an inpainting objective. To further decouple semantic content from adversarial noise, we design a Frequency-Gated Loss (FGL) that explicitly suppresses high-frequency adversarial residuals while preserving low-frequency fidelity. We design Attack-Aware and Generalist training paradigms to handle known and unknown threats, respectively. Extensive experiments on UCF-101 and HMDB-51 demonstrate that FMVP outperforms state-of-the-art methods (DiffPure, Defense Patterns (DP), Temporal Shuffling (TS) and FlowPure), achieving robust accuracy exceeding 87% against PGD and 89% against CW attacks. Furthermore, FMVP demonstrates superior robustness against adaptive attacks (DiffHammer) and functions as a zero-shot adversarial detector, attaining AUC-ROC scores of 0.98 for PGD and 0.79 for highly imperceptible CW attacks.
Authors: Ali Kashefi
Abstract: We present two novel generative geometric deep learning frameworks, termed Flow Matching PointNet and Diffusion PointNet, for predicting fluid flow variables on irregular geometries by incorporating PointNet into flow matching and diffusion models, respectively. In these frameworks, a reverse generative process reconstructs physical fields from standard Gaussian noise conditioned on unseen geometries. The proposed approaches operate directly on point-cloud representations of computational domains (e.g., grid vertices of finite-volume meshes) and therefore avoid the limitations of pixelation used to project geometries onto uniform lattices, as is common in U-Net-based flow matching and diffusion models. In contrast to graph neural network-based diffusion models, Flow Matching PointNet and Diffusion PointNet do not exhibit high-frequency noise artifacts in the predicted fields. Moreover, unlike such approaches, which require auxiliary intermediate networks to condition geometry, the proposed frameworks rely solely on PointNet, resulting in a simple and unified architecture. The performance of the proposed frameworks is evaluated on steady incompressible flow past a cylinder, using a geometric dataset constructed by varying the cylinder's cross-sectional shape and orientation across samples. The results demonstrate that Flow Matching PointNet and Diffusion PointNet achieve more accurate predictions of velocity and pressure fields, as well as lift and drag forces, and exhibit greater robustness to incomplete geometries compared to a vanilla PointNet with the same number of trainable parameters.
Authors: Babak Asadi, Peiyang Wu, Mani Golparvar-Fard, Ramez Hajj
Abstract: Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments. We introduce CrackSegFlow, a controllable Flow Matching synthesis method that renders synthetic images of cracks from masks with pixel-level alignment. Our renderer combines topology-preserving mask injection with edge gating to maintain thin-structure continuity. Class-conditional FM samples masks for topology diversity, and CrackSegFlow renders aligned ground truth images from them. We further inject cracks onto crack-free backgrounds to diversify confounders and reduce false positives. Across five datasets and using a CNN-Transformer backbone, our results demonstrate that adding synthesized pairs improves in-domain performance by +5.37 mIoU and +5.13 F1, while target-guided cross-domain synthesis driven by target mask statistics adds +13.12 mIoU and +14.82 F1. We also release CSF-50K, a benchmark dataset comprising 50,000 image-mask pairs.
Authors: Paraskevi Valergaki, Vassilis C. Nicodemou, Iason Oikonomidis, Antonis Argyros, Anastasios Roussos
Abstract: Reliable stress recognition is critical in applications such as medical monitoring and safety-critical systems, including real-world driving. While stress is commonly detected using physiological signals such as perinasal perspiration and heart rate, facial activity provides complementary cues that can be captured unobtrusively from video. We propose a multimodal stress estimation framework that combines facial videos and physiological signals, remaining effective even when biosignal acquisition is challenging. Facial behavior is represented using a dense 3D Morphable Model, yielding a 56-dimensional descriptor that captures subtle expression and head-pose dynamics over time. To study how stress modulates facial motion, we perform extensive experiments alongside established physiological markers. Paired hypothesis tests between baseline and stressor phases show that 38 of 56 facial components exhibit consistent, phase-specific stress responses comparable to physiological markers. Building on these findings, we introduce a Transformer-based temporal modeling framework and evaluate unimodal, early-fusion, and cross-modal attention strategies. Cross-modal attention fusion of 3D-derived facial features with physiological signals substantially improves performance over physiological signals alone, increasing AUROC from 52.7% and accuracy from 51.0% to 92.0% and 86.7%, respectively. Although evaluated on driving data, the proposed framework and protocol may generalize to other stress estimation settings.
Authors: Subhadeep Roy, Gagan Bhatia, Steffen Eger
Abstract: Automatic metrics are now central to evaluating text-to-image models, often substituting for human judgment in benchmarking and large-scale filtering. However, it remains unclear whether these metrics truly prioritize semantic correctness or instead favor visually and socially prototypical images learned from biased data distributions. We identify and study prototypicality bias as a systematic failure mode in multimodal evaluation. We introduce a controlled contrastive benchmark ProtoBias (Prototypical Bias), spanning Animals, Objects, and Demography images, where semantically correct but non-prototypical images are paired with subtly incorrect yet prototypical adversarial counterparts. This setup enables a directional evaluation of whether metrics follow textual semantics or default to prototypes. Our results show that widely used metrics, including CLIPScore, PickScore, and VQA-based scores, frequently misrank these pairs, while even LLM-as-Judge systems exhibit uneven robustness in socially grounded cases. Human evaluations consistently favour semantic correctness with larger decision margins. Motivated by these findings, we propose ProtoScore, a robust 7B-parameter metric that substantially reduces failure rates and suppresses misranking, while running at orders of magnitude faster than the inference time of GPT-5, approaching the robustness of much larger closed-source judges.
Authors: Zuhair Ahmed Khan Taha, Mohammed Mudassir Uddin, Shahnawaz Alam
Abstract: Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127 in cloud computing fees, which puts these tools out of reach for organizations operating on limited budgets. We present AgentCompress, a framework that tackles this problem through task-aware dynamic compression. The idea comes from a simple observation: not all tasks require the same computational effort. Complex reasoning, for example, is far more demanding than text reformatting, yet conventional compression applies the same reduction to both. Our approach uses a lightweight neural controller that looks at the first few tokens of each request, estimates how complex the task will be, and sends it to an appropriately quantized version of the model. This routing step adds only about 12 milliseconds of overhead. We tested the framework on 290 multi-stage workflows from domains including computer science, physics, chemistry, and biology. The results show a 68.3% reduction in computational costs while preserving 96.2% of the original success rate. These findings suggest that routing queries intelligently can make powerful language models substantially more affordable without sacrificing output quality
Authors: Zichen Wang, Ang Cao, Liam J. Wang, Jeong Joon Park
Abstract: We propose a simple yet effective approach to enhance the performance of feed-forward 3D reconstruction models. Existing methods often struggle near depth discontinuities, where standard regression losses encourage spatial averaging and thus blur sharp boundaries. To address this issue, we introduce a mixture-of-experts formulation that handles uncertainty at depth boundaries by combining multiple smooth depth predictions. A softmax weighting head dynamically selects among these hypotheses on a per-pixel basis. By integrating our mixture model into a pre-trained state-of-the-art 3D model, we achieve a substantial reduction of boundary artifacts and gains in overall reconstruction accuracy. Notably, our approach is highly compute efficient, delivering generalizable improvements even when fine-tuned on a small subset of training data while incurring only negligible additional inference computation, suggesting a promising direction for lightweight and accurate 3D reconstruction.
Authors: Yuang Shi, G\'eraldine Morin, Simone Gasparini, Wei Tsang Ooi
Abstract: We observe that Gaussians exhibit distinct roles and characteristics analogous to traditional artistic techniques -- like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features such as edges and contours, while others represent broader, smoother regions analogous to brush strokes that add volume and depth. Based on this observation, we propose a hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which represent high-frequency, boundary-defining features, and (ii) Patch Gaussians, which cover low-frequency, smooth regions. This semantic separation naturally enables layered progressive streaming, where the compact Sketch Gaussians establish the structural skeleton before Patch Gaussians incrementally refine volumetric detail. In this work, we extend our previous method to arbitrary 3D scenes by proposing a novel hierarchical adaptive categorization framework that operates directly on the 3DGS representation. Our approach employs multi-criteria density-based clustering, combined with adaptive quality-driven refinement. This method eliminates dependency on external 3D line primitives while ensuring optimal parametric encoding effectiveness. Our comprehensive evaluation across diverse scenes, including both man-made and natural environments, demonstrates that our method achieves up to 1.74 dB improvement in PSNR, 6.7% in SSIM, and 41.4% in LPIPS at equivalent model sizes compared to uniform pruning baselines. For indoor scenes, our method can maintain visual quality with only 0.5\% of the original model size. This structure-aware representation enables efficient storage, adaptive streaming, and rendering of high-fidelity 3D content across bandwidth-constrained networks and resource-limited devices.
Authors: Jingyu Li, Junjie Wu, Dongnan Hu, Xiangkai Huang, Bin Sun, Zhihui Hao, Xianpeng Lang, Xiatian Zhu, Li Zhang
Abstract: Recent end-to-end autonomous driving approaches have leveraged Vision-Language Models (VLMs) to enhance planning capabilities in complex driving scenarios. However, VLMs are inherently trained as generalist models, lacking specialized understanding of driving-specific reasoning in 3D space and time. When applied to autonomous driving, these models struggle to establish structured spatial-temporal representations that capture geometric relationships, scene context, and motion patterns critical for safe trajectory planning. To address these limitations, we propose SGDrive, a novel framework that explicitly structures the VLM's representation learning around driving-specific knowledge hierarchies. Built upon a pre-trained VLM backbone, SGDrive decomposes driving understanding into a scene-agent-goal hierarchy that mirrors human driving cognition: drivers first perceive the overall environment (scene context), then attend to safety-critical agents and their behaviors, and finally formulate short-term goals before executing actions. This hierarchical decomposition provides the structured spatial-temporal representation that generalist VLMs lack, integrating multi-level information into a compact yet comprehensive format for trajectory planning. Extensive experiments on the NAVSIM benchmark demonstrate that SGDrive achieves state-of-the-art performance among camera-only methods on both PDMS and EPDMS, validating the effectiveness of hierarchical knowledge structuring for adapting generalist VLMs to autonomous driving.
Authors: Mingi Jeong, Arihant Chadda, Ziang Ren, Luyang Zhao, Haowen Liu, Monika Roznere, Aiwei Zhang, Yitao Jiang, Sabriel Achong, Samuel Lensgraf, Alberto Quattrini Li
Abstract: This paper introduces the first publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, collected over 4 years and consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in ASVs by providing a multi-modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset by training and testing current deep learning-based open-source perception algorithms that have shown success in the autonomous ground vehicle domain. With the training and testing results, we discuss open challenges for existing datasets and methods, identifying future research directions. We expect that our dataset will contribute to the development of future marine autonomy pipelines and marine (field) robotics. This dataset is open source and found at https://seepersea.github.io/.
Authors: Shuhong Liu, Tianchen Deng, Heng Zhou, Liuzhuozheng Li, Hongyu Wang, Danwei Wang, Mingrui Li
Abstract: Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems.
Authors: Marimuthu Kalimuthu, David Holzm\"uller, Mathias Niepert
Abstract: Modeling high-frequency information is a critical challenge in scientific machine learning. For instance, fully turbulent flow simulations of the Navier-Stokes equations at Reynolds numbers 3500 and above can generate high-frequency signals due to swirling fluid motions caused by eddies and vortices. Faithfully modeling such signals using neural nets depends on the accurate reconstruction of moderate to high frequencies. However, it has been well known that neural nets exhibit spectral or frequency bias towards learning low-frequency components. Meanwhile, Fourier Neural Operators (FNOs) have emerged as a popular class of data-driven models for surrogate modeling and solving PDEs. Although impressive results were achieved on several PDE benchmark problems, FNOs perform poorly in learning non-dominant frequencies characterized by local features. This limitation stems from spectral bias inherent in neural nets and the explicit exclusion of high-frequency modes in FNOs and their variants. Therefore, to mitigate these issues and improve FNO's spectral learning capabilities to represent a broad range of frequency components, we propose two key architectural enhancements: (i) a parallel branch performing local spectral convolution (ii) a high-frequency propagation module. Moreover, we propose a novel frequency-sensitive loss based on radially binned spectral errors. This introduction of a parallel branch for local convolution reduces the trainable parameters by up to 50% while achieving the accuracy of FNO that relies solely on global convolution. Moreover, our findings demonstrate that the proposed model improves stability over longer rollouts. Experiments on six challenging PDEs in fluid mechanics, wave propagation, and biological pattern formation, and the qualitative and spectral analysis of predictions, show the effectiveness of our method over SOTA neural operator families of baselines.
Authors: Lu Han, Xiuying Wang
Abstract: Traditional decision tree models, which rely exclusively on numerical variables, often face challenges in handling high-dimensional data and are limited in their ability to incorporate textual information effectively. To address these limitations, we propose the integrated multivariate segmentation tree (IMST), a comprehensive framework designed to improve credit evaluation for small- and medium-sized enterprises (SMEs) by integrating financial data with textual sources. This method comprises three core stages: (1) transforming textual data into numerical matrices through matrix factorization, (2) selecting salient financial features using Lasso regression, and (3) constructing a multivariate segmentation tree based on either the Gini index or entropy, with weakest-link pruning applied to control model complexity. Experimental results based on a dataset of 1,428 Chinese SMEs demonstrated that IMST achieved an accuracy rate of 88.9%, surpassing both baseline decision trees (87.4%) and conventional models such as support vector machines and neural networks. Furthermore, the proposed model demonstrated superior interpretability and computational efficiency, featuring a more streamlined architecture and improved risk detection capabilities.
Authors: Luca Zhou, Pratham Yashwante, Marshall Fisher, Alessio Sampieri, Zihao Zhou, Fabio Galasso, Rose Yu
Abstract: Time series captioning, the task of describing time series in natural language, requires numeric and temporal reasoning, trend interpretation, and contextual understanding. Existing benchmarks, however, often rely on fully synthetic or generic captions, and typically neglect metadata and visual representations. We introduce CaTS-Bench, a comprehensive benchmark for Context-aware Time Series reasoning across $11$ diverse domains, centered on a gold-standard evaluation set of $1746$ human-rewritten captions that measure how effectively models translate numeric trends into immediately interpretable narratives. To address the scarcity of human-annotated data, we also propose a scalable pipeline for generating high-fidelity synthetic captions, the quality of which we validate. We evaluate leading Vision-Language Models on our benchmark, revealing that even proprietary models struggle to capture numeric nuances in temporal descriptions, while finetuning open-source models on synthetic data yields substantial performance gains. Finally, we release a diagnostic suite of $910$ multiple-choice questions and tailored numeric metrics to gauge time-series-specific reasoning capabilities, establishing CaTS-Bench as a reliable foundation for grounded, multimodal language generation in numeric domains.
Authors: Tianchen Deng, Yue Pan, Shenghai Yuan, Dong Li, Chen Wang, Mingrui Li, Long Chen, Lihua Xie, Danwei Wang, Jingchuan Wang, Javier Civera, Hesheng Wang, Weidong Chen
Abstract: In this paper, we provide a comprehensive overview of existing scene representation methods for robotics, covering traditional representations such as point clouds, voxels, signed distance functions (SDF), and scene graphs, as well as more recent neural representations like Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and the emerging Foundation Models. While current SLAM and localization systems predominantly rely on sparse representations like point clouds and voxels, dense scene representations are expected to play a critical role in downstream tasks such as navigation and obstacle avoidance. Moreover, neural representations such as NeRF, 3DGS, and foundation models are well-suited for integrating high-level semantic features and language-based priors, enabling more comprehensive 3D scene understanding and embodied intelligence. In this paper, we categorized the core modules of robotics into five parts (Perception, Mapping, Localization, Navigation, Manipulation). We start by presenting the standard formulation of different scene representation methods and comparing the advantages and disadvantages of scene representation across different modules. This survey is centered around the question: What is the best 3D scene representation for robotics? We then discuss the future development trends of 3D scene representations, with a particular focus on how the 3D Foundation Model could replace current methods as the unified solution for future robotic applications. The remaining challenges in fully realizing this model are also explored. We aim to offer a valuable resource for both newcomers and experienced researchers to explore the future of 3D scene representations and their application in robotics. We have published an open-source project on GitHub and will continue to add new works and technologies to this project.
Authors: Haitao Lin, Peiyan Hu, Minsi Ren, Zhifeng Gao, Zhi-Ming Ma, Guolin ke, Tailin Wu, Stan Z. Li
Abstract: Recent advances in few-step diffusion models have demonstrated their efficiency and effectiveness by shortcutting the probabilistic paths of diffusion models, especially in training one-step diffusion models from scratch (\emph{a.k.a.} shortcut models). However, their theoretical derivation and practical implementation are often closely coupled, which obscures the design space. To address this, we propose a common design framework for representative shortcut models. This framework provides theoretical justification for their validity and disentangles concrete component-level choices, thereby enabling systematic identification of improvements. With our proposed improvements, the resulting one-step model achieves a new state-of-the-art FID50k of 2.85 on ImageNet-256x256 under the classifier-free guidance setting with one step generation, and further reaches FID50k of 2.53 with 2x training steps. Remarkably, the model requires no pre-training, distillation, or curriculum learning. We believe our work lowers the barrier to component-level innovation in shortcut models and facilitates principled exploration of their design space.
Authors: Eric J. Elias, Michael Esswein, Jonathan P. How, David W. Miller
Abstract: As the popularity of on-orbit operations grows, so does the need for precise navigation around unknown resident space objects (RSOs) such as other spacecraft, orbital debris, and asteroids. The use of Simultaneous Localization and Mapping (SLAM) algorithms is often studied as a method to map out the surface of an RSO and find the inspector's relative pose using a lidar or conventional camera. However, conventional cameras struggle during eclipse or shadowed periods, and lidar, though robust to lighting conditions, tends to be heavier, bulkier, and more power-intensive. Thermal-infrared cameras can track the target RSO throughout difficult illumination conditions without these limitations. While useful, thermal-infrared imagery lacks the resolution and feature-richness of visible cameras. In this work, images of a target satellite in low Earth orbit are photo-realistically simulated in both visible and thermal-infrared bands. Pixel-level fusion methods are used to create visible/thermal-infrared composites that leverage the best aspects of each camera. Navigation errors from a monocular SLAM algorithm are compared between visible, thermal-infrared, and fused imagery in various lighting and trajectories. Fused imagery yields substantially improved navigation performance over visible-only and thermal-only methods.
Authors: YuChe Hsu, AnJui Wang, TsaiChing Ni, YuanFu Yang
Abstract: We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and natural-language prompts, enabling cross-modal reasoning for industrial simulation systems. To support this new paradigm, the study constructs the first large-scale dataset for generative digital twins, comprising over 120,000 prompt-sketch-code triplets that enable multimodal learning between textual descriptions, spatial structures, and simulation logic. In parallel, three novel evaluation metrics, Structural Validity Rate (SVR), Parameter Match Rate (PMR), and Execution Success Rate (ESR), are proposed specifically for this task to comprehensively evaluate structural integrity, parameter fidelity, and simulator executability. Through systematic ablation across vision encoders, connectors, and code-pretrained language backbones, the proposed models achieve near-perfect structural accuracy and high execution robustness. This work establishes a foundation for generative digital twins that integrate visual reasoning and language understanding into executable industrial simulation systems. Project page: https://danielhsu2014.github.io/GDT-VLSM-project/
Authors: Poojan Vanani, Darsh Patel, Danyal Khorami, Siva Munaganuru, Pavan Reddy, Varun Reddy, Bhargav Raghunath, Ishrat Lallmamode, Romir Patel, Assegid Kidan\'e, Tejaswi Gowda
Abstract: Motion capture remains costly and complex to deploy, limiting use outside specialized laboratories. We present Mesquite, an open-source, low-cost inertial motion-capture system that combines a body-worn network of 15 IMU sensor nodes with a hip-worn Android smartphone for position tracking. A low-power wireless link streams quaternion orientations to a central USB dongle and a browser-based application for real-time visualization and recording. Built on modern web technologies -- WebGL for rendering, WebXR for SLAM, WebSerial and WebSockets for device and network I/O, and Progressive Web Apps for packaging -- the system runs cross-platform entirely in the browser. In benchmarks against a commercial optical system, Mesquite achieves mean joint-angle error of 2-5 degrees while operating at approximately 5% of the cost. The system sustains 30 frames per second with end-to-end latency under 15ms and a packet delivery rate of at least 99.7% in standard indoor environments. By leveraging IoT principles, edge processing, and a web-native stack, Mesquite lowers the barrier to motion capture for applications in entertainment, biomechanics, healthcare monitoring, human-computer interaction, and virtual reality. We release hardware designs, firmware, and software under an open-source license (GNU GPL).
Authors: Fabian Gr\"oger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Lea Habermacher, Labelling Consortium, Ludovic Amruthalingam, Matthew Groh, Marc Pouly, Alexander A. Navarini
Abstract: The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth in publicly available dermatology images, the field lacks quantitative key performance indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Here we present SkinMap, a multi-modal framework for the first comprehensive audit of the field's entire data basis. We unify the publicly available dermatology datasets into a single, queryable semantic atlas comprising more than 1.1 million images of skin conditions and quantify (i) informational novelty over time, (ii) dataset redundancy, and (iii) representation gaps across demographics and diagnoses. Despite exponential growth in dataset sizes, informational novelty across time has somewhat plateaued: Some clusters, such as common neoplasms on fair skin, are densely populated, while underrepresented skin types and many rare diseases remain unaddressed. We further identify structural gaps in coverage: Darker skin tones (Fitzpatrick V-VI) constitute only 5.8% of images and pediatric patients only 3.0%, while many rare diseases and phenotype combinations remain sparsely represented. SkinMap provides infrastructure to measure blind spots and steer strategic data acquisition toward undercovered regions of clinical space.
Authors: Xin Wang, Yunhao Chen, Juncheng Li, Yixu Wang, Yang Yao, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang, Xia Hu
Abstract: The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for systematic evaluation. To address this, we introduce OpenRT, a unified, modular, and high-throughput red-teaming framework designed for comprehensive MLLM safety evaluation. At its core, OpenRT architects a paradigm shift in automated red-teaming by introducing an adversarial kernel that enables modular separation across five critical dimensions: model integration, dataset management, attack strategies, judging methods, and evaluation metrics. By standardizing attack interfaces, it decouples adversarial logic from a high-throughput asynchronous runtime, enabling systematic scaling across diverse models. Our framework integrates 37 diverse attack methodologies, spanning white-box gradients, multi-modal perturbations, and sophisticated multi-agent evolutionary strategies. Through an extensive empirical study on 20 advanced models (including GPT-5.2, Claude 4.5, and Gemini 3 Pro), we expose critical safety gaps: even frontier models fail to generalize across attack paradigms, with leading models exhibiting average Attack Success Rates as high as 49.14%. Notably, our findings reveal that reasoning models do not inherently possess superior robustness against complex, multi-turn jailbreaks. By open-sourcing OpenRT, we provide a sustainable, extensible, and continuously maintained infrastructure that accelerates the development and standardization of AI safety.
Authors: Yusheng Dai, Zehua Chen, Yuxuan Jiang, Baolong Gao, Qiuhong Ke, Jun Zhu, Jianfei Cai
Abstract: Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity of high-quality audio captions with tight A-V-T alignment, leading to severe semantic conflict between multimodal conditions, and (2) cross-task and intra-task competition, manifesting as an adverse V2A-T2A performance trade-off and modality bias in the VT2A task. First, to address data scarcity, we introduce SoundAtlas, a large-scale dataset (470k pairs) that significantly outperforms existing benchmarks and even human experts in quality. Powered by a novel agentic pipeline, it integrates Vision-to-Language Compression to mitigate visual bias of MLLMs, a Junior-Senior Agent Handoff for a 5 times cost reduction, and rigorous Post-hoc Filtering to ensure fidelity. Consequently, SoundAtlas delivers semantically rich and temporally detailed captions with tight V-A-T alignment. Second, we propose Omni2Sound, a unified VT2A diffusion model supporting flexible input modalities. To resolve the inherent cross-task and intra-task competition, we design a three-stage multi-task progressive training schedule that converts cross-task competition into joint optimization and mitigates modality bias in the VT2A task, maintaining both audio-visual alignment and off-screen audio generation faithfulness. Finally, we construct VGGSound-Omni, a comprehensive benchmark for unified evaluation, including challenging off-screen tracks. With a standard DiT backbone, Omni2Sound achieves unified SOTA performance across all three tasks within a single model, demonstrating strong generalization across benchmarks with heterogeneous input conditions. The project page is at https://swapforward.github.io/Omni2Sound.
Authors: Zulkhuu Tuya, Ignacio Alzugaray, Nicholas Fry, Andrew J. Davison
Abstract: Many emerging many-core accelerators replace a single large device memory with hundreds to thousands of lightweight cores, each owning only a small local SRAM and exchanging data via explicit on-chip communication. This organization offers high aggregate bandwidth, but it breaks a key assumption behind many volumetric rendering techniques: that rays can randomly access a large, unified scene representation. Rendering efficiently on such hardware therefore requires distributing both data and computation, keeping ray traversal mostly local, and structuring communication into predictable routes. We present a fully in-SRAM, distributed renderer for the Radiant Foam Voronoi-cell volumetric representation on the Graphcore Mk2 IPU(Intelligence Processing Unit), a many-core accelerator with tile-local SRAM and explicit inter-tile communication. Our system shards the scene across tiles and forwards rays between shards through a hierarchical routing overlay, enabling ray marching entirely from on-chip SRAM with predictable communication. On Mip-NeRF~360 scenes, the system attains near-interactive throughput of approximately 1 fps at 640x480 with image and depth map quality close to the original GPU-based Radiant Foam implementation, while keeping all scene data and ray state in on-chip SRAM. Beyond demonstrating feasibility, we analyze routing, memory, and scheduling bottlenecks that inform how future distributed-memory accelerators can better support irregular, data-movement-heavy rendering workloads.
Authors: Paul Pu Liang
Abstract: Our experience of the world is multisensory, spanning a synthesis of language, sight, sound, touch, taste, and smell. Yet, artificial intelligence has primarily advanced in digital modalities like text, vision, and audio. This paper outlines a research vision for multisensory artificial intelligence over the next decade. This new set of technologies can change how humans and AI experience and interact with one another, by connecting AI to the human senses and a rich spectrum of signals from physiological and tactile cues on the body, to physical and social signals in homes, cities, and the environment. We outline how this field must advance through three interrelated themes of sensing, science, and synergy. Firstly, research in sensing should extend how AI captures the world in richer ways beyond the digital medium. Secondly, developing a principled science for quantifying multimodal heterogeneity and interactions, developing unified modeling architectures and representations, and understanding cross-modal transfer. Finally, we present new technical challenges to learn synergy between modalities and between humans and AI, covering multisensory integration, alignment, reasoning, generation, generalization, and experience. Accompanying this vision paper are a series of projects, resources, and demos of latest advances from the Multisensory Intelligence group at the MIT Media Lab, see https://mit-mi.github.io/.
Authors: Yoav Evron, Michal Bar-Asher Siegal, Michael Fire
Abstract: The recent Artificial Intelligence (AI) revolution has opened transformative possibilities for the humanities, particularly in unlocking the visual-artistic content embedded in historical illuminated manuscripts. While digital archives now offer unprecedented access to these materials, the ability to systematically locate, extract, and analyze illustrations at scale remains a major challenge. We present a general and scalable AI-based pipeline for large-scale visual analysis of illuminated manuscripts. The framework integrates modern deep-learning models for page-level illustration detection, illustration extraction, and multimodal description, enabling scholars to search, cluster, and study visual materials and artistic trends across entire corpora. We demonstrate the applicability of this approach on large heterogeneous collections, including the Vatican Library and richly illuminated manuscripts such as the Bible of Borso d'Este. The system reveals meaningful visual patterns and cross-manuscript relationships by embedding illustrations into a shared representation space and analyzing their similarity structure (see figure 4). By harnessing recent advances in computer vision and vision-language models, our framework enables new forms of large-scale visual scholarship in historical studies, art history, and cultural heritage making it possible to explore iconography, stylistic trends, and cultural connections in ways that were previously impractical.