Authors: Roy Jiang, Hyunjae Kim, Zhenyue Qin, Morten Lee, Margaret MacGibeny, Ailish Hanly, Angela Sadlowski, Shanin Chowdhury, Xuguang Ai, Jeffrey Gehlhausen, Qingyu Chen
Abstract: Multimodal large language models (MLLMs) have demonstrated promise on publicly available dermatology benchmarks. However, benchmark performance may not generalize to real-world dermatologic decision-making. To quantify this benchmark-to-bedside gap, we evaluated four open-weight MLLMs (InternVL-Chat v1.5, LLaVA-Med v1.5, SkinGPT4 and MedGemma-4B-Instruct) and one commercial MLLM (GPT-4.1) across three publicly available dermatology datasets and a retrospective multi-site hospital-based dermatology consultation cohort comprising 5,811 cases and 46,405 clinical images. Models were evaluated on two clinically relevant tasks: differential diagnosis generation and severity-based triage. Diagnostic performance was modest on public datasets and declined substantially in the real-world cohort. On public benchmarks, top-3 diagnostic accuracy reached 26.55% for the best open-weight model and 42.25% for GPT-4.1. On real-world consultation cases using images alone, top-3 diagnostic accuracy fell to 1.50%-13.35% among open-weight models and 24.65% for GPT-4.1. Incorporating clinical context improved performance across all models, increasing top-3 diagnostic accuracy up to 28.75% among open-weight models and 38.93% for GPT-4.1. However, model outputs were highly sensitive to incomplete or erroneous consultation context. For severity-based triage, models achieved moderate sensitivity (above 60%), suggesting potential utility for screening but insufficient reliability for clinical deployment. These findings demonstrate that benchmark performance substantially overestimates the real-world clinical capability of current dermatology MLLMs.
Authors: Chamani Shiranthika, Hadi Hadizadeh, Parvaneh Saeedi
Abstract: Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning further partitions the model between clients and a server to reduce computation and communication at the client side. However, decentralized medical institutions rarely operate on a single shared task, making standard Federated and SplitFed collaborations poorly aligned with real clinical workflows. Multi-task FL extends these frameworks by allowing clients to handle different tasks, but often introduces instability and privacy vulnerabilities. This study proposes \textbf{MuCALD-SplitFed}, a multi-task SplitFed framework that integrates causal representation learning and latent diffusion. Experiments show MuCALD-SplitFed consistently improves segmentation, while baseline SplitFed fails to converge. The proposed approach further reduces information leakage at split points, mitigating reconstruction-based and membership inference attacks. Additionally, MuCALD SplitFed outperforms state-of-the-art personalized FL and multi-task FL approaches. The code repository is: https://github.com/ChamaniS/MuCALD_SplitFed.
Authors: Paarth Prasad, Ruchika Malhotra
Abstract: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.
Authors: Ji-Hun Oh, Dou Hoon Kwark, Kianoush Falahkheirkhah, Kevin Yeh, John Cheville, Volodymyr Kindratenko, Rohit Bhargava
Abstract: Mirroring its ubiquity in popular media and all human activities, the use of deep learning (DL) is rapidly growing in scientific imaging modalities. However, unlike everyday RGB pictures, pixels encode precise physicochemical properties in scientific imaging across potentially thousands of channels. While DL is well validated on human-centric RGB perceptual tasks, its effectiveness for scientific imaging remains uncertain. Here, we show that the naive application of DL frameworks to scientific images can lead to critical failures. We evaluate the use of DL for pathology, comparing RGB images of stained tissue with the quantitative and information-rich biochemical signatures of infrared (IR) imaging. Despite this informational advantage, DL models trained on IR data paradoxically underperform. We investigate this discrepancy to find that IR data priors interact poorly with the simplicity bias of DL, causing models to collapse to one-dimensional predictions. This constitutes a catastrophic DL failure because the model's representational capacity remains largely unused, while furthermore raising AI safety concerns and undermining the advantages of such scientific modalities. Notably, this problem persists even with state-of-the-art DL robustification strategies, which are primarily designed and validated for RGB imagery and thus inherit the same prior-bias mismatch. This work establishes a framework for understanding the limitations of generic DL in science and advocates for the study of modality-specific failure modes to guide the development of specialized, safe AI algorithms.
Authors: Qing Wu, Xuanyu Tian, Chenhe Du, Haonan Zhang, Xiao Wang, Le Lu, Yuyao Zhang
Abstract: Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient training and suboptimal imaging quality. Recent initialization-based approaches attempt to inject population priors into pre-trained networks, yet they rely on high-quality images and often suffer from catastrophic forgetting during fine-tuning. We present DisINR, a novel INR framework that explicitly disentangles shared and subject-specific representations. DisINR introduces a shared encoder-decoder pair and subject-specific encoders, whose features are jointly decoded for image reconstruction. By integrating differentiable forward models, it pre-trains the shared modules directly from limited raw measurements, removing the need for pre-acquired high-quality images. During test-time adaptation, only the subject-specific encoder is optimized, while the shared pair remains frozen, effectively preserving learned priors. Extensive evaluations on three representative medical imaging tasks show that DisINR significantly outperforms state-of-the-art INRs in both reconstruction accuracy and efficiency.
Authors: V\'eronique Defonte, Dawa Derksen, Alexandre Constantin, Bastien Nespoulous
Abstract: Optical satellite image time series are extensively used in many Earth observation applications, including agriculture, climate monitoring, and land surface analysis. However, clouds and swath edges result in irregular sampling along the temporal dimension, limiting continuous monitoring. To address this issue, a growing body of work has focused on temporal densification and reconstruction of satellite image time series, with the objective of filling missing or cloud-contaminated observations within the temporal extent of the available data. While these approaches improve temporal continuity, they are inherently restricted to the reconstruction of the gaps within the observed time periods, and do not address the prediction of future observations. This work proposes a probabilistic deep learning framework for the densification and forecasting of Sentinel-2 time series by generating optical images at arbitrary past or future dates. The approach leverages multimodal satellite data by jointly exploiting Sentinel-2 optical and Sentinel-1 SAR observations. Unlike most existing works, we propose to focus on the uncertainty of the generated images. Experimental results demonstrate effective densification and forecasting, on sparse and temporally misaligned time series.
Authors: Paula Pacheco, Pablo Granitto, Juan B. Cabral
Abstract: The Linear Mixing Model (LMM) dominates spectral unmixing for its simplicity, but fails under multiple scattering; existing nonlinear models compensate by applying a fixed regime uniformly across entire scenes. We propose Physics-Guided Regime Unmixing (PGRU), which estimates a pixel-wise scalar $\xi_i \in [0,1]$ from observable physical features to activate nonlinear mixing only where justified. Residuals from the Generalized Bilinear Model (GBM), the Post-Nonlinear Mixing Model (PPNM), and Hapke are combined via learned attention, yielding interpretable regime maps. Experiments on Samson, Jasper Ridge, and Urban show consistent improvements over baselines, with physical coherence $\rho > 0.90$.
Authors: Anju Rani, Daniel Ortiz-Arroyo, Petar Durdevic
Abstract: Remaining useful life (RUL) estimation of synthetic fibre ropes (SFRs) is critical for safe operation in offshore-crane, wind turbine installation, and heavy-load handling applications, where rope failure can result in catastrophic safety incidents and costly downtime. Despite growing research interest in data-driven condition monitoring, there is no publicly available image dataset that captures the complete degradation lifecycle of SFRs under controlled cyclic fatigue loading. To address this gap, we present a novel image dataset comprising approximately 34,700 high-resolution images of eleven Dyneema SK75/78 high-modulus polyethylene (HMPE) rope samples subjected to cyclic fatigue on a sheave-bend test stand at seven distinct axial load levels ranging from 60 kN to 280 kN. Ropes were loaded until mechanical failure, with fatigue lifetimes ranging from 695 cycles to 8,340 cycles. After every fixed number of sheave cycles (an inspection burst), ten images were captured at different cross-sectional positions along the rope, providing spatially representative sampling of surface degradation throughout the rope's entire service life. The images obtained from each load are annotated with the corresponding elapsed cycle count, enabling a direct computation of RUL for any rope in the sequence. This dataset aims to support a broad range of machine learning (ML) tasks including RUL regression, damage progression modelling, anomaly detection, and load-conditioned prognostics. The dataset is intended to serve as a benchmark resource for the development and comparison of vision-based condition monitoring (CM) and prognostics algorithms for SFRs.
Authors: Maryam Sadat Hosseini Azad, Shahriar Baradaran Shokouhi
Abstract: Scene understanding is a vital part of autonomous driving systems, which requires the use of deep learning models. Deep learning methods are intrinsically black box models, which lack transparency and safety in autonomous driving. To make these systems transparent, multi-task visual understanding has become crucial for explainable autonomous driving perception systems, where simultaneous prediction of multiple driving behaviors and their underlying explanations is essential for safe navigation and human trust in autonomous vehicles. In order to design an accurate and cross-cultural explainable autonomous driving system, we introduce a comprehensive confidence threshold sensitivity analysis that evaluates various threshold values to identify optimal decision boundaries for different tasks. Our analysis demonstrates that traditional fixed threshold approaches are suboptimal for multi-task scenarios. Through extensive evaluation, we demonstrate that our adaptive threshold selection methodology improves F1-scores across different tasks. In addition, we introduce IUST-XAI-AD, a novel dataset consisting of 958 images with human annotations for driving decisions and corresponding reasoning. This dataset addresses the critical gap in domain-specific evaluation benchmarks for distinct driving contexts and provides a more challenging test environment compared to existing datasets. Experimental results demonstrate that confidence threshold sensitivity analysis can significantly improve model performance, while the introduction of the IUST-XAI-AD dataset reveals important insights about cross-cultural driving behavior patterns. The combined contributions of this work provide both methodological advances and practical evaluation tools that can accelerate the development of more reliable, explainable, and culturally-adaptive autonomous driving systems for global deployment.
Authors: Qihua Dong, Ruozhen He, Junwen Chen, Yizhou Wang, Xu Ma, Songyao Jiang, Yun Fu
Abstract: Advanced chart question answering requires both precise perception of small visual elements and multi-step reasoning across several subplots. While existing MLLMs are strong at understanding single plots, they often struggle with multi-step reasoning across multiple subplots. We propose HierVA, a hierarchical visual agent framework for chart reasoning that iteratively constructs and updates a working context in a joint image--text space. A high-level manager generates plans and maintains a compact context containing only key information, while specialized workers perform reasoning, gather evidence, and return results. In particular, the agent maintains separate visual and textual contexts, using a zoom-in tool to restrict the visual context. Experiments on the CharXiv reasoning subset demonstrate consistent improvements over strong multimodal baselines, and ablation studies verify that hierarchical architecture, scoped visual context, and distilled context contribute complementary gains.
Authors: Mustafa Sakhaia, Kaung Sithua, Min Khant Soe Okea, Maciej Wielgosza
Abstract: Autonomous driving systems rely heavily on robust sensor fusion to perceive complex envi- ronments. Traditional setups using RGB cameras and LiDAR often struggle in high-dynamic- range scenes or high-speed scenarios due to motion blur and latency. Dynamic Vision Sensors (DVS), or event cameras, offer a paradigm shift by capturing asynchronous brightness changes with microsecond temporal resolution and high dynamic range. In this paper, we propose an extended architecture of the state-of-the-art InterFuser model, integrating DVS as an additional modality to enhance perception reliability. We introduce a novel token-based fusion strategy that incorporates accumulated event frames into the transformer-based backbone of InterFuser. Our method leverages the complementary nature of RGB, LiDAR, and DVS data. We evaluate our approach on the Car Learning to Act (CARLA) Leaderboard benchmarks, demonstrating that the inclusion of DVS improves the robustness of the driving agent, achieving a competitive Driving Score of 77.2 and a superior Route Completion of 100%. The results indicate that event-based vision is a promising direction for improving safety and performance in adverse lighting and dynamic conditions.
Authors: Zhenhan Huang, Pin-Yu Chen, Tejaswini Pedapati, Jianxi Gao
Abstract: The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.
Authors: Jieying Wang, Xinqi Cai, Caifeng Shan, Wenjin Wang
Abstract: Remote photoplethysmography (rPPG) holds great promise for continuous heart-rate monitoring of drivers in intelligent vehicles. However, its performance is severely degraded by the highly dynamic illumination changes. A critical yet overlooked factor is the lack of exposure controlling during video acquisition -- most existing systems rely on either fixed exposure settings or camera build-in auto-exposure, both of which fail to maintain stable facial brightness under rapidly changing lighting conditions during driving. To address this gap, we propose a highly-adaptive exposure controlling framework that proactively adjusts exposure parameters based on predictive modeling of historical skin reflections. Unlike standard auto-exposure, our method is specifically optimized for rPPG measurement, ensuring the skin region of interest (ROI) remains within the optimal dynamic range for rPPG signal extraction. As an important contribution of this study, we introduce ExpDrive, a public in-vehicle physiological monitoring dataset comprising synchronized facial video and reference ECG from 48 subjects captured under real driving conditions. Extensive experiments demonstrate that our method consistently outperforms fixed exposure and standard auto-exposure strategies. Specifically, it reduces the Mean Absolute Error (MAE) by 6.31 bpm (from 14.1 to 7.79 bpm) and significantly increases the success rate by 32.3 percentage points (p < 0.001) (from 24.9% to 57.2%) across challenging driving scenarios. Notably, it clearly improved the performance of non-contact heart-rate monitoring in both low-light (rainy) and high-glare (sunny) conditions, validating the efficacy of exposure-aware acquisition design.
Authors: Harry Cheng, Ming-Hui Liu, Tianyi Wang, Weili Guan, Liqiang Nie, Mohan Kankanhalli
Abstract: Driven by the rapid development of generative AI models, deepfake detectors are compelled to undergo periodic recalibration to capture newly developed synthetic artifacts. To break this cycle, we propose a new perspective on deepfake detection: moving from static pattern recognition to dynamical stability analysis. Specifically, our approach is motivated by physics-inspired priors: we hypothesize that natural images, as products of dissipative physical processes, tend to settle near stable, low-energy equilibria. In contrast, generative models optimize for statistical similarity to real images but do not explicitly enforce structural constraints such as geometric smoothness, leaving deepfakes more likely to occupy unstable, high-energy states. To operationalize this, we introduce Hamiltonian Action Anomaly Detection (HAAD), comprising three contributions: \textbf{i)} We model the image latent manifold as a potential energy surface. Under this hypothesis, real images are expected to produce basin-like low-energy responses, whereas fake images are more likely to induce high-potential, high-gradient responses. \textbf{ii)} We employ Hamiltonian-inspired dynamics as a stability probe. By releasing latent states from rest, samples near stable regions remain bounded, while high-gradient samples produce larger trajectory responses. \textbf{iii)} We quantify these dynamic behaviors through two trajectory statistics, \ie, Hamiltonian action and energy dissipation. Extensive experiments show that HAAD outperforms evaluated state-of-the-art baselines on challenging cross-dataset transfer benchmarks, supporting a physics-inspired stability prior for digital forensics.
Authors: Yupeng Gao, Tianyu Li, Guoqing Wang, Yang Yang
Abstract: Remote Sensing Image Change Captioning (RSICC) aims to generate spatially grounded natural language descriptions of scene evolution from bi-temporal imagery, moving beyond binary change masks toward semantic-level understanding. However, existing methods rely on implicit feature differencing without explicitly modeling structured change semantics, and struggle to reconcile the conflicting representation demands of change detection and caption generation. In addition, current benchmarks provide limited coverage of high-resolution urban construction scenarios. To address these challenges, we propose PTNet, a prototype-guided task-adaptive framework for joint change captioning and detection. PTNet explicitly models structured change semantics through a learnable prototype bank that guides cross-temporal interaction, disentangles task-specific representations via multi-head gating, and injects detection-derived spatial priors into caption generation, enabling coherent semantic correspondence while preserving fine-grained spatial sensitivity. Furthermore, we construct UCCD, a large-scale UAV-based benchmark comprising 9,000 high-resolution image pairs and 45,000 annotated sentences for urban construction monitoring. Extensive experiments on UCCD and WHU-CDC demonstrate that PTNet consistently outperforms existing methods. The dataset and source code are publicly available at https://github.com/G124556/ptnet.
Authors: Rokas Gipi\v{s}kis, Olga Kurasova
Abstract: The evaluation of explainable AI (XAI) methods is affected by a lack of standardization. Metrics are inconsistently defined, incompletely reported, and rarely validated against common baselines. In this paper, we identify transparency of evaluation reporting as a central, under-addressed problem. We propose the XAI Evaluation Card, a documentation template analogous to model cards, designed to accompany any study that introduces an XAI evaluation metric. The card covers explicit declaration of target properties, grounding levels, metric assumptions, validation evidence, gaming risks, and known failure cases. We argue that adopting this template as a community norm would reduce evaluation fragmentation, support meta-analysis, and improve accountability in XAI research.
Authors: Yiran Qiao, Yiren Lu, Yunlai Zhou, Disheng Liu, Linlin Hou, Rui Yang, Yu Yin, Jing Ma
Abstract: 3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects from a single or multiple images. Building on this capability, enabling style-controllable generation naturally emerges as an important and desirable direction. However, existing approaches typically rely on style images that lie within or are similar to the training distribution of 3D generation models. When presented with out-of-distribution (OOD) styles, their performance degrades significantly or even fails. To address this limitation, we introduce \textbf{DiLAST}: 2D Diffusion-based Latent Awakening for 3D Style Transfer. Specifically, we leverage a pretrained 2D diffusion model as a teacher to provide rich and generalizable style priors. By aligning rendered views with the target style under diffusion-based guidance, our method optimizes the structured 3D latent representations for stylization. We observe that this limitation stems not from insufficient model capacity, but from the underutilization of structured 3D latents, which are inherently expressive. Despite being trained on comparatively limited data, 3D generation models can leverage 2D diffusion guidance to steer denoising toward specific directions in latent space, thereby producing diverse, OOD styles. Extensive experiments across diverse data and multiple 3D generation backbones demonstrate the effectiveness and plug-and-play nature of our approach.
Authors: Yating Wang, Yaqi Zhao, Yongshun Gong, Yilong Yin, Haoliang Sun
Abstract: Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves interpretability, it usually depends on large external models, leading to high computational costs and limited scalability. In this paper, we propose Interpretable Prompt Learning (IPL), a hybrid framework that alternates between discrete semantic token selection and continuous prompt optimization. Specifically, IPL formulates semantic token selection as an approximate submodular optimization problem, encouraging tokens that are both human-understandable and semantically diverse. It further adopts an alternating optimization strategy to integrate discrete token selection with continuous prompt tuning, improving interpretability while preserving adaptability to downstream tasks. Our framework is plug-and-play, allowing seamless integration with existing prompt learning methods. Extensive experiments on multiple benchmarks show that IPL consistently improves both interpretability and accuracy across five representative prompt learning methods, providing an effective and scalable extension to existing frameworks.
Authors: Shuo Wang, Jilin Mei, Fuyang Liu, Wenfei Guan, Fanjie Kong, Zhihua Zhao, Shuai Wang, Chen Min, Yu Hu
Abstract: Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter, and increased non-rigid dynamics. These factors introduce conflicting Gaussian observations across timestamps, leading to either over-smoothed renderings or structural artifacts. To address this issue, we propose Ground4D, a spatially-grounded 4D feedforward framework for pose-free off-road reconstruction. The key idea is to resolve temporal conflicts through spatially localized conditioning. Specifically, we introduce voxel-grounded temporal Gaussian aggregation, which partitions the canonical Gaussian space into spatial voxels and performs query-conditioned temporal attention within each voxel. Intra-voxel softmax normalization ensures that temporal selectivity and spatial occupancy become mutually reinforcing rather than conflicting. We furthermore introduce surface normal cues as auxiliary geometric guidance to regularize the geometry of Gaussian primitives. Extensive experiments on ORAD-3D and RELLIS-3D demonstrate that Ground4D consistently outperforms existing feedforward methods in reconstruction quality and generalizes zero-shot to unseen off-road domains. Project page and code:https://github.com/wsnbws/Ground4D.
Authors: Chunwei Tian, Jingyuan Xie, Qi Zhang, Chao Li, Wangmeng Zuo, Shichao Zhang
Abstract: Deep neural networks enriched with structural information have been widely employed for facial expression recognition tasks. However, these methods often depend on hierarchical information rather than face property to finish expression recognition. In this paper, we propose a cross-modal network with strong biological and structural information for facial expression recognition (CMNet). CMNet can respectively learn expression information via face symmetry on a whole face, left and right half faces to extract complementary facial features. To prevent negative effect of biological and structural information fusion, a salient facial information refinement module can obtain salient facial expression information to improve stability of an obtained facial expression classifier. To reduce reliance on unilateral facial features, a half-face alignment optimization mechanism is designed to align obtained expression information of learned left and right half faces. Our experimental results demonstrate that CMNet outperforms several novel methods, i.e., SCN and LAENet-SA for facial expression recognition. Codes can be obtained at https://github.com/hellloxiaotian/CMNet.
Authors: Yutong Xiao, Ran Ran, Jiwei Wei, Shuchang Zhou, Ke Liu, Zheng Ziqiang, Caiyan Qin
Abstract: The rapid advancement of generative technologies has made synthetic images nearly indistinguishable from real ones, thereby creating an urgent need for robust detectors to counter misinformation. However, existing methods mainly rely on universal artifact features that are shared across multiple generators. We observe that as the diversity of generators increases, the overlap of these common features gradually decreases. This severely undermines model generalization. In contrast, focusing only on unique artifacts tends to cause overfitting to specific forgery patterns. To address this challenge, we propose LEGO (LoRA-Enabled Generator-Oriented Framework). The core mechanism of LEGO employs an MLP to modulate multiple LoRA (Low-Rank Adaptation) blocks, each pretrained to capture the unique artifacts of a specific generator, followed by attention-based feature fusion. Unlike conventional methods that seek a single universal solution, LEGO delegates unique artifact extraction to specialized LoRA modules by dividing its training procedure into two stages. Each LoRA module is individually trained on a single-generator dataset to learn generator-specific representations, then MLP and attention layers are trained on mixed datasets to dynamically regulate the contribution of each module. Benefiting from its modular yet robust design, LEGO can be naturally extended by incorporating new LoRA modules for adaptation to newly emerging next-generation datasets, while still achieving substantially better performance than prior SOTA methods with fewer than 30,000 training images, less than 10% of their training data, and only 5 epochs in each training stage.
Authors: Siyuan Du, Yuhang Zhou, Haolin Li, Jiangchao Yao, Haishuai Wang, Hui Lin, Ya Zhang, Yanfeng Wang
Abstract: Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap induced by the discrepancy between pre-training and downstream tasks, the real-world computation, and speed constraints. Relevant techniques that probably handle this challenge more or less suffer from some intrinsic limitations. For example, knowledge distillation (KD) assumes that teacher and student models share the same task, training strategy, and model structure family, while prevalent parameter-efficient fine-tuning (PEFT) fails to achieve personalized and lightweight deployment. Even the combination of PEFT and KD still struggles to resolve model structures and training strategies inconsistencies between teacher and student models, leading to inefficient knowledge transfer. In this study, we propose a novel framework called Deep Reprogramming Distillation (DRD) to combat the general adaptation challenge. Specifically, DRD introduces the novel reprogramming module that on the one side overcomes the domain and task discrepancy between pretraining and downstream scenarios, and on the other side builds the student-friendly efficient distillation from foundation models to lightweight downstream models. Furthermore, to mitigate variability under different training conditions, we design a centered kernel alignment (CKA) distillation method to promote robust knowledge transfer. Empirical results show that DRD surpasses previous PEFT and KD methods across 18 medical downstream tasks under different foundation models, covering various scenarios including 2D/3D classification and 2D/3D segmentation.
Authors: Liang Yao, Fan Liu, Shengxiang Xu, Chuanyi Zhang, Rui Min, Shimin Di, Yuhui Zheng
Abstract: Geospatial reasoning requires models to resolve complex spatial semantics and user intent into precise target locations for Earth observation. Recent progress has liberated the reasoning path from manual curation, allowing models to generate their own inference chains. Yet a final dependency remains: they are still supervised by human-annotated ground-truth coordinates. This leaves the reasoning process autonomous, but not its spatial endpoint, and prevents true self-evolution on abundant unlabeled remote sensing data. To break this bottleneck, we introduce RemoteZero, a box-supervision-free framework for geospatial reasoning. RemoteZero is motivated by a simple asymmetry: an MLLM is typically better at verifying whether a region satisfies a query than at directly generating precise coordinates. Leveraging this stronger discriminative ability, RemoteZero replaces geometric supervision with intrinsic semantic verification and enables GRPO training without box annotations. The resulting framework further supports iterative self-evolution, allowing the model to improve from unlabeled remote sensing imagery through its own verification signal. Experiments show that RemoteZero achieves competitive performance against strong supervised methods, demonstrating the potential of self-verifying training for geospatial reasoning localization.
Authors: Jiayang Li, Shuo Cao, Xiaohui Li, Zhizhen Zhang, Kaiwen Zhu, Yule Duan, Yu Qiao, Jian Zhang, Yihao Liu
Abstract: In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems.
Authors: Yijing Tu, Shaojin Wu, Mengqi Huang, Wenchuan Wang, Yuxin Wang, Chunxiao Liu, Zhendong Mao
Abstract: While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration costs and lack temporal guidance. To address these structural bottlenecks, we propose shifting the focus to streaming video generation. We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced Stream-T1, a pioneering comprehensive TTS framework exclusively tailored for streaming video generation. Specifically, Stream-T1 is composed of three units: (1) Stream -Scaled Noise Propagation, which actively refines the initial latent noise of the generating chunk using historically proven, high-quality previous chunk noise, effectively establishes temporal dependency and utilizing the historical Gaussian prior to guide the current generation; (2) Stream -Scaled Reward Pruning, which comprehensively evaluates generated candidates to strike an optimal balance between local spatial aesthetics and global temporal coherence by integrating immediate short-term assessments with sliding-window-based long-term evaluations; (3) Stream-Scaled Memory Sinking, which dynamically routes the context evicted from KV-cache into distinct updating pathways guided by the reward feedback, ensuring that previously generated visual information effectively anchors and guides the subsequent video stream. Evaluated on both 5s and 30s comprehensive video benchmarks, Stream-T1 demonstrates profound superiority, significantly improving temporal consistency, motion smoothness, and frame-level visual quality.
Authors: Shuo Liu, Lei Shi, Haowen Liu, Jing Xu, Yufei Gao, Yucheng Shi
Abstract: Reliable autonomous driving requires scene understanding that is semantically consistent across heterogeneous sensors and verifiable at the reasoning stage. However, many recent LLM-driven driving systems attach the language model as a post-processor and force it to reason over redundant or conflicting perception outputs, which can amplify hallucinated entities and unsafe conclusions. This paper proposes InfoCoordiBridge, a BEV-centric neuro-symbolic architecture that inserts an explicit coordination bridge between perception and language reasoning. InfoCoordiBridge comprises (i) a unified multi-agent perception layer that outputs typed structured facts together with modality-focused synopses, (ii) an ICA module that aligns and fuses multi-source outputs into a single SceneSummary, and (iii) an SSRE module that performs SceneSummary-grounded reasoning with verification. Experiments on nuScenes and Waymo show that ICA preserves competitive 3D detection accuracy while substantially improving fusion consistency, reducing redundancy to below 1% and achieving about 98% attribute agreement. On NuScenes-QA and a template-aligned Waymo-QA benchmark, SSRE improves factual grounding and reduces hallucinated entity mentions compared with representative VLM and agentic baselines. Overall, by coordinating multi-sensor outputs into a single conflict-aware SceneSummary before prompting, InfoCoordiBridge prevents redundant and cross-modally inconsistent perception evidence from propagating into high-level reasoning.
Authors: ZhiXin Sun
Abstract: In recent years, object detection has achieved significant progress, especially in the field of open-vocabulary object detection. Unlike traditional methods that rely on predefined categories, open-vocabulary approaches can detect arbitrary objects based on human-provided prompts. With the advancement of prompt-based detection techniques, models such as SAM3 can even outperform some category-specific detectors trained on particular datasets without requiring additional training on those datasets. However, despite these advancements, false positives and false negatives still occur. In practical engineering applications, persistent misdetections or missed detections of the same object are unacceptable. Yet retraining the model every time such errors occur incurs substantial costs in terms of human effort, computational resources, and time. Therefore, how to leverage existing false positive and false negative samples to prevent such errors from recurring remains a highly challenging and urgent problem. To address this issue, we propose EBOD (Example-Based Object Detection), which integrates a prompt-based detector (SAM3) with robust feature matching modules (DINOv3 and LightGlue). The proposed framework effectively suppresses the repeated occurrence of false positives and false negatives by leveraging previous error examples, without requiring additional model retraining. Code is available at https://github.com/sunzx97/examples_based_object_detection.
URLs: https://github.com/sunzx97/examples_based_object_detection.
Authors: Yuancheng Wei, Haojie Zhang, Linli Yao, Lei Li, Jiali Chen, Tao Huang, Yiting Lu, Duojun Huang, Xin Li, Zhao Zhong
Abstract: Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key benchmark for fine-grained change perception, cross-modal reasoning, and image editing data construction. However, existing benchmarks lack diversity and compositional complexity, and standard lexical-overlap metrics (e.g., BLEU, METEOR) fail to capture semantic consistency or penalize hallucinations, which together prevent a comprehensive and robust evaluation of multimodal large language models (MLLMs) on IDC. To address these gaps, we introduce DiffCap-Bench, a comprehensive IDC benchmark covering ten distinct difference categories to ensure diversity and compositional complexity. Furthermore, we propose an LLM-as-a-Judge evaluation protocol grounded in human-validated Difference Lists, enabling a robust assessment of models' ability to both capture and describe visual changes. Through extensive evaluation of state-of-the-art MLLMs, we reveal significant performance gaps between proprietary and open-source models, highlight the critical importance of reasoning capability, and identify clear limitations in model scaling. Our framework also demonstrates strong alignment with human expert judgments and strong correlation with downstream image editing data construction quality. These findings establish DiffCap-Bench as both a reliable IDC evaluation framework and a practical predictor of downstream utility. The benchmark and code will be made publicly available to support further research.
Authors: Jingtao Zhou, Xirui Kang, Feiyang Huang, Lai-Man Po
Abstract: Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglecting the spectral granularity essential for fine-grained discrimination. To bridge this, we introduce Disentangling Spectral Granularity for Prompt Learning (SpecPL), which approaches prompt learning from a novel spectral perspective via Counterfactual Granule Supervision. Specifically, we leverage a frozen VAE to decompose visual signals into semantic low-frequency bands and granular high-frequency details. A frozen Visual Semantic Bank anchors text representations to universal low-frequency invariants, mitigating overfitting. Crucially, fine-grained discrimination is driven by counterfactual granule training: by permuting high-frequency signals, we compel the model to explicitly distinguish visual granularity from semantic invariance. Uniquely, SpecPL serves as a universal plug-and-play booster, revitalizing text-oriented baselines like CoOp and MaPLe via visual-side guidance. Experiments on 11 benchmarks demonstrate competitive state-of-the-art performance, achieving a new performance ceiling of 81.51\% harmonic-mean accuracy. These results validate that spectral disentanglement with counterfactual supervision effectively bridges the gap in the stability-generalization trade-off. Code is released at https://github.com/Mlrac1e/SpecPL-Prompt-Learning.
Authors: Binh Long Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes, Peyman Moghadam
Abstract: We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association, which undermines cross-view consistency, lacks coherent instance-level reasoning, and limits precision in downstream 3D tasks. To address these limitations, our method jointly optimizes scene geometry and semantic representations by augmenting Gaussian splats with view-consistent feature fields. Specifically, we leverage multi-resolution hash embedding to efficiently encode language-aligned CLIP features, enabling dense and coherent language grounding in 3D space. We further train an instance feature field using contrastive loss over SAM masks, supporting fine-grained object distinction across views. At inference time, CLIP-encoded queries are matched against the learned features, followed by two-stage 3D clustering to retrieve relevant Gaussian groups. This enables our framework to identify arbitrary objects in 3D scenes based on natural language descriptions, without requiring category supervision or manual annotations. Experiments on standard benchmarks demonstrate that Ilov3Splat outperforms prior open-vocabulary 3D-GS methods in both object selection and instance segmentation, offering a flexible and accurate solution for language-driven 3D scene understanding. Project page: https://csiro-robotics.github.io/Ilov3Splat.
Authors: Zicheng Zhao, Chaofan Gan, Shijie Li, Weiyao Lin
Abstract: While Video Large Language Models (Video-LLMs) excel in general understanding, they exhibit systematic deficits in fine-grained physical reasoning. Existing interventions not only suffer from limited generalization but fundamentally conflate generative artifacts with genuine physical fallacies. Furthermore, we find that models fail systematically not only in anti-physics anomalies but also in counter-intuitive scenarios where visual facts contradict statistical expectations. Accordingly, we propose the Unified Attribution Theory: this dual failure stems not from perception deficiency, but from Semantic Prior Dominance -- the reasoning mechanism is deeply hijacked by internal narrative scripts. To address this, we construct the Programmatic Adversarial Curriculum (PACC), the first high-fidelity adversarial video dataset synthesized based on physical laws, thoroughly decoupling visual artifacts from logical errors. Concurrently, we design the Visual-Anchored Reasoning Chain (VARC) to force models to explicitly ground their judgments in low-level visual facts prior to logical adjudication. Experiments demonstrate that without invasive architectural modifications, standard LoRA fine-tuning with the PACC curriculum effectively neutralizes prior interference in state-of-the-art (SOTA) models, yielding a substantial leap in physical reasoning capabilities.
Authors: Nand Kumar Mishra, Dhruv Mishra, Dr Manu Pratap Singh
Abstract: Automatic brain tumor segmentation from multi-modal MRI remains challenging because volumetric models often incur substantial computational cost. This paper presents DALight-3D, a compact 3D U-Net variant that combines depthwise separable 3D convolutions, identifier-conditioned normalization, cross-slice attention, and adaptive skip fusion. The method is evaluated on the Medical Segmentation Decathlon Task01 BrainTumour benchmark under matched optimization settings against standard 3D U-Net, Attention U-Net, Residual 3D U-Net, and V-Net baselines. In the reported 50-epoch comparison, DALight-3D achieves a mean Dice of 0.727 with 2.22M parameters, compared with 0.710 Dice and 3.20M parameters for Residual 3D U-Net. Component-wise ablations show consistent performance degradation when SepConv, identifier-conditioned normalization, CSA, or SSFB is removed. These results indicate that DALight-3D offers a favorable accuracy-efficiency trade-off within the present benchmark setting.
Authors: Yunmu Wang, Zoubin Bi, Bowen Cai, Chenchu Rong, Jinlong Wang, Junchen Deng, Aocheng Huang, Jidong Jia, Huan Fu
Abstract: We present a single-image head mesh reconstruction framework that addresses the longstanding challenge of simultaneously preserving facial identity and producing industry-grade topology. Our framework adopts a coarse-to-fine optimization pipeline that refines a rigged template across three stages -- rig, joint, and vertex -- achieving stable convergence and consistent topology. To mitigate the ill-posed nature of single-image 3D face reconstruction and ensure identity preservation, we employ a normal consistency objective jointly with landmark alignment. To further preserve local surface structure and enforce topological regularity, we introduce geometry-aware constraints based on Gaussian curvature and conformal consistency, along with auxiliary regularizations that correct fine artifacts such as lip seams and eyelid discontinuities. Our hierarchical optimization with geometry-aware regularization yields meshes with semantically meaningful edge flow and industry-grade topology. After geometry reconstruction, we extract UV-space texture and normal maps to preserve appearance details for visualization and downstream use. In a user study with 22 professional technical artists, our results were assessed as approaching industry-grade usability, and 95% of participants ranked our method as the top-performing approach, underscoring its effectiveness for real-world digital human production.
Authors: Anagh Malik, Dorian Chan, Xiaoming Zhao, David B. Lindell, Oncel Tuzel, Jen-Hao Rick Chang
Abstract: We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downstream efficiency; and accessible, requiring minimal input, i.e., an unstructured dynamic point cloud, to construct. Specifically, Velox trains an encoder to compress spatiotemporal color point clouds into a set of dynamic shape tokens. These tokens are supervised using two complementary decoders: a 4D surface decoder, which models the time-varying surface distribution capturing the geometry; and a Gaussian decoder, which maps the tokens to 3D Gaussians, helping learn appearance. To demonstrate the utility of our representation, we evaluate it across three downstream tasks -- video-to-4D generation, 3D tracking, and cloth simulation via image-to-4D generation -- and observe strong performances in all settings.
Authors: Lihua Zhou, Mao Ye, Xiatian Zhu, Nianxin Li, Changyi Ma, Shuaifeng Li, Yitong Qin, Hongbin Liu, Jiebo Luo, Zhen Lei
Abstract: Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted visual embeddings of region proposals. While recent test-time adaptive object detection methods for VLM-based either rely on costly backpropagation or bypass semantic misalignment via external memory, none directly and efficiently align text and vision in a training-free manner. To address this, we propose Reward-Guided Semantic Evolution (RGSE), a training-free framework that directly refines the text embeddings at test time. Inspired by evolutionary search, RGSE treats text embedding adaptation as a semantic search process: it perturbs text embeddings as candidate variants, evaluates them via cosine similarity with current and historical high-confidence visual proposals as a reward signal, and fuses them into a refined embedding through reward-weighted averaging. Without any backpropagation, RGSE achieves state-of-the-art performance across multiple detection benchmarks while adding minimal computational overhead. Our code will be open source upon publication.
Authors: Muyao Peng, Shun Zou, Pei An, You Yang, Qiong Liu
Abstract: Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization. Existing deep learning-based I2P methods seek to align image and point cloud features in a learned representation space to establish correspondences, and have achieved promising results. However, when the inlier ratio of the initial matching pairs is low, conventional Perspective-n-Points (PnP) methods may struggle to achieve accurate results. To address this limitation, we propose Angle-I2P, an outlier rejection network that leverages angle-consistent geometric constraints and hierarchical attention. First, we design a scale-invariant, crossmodality geometric constraint based on angular consistency. This explicit geometric constraint guides the model in distinguishing inliers from outliers. Furthermore, we propose a global-tolocal hierarchical attention mechanism that effectively filters out geometrically inconsistent matches under rigid transformation, thereby improving the Inlier Ratio (IR) and Registration Recall (RR). Experimental results demonstrate that our method achieves state-of-the-art performance on the 7Scenes, RGBD Scenes V2, and a self-collected dataset, with consistent improvements across all benchmarks.
Authors: Kaili Zheng, Kaiwen Wang, Xun Zhu, Chenyi Guo, Ji Wu
Abstract: Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relationships through self-attention across all human queries. However, these approaches model interactions only implicitly and lack explicit reasoning about how humans interact with objects and with each other. In this paper, we propose InterMesh, a simple yet effective framework that explicitly incorporates human-environment interaction information into human mesh recovery pipeline. By leveraging a human-object interaction detector, InterMesh enriches query representations with structured interaction semantics, enabling more accurate pose and shape estimation. We design lightweight modules, Contextual Interaction Encoder and Interaction-Guided Refiner, to integrate these features into existing HMR architectures with minimal overhead. We validate our approach through extensive experiments on 3DPW, MuPoTS, CMU Panoptic, Hi4D, and CHI3D datasets, demonstrating remarkable improvements over state-of-the-art methods. Notably, InterMesh reduces MPJPE by 9.9% on CMU Panoptic and 8.2% on Hi4D, highlighting its effectiveness in scenarios with complex human-object and inter-human interactions.
Authors: Vlad Vasilescu, Daniela Faur, Teodor Costachioiu
Abstract: High-resolution satellite images are often scarce and costly, especially for remote areas or infrequent events. This shortage hampers the development and testing of machine learning models for land-cover classification, change detection, and disaster monitoring. In this paper, we tackle the problem of geometry-controlled high-resolution satellite image synthesis by adding control over existing pre-trained diffusion models. We propose a simple yet efficient method for controlling the synthesis process by leveraging only skip connection features using windowed cross-attention modules. Several previously established control techniques are compared, indicating that our method achieves comparable performance while leading to a better alignment with the geometry control map. We also discuss the limitations in current evaluation approaches, amplifying the necessity of a consistent alignment assessment.
Authors: Jiaqian Zhang, Hao Wei, Chenyang Ge, Yanhui Zhou
Abstract: Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or diffusion models, at the cost of substantial model complexity. To this end, we present an efficient perceptual image compression method that exploits the long-range modeling capability and linear computational complexity of state space models, with a particular focus on Mamba. Unlike existing methods that rely on an inherently fixed scanning order and consequently impair semantic continuity and spatial correlation, we develop a semantic-aware Mamba block (SAMB) to enable scanning guided by dynamically clustered semantic features, thereby alleviating the strict causality constraints and long-range information decay inherent to Mamba. Inspired by singular value decomposition, we design an SVD-inspired redundancy reduction module (SVD-RRM) that performs a low-rank approximation on the latent features by introducing a learnable soft threshold, leading to channel-wise redundancy information reduction. The proposed SAMB is integrated into both the encoder and decoder of the compression framework, whereas the SVD-RRM is incorporated only in the encoder. Extensive experiments demonstrate that our method performs favorably against state-of-the-art approaches in terms of rate-distortion-perception tradeoff and model complexity. The source code and pretrained models will be available at https://github.com/Jasmine-aiq/SAMIC.
Authors: Wei Liu, Jiaxin Lin, Rui Chen
Abstract: Recent studies have shown that large generative models can solve vision tasks they were not explicitly trained for. However, existing evidence relies on closed-source models~(Veo~3, Nano Banana Pro) or requires task-specific instruction tuning, leaving open whether publicly available image-editing models possess zero-shot vision abilities out of the box. We conduct a systematic evaluation of three open-source image-editing models -- Qwen-Image-Edit, FireRed-Image-Edit, and LongCat-Image-Edit -- on dense visual prediction tasks \emph{without any fine-tuning}. We benchmark monocular depth estimation on NYUv2 and DIODE, surface normal estimation on NYUv2, and semantic segmentation on Cityscapes, covering both geometric and semantic scene understanding. Results show that open-source image-editing models exhibit non-trivial zero-shot visual understanding. On NYUv2 surface normals, FireRed-Image-Edit achieves a mean angular error of $17.69^\circ$, surpassing the fine-tuned Marigold ($20.86^\circ$) and matching the instruction-tuned Vision Banana ($17.78^\circ$) without any task-specific training. On NYUv2 depth estimation, LongCat-Image-Edit obtains $\delta_1{=}0.822$ with affine alignment, and Qwen-Image-Edit leads on DIODE Indoor ($\delta_1{=}0.868$). On Cityscapes semantic segmentation, Qwen-Image-Edit reaches 25.7 mIoU at the 19-class level and 49.5 mIoU at a coarser 7-category level. By comparing three independently trained editors, we test whether zero-shot vision ability is an emergent property of image-editing pretraining rather than a model-specific artifact. Code, evaluation scripts, and all results are publicly released to serve as a reproducible baseline for future work.
Authors: Shitong Shao, Zikai Zhou, Haopeng Li, Yingwei Song, Wenliang Zhong, Lichen Bai, Zeke Xie
Abstract: Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \textbf{\texttt{LIVEditor}} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor achieves a $\sim$60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.
Authors: Boyue Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu
Abstract: UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance matching, which struggles to establish reliable correspondence under drastic view differences, leading to tracking unreliability. To address these limitations, we propose VL-UniTrack, a fully unified framework enhanced by visual-language prompts. By encoding features from both views within a single shared encoder, our method breaks the barrier of feature isolation to facilitate sufficient cross-view interaction. To overcome the ambiguity caused by relying solely on appearance matching, we design visual-language geometric prompting module, which fuses language descriptions with visual features to generate learnable prompts. These prompts are then fed into our prompt-guided cross-view adapter module to enable sufficient cross-view feature interaction and to guide the learning of view-specific feature representations. Furthermore, a confidence-modulated mutual distillation loss is proposed to regularize the training by mitigating noise propagation. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the latest benchmark. The code can be downloaded in https://github.com/xuboyue1999/VL-UniTrack.git
Authors: Kunyu Li, Fei Wang, Lichao Zhang, Junjie Liu, Bihong Li
Abstract: Light field (LF) image super-resolution benefits from Epipolar Plane Images (EPIs), whose line slopes explicitly encode disparity. However, existing Transformer-based LF SR methods mainly attend to horizontal and vertical EPIs, leaving diagonal epipolar geometry underexplored. We present GTF, an omnidirectional EPI Transformer that explicitly models horizontal, vertical, 45-degree, and 135-degree EPIs within a unified reconstruction framework. GTF combines directional EPI processing, MacPI-based prior injection, adaptive directional fusion, and a topology-preserving feed-forward network to better exploit LF geometry. For the NTIRE 2026 fidelity tracks, we use GTF as the main model, while a lightweight GTF-Tiny variant targets the efficiency track. On five standard LF SR benchmarks covering both real-captured and synthetic scenes, GTF reaches 32.78 dB without inference-time enhancement, and stronger inference settings with EPSW and test-time augmentation further improve performance. Under the NTIRE 2026 efficiency constraint, GTF-Tiny attains 32.57 dB with only 0.915M parameters and 19.81 GFLOPs. In the NTIRE 2026 Light Field Image Super-Resolution Challenge, our submissions rank 3rd on Track 1 and Track 3 and 4th on Track 2. Architecture-evolution, channel-width, and inference analyses further support the effectiveness of diagonal EPI modeling, directional fusion, and the lightweight design.
Authors: Zishen Qu, Xuesong Li, Haijian Gu, Hongwei Kang, Quan Meng, Tianrui Niu, Xin Yang, Ruidong Pan
Abstract: Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have shown that diffusion models (e.g., Stable Diffusion) can provide rich multimodal semantic features, leading to studies of using diffusion models as feature extractors for segmentation tasks. Such methods, however, inherit the generative natures of diffusion models that are harmful to discriminative segmentation tasks. In response, we propose RLFSeg, a novel framework that leverages Rectified Flow to learn direct mapping from the image to the segmentation mask within the latent space. The model is thus freed from the noise-denoise process and the need to optimize the time step of diffusion models, resulting in substantially better performance than previous diffusion-based methods, especially on zero-shot scenarios. By introducing label refinement and an Adaptive One-Step Sampling strategy, the model achieves higher accuracy even on a single inference step. The framework redirects a pretrained generative model to the discriminative segmentation task with zero modification to model structure, thus reveals promising application potential and significant research value.
Authors: Zhiwei Yang, Pengfei Song, Yucong Meng, Kexue Fu, Shuo Wang, Zhijian Song
Abstract: Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to generate CAMs in WSSS. However, previous WSSS methods solely adopt CLIP's vision-language paired property for dense localization, neglecting its inherently limited dense knowledge across both visual and text modalities, which renders CAM generation suboptimal. In this work, we propose DiCLIP, a novel WSSS framework that leverages the generative diffusion model to enhance CLIP's dense knowledge across two modalities. Specifically, Visual Correlation Enhancement (VCE) and Text Semantic Augmentation (TSA) modules are proposed for dense prediction enhancement. To improve the spatial awareness of visual features, our VCE module utilizes diffusion's reliable spatial consistency to mitigate the over-smoothing issue in CLIP's attention. It designs the Attention Clustering Refinement (ACR) module to reliably extract diverse correlation maps from the diffusion model. The correlation maps act as a diversity bias for CLIP's self-attention, recursively pushing its visual features towards a more discriminative dense distribution. To augment the semantics of text embeddings, our TSA module argues that a single text modality is insufficient to encompass the variability of visual categories. Thus, we leverage diffusion's generative power to maintain a dynamic key-value cache model, shifting CAM generation from a patch-text matching mechanism to a novel visual knowledge retrieval paradigm. With these enhancements, DiCLIP not only outperforms state-of-the-art methods on PASCAL VOC and MS COCO but also significantly reduces training costs. Code is publicly available at https://github.com/zwyang6/DiCLIP.
Authors: Yichen Li, Qiankun Liu, Ying Fu
Abstract: Traditional one-shot detection methods have addressed the closed-set problem in object detection, but the high cost of data annotation remains a critical challenge. General unsupervised methods generate pseudo boxes without category labels, thus failing to achieve category-aware classification. To overcome these limitations, we propose Reference-based Category Discovery (RefCD), an unsupervised detector that enables category-aware\footnotemark[1] detection without any manually annotated labels. It leverages feature similarity between predicted objects and unlabeled reference images. Unlike previous unsupervised methods that lack category guidance and one-shot methods which require labeled data, RefCD introduces a carefully designed feature similarity loss to explicitly guide the learning of potential category-specific features. Additionally, RefCD supports category-agnostic detection without reference images, serving as a unified framework. Comprehensive quantitative and qualitative analysis of category-aware and category-agnostic detection results demonstrates its effectiveness, and RefCD can learn category information in an unsupervised paradigm even without category labels.
Authors: Kai Zou, Zhiwei Zhao, Bin Liu, Nenghai Yu
Abstract: Composition is a cornerstone of visual aesthetics, influencing the appeal of an image. While its principles operate independently of specific content, in practice, composition is often coupled with semantics. As a result, existing methods often enhance composition either through implicit learning or by semantics-based layout control, rather than explicitly modeling composition itself. To address this gap, we introduce Composer, a framework rooted in aesthetic theory, designed to model composition in a semantic-agnostic manner. First, it supports composition transfer by extracting key composition-aware representations from a reference image and leveraging a tailored conditional guidance module to control composition based on pre-trained diffusion models. Second, when users specify only text themes without a composition reference, Composer supports theme-driven composition retrieval by leveraging the in-context learning capabilities of Large Vision-Language Models (LVLMs), achieving explicit composition planning. To enhance composition in a reference-free mode, we conduct text-to-composition fine-tuning on the trained control module to enable implicit composition planning. Furthermore, we curated a high-quality dataset comprising 2 million image-text pairs using state-of-the-art generative models to support model training. Experimental results demonstrate that Composer significantly enhances aesthetic quality in text-to-image tasks and facilitates personalized composition control and transfer, offering users precision and flexibility in the creative process.
Authors: Zishu Zhou, Zaipeng Xie, Xuanyao Jie
Abstract: Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled test streams, yet existing methods largely inherit assumptions from vision tasks and underexploit the inherent inter-window temporal structure in WHAR streams. In this paper, we revisit such temporal structure as a feature-conditioned inference signal rather than merely an output-space smoothing prior. We derive the insight that temporal continuity and observation-induced feature deviations provide complementary cues for determining when to preserve or release temporal inertia and where to route prediction refinement during likely transitions. Building upon this insight, we propose SIGHT, a lightweight and backpropagation-free TTA framework for WHAR, enabling real-time edge deployment. SIGHT estimates predictive surprise by comparing the current feature with a prototype-based expected state, and then uses the resulting feature deviation to guide geometry-aware transition routing based on prototype alignment and stream-level marginal habit tracking. Evaluations on real-world datasets confirm that SIGHT outperforms existing TTA baselines while reducing computational and memory costs.
Authors: Huan Zhang, Lianghong Tan, Yichu Xu, Jiangzhong Cao, Huanqi Wu, Linwei Zhu, Xu Zhang
Abstract: Printed Circuit Board (PCB) defect inspection faces two compounding challenges: scarce and imbalanced defect samples that limit model training, and insufficient feature representation under complex circuit backgrounds. Existing generation methods rely on single-modality conditions with coarse structural control, while detection methods improve architectures without addressing the data bottleneck. To resolve both challenges jointly, we propose a generation-assisted PCB defect inspection framework that integrates controlled defect synthesis with task-specific defect detection. On the generation side, a Multi-modal Condition Generator extracts complementary edge, depth, and text conditions in parallel. A ScaleEncoder then embeds these conditions into the diffusion U-Net at four resolutions, and a Condition Modulation applies FiLM-style spatially-adaptive modulation at each scale, enabling structurally aligned and defect-aware sample synthesis. On the detection side, an Inverted Residual Shift Attention couples self-attention with shift-wise convolution to jointly capture global context and local texture, and a Cross-level Complementary Fusion Block generates pixel-level gates for selective cross-level feature fusion. The synthesized samples directly enrich the detection training set, so that improvements in generation compound with improvements in detection. Extensive experiments on DsPCBSD+ demonstrate that UniPCB achieves mAP@0.5 of 98.0% and mAP@0.5:0.95 of 61.8% on defect detection, surpassing all compared methods, while the generation branch attains an FID of 129.61 and SSIM of 0.619, outperforming existing conditional generation approaches.
Authors: Qiming Li, Zekai Ye, Xiaocheng Feng, Weihong Zhong, Libo Qin, Ruihan Chen, Lei Huang, Baohang Li, Kui Jiang, Yaowei Wang, Ting Liu, Bing Qin
Abstract: Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or decoding strategies which significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly enhanced when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-guided Visual Attention Steering (CAST), a training-free, plug-and-play hallucination mitigation method that leverages the attention activation pattern corresponding to caption queries to enhance LVLMs' visual perception capability. Specifically, we use probing techniques to identify attention heads that are highly sensitive to caption queries and estimate optimized steering directions for their outputs. This steering strengthens LVLM's fine-grained visual perception capabilities, thereby effectively mitigating object hallucination. CAST reduced object hallucination by an average of 6.03% across five widely used LVLMs and five benchmarks including both discriminative and generative tasks, demonstrating state-of-the-art performance while adding little inference cost and preserving other foundational capabilities.
Authors: Xuhai Chen, Zhi Cen, Huaijin Pi, Sida Peng, Xiaowei Zhou, Yong Liu
Abstract: Generating realistic reactive motions, in which one person reacts to the fixed motions of others, is challenging due to strict interaction constraints and a limited feasible solution space. This paper focuses on a typical scenario: duet dance, where high-quality data is scarce, motion patterns are complex, and the details of human interactions are both intricate and abundant. To tackle these challenges, we propose a novel two-stage framework. In the first stage, we introduce a motion VQ-VAE with separate body-part encoders and a joint decoder, enabling specialized codebooks to enhance representation capacity while dynamically modeling dependencies across body parts during decoding, thereby preventing inconsistencies in the generated motions. In the second stage, we propose a contact-aware diffusion model for reactive motion generation that jointly generates motion and a contact matrix between individuals, enabling explicit interaction modeling and providing guidance toward more precise and constrained interaction dynamics during sampling. Experiments show that our method outperforms Duolando with lower $\text{FID}_k$ (8.89 vs. 25.30) and $\text{FID}_{cd}$ (8.01 vs. 9.97), as well as a higher BED (0.4606 vs. 0.2858), indicating improved interaction fidelity and rhythmic synchronization.
Authors: Xiaopei Zhu, Guanning Zeng, Zhanhao Hu, Jun Zhu, Xiaolin Hu
Abstract: Visible-thermal (RGB-T) object detection is a crucial technology for applications such as autonomous driving, where multimodal fusion enhances performance in challenging conditions like low light. However, the security of RGB-T detectors, particularly in the physical world, has been largely overlooked. This paper proposes a novel approach to RGB-T physical attacks using adversarial clothing with a non-overlapping RGB-T pattern (NORP). To simulate full-view (0$^{\circ}$--360$^{\circ}$) RGB-T attacks, we construct 3D RGB-T models for human and adversarial clothing. NORP is a new adversarial pattern design using distinct visible and thermal materials without overlap, avoiding the light reduction in overlapping RGB-T patterns (ORP). To optimize the NORP on adversarial clothing, we propose a spatial discrete-continuous optimization (SDCO) method. We systematically evaluated our method on RGB-T detectors with different fusion architectures, demonstrating high attack success rates both in the digital and physical worlds. Additionally, we introduce a fusion-stage ensemble method that enhances the transferability of adversarial attacks across unseen RGB-T detectors with different fusion architectures.
Authors: Jingtao Liu, Peiliang Gong, Chuhang Zheng, Yiheng Liu, Qi Zhu
Abstract: EEG-based visual neural decoding aims to align neural responses with visual stimuli for tasks such as image retrieval. However, limited paired data and a fundamental mismatch between high-fidelity digital images and biological visual perception - distorted by retinotopic mapping and subject-specific neuroanatomy - severely impede cross-modal alignment. To address this, we propose MB2L, a Multi-Level Bidirectional Biomimetic Learning framework that incorporates structured physiological inductive biases into representation learning. Specifically, we propose Adaptive Blur with Visual Priors to mitigate perceptual-structural mismatch by reweighting visual inputs according to retinotopic priors. We further propose Biomimetic Visual Feature Extraction to learn multi-level visual representations consistent with hierarchical cortical processing, enhancing subject-invariant encoding. These modules are jointly optimized via Multi-level Bidirectional Contrastive Learning, which aligns EEG and visual features in a shared semantic space through bidirectional contrastive objectives. Experiments show MB2L achieves 80.5% Top-1 and 97.6% Top-5 accuracy on zero-shot EEG-to-image retrieval, significantly outperforming prior methods and demonstrating strong generalization across subjects and experimental settings.
Authors: Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng, Bing Ma, Kai Yu, Sen Liang, Wenyue Li, Tianxiang Zheng, Qinglin Lu, Zhen Cui
Abstract: Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose \textit{FaithfulFaces}, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur.
Authors: Alexander Vedernikov
Abstract: Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision, making post-hoc dataset revision a practical problem. Existing noisy-label and data-cleaning methods largely operate at the sample level before or during training, but do not directly address a different question: once a model has already been trained, can the influence of an entire problematic subject be removed without full retraining? We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition. Starting from a baseline trained on all subjects, we rank candidate harmful subjects using a model-dependent proxy, apply a lightweight approximate unlearning update, and compare the result against an oracle model retrained from scratch on the retained subjects only. We instantiate this protocol on DAiSEE and EngageNet using Tensor-Convolution and Convolution-Transformer Network (TCCT-Net) as a fixed platform and evaluate three matched model states under the same removal scenario: baseline, unlearned, and oracle. In representative K=3 forget-set settings, the unlearned model recovers 89.3% and 92.5% of the oracle gain on EngageNet and DAiSEE, respectively, at roughly one quarter of retraining cost. Across the tested small-audit regimes, effectiveness is strongest at an intermediate forget-set size, indicating that approximate subject-level unlearning is a useful low-cost correction mechanism, but one whose benefit depends on subject selection quality and removal regime.
Authors: Laura Bravo-S\'anchez, Matthieu Armando, Romain Br\'egier, Gr\'egory Rogez, Serena Yeung-Levy, Fabien Baradel
Abstract: Recovering 3D human pose and shape from a single image remains a cornerstone of human-centric vision, yet most methods assume adult subjects and optimize each person independently. These assumptions fail in real-world, all-age scenes, where body proportions and depth must be resolved jointly. We introduce Anny-Fit, a multi-person, camera-space optimization framework for all-age 3D human mesh recovery (HMR). Unlike existing per-person fitting methods, Anny-Fit jointly optimizes all individuals directly in the camera coordinate system, enforcing global spatial consistency. At the core of our approach is the use of multiple forms of expert knowledge -- including metric depth maps, instance segmentation, 2D keypoints, and, VLM-derived semantic attributes such as age and gender -- each obtained from dedicated off-the-shelf networks. These complementary signals jointly guide the optimization, constraining the depth-scale ambiguity characteristic of all-age scenes. Across diverse datasets, Anny-Fit consistently improves 2D reprojection accuracy (+13 to 16), relative depth ordering (+6 to 7), 3D estimation error (-9 to -29) and shape estimation (+25 to +82), producing more coherent scenes. Finally, we show that VLM-based semantic knowledge can be distilled into an HMR model via the pseudo-ground-truth annotations produced by Anny-Fit on training data, enabling it to learn semantically meaningful shape parameters while improving HMR performance. Our approach bridges adult-only and all-age modeling by enabling zero-shot adaptation of adult-trained HMR pipelines to the full age spectrum without retraining. Code is publicly available at https://github.com/naver/anny-fit.
Authors: Yingdong Gu, Shaocheng Yan, Zhenjun Zhao, Yuan Kou, Jianxin Luo, Pengcheng Shi, Jiayuan Li
Abstract: Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with feature-based localization. These methods rely on direct matching between 2D query features and the 3D Gaussian feature field, but this often results in mismatches due to an inherent bias in the learned Gaussian feature. We theoretically analyze the feature learning process in 3DGS, revealing that the widely adopted $\alpha$-blending optimization inherently introduces bias into 3D point features. This bias stems from the entanglement between individual Gaussians and their neighboring Gaussians, making the learned features unsuitable for precise matching tasks. Motivated by these findings, we propose ULF-Loc, an unbiased landmark feature framework that replaces biased feature optimization with geometry-weighted feature fusion. We further introduce keypoint-consensus landmark sampling to select reliable Gaussians and local geometric consistency verification to reject mismatches caused by rendering artifacts. On the Cambridge Landmarks dataset, ULF-Loc reduces the mean median translation error by 17\% compared to the state-of-the-art, while achieving superior efficiency with only 1/10 the training time and 1/6 the GPU memory of STDLoc.
Authors: Jinzhen Han, JinByeong Lee, Jisung Kim, HongSik Yun
Abstract: Building height (BH) and building footprint (BF) jointly describe the vertical and horizontal extent of the built environment and are required inputs for urban climate, disaster-risk, and population-mapping models. The two parameters are coupled through floor-area-ratio (FAR) constraints, yet remote-sensing approaches typically treat them as independent regression targets. We argue that explicitly encoding this cross-task coupling is more impactful than further refining individual encoders, and propose MorphoFormer, a joint BH/BF estimation framework built around two complementary mechanisms: (i) a BF-Guided Task Decoder (BGTD) that gates the height branch via cross-attention on a footprint-derived morphology context, and (ii) a Morphology Consistency Loss (MCL) that supervises a height-from-footprint surrogate against the ground-truth BH, indirectly forcing the BF feature to encode height-correlated structure. The encoder is a single-stage Swin backbone fed by Sentinel-1 SAR, Sentinel-2 multispectral, and DEM inputs, trained and evaluated on a geo-blocked split of 54 cities. Against a Swin-MTL baseline at identical receptive field, MorphoFormer reduces BH test RMSE from 3.39 to 3.15 m (R^2 improves 0.62 -> 0.67) with BF R^2 stable at 0.80. Controlled ablations at identical capacity attribute most of this 0.24 m improvement to the two proposed mechanisms: removing BGTD raises BH RMSE by 0.11 m and removing MCL raises it by 0.11 m, with the residual approximately 0.02 m falling within the noise floor of encoder-side variations. Because both mechanisms act on cross-task representations rather than pixels, the design carries no intrinsic dependence on input resolution.
Authors: Yasod Ginige, Ransika Gunasekara, Darsha Hewavitharana, Manjula Ariyarathne, Peshala Jayasekara, Ranga Rodrigo
Abstract: Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle dataset and a thermal maritime dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above datasets in mAP scores, respectively. We also plan to make our thermal dataset available, the first of its kind for maritime vessel identification.
Authors: Eugene Kofi Okrah Denteh, Blessing Agyei Kyem, Joshua Kofi Asamoah, Armstrong Aboah
Abstract: Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on appearance cues with standard temporal pooling, which can bias predictions toward static infrastructure, whereas signal-based approaches characterize temporal dynamics but lack the spatial context needed for scene-level localization. These complementary limitations motivate a unified framework that links motion evidence to spatial feature selection while preserving data-adaptive temporal characterization. This study therefore proposes FLO-EMD, a hybrid approach that couples motion-guided attention with empirical, data-driven temporal decomposition. Dense optical flow guides channel and spatial attention so that RGB features are refined toward motion-relevant regions. In parallel, aggregated flow statistics form compact motion traces that are decomposed using Empirical Mode Decomposition (EMD) to extract intrinsic temporal components. The resulting EMD embedding is fused with learned spatiotemporal representations to classify light, medium, and heavy congestion. Experiments on 1,050 five-second clips from four surveillance networks show that FLO-EMD achieves 97.5% overall test accuracy (weighted F1 = 0.9742), outperforming established baselines and remaining robust across diverse environmental conditions; ablation and sensitivity analyses further quantify the contributions of EMD, the number of intrinsic mode functions, and the selected motion descriptors.
Authors: Anjith George, Sebastien Marcel
Abstract: Heterogeneous Face Recognition (HFR) aims at matching face images captured across different sensing modalities, such as thermal-to-visible or near-infrared-to-visible, enhancing the usability of face recognition systems in challenging real-world conditions. Although recent HFR methods have achieved significant improvements in performance, many rely on computationally expensive models, making them impractical for deployment on resource-limited edge devices. In this work, we introduce a lightweight yet effective HFR framework by adapting a hybrid CNN-Transformer model originally developed for RGB homogeneous face recognition. Our approach enables efficient end-to-end training with only a small amount of paired heterogeneous data, while still maintaining strong performance on standard RGB face recognition benchmarks. This makes it suitable for both homogeneous and heterogeneous settings. Comprehensive experiments on several challenging HFR and face recognition benchmarks show that our method achieves state-of-the-art or competitive performance while keeping computational requirements low.
Authors: Berk Sezer, Ali G\"orkem K\"u\c{c}\"uk, Erol \c{S}ahin, Sinan Kalkan
Abstract: While zero-shot appearance-based 3D gaze estimation offers significant cost-efficiency by directly mapping RGB images to gaze vectors, its reliability in Human-Robot Interaction (HRI) settings remains uncertain. Existing benchmarks frequently overlook fundamental HRI conditions, such as dynamic camera viewpoints and moving targets in video. Furthermore, current cross-dataset evaluations often suffer from a complexity gap, where methods trained on diverse datasets are tested on significantly smaller and less varied sets, failing to assess true robustness. To bridge these gaps, we introduce Gaze4HRI, a large-scale dataset (50+ subjects, 3,000+ videos, 600,000+ frames) designed to evaluate state-of-the-art performance against critical HRI variables: illumination, head-gaze conflict, as well as the motion of camera and gaze target in video. Our benchmark reveals that all evaluated methods fail in at least one condition, identifying steeply-downward gaze as a universal failure point. Notably, PureGaze trained on the ETH-X-Gaze dataset uniquely maintains resilience across all other conditions. These results challenge the recent focus in the literature on complex spatial-temporal modeling and Transformer-based architectures. Instead, our findings suggest that extensive data diversity, as exemplified by the ETH-X-Gaze dataset, serves as the primary driver of zero-shot robustness in unconstrained environments, while resilience-enhancing frameworks, such as PureGaze's self-adversarial loss for gaze feature purification, provide a substantial further improvement. Ultimately, this study establishes a rigorous benchmark that provides practical guidelines for practitioners as well as reshaping future research. The dataset and codes are available at https://gazeforhri.github.io.
Authors: Miguel Diaz Benito, Cecilia Diana Albelda, Alvaro Garcia Martin, Jesus Bescos Cano, Marcos Escudero-Vinolo, Juan C. SanMiguel
Abstract: Access to diverse, well-annotated medical images with interactive learning tools is fundamental for training practitioners in medicine and related fields to improve their diagnostic skills and understanding of anatomical structures. While medical atlases are valuable, they are often impractical due to their size and lack of interactivity, whereas online image search may provide mislabeled or incomplete material. To address this, we propose MIRAGE, a multimodal medical text and image retrieval and generation system that allows users to find and generate clinically relevant images from trustworthy sources by mapping both text and images to a shared latent space, enabling semantically meaningful queries. The system is based on a fine-tuned medical version of CLIP (MedICaT-ROCO), trained with the ROCO dataset, obtained from PubMed Central. MIRAGE allows users to give prompts to retrieve images, generate synthetic ones through a medical diffusion model (Prompt2MedImage) and receive enriched descriptions from a large language model (Dolly-v2-3b). It also supports a dual search option, enabling the visual comparison of different medical conditions. A key advantage of the system is that it relies entirely on publicly available pretrained models, ensuring reproducibility and accessibility. Our goal is to provide a free, transparent and easy-to-use didactic tool for medical students, especially those without programming skills. The system features an interface that enables interactive and personalized visual learning through medical image retrieval and generation. The system is accessible to medical students worldwide without requiring local computational resources or technical expertise, and is currently deployed on Kaggle: http://www-vpu.eps.uam.es/mirage
Authors: Xinze Li, Bohan Yang, Pengxu Chen, Yiyuan Wang, Hongcheng Luo, Wentao Cheng, Weifeng Su
Abstract: 3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using differentiable Gaussian primitives. However, efficiently computing precise Gaussian-tile intersections remains a critical task in the rasterization pipeline. To this end, we propose QuadBox, a method that leverages four axis-aligned bounding boxes to tightly encapsulate projected Gaussians in a discrete manner. First, we derive a geometry-aware stretching factor that enables the construction of a tile-aligned QuadBox, which covers the elliptical projection and largely excludes irrelevant tiles. Second, we introduce QPass, a single-pass tile traversal algorithm that exhaustively exploits the discrete nature of QuadBox, ensuring that the tile intersection check is performed with simple interval tests. Experiments on public datasets show that our method accelerates the rendering speed of 3DGS by 1.85$\times$. Code is available at \href{https://github.com/Powertony102/QuadBox}{https://github.com/Powertony102/QuadBox}.
URLs: https://github.com/Powertony102/QuadBox, https://github.com/Powertony102/QuadBox
Authors: Sapna Sachan, Amulya Kumar Mahto
Abstract: Computed tomography (CT) is indispensable for clinical diagnosis and image-guided interventions but exposes patients to ionizing radiation, motivating the development of safer imaging alternatives. Ultrasound (US) is non-ionizing and widely accessible; however, it is highly operator dependent and lacks quantitative tissue characterization, often leading to diagnostic uncertainty and unnecessary CT examinations. This work presents a 3D ultrasound-derived pseudo-CT (UD-pCT) framework that generates CT-like anatomical reference volumes inferred from US, without aiming to reproduce physically accurate Hounsfield Units. Paired 3D kidney US and CT volumes from the TRUSTED dataset are first spatially aligned using a landmark-based multimodal registration pipeline, creating high-quality paired inputs for supervised training of an adversarial framework. The proposed Bottleneck Transformer Residual U-Net3D (BT-ResUNet3D) model employs a 3D residual encoder-decoder generator augmented with a transformer bottleneck, enabling effective modeling of fine-grained local anatomical structures as well as long-range volumetric dependencies, while a 3D Conditional PatchGAN discriminator enforces local structural realism in the synthesized pseudo-CT volumes. Quantitative evaluation using PSNR and SSIM demonstrates that the proposed method outperforms established baselines in structural fidelity and perceptual image quality. The UD-pCT volumes provide real-time anatomical reference for operator guidance, potentially reducing acquisition variability and unnecessary CT use. A limitation of this study is the relatively small paired dataset, which may limit the generalizability of the proposed model.
Authors: Haibin He, Maoyuan Ye, Jing Zhang, Juhua Liu, Bo Du
Abstract: Video text-based visual question answering (Video TextVQA) aims to answer questions by reasoning over visual textual content appearing in videos. Despite the strong multimodal video understanding capabilities of recent Video-LLMs, their performance on existing Video TextVQA benchmarks remains limited. To better understand this gap, we conduct an upper-bound analysis through frame-wise question answering, counting a sample as correct if any frame yields the right answer, which significantly outperforms direct video-based inference and reveals a substantial performance gap. The results suggest that the primary bottleneck lies in the localization of key question-relevant evidence, rather than in reasoning capacity itself. Building on this insight, we propose a question-guided agent framework that explicitly anchors the relevant keyframes before answering. The approach operates effectively in a training-free setting and consistently surpasses direct video inference. With additional supervised fine-tuning (SFT) and reinforcement learning (RL), it achieves an average improvement of +12.12 in accuracy and +11.15 in ANLS across benchmarks, establishing new state-of-the-art results. Our study underscores the critical role of explicit keyframe anchoring for advancing Video TextVQA. The code will be publicly released.
Authors: Mohamed Elhabebe, Ayman El-Baz, Qing Liu
Abstract: Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairness across diverse patient populations remains a significant challenge. In this paper, we propose FairEnc, a fair pretraining method for vision-language models (VLMs) that enables simultaneous debiasing across multiple sensitive attributes. FairEnc jointly mitigates biases in both textual and visual modalities with respect to multiple sensitive attributes, including race, gender, ethnicity, and language. Specifically, for the textual encoder, we leverage a large language model to generate synthetic clinical descriptions with varied sensitive attributes while preserving disease semantics, and employ a contrastive alignment objective to encourage demographic-invariant representations. For the visual encoder, we propose a dual-level fairness strategy that combines mutual information regularization to reduce statistical dependence between learned features and demographic groups, with multi-discriminator adversarial debiasing. Comprehensive experiments on the publicly available Harvard-FairVLMed dataset demonstrate that FairEnc effectively reduces demographic disparity as measured by DPD and DEOdds while achieving strong diagnostic performance under both zero-shot and linear probing evaluations. Additional experiments on the private FairFundus dataset show that FairEnc consistently preserves fairness advantages under cross-domain and cross-modality settings and maintains diagnostic performance within a competitive range. These results highlight FairEnc's ability to generalize fairness under distribution shifts, supporting its potential for more equitable deployment in real-world clinical settings. Our codebase and synthetic clinical notes are available at https://github.com/Mohamed-Elhabebe/FairEnc
Authors: Jens van Bijsterveld, Daniele Avitabile, Fons J. Verbeek, Rita Pucci
Abstract: In this paper, we explore deep learning techniques for individual identification of animals based on their skin patterns. Individual identification is crucial in biodiversity monitoring, since it enables analysis of decline or growth of populations, or intra-species interactions within populations. Models trained for the task of individual identification often do not focus on the skin pattern of animals, but on background details or body shape details. These characteristics are not individually specific, or can change drastically through time. We focus on techniques that will make machine learning models more responsive to skin pattern structure when extracting individual visual embeddings from images. For this, we explore image inpainting of task-specific masks as an auxiliary task to enhance ML-based individual identification from animal skin patterns. We propose a comparative analysis among four models as an encoder backbone for the individual identification task. We focus on the case study of zebrafish, which is a widely recognized biological model organism, and which exhibits individually identifying skin patterns. To evaluate encoder backbone performance, we present standard metrics for classification accuracy, embedding clustering metrics, and GradCAM visualizations.
Authors: Anju Rani, Daniel Ortiz-Arroyo, Petar Durdevic
Abstract: The condition monitoring (CM) of synthetic fibre ropes (SFRs) used in offshore, maritime, and industrial settings demands more than a classifier: inspectors need continuous severity estimates, maintenance recommendations, anomaly flags, deterioration timelines, and automated reports, all from a single inspection image. We present DART (Damage Assessment via Rope Transformer), a vision-language foundation model that addresses the full rope inspection workflow through a unified multi-task architecture. DART extends the Joint-Embedding Predictive Architecture (JEPA) to the cross-modal domain by coupling a Vision Transformer (ViT-H/14) with Llama-3.2-3B-Instruct via a Severity-Conditioned Cross-Modal Fusion (SC-CMF) module. Three architectural innovations drive the model's versatility: (1) HD-MASK, a saliency-guided masking strategy that focuses self-supervised reconstruction on damage-dense patches; (2) per-class learnable severity gates that adaptively weight language grounding by damage category; and (3) a Contrastive Damage Disentanglement (CDD) loss that shapes the embedding space to simultaneously encode damage type, severity ordering, and cross-modal semantics. Trained once on 4,270 images spanning 14 fine-grained rope damage classes, the frozen DART backbone supports downstream tasks without any task-specific fine-tuning: damage classification (93.22 % accuracy, 91.04 % macro-F1, +38.5 pp over a vision-only baseline), continuous severity regression (Spearman rho = 0.94, within-1-ordinal accuracy 99.6 %), few-shot recognition (89.2 % macro-F1 at 20 shots). These results demonstrate that DART functions as a general-purpose CM backbone that goes well beyond classification, providing actionable inspection intelligence from a single shared representation.
Authors: Rapha\"el Del\'ecluse, Hazem Wannous, Laurent Guimas
Abstract: This companion paper reports the ICPR 2026 TVRID competition on privacy-aware top-view person re-identification. We present the competition setting, the released RGB-Depth dataset, and a summary of final results with descriptions of the top entries. TVRID contains 86 identities captured by four synchronized overhead Intel RealSense D455 cameras, with paired RGB/Depth streams and structured geometric variation across flat, ascent, descent, and oblique viewpoints. The evaluation protocol includes three tracks: RGB Re-ID, Depth Re-ID, and RGB$\leftrightarrow$Depth cross-modal retrieval. Submissions are ranked using mAP and CMC-1 under a unified server-side evaluation. The final results show a clear difficulty ordering (RGB $>$ Depth $>$ Cross-Modal), highlighting both the challenge of modality-constrained retrieval and the feasibility of strong performance with modality-invariant learning. By releasing the dataset at https://zenodo.org/records/17909410, the evaluation scripts at https://github.com/RaphaelDel/ICPR-TVRID, and the accompanying documentation, TVRID establishes a reproducible benchmark for top-view, depth-based, and cross-modal person re-id.
URLs: https://zenodo.org/records/17909410,, https://github.com/RaphaelDel/ICPR-TVRID,
Authors: Joao Batista Florindo, Amanda Pontes de Oliveira Ornelas
Abstract: Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful alternative, yet common methods like masked autoencoders (MAEs) may inadvertently destroy fine-grained diagnostic features by using random masking. In this paper, we propose a novel SSL pre-training strategy, the Chaotic Denoising Autoencoder (CDAE). Instead of masking, we apply a chaotic transformation to the input image, tasking an autoencoder to reconstruct the original. We hypothesize this forces the encoder to learn robust, domain-specific features by "inverting the chaos". Furthermore, we propose an attentive fusion mechanism that combines features from our CDAE-trained encoder with a standard encoder, leveraging the strengths of both general and domain-specific representations. Our method is evaluated on two public medical datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). The proposed model achieves high performance, with an accuracy of 0.9221 and an F1-macro of 0.8530 on ISIC 2018, and an accuracy of 0.8644 and F1-macro of 0.7433 on APTOS 2019, demonstrating the efficacy of our approach.
Authors: Ali Shibli, Andrea Nascetti, Yifang Ban
Abstract: Wildfire burned-area mapping is essential for damage assessment, emissions modeling, and understanding fire-climate interactions across diverse ecological regions. Recent geospatial foundation models provide strong general-purpose representations for satellite imagery, yet there is still no clear understanding of how to efficiently adapt these models for downstream Earth observation tasks, particularly under geographic and temporal domain shift. This study evaluates three state-of-the-art Geospatial Foundation Models (GFMs) - Terramind, DINOv3, and Prithvi-v2 - for burned-area mapping across the United States and Canada using Sentinel-2 data. Leveraging 3,820 wildfire events from 2017-2023, we conduct spatial and temporal generalization tests across diverse biomes. We systematically compare full fine-tuning, decoder-only fine-tuning, and Low-Rank Adaptation (LoRA) for adapting each model. Across all experiments, LoRA provides the strongest cross-domain generalization while updating less than 1% of parameters, demonstrating a favorable trade-off between accuracy and efficiency. Prithvi-v2 with LoRA achieves the highest overall accuracy and the largest improvement compared to full fine-tuning. These findings indicate that geospatial foundation models, when adapted using lightweight parameter-efficient methods such as LoRA, offer a robust and scalable solution for large-scale burned-area mapping. Code is available at https://github.com/alishibli97/wildfire-lora-gfm.
Authors: Joao B Florindo
Abstract: Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks (CNNs) and recent Vision Transformers have set performance benchmarks, they often require extensive labeled datasets or struggle to generalize across domains due to an over-reliance on color and shape features. This paper introduces a novel framework that synergizes Self-Supervised Learning (SSL) with deterministic chaotic dynamics. We propose a chaotic contrastive pre-training strategy, where pixel-wise chaotic maps, specifically Logistic, Tent, and Sine maps, act as non-linear data augmentation techniques. These chaotic perturbations, grounded in ergodic theory, force the network to learn topologically robust features by mimicking complex environmental noise and reflectance variations. Furthermore, we introduce an attention-based feature ensemble that fuses high-level semantic representations from a supervised large backbone with low-frequency structural features from a chaos-pretrained tiny encoder. Experimental results on six texture benchmarks (FMD, UMD, KTH-TIPS2-b, DTD, GTOS, and 1200Tex) demonstrate the superiority of the proposed method, outperforming state-of-the-art approaches and achieving promising accuracies on all the analyzed datasets.
Authors: Gasser Elazab, Frank Neuhaus, Tilman Ko{\ss}, Malte Splietker, Aditya Date, Michael Unterreiner, Maximilian Jansen, Olaf Hellwich
Abstract: Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. Moreover, recent driving datasets primarily provide sparse LiDAR ground truth for images, which is insufficient for assessing fine-grained geometry in depth estimation and completion. To address these gaps, we introduce CARD, a multi-modal driving dataset that delivers quasi-dense 3D ground truth across continuous sequences rich in speed bumps, potholes, irregular surfaces and off-road segments. Our sensor suite includes synchronized global-shutter stereo cameras, front and rear LiDARs, 6-DoF poses from LiDAR-inertial odometry, per-wheel motion traces, and full calibration. Notably, our multi-LiDAR fusion yields ~500K valid depth pixels per frame, about 6.5x more than KITTI Depth Completion and 10x more on average than other public driving datasets. The dataset spans ~110 km and 4.7 hours across Germany and Italy. In addition, CARD provides 2D bounding boxes targeting road-topography irregularities, enabling accurate benchmarking for both geometry and perception tasks. Furthermore, we establish a standardized evaluation protocol for road surface irregularities on CARD and benchmark state-of-the-art depth estimation models to provide strong baselines. The CARD dataset is hosted on https://huggingface.co/CARD-Data.
Authors: Bartlomiej Sobieski, Matthew Tivnan, Dawid P{\l}udowski, Micha{\l} Jan W{\l}odarczyk, Pengfei Jin, Przemyslaw Biecek, Quanzheng Li
Abstract: Diffusion models are prone to generating structural hallucinations - samples that match the statistical properties of the training data yet defy underlying structural rules, resulting in anomalies like hands with more than five fingers. Recent research studied this failure mode from several viewpoints, offering partial explanations to their occurrence, such as mode interpolation. In this work, we propose a complementary perspective that treats hallucinations as instabilities on the model-induced manifold. We begin by showing that a hallucination filter based on such instabilities matches or exceeds the performance of the recently proposed temporal one. By tracing the source of these instabilities, we identify local intrinsic dimension (LID) as their primary driver and propose Intrinsic Quenching (IQ), a direct corrective mechanism that deflates it to alleviate hallucinations. IQ consistently outperforms standard hallucination reduction baselines across a wide array of benchmarks and offers a highly promising solution for enforcing anatomical consistency in downstream medical imaging tasks.
Authors: Wen Wen, Hao Chen, Shiliang Zhang
Abstract: Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization, while overlooking the potential of auxiliary modalities, such as text, to preserve semantic stability and enable incremental plasticity. We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains. To decouple the roles of vision and text, we propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization. On the textual side, we distill prompts to preserve vision-text alignment under a fixed semantic space, acting as a global semantic reference rather than a dominant learning signal. On the visual side, an EMA-based teacher with an adaptive prompt pool enables domain-wise adaptation by allocating new slots while freezing past ones. Extensive experiments show that PAD substantially outperforms state-of-the-art methods across seen and unseen domains, achieving a strong balance between stability and plasticity. Project page is available at https://github.com/zu-zi/PAD.
Authors: Honghu Pan, Xiaoling Luo, Yongyong Chen, Zhenyu He, Pengyang Wang
Abstract: Recent deep learning approaches seek to automate CAD creation by representing a model as a sequence of discrete commands and parameters, and then generating them using autoregressive models or continuous diffusion operating in Euclidean embedding space. However, continuous diffusion perturbs representations in a continuous Euclidean domain that does not reflect the inherently discrete and heterogeneous nature of CAD tokens, often producing perturbed representations that map to semantically invalid symbols. To overcome this limitation, we propose a cascaded discrete diffusion framework for CAD generation, which consists of a command diffusion for generating CAD commands and a parameter diffusion conditioned on CAD commands. Unlike isotropic Gaussian perturbation, the forward process of our approach operates directly over categorical token distributions using delicate transition matrices. For commands, we adopt an absorbing-state transition matrix that progressively corrupts tokens to a designated symbol; for parameters, we introduce specific transition matrices tailored to heterogeneous attributes: a Gaussian kernel for coordinate continuity, a scale-invariant kernel for dimensional values, and a prior-preserving kernel for boolean attributes. The reverse process is achieved by two denoising networks: a Transformer-based encoder for command recovery, and a parameter network with extra local self-attention for command-level interaction and cross-attention for conditional injection. Experiments on the DeepCAD dataset show that the proposed approach surpasses existing autoregressive and continuous diffusion models on unconditional generation metrics, while qualitative results validate effective controllability in conditional generation tasks. Source codes will be released.
Authors: Md. Safirur Rashid, Sabbir Ahmed, Muhammad Usama Islam, Sumona Hoque Mumu, Md. Hasanul Kabir
Abstract: Despite the strong performance of Convolutional Neural Networks (CNNs) in disease classification, their effectiveness often depends on access to large annotated datasets, which is an impractical requirement for emerging or rare conditions such as Monkeypox. To overcome this limitation, we propose a few-shot learning (FSL) framework that employs SimpleShot, a lightweight, non-parametric, inductive classifier, for Monkeypox and pox-like skin disease recognition from limited labeled examples. The proposed pipeline passes the skin lesion images through a frozen, pretrained CNN backbone to obtain feature embeddings, which are then classified via SimpleShot using nearest-centroid comparisons in a normalized embedding space. We systematically benchmark six widely used CNN backbones as feature extractors under consistent experimental settings, enabling fair comparison. Experiments on three publicly available datasets (MSLD v1.0, MSID, and MSLD v2.0) are conducted across 2-way, 4-way, and 6-way tasks with 1-shot, 5-shot, and 10-shot configurations. Among all models, MobileNetV2_100 consistently achieves the highest accuracy. In addition, we present a cross-dataset evaluation for Monkeypox classification, revealing that binary Mpox-vs-Others transfer remains comparatively stable while multi-class performance degrades significantly under domain shift. Together, these results demonstrate the practical utility of combining inductive FSL methods with lightweight CNN backbones and highlight the importance of domain robustness for reliable real-world clinical deployment.
Authors: Philip Wootaek Shin, Ajay Narayanan Sridhar, Sivani Devarapalli, Rui Zhang, Jack Sampson, Vijaykrishnan Narayanan
Abstract: Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically rotation and noise, and show that even mild distortions significantly degrade relational reasoning across models and datasets. We further evaluate prompt-based augmentation and preprocessing strategies (orientation correction and denoising), finding that while they offer partial improvements, they do not fully resolve hallucinations. Our results reveal a gap between perceptual robustness and relational understanding, highlighting the need for more robust, geometry-aware VLMs.
Authors: Hongxu Chen, Yanghao Wang, Bowei Zhu, Hongxiang Li, Zhen Wang, Ziqi Jiang, Lin Li, Rui Liu, Long Chen
Abstract: Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we argue that existing FM methods are inherently constrained by incompatible geometric priors on pre-trained cross-modal features, resulting in suboptimal adaptation performance. We first analyze these methods from a polar decomposition perspective (i.e., radial and angular sub-manifolds). Under this new geometric view, we identify three overlooked limitations in them: 1) Angular dynamics distortion: The radial-angular coupling induces non-uniform speed on the angular sub-manifold, leading to regression training difficulty and extra truncation errors. 2) Radial dynamics neglect: Feature normalization discards modality confidence, failing to distinguish out-of-distribution and in-distribution data, and abandoning crucial radial dynamics. 3) Context-agnostic unconditional flow: Dataset-specific information loss during pre-trained cross-modal feature extraction remains unrecovered. To resolve these issues, we propose warped product flow matching (WP-FM), a unified Riemannian framework that reformulates alignment on a warped product manifold. Within this framework, we derive direct product flow matching (DP-FM) by introducing a constant-warping metric, which yields a decoupled cylindrical manifold (i.e., direct product manifold). DP-FM enables independent radial evolution and constant-speed angular geodesic transport, effectively eliminating angular dynamics distortion while preserving radial consistency. Meanwhile, we incorporate classifier-free guidance by conditioning the flow on the pre-trained VLMs' hidden states to inject missing dataset-specific information. Extensive results across 11 benchmarks have demonstrated that DP-FM achieves a new state-of-the-art for multi-step few-shot adaptation.
Authors: Minh Anh Nguyen, Quang Huy Tran, Bao Ngoc Le, SuiYang Guang, Tuan Kiet Pham, Linh Chi Vo
Abstract: Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching human-object features with text embeddings, but their predictions are often dominated by object affordance and phrase-level co-occurrence. As a result, a model may predict \textit{cut cake} from the presence of a knife and a cake without verifying whether the hand, tool, target, contact pattern, and object state jointly support the action. We propose \textbf{ScriptHOI}, a structured framework that represents each interaction phrase as a soft scripted state transition. Rather than treating a phrase as a single class token, ScriptHOI decomposes it into body-role, contact, geometry, affordance, motion, and object-state slots. A visual state tokenizer parses each detected human-object pair into corresponding state tokens, and a slot-wise matcher estimates both script coverage and script conflict. These two quantities calibrate HOI logits, expose missing visual evidence, and provide training constraints for incomplete annotations. To avoid suppressing valid but unannotated interactions, we further introduce interval partial-label learning, which constrains unannotated candidates with script-derived lower and upper probability bounds instead of assigning closed-world negatives. A counterfactual script contrast loss swaps individual script slots to discourage object-only shortcuts. Experiments on HICO-DET, V-COCO, and open-vocabulary HOI splits show that ScriptHOI improves rare and unseen interaction recognition while substantially reducing affordance-conflict false positives.
Authors: Yuan Wu, Zhiqiang Yan, Jiawei Lian, Zhengxue Wang, Jian Yang
Abstract: 3D occupancy prediction aims to infer dense, voxel-wise scene semantics from sensor observations, where the 2D-to-3D view transformation serves as a crucial step in bridging image features and volumetric representations. Most previous methods rely on a fixed projection space, where 3D reference points are uniformly sampled along pillars. However, such sampling struggles to capture the sparsity and height variations of real-world scenes, leading to ambiguous correspondences and unreliable feature aggregation. To address these challenges, we propose HiPR, a camera-LiDAR occupancy framework with Height-Guided Projection Reparameterization. HiPR first encodes LiDAR into a BEV height map to capture the maximum height of the point cloud. HiPR then adjusts the sampling range of each pillar using the height prior, enabling adaptive reparameterization of the projection space. As a result, the projected points are redistributed into geometrically meaningful regions rather than fixed ranges. Meanwhile, we mask out the invalid parts of the height map to avoid misleading the feature aggregation. In addition, to alleviate the training instability caused by noisy LiDAR-derived heights, we introduce a training-time Progressive Height Conditioning strategy, which gradually transitions the conditioning signal from ground-truth heights to LiDAR heights. Extensive experiments demonstrate that HiPR consistently outperforms existing state-of-the-art methods while maintaining real-time inference. The code and pretrained models can be found at https://github.com/Rayn-Wu/HiPR.
Authors: Andranik Sargsyan, Shant Navasardyan
Abstract: Accurate image segmentation is essential for modern computer vision applications such as image editing, autonomous driving, and medical image analysis. In recent years, Dichotomous Image Segmentation (DIS) has become a standard task for training and evaluating highly accurate segmentation models. Existing DIS approaches often fail to preserve fine-grained details or fully capture the semantic structure of the foreground. To address these challenges, we present FlowDIS, a novel dichotomous image segmentation method built on the flow matching framework, which learns a time-dependent vector field to transport the image distribution to the corresponding mask distribution, optionally conditioned on a text prompt. Moreover, with our Position-Aware Instance Pairing (PAIP) training strategy, FlowDIS offers strong controllability through text prompts, enabling precise, pixel-level object segmentation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches both with and without language guidance. Compared with the best prior DIS method, FlowDIS achieves a 5.5% higher $F_{\beta}^{\omega}$ measure and 43% lower MAE ($\mathcal{M}$) on the DIS-TE test set. The code is available at: https://github.com/Picsart-AI-Research/FlowDIS
Authors: Maxim V. Shugaev, Md Reshad Ul Hoque, Bridget Kennedy, Joseph T. Riley, Fiona Hwang, Justin Hagen, Harvir Ghuman, Ethan Garcia-O'Donnell, Syed Noor Qadri, Freddie Santiago, Mun Wai Lee
Abstract: Video sequence capturing through refractive dynamic media, such as a turbulent air or water surface, often suffer from severe geometric distortions and temporal instability. While recent advances address mild atmospheric turbulence, no existing benchmarks systematically evaluate restoration methods under strong and highly nonuniform refractive conditions. We present a comprehensive benchmark for geometric distortion removal in video, covering a range from turbulence-like mild warping to strong discontinuous refractive deformations. The benchmark includes both laboratory-captured real data and synthetic sequences generated for static scenes via physics-based light refraction modeling across four distortion levels and multiple surface wave types. We evaluate a spectrum of methods from simple baselines and classical registration algorithms to advanced learning-based approaches including DATUM and our proposed diffusion based V-cache for high and extreme distortions regimes. Evaluation uses both pixel-level (PSNR, SSIM), and perceptual (LPIPS, DINO, CLIP) metrics providing the first large scale analysis of geometric distortion removal. Our benchmark establishes a new foundation for developing and evaluating algorithms capable of reconstructing video from highly distorted optical environments. Our code and datasets are available at https://github.com/iafoss/refractive-mfir-benchmark.
Authors: Yu-Hsi Chen, Abd-Krim Seghouane
Abstract: Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains. While recent invariant learning strategies and architectural advances have achieved strong performance, explicitly discovering a structured domain-invariant subspace through second-order statistics remains underexplored. In this work, we propose CPCANet, a novel framework grounded in Common Principal Component Analysis (CPCA), which unrolls the iterative Flury-Gautschi (FG) algorithm into fully differentiable neural layers. This approach integrates the statistical properties of CPCA into an end-to-end trainable framework, enforcing the discovery of a shared subspace across diverse domains while preserving interpretability. Experiments on four standard DG benchmarks demonstrate that CPCANet achieves state-of-the-art (SOTA) performance in zero-shot transfer. Moreover, CPCANet is architecture-agnostic and requires no dataset-specific tuning, providing a simple and efficient approach to learning robust representations under distribution shift. Code is available at https://github.com/wish44165/CPCANet.
Authors: Kedar Tatwawadi, Parisa Rahimzadeh, Zhanghao Sun, Zhiqi Chen, Ziyun Yang, Sanjay Nair, Divija Hasteer, Oren Rippel
Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim to close this gap. We conduct a comprehensive study of the key modeling choices that govern the design of a practical learned image codec, jointly optimized for perceptual quality and runtime -- including within the ablations several novel techniques. We then perform performance-aware neural architecture search over millions of backbone configurations to identify models that achieve the target on-device runtime while maximizing compression performance as captured by perceptual metrics. We combine the various optimizations to construct a new codec that achieves a significantly improved tradeoff between speed and perceptual quality. Based on rigorous subjective user studies, it provides 2.3-3x bitrate savings against AV1, AV2, VVC, ECM and JPEG-AI, and 20-40% bitrate savings against the best learned codec alternatives. At the same time, on an iPhone 17 Pro Max, it encodes 12MP images as fast as 230ms, and decodes them in 150ms -- faster than most top ML-based codecs run on a V100 GPU.
Authors: Chuanzhi Xu, Boyu Wei, Haoxian Zhou, Xuanhua Yin, Zihan Deng, Haodong Chen, Qiang Qu, Weidong Cai
Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment. Code and datasets will be made available in a future version.
Authors: Bernhard Kainz, Johanna P Mueller, Matthew Baugh, Cosmin Bercea
Abstract: Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-aware reference selection from DINOv2 patch distributions, (ii) Goldilocks zone sampling exploiting the non-monotonic relationship between reference similarity and localisation accuracy, and (iii) self-consistency aggregation via weighted non-maximum suppression. We theoretically analyse the Goldilocks effect through distributional divergence, and show that references with moderate similarity minimize a bias-variance trade-off in comparative visual reasoning. On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves $43.5_{\pm1.6}\%$ mAP@30 (95\% CI: [40.4, 46.7]), representing a 19\% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves $32.0_{\pm6.5}\%$ and Qwen3-VL-32B achieves $32.0_{\pm6.6}\%$ mAP@30. Paired McNemar tests confirm statistical significance ($p<0.01$). Source code is available at https://github.com/bkainz/WALDO_MICCAI26_demo .
Authors: Yunhan Yang, Chunshi Wang, Junliang Ye, Yang Li, Zanxin Chen, Zehuan Huang, Yao Mu, Zhuo Chen, Chunchao Guo, Xihui Liu
Abstract: Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a "physical architect" to plan a "Hierarchical Physical Blueprint" defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.
Authors: Enhui Chai, Sicheng Chen, Tianyi Zhang, Chad Wong, Kecheng Huang, Zeyu Liu, Fei Xia
Abstract: Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specimens at gigapixel resolution, are fundamental to this process but require aggregating thousands of patches for slide-level predictions. Multiple Instance Learning (MIL) tackles this challenge with a two-stage paradigm, decoupling tile-level embedding and slide-level prediction. However, most existing methods implicitly embed patch representations in homogeneous Euclidean spaces, overlooking the hierarchical organization and regional heterogeneity of pathological tissues. This limits current models' ability to capture global tissue architecture and fine-grained cellular morphology. To address this limitation, we introduce a hybrid hyperbolic-Euclidean representation that embeds WSI features in dual geometric spaces, enabling complementary modeling of hierarchical tissue structures and local morphological details. Building on this formulation, we develop BatMIL, a WSI classification framework that leverages both geometric spaces. To model long-range dependencies among thousands of patches, we employ a structured state space sequence model (S4) backbone that encodes patch sequences with linear computational complexity. Furthermore, to account for regional heterogeneity, we introduce a chunk-level mixture-of-experts (MoE) module that groups patches into regions and dynamically routes them to specialized subnetworks, improving representational capacity while reducing redundant computation. Extensive experiments on seven WSI datasets spanning six cancer types demonstrate that BatMIL consistently outperforms state-of-the-art MIL approaches in slide-level classification tasks. These results indicate that geometry-aware representation learning offers a promising direction for next-generation computational pathology.
Authors: Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang, Dasen Dai, Quanxin Shou, Yunlong Lin, Xiangyu Yue, Shenghua Gao, Tianyu Pang
Abstract: Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and SearchVL-RL-8k for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.
Authors: Wei Luo, Yiting Lu, Xin Li, Haoran Li, Fengbin Guan, Chen Gao, Xin Jin, Yong Li, Zhibo Chen, Sijing Wu, Kang Fu, Yunhao Li, Ziang Xiao, Huiyu Duan, Jing Liu, Qiang Hu, Xiongkuo Min, Guangtao Zhai, Manxi Sun, Zixuan Guo, Yun Li, Ziyang Chen, Manabu Tsukada, Zhengyang Li, Zhenglin Du, Yi Wen, Licheng Jiao, Fang Liu, Lingling Li, Yiwen Ren, Zhilong Song, Dubing Chen, Yucheng Zhou, Tianyi Yan, Huan Zheng
Abstract: This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The challenge is motivated by a central gap in current evaluation practice: perceptual quality alone is insufficient to judge whether generated dynamics are physically plausible, temporally coherent, and consistent with input conditions. Participants are required to build a metric that jointly predicts four dimensions, i.e., Video Quality, Physical Realism, Condition-Video Alignment, and Temporal Consistency. Depart from that, participants also need to localize physical anomaly timestamps for fine-grained diagnosis. The benchmark dataset contains 1,554 videos generated by seven representative world generative models, organized into three tracks (text-2D, image-to-4D, and video-to-4D) and spanning 26 categories. These categories explicitly cover physics-relevant scenarios, including dynamics, optics, and thermodynamics, together with diverse real-world and creative content. To ensure label reliability, scores and anomaly timestamps are produced through trained human annotation with an additional automated quality-control pass. Evaluation is based on both score prediction and anomaly localization, with a composite protocol that combines TimeStamp_IOU and SRCC/PLCC. This report summarizes the challenge design and provides method-level insights from submitted solutions.
Authors: Dengyang Jiang, Xin Jin, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Ruoyi Du, Xiangpeng Yang, Qilong Wu, Zhen Li, Peng Gao, Harry Yang, Steven Hoi
Abstract: The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for directly continuous supervised fine-tuning. For example, applying the commonly used fine-tuning technique would compromises their inherent few-step inference capability. To address this, we propose D-OPSD, a novel training paradigm for step-distilled diffusion models that enables on-policy learning during supervised fine-tuning. We first find that the modern diffusion model where the LLM/VLM serves as the encoder can inherit its encoder's in-context capabilities. This enables us to make the training as an on-policy self-distillation process. Specifically, during training, we make the model acts as both the teacher and the student with different contexts, where the student is conditioned only on the text feature, while the teacher is conditioned on the multimodal feature of both the text prompt and the target image. Training minimizes the two predicted distributions over the student's own roll-outs. By optimized on the model's own trajectory and under it's own supervision, D-OPSD enables the model to learn new concept, style, etc. without sacrificing the original few-step capacity.
Authors: Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu, Liang-Chieh Chen, Zhe Gan, Chen Wei
Abstract: We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying limited local information, but their role in generative models remains underexplored. We show that this phenomenon appears in both the encoder and denoiser of modern Representation Autoencoder (RAE)-DiT pipelines: pretrained ViT encoders can produce outlier representations, and DiTs themselves can develop internal outlier tokens, especially in intermediate layers. Moreover, simply masking high-norm tokens does not improve performance, indicating that the problem is not only caused by a few extreme values, but is more closely related to corrupted local patch semantics. To address this issue, we introduce Dual-Stage Registers (DSR), a register-based intervention for both components: trained registers when available, recursive test-time registers otherwise, and diffusion registers for the denoiser. Across ImageNet and large-scale text-to-image generation, these interventions consistently reduce outlier artifacts and improve generation quality. Our results highlight outlier-token control as an important ingredient in building stronger DiTs.
Authors: Zeren Jiang, Yushi Lan, Yihang Luo, Yufan Deng, Zihang Lai, Edgar Sucar, Christian Rupprecht, Iro Laina, Diane Larlus, Chuanxia Zheng, Andrea Vedaldi
Abstract: Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by the scarcity of high-quality datasets with dense, complete, and accurate geometric annotations. To address this limitation, we introduce Syn4D, a multiview synthetic dataset of dynamic scenes that includes ground-truth camera motion, depth maps, dense tracking, and parametric human pose annotations. A key feature of Syn4D is the ability to unproject any pixel into 3D to any time and to any camera. We conduct extensive evaluations across multiple downstream tasks to demonstrate the utility and effectiveness of the proposed dataset, including 4D scene reconstruction, 3D point tracking, geometry-aware camera retargeting, and human pose estimation. The experimental results highlight Syn4D's potential to facilitate research in dynamic scene understanding and spatiotemporal modeling.
Authors: Toka Alokda, Cristiano Porciani
Abstract: The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically modeled through N-body simulations. In this work, we explore the use of deep learning to segment and classify proto-halo regions in the initial density field according to their final halo mass at redshift z=0. We compare two architectures: a fully convolutional neural network (CNN) based on the V-Net design and a U-Net transformer. We find that the transformer-based network significantly outperforms the CNN across all metrics, achieving sub-percent error in the total segmented mass per halo class. Both networks deliver much higher accuracy than the perturbation-theory-based model \textsc{pinocchio}, especially at low halo masses and in the detailed reconstruction of proto-halo boundaries. We also investigate the impact of different input features by training models on the density field, the tidal shear, and their combination. Finally, we use Grad-CAM to generate class-activation heatmaps for the CNN, providing preliminary yet suggestive insights into how the network exploits the input fields.
Authors: Subhadip Mitra
Abstract: Low Earth orbit (LEO) satellites increasingly carry compute hardware capable of on-board processing, yet each satellite generates roughly two orders of magnitude more data than it can downlink per orbit. This mismatch forces operators to decide, for every workload, which computation runs on-board and which runs on the ground, how intermediate data crosses the space-ground boundary through narrow contact windows, and how to maintain delivery guarantees over noisy channels. We present Constraint-Aware Execution (CAE), a planning system that takes a satellite identifier, a workload expressed as a directed acyclic graph of processing steps, and a set of orbital and resource constraints, and produces a deterministic, physically grounded execution plan. CAE operates in four phases: (1) orbital environment construction via SGP4 propagation with eclipse detection and ground station pass prediction, (2) compute placement using a cost model that compares on-board resource consumption against transfer overhead, (3) transfer insertion with adaptive forward error correction and security overhead modeling, and (4) greedy first-fit scheduling into orbital windows under power, thermal, compute, and communication constraints. We evaluate CAE against five representative workload patterns across satellites in distinct orbital regimes and demonstrate that the system produces feasible plans in under two seconds, correctly exploits onboard data reduction to minimize transfer volume, and adapts FEC and multi-pass allocation to varying channel conditions. CAE is deployed as a production API computing plans for any cataloged satellite using live two-line element data.
Authors: Nicolas Michel, Maorong Wang, Jiangpeng He, Toshihiko Yamasaki
Abstract: Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Distillation (CD), where a student learns sequentially from a stream of teacher models without retaining access to earlier teachers. CD faces two challenges: teacher training data is unavailable, and teachers have varying expertise. We show that external unlabeled data enables Unseen Knowledge Transfer (UKT), allowing the student to acquire information from domains not present in the training data, while known to the teacher. We also show that sequential distillation causes Unseen Knowledge Forgetting (UKF) when transferred knowledge is lost after training on later teachers. To better trade off between UKT and UKF, we propose Self External Data Distillation (SE2D), a method that preserves logits on external data to stabilize learning across heterogeneous teachers. Experiments on multiple benchmarks show that SE2D reduces UKF and improves cross-domain generalization. The code and implementation for this work are publicly available at: https://github.com/Nicolas1203/continual_distillation.
URLs: https://github.com/Nicolas1203/continual_distillation.
Authors: Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn
Abstract: Recently, a new paradigm named \emph{drifting model} has been proposed for mapping distributions, which achieves the SOTA image generation performance over ImageNet via one-step neural functional evaluation (NFE). The basic idea is to compute a drifting term at each training iteration and then push the output of the model towards the direction of the drifting term. In this paper, we propose a \emph{lookahead drifting model}. At each training iteration, we compute a set of drifting terms sequentially. Each drifting term is calculated by making use of previously computed ones as well as the positive samples and the output of the model. %One key step is to properly scale the drifting terms so that their magnitudes are in a comparable range. In principle, the drifting terms obtained at a later stage capture higher order gradient information towards the positive samples. At each training iteration, the model is optimized by pushing its output towards the direction of the (weighted) summation of the drifting terms. Experimental results on toy examples and CIFAR10 demonstrate the better performance of the new method than the baseline.
Authors: Halil Ibrahim Gulluk, Olivier Gevaert
Abstract: Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanations. We address this by generating reasoning trajectories for six medical VQA benchmarks using the COMCTS algorithm with open-source vision-language models, with an LLM serving as the verification judge. Building on these generated datasets, we propose a two-stage training framework: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO) with a novel process-based reward. While standard approaches rely solely on exact-match rewards for final answers, we introduce a trajectory-aware reward that measures the similarity between generated and ground-truth reasoning processes. Specifically, we embed reasoning steps using sentence transformers and compute the Dynamic Time Warping (DTW) distance between the resulting vector sequences. Experiments across six benchmarks demonstrate that combining the DTW-based process reward with exact-match reward consistently outperforms SFT-only training, raising mean accuracy from 0.598 to 0.689, mean BERTScore from 0.845 to 0.881, and mean ROUGE-L from 0.665 to 0.748. Our results highlight the importance of process supervision in training reasoning-capable medical VLMs. We make our code and generated reasoning datasets publicly available at https://anonymous.4open.science/r/MICCAI-R1-MED-VQA-code-B14B/
URLs: https://anonymous.4open.science/r/MICCAI-R1-MED-VQA-code-B14B/
Authors: Vageesh Kumar Saxena
Abstract: This research investigated how online criminal activities can be better understood and connected using data-driven machine learning methods. Many illegal activities, such as human trafficking and illicit trade, have moved to online platforms where offenders hide behind anonymous accounts and frequently change identities. This makes it difficult for authorities to understand how large these networks are and how different online profiles may be linked. The research shows that people tend to maintain consistent patterns in how they write advertisements and present images online, even when they try to stay anonymous. By analysing these patterns across large collections of online advertisements, the research demonstrates how to link related accounts and identify repeated behaviour across illegal online markets. In addition, the research also addresses how such methods should be used responsibly. It proposes clear guidelines to ensure that privacy, fairness, and transparency are respected when these tools are applied. Overall, the research provides practical ways to support law enforcement investigations while emphasising careful and ethical use.
Authors: Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Abstract: Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-world deployment, the traditional focus on hardware-aware efficiency is no longer sufficient. We observe that modern NAS methods, especially those that target edge AI, are evolving to address a triple objective: Efficiency, Robustness, and Continual Learning. While efficiency ensures feasibility in resource-constrained environments, robustness guarantees reliability under environmental variabilities, and continual learning enables adaptation to sequential tasks without catastrophic forgetting. We propose a taxonomy of NAS approaches through this triple lens, distinguishing between methods targeting resource optimization, environmental resilience, and architectural plasticity. This unified perspective reveals that these axes, though often studied in isolation, are mutually reinforcing. Building on this taxonomy, we map the current landscape of these NAS methods into a new framework called Hardware-Efficient, Robust, and ContinUal LEarning Search (HERCULES). We define the desiderata, the twelve labours of HERCULES, addressing the non-trivial challenge of balancing an adequate search-space exploration with the immense computational costs of a multi-objective NAS, accounting for these crucial objectives of current AI systems. By identifying critical gaps in existing research, this survey outlines a roadmap toward integrated algorithmic, architectural, and hardware-software co-design for truly deployable, lifelong-learning AI systems.
Authors: Lin Song, Wenbo Li, Guoqing Ma, Wei Tang, Bo Wang, Yuan Zhang, Yijun Yang, Yicheng Xiao, Jianhui Liu, Yanbing Zhang, Guohui Zhang, Wenhu Zhang, Hang Xu, Nan Jiang, Xin Han, Haoze Sun, Maoquan Zhang, Haoyang Huang, Nan Duan
Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.
Authors: Rihuan Ke
Abstract: This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many existing successful denoising approaches for handling different kinds of noise, they typically require accurate modelling of the images and the noise (implicitly or explicitly), and hence the denoising results can be suboptimal due to different practical factors such as imperfect models, unreliable noise assumptions, or low quality data. In particular, when clean image samples are not available and there is a lack of knowledge of the underlying noise distribution, which is the case in various practical situations, the results may not well align with the noise statistics. The unawareness of the useful statistical information leads to suboptimal results. This work aims to make the best use of the statistical information to improve the consistency between the given denoising results and the noise statistics, under the assumption that the noise is conditionally pixel-wise independent given the clean signal. A method, based on a Bayesian formulation of an auxiliary signal in the noisy data, is proposed for evaluating the consistency of the denoising results, without precise information on noise distribution. By leveraging the statistical information from noisy data, the method enhances the statistical noise consistency and improves denoising quality.
Authors: Xiaoyi Jiang, Bashir M. Al-Hashimi, Kai Xu
Abstract: The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly under-perform backpropagation on complex benchmarks such as ImageNet-100 and Tiny-ImageNet. We identify this gap as a structural bottleneck in goodness extraction: standard sum-of-squares formulation collapses feature volumes into channel-wise activation energies which omits critical second-order dependencies. To address this, we propose a framework centered on three key components. First, Bi-axis Covariance Goodness(BiCovG) explicitly augments the standard goodness function with structured second-order information along two axes: cross-channel projections that model inter-feature covariance, and nested multi-scale aggregation that encodes spatial correlation statistics. This provides a tractable approximation to covariance-aware goodness without the prohibitive O(C^2) complexity of explicit matrix estimation. Second, a lightweight Logistic Fusion module aggregates layer-wise predictions, amplifying the contribution of deeper representations. Third, the Feature Alignment Layer(FAL) introduces a zero-initialized correction at block boundaries to mitigate representation misalignment in deep locally trained networks. By introducing these three components, we effectively double the depth of viable Forward-Forward learning, extending robust layer utilization from shallow baselines to 16 layer architectures like VGG-16. The resulting BP-free model achieves 73.01% on ImageNet-100 and 50.30% on Tiny-ImageNet. As a practical extension, Hybrid Goodness Blocks control the scope of gradient propagation via configurable block sizes, further narrowing the ImageNet-100 gap to 3.6% and matching BP on Tiny-ImageNet, while still reducing peak memory by approximately 50% relative to BP.
Authors: Jiaming Hu, Jiamu Bai, Haoyu Wang, Debarghya Mukherjee, Ioannis Ch. Paschalidis
Abstract: Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally efficient alternative that avoids explicit reward modeling and has been widely adopted in diffusion alignment. However, existing preference-based methods for diffusion alignment still rely on reward-induced preference signals and typically assume that human preferences can be adequately modeled by the Bradley--Terry (BT) model, which may fail to capture the full complexity of human preferences. In this paper, we formulate diffusion alignment from a game-theoretic perspective. We propose Diffusion Nash Preference Optimization (Diff.-NPO), an intuitive general preference framework for diffusion alignment. Diff.-NPO encourages the current policy to play against itself to achieve self improvement and lead to a better alignment. Empirically, we demonstrate the effectiveness of Diff.-NPO on the text-to-image generation task via various metrics. Diff.-NPO consistently outperforms existing preference-based diffusion alignment methods.
Authors: Yihan Lin, Haoyang Li, Yang Li, Haitao Shen, Yihan Zhao, Chao Shao, Jing Zhang
Abstract: Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and lack a systematic comparison. This work structures the study of latent action supervision from two perspectives: (i) regularizing the trajectory via image-based latent actions, and (ii) unifying the target space with action-based latent actions. Under a unified VLA baseline, we instantiate and compare four representative integration strategies. Our results reveal a formulation-task correspondence: image-based latent actions benefit long-horizon reasoning and scene-level generalization, whereas action-based latent actions excel at complex motor coordination. Furthermore, we find that directly supervising the VLM with discrete latent action tokens yields the most effective performance. Finally, our experiments offer initial insights into the benefits of latent action supervision in mixed-data, suggesting a promising direction for VLA training. Code is available at https://github.com/RUCKBReasoning/From_Pixels_to_Tokens.
URLs: https://github.com/RUCKBReasoning/From_Pixels_to_Tokens.
Authors: Keunho Byeon, Jin Tae Kwak
Abstract: Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend this capability to routine practice, recent computational methods aim to infer spatial gene expression directly from ubiquitous hematoxylin and eosin-stained histology slides. However, most existing models assume Cartesian or geometry-agnostic locality, despite the hexagonal sampling of widely used spot-array platforms, and point-wise regression objectives often yield over-smoothed gene expression profiles, obscuring gene-specific spatial heterogeneity. To address these, we propose HEXST, a geometry-aligned Transformer for spatial gene expression prediction from histology. HEXST operates directly on hexagonal spot coordinates to enable efficient local-to-global contextual modeling via tailored shifted-window attention mechanism and hexagonal rotary positional encoding. To enhance gene-wise spatial contrast, HEXST complements point-wise regression with a contrast-sensitive differential objective and transcriptomic priors from a pretrained single-cell foundation model during training. Across seven spatial transcriptomics datasets, HEXST consistently outperforms state-of-the-art models, providing accurate and robust spatial gene expression predictions while preserving gene-wise contrast and spatial heterogeneity.
Authors: Eduardo Santos, Juliana Carvalho, C\'esar Renn\'o-Costa
Abstract: This paper presents the development and validation of an eye-tracking dataset designed to investigate how second-language (L2) learners process idiomatic expressions. While native speakers often rely on direct retrieval of figurative meanings, L2 speakers frequently adopt a literal-first approach, which incurs measurable cognitive costs. This resource captures these costs through ocular metrics recorded from Portuguese L1 speakers of English across all CEFR proficiency levels (A1-C2). Although the study uses entry-level 60 Hz hardware (Tobii Pro Spark), we demonstrate that this sampling rate provides sufficient data density to detect macro-cognitive events such as fixations and regressions in reading. Preliminary analysis validates the dataset by revealing a strong inverse correlation between language proficiency and regressive eye movements. Integrated into the MIA (Modeling Idiomaticity in Human and Artificial Language Processing) initiative, this dataset serves as a cognitively grounded benchmark for evaluating both human processing models and the alignment of large language models with human-like figurative understanding.
Authors: Huatian Zhang, Zhendong Mao, Lei Zhang, Yongdong Zhang
Abstract: Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) by learning from preference pairs. One of its key challenges lies in how to transfer the sequence-level preference into fine-grained supervision on visual fidelity. To safeguard vision-related tokens that are prone to hallucination, existing methods typically allocate training emphasis according to the model's self-assessed visual sensitivity signals. However, such sensitivity, estimated by a model still under training, introduces self-referential bias: reinforcing already well-learned visual cues while neglecting hard-to-perceive but critical details, thereby limiting deeper alignment. In this work, we propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for MLLMs, which enables the model to uncover its cognitive deficiencies and actively explore for self-correction, guided by token-level epistemic uncertainty. Specifically, we first quantify the uncertainty from the model's failure to ground token predictions in the given image. Then, based on an uncertainty-aware exploration intensity, we encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples. Further, we provide a theoretical justification for our method, and extensive experiments demonstrate its effectiveness and robustness.
Authors: Santosh Premi Adhikari, Radu Timofte, Dmitry Ignatov
Abstract: Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs (deltas) to refine baseline architectures rather than synthesizing entire models. Our pipeline iteratively fine-tunes the LLM via LoRA on curated architectures from the LEMUR dataset, with MinHash-Jaccard novelty filtering for structural diversity. We evaluate three 7B-class LLMs -- DeepSeek-Coder-7B, Qwen2.5-Coder-7B, and Mistral-7B -- across six datasets (CIFAR-10, CIFAR-100, MNIST, SVHN, ImageNette, CelebA) using a 22-cycle protocol (1,100 candidates per LLM). All three substantially surpass the full-generation baseline (50.6% valid rate, 42.3% mean first-epoch accuracy): DeepSeek-Coder reaches 75.3% valid rate and 65.8% mean accuracy; Qwen2.5-Coder 72.1%/64.6%; Mistral 66.6%/66.1%. On CIFAR-10, best first-epoch accuracies reach 85.5% (Mistral), 85.2% (DeepSeek), 80.6% (Qwen) -- well above 63.98% full generation and 71.5% for the concurrent approach of Gu et al. Output lengths are 30-50 lines versus 200+ for full generation (75-85% reduction). A 50-epoch study confirms the 1-epoch proxy preserves rankings (Mistral: Spearman $\rho$ = 0.926). Delta-based generation is a token-efficient, multi-domain, LLM-agnostic alternative to full-model synthesis for LLM-driven NAS.
Authors: Yuhu Guo, Zhikai Shen, Jiasheng Qu, Chenghao Qian, Yuming Huang, Bin Chen, Guoxing Fang
Abstract: Tactile perception is key to dexterous manipulation, yet simulating high-resolution elastomer deformation remains computationally prohibitive. Finite element methods (FEM) deliver high fidelity but demand costly remeshing, while Material Point Methods (MPM) suffer from heavy particle-memory tradeoffs. We propose a {reduced-order neural simulation framework} that couples coarse-grained MPM dynamics with an implicit neural decoder to reconstruct sub-particle tactile details from compact latent states. The framework learns a continuous deformation manifold from paired high- and low-resolution simulations, enabling physically consistent, differentiable inference. Compared to the TacIPC, our method achieves over 65\% faster simulation and {40\% lower memory usage}, while maintaining better geometric fidelity. In tactile rendering and 3D surface reconstruction, our methods further improve accuracy by 25\% and produce realistic depth images and surface mesh within a faster inference speed. These results demonstrate that the proposed reduced-order neural model enables high-detail, physically grounded tactile simulation with substantial efficiency gains for robotic interaction and optimization.
Authors: Avhishek Biswas, Apala Pramanik, Eylem Ekici, Mehmet C. Vuran
Abstract: Millimeter-wave (mmWave) frequencies promise multi-gigabit connectivity for vehicle-to-everything (V2X) networks, but face challenges in terms of severe path loss and mobility-related beam misalignment. Reliable V2X connectivity requires fast, double-directional beam alignment. However, existing methods suffer from high training overhead and limited generalization to unseen scenarios. This paper presents VIsion-based BEamforming(VIBE), a hybrid model-based, closed-loop, learning architecture for real-time double-directional mmWave beam management primed by camera sensing. VIBE fuses machine learning, model-based reasoning, and closed-loop RF feedback to balance beam-pair establishment latency with link quality. VIBE bypasses exhaustive training overhead and accelerates link establishment by leveraging camera observations to reduce the beam-search space. Lightweight beam refinement and offset tracking mechanisms adaptively refine beams in response to dynamic application requirements. VIBE is implemented and evaluated across online indoor/outdoor testbeds, public datasets, and real-time vehicular experiments, demonstrating strong generalization capabilities, making it suitable for real-time V2X communication. Comparisons with 5G NR hierarchical beamforming show that VIBE consistently maintains lower outage rates. Furthermore, VIBE outperforms state-of-the-art end-to-end ML models for beam selection when evaluated on public datasets and achieves outage rates as low as 1.1-1.4 %. The results show that a hybrid model-based, closed-loop learning architecture is better suited for real-world mmWave vehicular connectivity than end-to-end trained ML models. For reproducibility, we publish our code to https://github.com/UNL-CPN-Lab/Look-Once-Beam-Twice.
Authors: Yuxuan Chen, Arianna Bunnell, Yanqi Xu, Haoyan Yang, Thomas K. Wolfgruber, John A. Shepherd, Yiqiu Shen
Abstract: We externally validated three deep learning models (DenseNet121, ViT-B/32, and ResNet50) for predicting mammographic breast density from breast ultrasound exams on an independent cohort. The external validation set comprised 2,000 ultrasound exams, including 500 cancer cases defined by an initial negative exam (BI-RADS 1 or 2) followed by a cancer diagnosis within 6 months to 10 years, and 1,500 negative controls matched by manufacturer and study year. Performance was measured using patient-level AUROC across four density categories: A (fatty), B (scattered), C (heterogeneous), and D (extremely dense). As a downstream assessment, we also evaluated 10-year risk prediction by incorporating age and AI-derived density into the Tyrer-Cuzick model and comparing performance against a reference model using age and mammography-reported density. All three models performed best in extremely dense breasts (AUROC 0.868-0.899), with strong performance in fatty (0.814-0.838) and scattered density (0.764-0.799), and lower performance in heterogeneously dense breasts (0.699-0.729). DenseNet121 achieved the highest overall performance (micro-averaged AUROC 0.885), and performance across categories was comparable between internal and external testing. For risk modeling, age combined with AI-derived density yielded a lower AUROC than age combined with mammography-reported density (0.541 vs. 0.570; p = 0.23), with no statistically significant difference. These findings indicate that deep learning models generalize well to external data with different racial composition for breast density assessment. While performance is strongest in extremely dense breasts, heterogeneously dense remains more challenging, highlighting the need for targeted optimization.
Authors: Haozhuang Chi, Daosheng Qiu, Hao Su, Haochen Liu, Zirui Li, Haoruo Zhang, Chen Lv
Abstract: Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions. While most driving world models forecast the external environment, in-cabin intelligence remains strictly recognition-oriented and lacks multi-step rollout capabilities for driver dynamics. We introduce Driver-WM, a driver-centric latent world model that rolls out in-cabin dynamics causally conditioned on out-cabin traffic context. This formulation unifies physical kinematics forecasting with auxiliary behavioral and emotional semantic recognition. Operating in a compact latent space constructed from frozen vision-language features, Driver-WM adopts a dual-stream architecture to separately encode external traffic and internal driver states. These streams are directionally coupled via a gated causal injection mechanism, which uses a learned vector gate to modulate external contextual perturbations while strictly enforcing temporal causality. Evaluations on a multi-task assistive driving benchmark demonstrate that Driver-WM yields robust long-horizon geometric forecasting for reactive high-motion maneuvers and improves semantic alignment for both driver and traffic states. Finally, the explicit external-to-internal conditioning allows for controlled test-time interventions to systematically analyze mechanism responses.
Authors: Jingsen Zhu, Silvia Sell\'an, Alexander Terenin
Abstract: We develop a framework for task-specific active next-best-view selection in 3D reconstruction from point clouds, by casting the problem in the language of Bayesian decision theory. Our framework works by (a) placing a prior distribution over the space of implicit surfaces, (b) using recently-developed stochastic surface reconstruction methods to calculate the resulting posterior distribution, then (c) using the posterior distribution to carefully reason about which view to scan next. This enables us to perform camera selection in a manner that is directly optimized for the intended use of the reconstructed data - meaning, we reduce uncertainty only in those regions that make a difference in the task at hand, as opposed to prior approaches that reduce it uniformly across space. We evaluate our method across three distinct downstream tasks: semantic classification, segmentation, and PDE-guided physics simulation. Experimental results demonstrate that our framework achieves superior task performance with fewer views compared to commonly used baselines and prior general uncertainty-reduction techniques.
Authors: Yijie Deng, Lei Han, Tianpeng Lin, Lin Li, Jinzhi Zhang, Lu Fang
Abstract: With the rise of Extended Reality (XR) technology, there is a growing need for real-time light field reconstruction from sparse view inputs. Existing methods can be classified into offline techniques, which can generate high-quality novel views but at the cost of long inference/training time, and online methods, which either lack generalizability or produce unsatisfactory results. However, we have observed that the intrinsic sparse manifold of Multi-plane Images (MPI) enables a significant acceleration of light field reconstruction while maintaining rendering quality.Based on this insight, we introduce \textbf{RealLiFe}, a novel light field optimization method, which leverages the proposed Hierarchical Sparse Gradient Descent (HSGD) to produce high-quality light fields from sparse input images in real time. Technically, the coarse MPI of a scene is first generated using a 3D CNN, and it is further optimized leveraging only the scene content aligned sparse MPI gradients in a few iterations. Extensive experiments demonstrate that our method achieves comparable visual quality while being 100x faster on average than state-of-the-art offline methods and delivers better performance (about 2 dB higher in PSNR) compared to other online approaches.
Authors: Junmyeong Lee, Hoseung Choi, Yoonwoo Jeong, Minsu Cho
Abstract: 4D reconstruction from casually captured monocular videos is challenging due to inherent ambiguity in reconstructing dynamic 3D geometry. To address this challenge, we introduce Robust Dynamic Gaussian Splatting (RoDyGS), a method that reconstructs dynamic scene representation from casual monocular videos. RoDyGS explicitly separates static and dynamic scene elements, and applies spatiotemporal regularization to enforce physically plausible geometry and temporally consistent motion. Furthermore, we propose a comprehensive benchmark, Kubric-MRig, which provides extensive camera and object motion along with simultaneous multi-view capture, features that are absent in previous benchmarks. Experiments demonstrate that RoDyGS significantly outperforms previous pose-free dynamic novel view synthesis approaches and achieves competitive rendering quality compared to existing pose-free static novel view synthesis approaches. Our proejct page is available at https://rodygs.github.io
URLs: https://rodygs.github.io
Authors: Lezhong Wang, Duc Minh Tran, Ruiqi Cui, Thomson TG, Anders Bjorholm Dahl, Siavash Arjomand Bigdeli, Jeppe Revall Frisvad, Manmohan Chandraker
Abstract: Achieving physically consistent image editing remains a significant challenge in computer vision. Existing image editing methods typically rely on neural networks, which struggle to accurately handle shadows and refractions. Conversely, physics-based inverse rendering often requires multi-view optimization, limiting its practicality in single-image scenarios. In this paper, we propose Materialist, a neural-initialized physically based rendering pipeline for single-image inverse rendering. Unlike previous hybrid methods that use physics to guide neural generation, our method leverages neural networks to predict initial material properties, which are then rigorously optimized via progressive differentiable rendering. Our approach enables a range of applications, including material editing, object insertion, and relighting, while also introducing an effective method for editing material transparency via ray-traced refraction without requiring full scene geometry. Furthermore, our envmap estimation method also achieves competitive performance, further enhancing the accuracy of image editing task. Experiments demonstrate strong performance across synthetic and real-world datasets, excelling even on challenging out-of-domain images.
Authors: Md Rakibul Hasan, Md Zakir Hossain, Aneesh Krishna, Shafin Rahman, Tom Gedeon
Abstract: Detecting empathy from video interactions has emerging applications, yet raw videos that could be used for training AI models are rarely available due to privacy and ethical constraints. Public benchmarks are consequently released only as pre-extracted features, creating a privacy-constrained learning regime whose privacy-utility trade-off is poorly characterised. We formalise three levels of privacy for video-based behavioural prediction -- no privacy (raw video), partial privacy (temporal visual features such as facial landmarks, action units and eye gaze) and strong privacy (summary statistics of those features) -- and ask whether strong, subject-generalisable empathy detection is achievable at the strong-privacy level. We propose TFMPathy, instantiated with two recent Tabular Foundation Models (TFMs) (TabPFN v2 and TabICL), under both in-context learning and fine-tuning paradigms. On a public human-robot interaction benchmark, TFMPathy achieves strong utility under strong privacy, outperforming established baselines by a substantial margin. To assess robustness and facilitate fair, safe deployment, we introduce a cross-subject evaluation protocol that was previously lacking in this benchmark. Under this protocol, TFM fine-tuning improves generalisation capacity substantially (accuracy: $0.590 \rightarrow 0.730$; AUC: $0.564 \rightarrow 0.669$). Aggregating temporal features into summary statistics also suppresses subject-specific and demographic cues, aligning TFMPathy with data-minimisation principles. TFMPathy, therefore, offers a practical route to building AI systems that depend on human-centred video when governance, consent or institutional policies restrict the sharing of raw video. Code will be released upon acceptance at https://github.com/hasan-rakibul/TFMPathy.
Authors: Yulong Zhang, Tianyi Liang, Xinyue Huang, Erfei Cui, Guoqing Wang, Xu Guo, Chenhui Li, Gongshen Liu
Abstract: Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting sample-level errors and lack effective unsupervised quality control. We introduce Consensus Entropy (CE), a training-free, model-agnostic metric that estimates output reliability by measuring inter-model agreement entropy. The core insight is that correct predictions converge in output space, while errors diverge. Based on CE, we develop CE-OCR, a lightweight multi-model framework that verifies outputs by ensemble agreement, selects the best outputs, and further improves efficiency through adaptive routing. Experiments demonstrate that CE is robust for quality verification, improving F1 scores by 42.1% over VLM-as-Judge. CE-OCR achieves consistent OCR gains, outperforming self-consistency and single-model baselines at the same cost. Notably, CE requires no training or supervision, enabling plug-and-play integration. Code: https://github.com/Aslan-yulong/consensus-entropy.
Authors: Zhiyu Pan, Xiongjun Guan, Yongjie Duan, Jianjiang Feng, Jie Zhou
Abstract: Fixed-length fingerprint representations, which map each fingerprint to a compact and fixed-size feature vector, are computationally efficient and well-suited for large-scale matching. However, designing a robust representation that effectively handles diverse fingerprint modalities, pose variations, and noise interference remains a significant challenge. In this work, we propose a fixed-length dense descriptor of fingerprints, and introduce FLARE-a fingerprint matching framework that integrates the Fixed-Length dense descriptor with pose-based Alignment and Robust Enhancement. This fixed-length representation employs a three-dimensional dense descriptor to effectively capture spatial relationships among fingerprint ridge structures, enabling robust and locally discriminative representations. To ensure consistency within this dense feature space, FLARE incorporates pose-based alignment using complementary estimation methods, along with dual enhancement strategies that refine ridge clarity while preserving the original fingerprint modality. The proposed dense descriptor supports fixed-length representation while maintaining spatial correspondence, enabling fast and accurate similarity computation. Extensive experiments demonstrate that FLARE achieves superior performance across rolled, plain, latent, and contactless fingerprints, significantly outperforming existing methods in cross-modality and low-quality scenarios. Further analysis validates the effectiveness of the dense descriptor design, as well as the impact of alignment and enhancement modules on the accuracy of dense descriptor matching. Experimental results highlight the effectiveness and generalizability of FLARE as a unified and scalable solution for robust fingerprint representation and matching. The implementation and code will be publicly available at https://github.com/Yu-Yy/FLARE.
Authors: Jiajun Qin, Yuan Pu, Zhuolun He, Seunggeun Kim, David Z. Pan, Bei Yu
Abstract: Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing approaches often fail to align all modality combinations within a unified embedding space during training, leading to degraded performance on rare modality patterns during inference. To address this fundamental limitation, we propose UniMoCo, a novel architecture featuring a modality-completion module that generates visual features from text, thereby ensuring modality completeness for both queries and targets. Additionally, UniMoCo incorporates a specialized training strategy that aligns embeddings from both original and modality-completed inputs, thus ensuring consistent and robust embeddings for diverse modality combinations. Comprehensive experiments demonstrate that UniMoCo outperforms previous methods while exhibiting consistent robustness across diverse settings. Furthermore, we identify and quantify the inherent bias in conventional approaches caused by imbalanced modality combinations in training data, showing that our modality-completion paradigm effectively mitigates this limitation. The code is available at https://github.com/HobbitQia/UniMoCo.
Authors: Chaoyang Wang, Zeyu Zhang, Meng Meng, Xu Zhou, Haiyun Jiang
Abstract: Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement Learning (RL) fine-tuning (e.g., GRPO). However, current RL approaches sample action groups solely from the policy model itself, which limits the upper boundary of the model's reasoning capability and leads to inefficient training. To address these limitations, this paper proposes a novel RL framework called \textbf{Vision-EKIPL}. The core of this framework lies in introducing high-quality actions generated by external auxiliary models during the RL training process to guide the optimization of the policy model. The policy learning with knowledge infusion from external models significantly expands the model's exploration space, effectively improves the reasoning boundary, and substantially accelerates training convergence speed and efficiency. Experimental results demonstrate that our proposed Vision-EKIPL achieved up to a 5\% performance improvement on the Reason-RFT-CoT Benchmark compared to the state-of-the-art (SOTA). It reveals that Vision-EKIPL can overcome the limitations of traditional RL methods, significantly enhance the visual reasoning performance of MLLMs, and provide a new effective paradigm for research in this field.
Authors: Quoc-Duy Tran, Anh-Tuan Vo, Dinh-Khoi Vo, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: Humans possess a unique ability to perceive meaningful patterns in ambiguous stimuli, a cognitive phenomenon known as pareidolia. This paper introduces Shape2Animal framework to mimics this imaginative capacity by reinterpreting natural object silhouettes, such as clouds, stones, or flames, as plausible animal forms. Our automated framework first performs open-vocabulary segmentation to extract object silhouette and interprets semantically appropriate animal concepts using vision-language models. It then synthesizes an animal image that conforms to the input shape, leveraging text-to-image diffusion model and seamlessly blends it into the original scene to generate visually coherent and spatially consistent compositions. We evaluated Shape2Animal on a diverse set of real-world inputs, demonstrating its robustness and creative potential. Our Shape2Animal can offer new opportunities for visual storytelling, educational content, digital art, and interactive media design. Our project page is here: https://shape2image.github.io
Authors: Advait Gupta, Rishie Raj, Dang Nguyen, Tianyi Zhou
Abstract: We develop a cost-efficient neurosymbolic agent to address challenging multi-turn image editing tasks such as ``Detect the bench in the image while recoloring it to pink. Also, remove the cat for a clearer view and recolor the wall to yellow.'' It combines the fast, high-level subtask planning by large language models (LLMs) with the slow, accurate, tool-use, and local A$^*$ search per subtask to find a cost-efficient toolpath -- a sequence of calls to AI tools. To save the cost of A$^*$ on similar subtasks, we perform inductive reasoning on previously successful toolpaths via LLMs to continuously extract/refine frequently used subroutines and reuse them as new tools for future tasks in an adaptive fast-slow planning, where the higher-level subroutines are explored first, and only when they fail, the low-level A$^*$ search is activated. The reusable symbolic subroutines considerably save exploration cost on the same types of subtasks applied to similar images, yielding a human-like fast-slow toolpath agent ``FaSTA$^*$'': fast subtask planning followed by rule-based subroutine selection per subtask is attempted by LLMs at first, which is expected to cover most tasks, while slow A$^*$ search is only triggered for novel and challenging subtasks. By comparing with recent image editing approaches, we demonstrate FaSTA$^*$ is significantly more computationally efficient while remaining competitive with the state-of-the-art baseline in terms of success rate. Our code and data can be accessed at https://github.com/tianyi-lab/FaSTAR.
Authors: Hengkai Tan, Yao Feng, Xinyi Mao, Shuhe Huang, Guodong Liu, Zhongkai Hao, Hang Su, Jun Zhu
Abstract: Learning generalizable manipulation policies hinges on data, yet robot manipulation data is scarce and often entangled with specific embodiments, making both cross-task and cross-platform transfer difficult. We tackle this challenge with task-agnostic embodiment modeling, which learns embodiment dynamics directly from task-agnostic action data and decouples them from high-level policy learning. By focusing on exploring all feasible actions of the embodiment to capture what is physically feasible and consistent, task-agnostic data takes the form of independent image-action pairs with the potential to cover the entire embodiment workspace, unlike task-specific data, which is sequential and tied to concrete tasks. This data-driven perspective bypasses the limitations of traditional dynamics-based modeling and enables scalable reuse of action data across different tasks. Building on this principle, we introduce AnyPos, a unified pipeline that integrates large-scale automated task-agnostic exploration with robust embodiment modeling through inverse dynamics learning. AnyPos generates diverse yet safe trajectories at scale, then learns embodiment representations by decoupling arm and end-effector motions and employing a direction-aware decoder to stabilize predictions under distribution shift, which can be seamlessly coupled with diverse high-level policy models. In comparison to the standard baseline, AnyPos achieves a 51% improvement in test accuracy. On manipulation tasks such as operating a microwave, toasting bread, folding clothes, watering plants, and scrubbing plates, AnyPos raises success rates by 30-40% over strong baselines. These results highlight data-driven embodiment modeling as a practical route to overcoming data scarcity and achieving generalization across tasks and platforms in visuomotor control. Project page: https://embodiedfoundation.github.io/vidar_anypos.
Authors: Jiajin Guan (Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu, China), Haibo Mei (School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China), Bonan Zhang (Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu, China), Dan Liu (Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu, China), Yuanshuang Fu (Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu, China), Yue Zhang (School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China)
Abstract: Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicle (UAV)-based aerial imagery, which features high resolution, complex spatial semantics, and strict real-time constraints. These challenges limit the applicability of general-purpose VLMs to structured aerial reasoning tasks. To address these challenges, we propose UAV-VL-R1, a lightweight VLM explicitly designed for aerial visual reasoning. It is trained using a hybrid method that combines supervised fine-tuning (SFT) and multi-stage reinforcement learning (RL). We leverage the group relative policy optimization (GRPO) algorithm to promote structured and interpretable reasoning through rule-guided rewards and intra-group policy alignment. To support model training and evaluation, we introduce a high-resolution visual question answering dataset named HRVQA-VL, which consists of 50,019 annotated samples covering eight UAV-relevant reasoning tasks, including object counting, transportation recognition, and spatial scene inference. Experimental results show that UAV-VL-R1 achieves a 48.17% higher zero-shot accuracy than the Qwen2-VL-2B-Instruct baseline and even outperforms its 72B-scale variant, which is 36x larger, on multiple tasks. Ablation studies reveal that while SFT improves semantic alignment, it may reduce reasoning diversity in mathematical tasks. GRPO-based RL compensates for this limitation by enhancing logical flexibility and the robustness of inference. Additionally, UAV-VL-R1 requires only 3.9GB of memory under FP16 inference and can be quantized to 2.5GB with INT8, supporting real-time deployment on resource-constrained UAV platforms.
Authors: B\'alint M\'esz\'aros, Ahmet Firintepe, Sebastian Schmidt, Stephan G\"unnemann
Abstract: AI tasks in the car interior like identifying and localizing externally introduced objects is crucial for response quality of personal assistants. However, computational resources of on-board systems remain highly constrained, restricting the deployment of such solutions directly within the vehicle. To address this limitation, we propose the novel Object Detection and Localization (ODAL) framework for interior scene understanding. Our approach leverages vision foundation models through a distributed architecture, splitting computational tasks between on-board and cloud. This design overcomes the resource constraints of running foundation models directly in the car. To benchmark model performance, we introduce ODALbench, a new metric for comprehensive assessment of detection and localization.Our analysis demonstrates the framework's potential to establish new standards in this domain. We compare the state-of-the-art GPT-4o vision foundation model with the lightweight LLaVA 1.5 7B model and explore how fine-tuning enhances the lightweight models performance. Remarkably, our fine-tuned ODAL-LLaVA model achieves an ODAL$_{score}$ of 89%, representing a 71% improvement over its baseline performance and outperforming GPT-4o by nearly 20%. Furthermore, the fine-tuned model maintains high detection accuracy while significantly reducing hallucinations, achieving an ODAL$_{SNR}$ three times higher than GPT-4o.
Authors: Jiahua Li, Zhanhe Zhang, Chenghao Xu, Zhe Xu, Kun Wei, Xu Yang, Cheng Deng
Abstract: Long videos, characterized by temporal complexity and sparse task-relevant information, pose significant reasoning challenges for AI systems. Although existing Large Language Model (LLM)-based approaches have advanced long video understanding, they remain bottlenecked by task-agnostic, fixed-granularity perception pipelines and suffer from vision-language hallucinations. Inspired by human adaptive perception and active verification, we propose CogniGPT, a framework leveraging an interactive loop between a Multi-Granular Perception Agent (MPA) and an Active Verification Agent (AVA). Specifically, instead of predetermined heuristics, MPA adaptively determines the optimal perception granularity and strategy based on the evolving context, while AVA actively mines multi-perspective visual evidence to cross-verify key observations and eliminate hallucinations. This interaction allows CogniGPT to efficiently identify a minimal set of reliable task-related clues. Extensive experiments on EgoSchema, Video-MME, NExT-QA, and MovieChat demonstrate its superiority in accuracy and efficiency. Notably, on EgoSchema, it surpasses existing training-free methods using only 11.2 frames and achieves performance comparable to Gemini 1.5-Pro.
Authors: Xiaoyang Liu, Zhengyan Zhou, Zihang Xu, Jiezhang Cao, Zheng Chen, Yulun Zhang
Abstract: Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality image restoration tasks such as deblurring, demonstrating stronger generative capabilities than CNN and transformer-based methods. However, challenges such as unbearable inference time and compromised fidelity still limit the full potential of the diffusion models. To address this, we introduce FideDiff, a novel single-step diffusion model designed for high-fidelity deblurring. We reformulate motion deblurring as a diffusion-like process where each timestep represents a progressively blurred image, and we train a consistency model that aligns all timesteps to the same clean image. By reconstructing training data with matched blur trajectories, the model learns temporal consistency, enabling accurate one-step deblurring. We further enhance model performance by integrating Kernel ControlNet for blur kernel estimation and introducing adaptive timestep prediction. Our model achieves superior performance on full-reference metrics, surpassing previous diffusion-based methods and matching the performance of other state-of-the-art models. FideDiff offers a new direction for applying pre-trained diffusion models to high-fidelity image restoration tasks, establishing a robust baseline for further advancing diffusion models in real-world industrial applications. Our dataset and code will be available at https://github.com/xyLiu339/FideDiff.
Authors: Kaiwen Zheng, Yuji Wang, Qianli Ma, Huayu Chen, Jintao Zhang, Yogesh Balaji, Jianfei Chen, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang
Abstract: Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of evaluation benchmarks like FID. This work represents the first effort to scale up continuous-time consistency to general application-level image and video diffusion models, and to make JVP-based distillation effective at large scale. We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks. Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the "mode-covering" nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. This integration complements sCM with the "mode-seeking" reverse divergence, effectively improving visual quality while maintaining high generation diversity. Validated on large-scale models (Cosmos-Predict2, Wan2.1) up to 14B parameters and 5-second videos, rCM generally matches the state-of-the-art distillation method DMD2 on quality metrics while mitigating mode collapse and offering notable advantages in diversity, all without GAN tuning or extensive hyperparameter searches. The distilled models generate high-fidelity samples in only $1\sim4$ steps, accelerating diffusion sampling by $15\times\sim50\times$. These results position rCM as a practical and theoretically grounded framework for advancing large-scale diffusion distillation. Code is available at https://github.com/NVlabs/rcm.
Authors: Minkwan Kim, Seungmin Lee, Junho Kim, Young Min Kim
Abstract: Recent advances in novel-view synthesis can create the photo-realistic visualization of real-world environments from conventional camera captures. However, the everyday environment experiences frequent scene changes, which require dense observations, both spatially and temporally, that an ordinary setup cannot cover. We propose long-term Gaussian scene chronology from sparse-view updates, coined LTGS, an efficient scene representation that can embrace everyday changes from highly under-constrained casual captures. Given an incomplete and unstructured 3D Gaussian Splatting (3DGS) representation obtained from an initial set of input images, we robustly model the long-term chronology of the scene despite abrupt movements and subtle environmental variations. We construct objects as template Gaussians, which serve as structural, reusable priors for shared object tracks. Then, the object templates undergo a further refinement pipeline that modulates the priors to adapt to temporally varying environments given few-shot observations. Once trained, our framework is generalizable across multiple time steps through simple transformations, significantly enhancing the scalability for a temporal evolution of 3D environments. As existing datasets do not explicitly represent the long-term real-world changes with a sparse capture setup, we collect real-world datasets to evaluate the practicality of our pipeline. Experiments demonstrate that our framework achieves superior reconstruction quality compared to other baselines while enabling fast and light-weight updates. Project page is available at: https://mkjjang3598.github.io/LTGS.
Authors: Zhen Yang, Wenyi Hong, Mingde Xu, Xinyue Fan, Weihan Wang, Jiale Cheng, Xiaotao Gu, Jie Tang
Abstract: UI-to-code aims to translate UI screenshots into executable front-end code. Despite progress with vision-language models (VLMs), most existing methods formulate UI-to-code as a single-pass generation, which mismatches real-world UI development that is inherently iterative and feedback-driven. We reformulate UI-to-code as an interactive visual optimization problem, where code generation is embedded in a closed-loop process of execution, visual inspection, and iterative refinement driven by rendered visual feedback. To address the non-differentiability of visual objectives and the noise of absolute visual evaluators, we propose Relative Visual Policy Optimization (RVPO), a preference-based reinforcement learning method that optimizes relative visual rankings among rendered candidates under execution feedback. We instantiate this paradigm in UI2Code^N, an open-source 9B model trained via continual pre-training, supervised fine-tuning, and reinforcement learning. Experiments demonstrate state-of-the-art performance on UI drafting, UI polishing, and UI editing benchmarks, even outperforming larger models, with performance consistently improving through iterative visual optimization. Our code and models are available at https://github.com/zai-org/UI2Code_N.
Authors: Haotian Dong, Ye Li, Rongwei Lu, Chen Tang, Shu-Tao Xia, Zhi Wang
Abstract: Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm introduces considerable inference latency. Although speculative decoding (SD) has been proven effective for accelerating visual AR models, its "draft one step, then verify one step" paradigm prevents a direct reduction in the number of forward passes, limiting its acceleration potential. Motivated by the interchangeability of visual tokens, we explore verification skipping in the SD process for the first time to explicitly cut the number of target model forward passes, thereby reducing inference latency. By analyzing the characteristics of the drafting stage, we observe that verification redundancy and stale feature reusability are key factors to maintain generation quality while improving speed for verification-free steps. Inspired by these two observations, we propose a novel SD framework VVS to accelerate visual AR model via partial verification skipping, which integrates three complementary modules: (1) a verification-free token selector with dynamic truncation, (2) token-level feature caching and reuse, and (3) fine-grained skipped step scheduling. Consequently, VVS reduces the number of target model forward passes by $2.8\times$ relative to vanilla AR decoding while maintaining competitive generation quality, offering a superior speed-quality trade-off over conventional SD frameworks and revealing strong potential to reshape the SD paradigm. Our code is available at https://github.com/HyattDD/VVS.
Authors: Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
Abstract: In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordinates on a structured 2D grid, preserving global 3D geometry while remaining compatible with the input format of 2D foundation models. To transfer rich 2D priors into POMA-3D, a view-to-scene alignment strategy is designed. Moreover, as point maps are view-dependent with respect to a canonical space, we introduce POMA-JEPA, a joint embedding-predictive architecture that enforces geometrically consistent point map features across multiple views. Additionally, we introduce ScenePoint, a point map dataset constructed from 6.5K room-level RGB-D scenes and 1M 2D image scenes to facilitate large-scale POMA-3D pretraining. Experiments show that POMA-3D serves as a strong backbone for both specialist and generalist 3D understanding. It benefits diverse tasks, including 3D question answering, embodied navigation, scene retrieval, and embodied localization, all achieved using only geometric inputs (i.e., 3D coordinates). Overall, our POMA-3D explores a point map way to 3D scene understanding, addressing the scarcity of pretrained priors and limited data in 3D representation learning. Project Page: https://matchlab-imperial.github.io/poma3d/
Authors: He Wang, Longteng Guo, Pengkang Huo, Xuanxu Lin, Yichen Yuan, Jie Jiang, Jing Liu
Abstract: Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap between complex scientific imagery and sparse textual descriptions. We present S1-MMAlign, a large-scale, multi-disciplinary multimodal dataset comprising over 15.5 million high-quality image-text pairs derived from 2.5 million open-access scientific papers. Spanning disciplines from physics and biology to engineering, the dataset captures diverse visual modalities including experimental setups, heatmaps, and microscopic imagery. To address the pervasive issue of weak alignment in raw scientific captions, we introduce an AI-ready semantic enhancement pipeline that leverages advanced multimodal large language models to recaption images, by synthesizing comprehensive context from paper abstracts and the citation contexts of corresponding figures. Technical validation confirms that our enhancement pipeline markedly improves data quality via reduced SciBERT pseudo-perplexity and enhanced CLIP image-text alignment, while also significantly boosting multimodal large language models performance in zero-shot scientific captioning, multi-domain scientific reasoning, and visual instruction tuning. S1-MMAlign provides a pivotal foundational resource for cross-modal scientific understanding in the AI for Science era, supporting the development of scientific foundation models and a wide range of downstream scientific intelligence applications. The dataset is publicly available at https://huggingface.co/datasets/ScienceOne-AI/S1-MMAlign.
URLs: https://huggingface.co/datasets/ScienceOne-AI/S1-MMAlign.
Authors: Jun-Jee Chao, Volkan Isler
Abstract: Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on multi-view videos captured at each time step. However, such setups are only possible in constrained environments. In real-world scenarios, observations are often sparse over time and captured sparsely from diverse viewpoints (e.g., from security cameras), making dynamic reconstruction highly ill-posed. We present SV-GS, a framework that simultaneously estimates a deformation model and the object's motion over time under sparse observations. To initialize SV-GS, we leverage a rough skeleton graph and an initial static reconstruction as inputs to guide motion estimation. (Later, we show that this input requirement can be relaxed.) Our method optimizes a skeleton-driven deformation field composed of a coarse skeleton joint pose estimator and a module for fine-grained deformations. By making only the joint pose estimator time-dependent, our model enables smooth motion interpolation while preserving learned geometric details. Experiments on synthetic datasets show that our method outperforms existing approaches under sparse observations by up to 34% in PSNR, and achieves comparable performance to dense monocular video methods on real-world datasets despite using significantly fewer frames. Moreover, we demonstrate that the input initial static reconstruction can be replaced by a diffusion-based generative prior, making our method more practical for real-world scenarios.
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 chromatic 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: Renyang Liu, Kangjie Chen, Han Qiu, Jie Zhang, Kwok-Yan Lam, Tianwei Zhang, See-Kiong Ng
Abstract: Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to the reproduction of unsafe content such as NSFW imagery and copyrighted artistic styles. Such behaviors pose persistent safety and compliance risks in real-world deployments and cannot be reliably mitigated by post-hoc filtering, owing to the limited robustness of such mechanisms and a lack of fine-grained semantic control. Recent unlearning methods seek to erase harmful concepts at the model level, which exhibit the limitations of requiring costly retraining, degrading the quality of benign generations, or failing to withstand prompt paraphrasing and adversarial attacks. To address these challenges, we introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection. Without modifying the underlying IGMs, SafeRedir adaptively routes unsafe prompts toward safe semantic regions through token-level interventions in the embedding space. The framework comprises two core components: a latent-aware multi-modal safety classifier for identifying unsafe generation trajectories, and a token-level delta generator for precise semantic redirection, equipped with auxiliary predictors for token masking and adaptive scaling to localize and regulate the intervention. Empirical results across multiple representative unlearning tasks demonstrate that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks. Furthermore, SafeRedir generalizes effectively across a variety of diffusion backbones and existing unlearned models, validating its plug-and-play compatibility and broad applicability. Code and data are available at https://github.com/ryliu68/SafeRedir.
Authors: Yichao Liu, Zongru Shao, Yueyang Teng, Junwen Guo
Abstract: Self-supervised learning has been increasingly investigated for low-dose computed tomography (LDCT) image denoising, as it alleviates the dependence on paired normal-dose CT (NDCT) data, which are often difficult to collect. However, many existing self-supervised blind-spot denoising methods suffer from training inefficiencies and suboptimal performance due to restricted receptive fields. To mitigate this issue, we propose a novel Progressive $\mathcal{J}$-invariant Learning that maximizes the use of $\mathcal{J}$-invariant to enhance LDCT denoising performance. We introduce a step-wise blind-spot denoising mechanism that enforces conditional independence in a progressive manner, enabling more fine-grained learning for denoising. Furthermore, we explicitly inject a combination of controlled Gaussian and Poisson noise during training to regularize the denoising process and mitigate overfitting. Extensive experiments on the Mayo LDCT dataset demonstrate that the proposed method consistently outperforms existing self-supervised approaches and achieves performance comparable to, or better than, several representative supervised denoising methods.
Authors: Renrong Shao, Dongyang Li, Dong Xia, Lin Shao, Jiangdong Lu, Fen Zheng, Lulu Zhang
Abstract: Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing long-range dependencies with a linear-time overhead. Several prospective studies have further designed Vision Mamba based on UNet(VM-UNet) for medical image segmentation. These approaches primarily focus on optimizing architectural designs by creating more complex structures to enhance the model's ability to perceive semantic features. In this paper, we propose a simple yet effective approach to improve the model by Dual Self-distillation for VM-UNet (DSVM-UNet) without any complex architectural designs. To achieve this goal, we develop double self-distillation methods to align the features at both the global and local levels. Extensive experiments conducted on the ISIC2017, ISIC2018, and Synapse benchmarks demonstrate that our approach achieves state-of-the-art performance while maintaining computational efficiency. Code is available at https://github.com/RoryShao/DSVM-UNet.git.
Authors: Jin Li, Tao Chen, Shuai Jiang, Weijie Wang, Jingwen Luo, Chenhui Wu
Abstract: Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and Gemini-powered dense captioning, ensuring a uniform distribution across 20 fine-grained garment categories. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Experimental results show strong agreement with human judgments (Kendall's $\tau$ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.
Authors: Yixin Chen, Ziyu Su, Lingbin Meng, Elshad Hasanov, Wei Chen, Anil Parwani, M. Khalid Khan Niazi
Abstract: Metastatic Progression remains the leading cause of cancer-related mortality, yet predicting whether a primary tumor will metastasize and where it will disseminate directly from histopathology remains a fundamental challenge. Although whole-slide images (WSIs) provide rich morphological information, prior computational pathology approaches typically address metastatic status or site prediction as isolated tasks, and do not explicitly model the clinically sequential decision process of metastatic risk assessment followed by downstream site-specific evaluation. To address this research gap, we present a decision-aware, concept-aligned MIL framework, HistoMet, for prognostic metastatic outcome prediction from primary tumor WSIs. Our proposed framework adopts a two-module prediction pipeline in which the likelihood of metastatic progression from the primary tumor is first estimated, followed by conditional prediction of metastatic site for high-risk cases. To guide representation learning and improve clinical interpretability, our framework integrates linguistically defined and data-adaptive metastatic concepts through a pretrained pathology vision-language model. We evaluate HistoMet on a multi-institutional pan-cancer cohort of 6504 patients with metastasis follow-up and site annotations. Under clinically relevant high-sensitivity screening settings (95 percent sensitivity), HistoMet significantly reduces downstream workload while maintaining high metastatic risk recall. Conditional on metastatic cases, HistoMet achieves a macro F1 of 74.6 with a standard deviation of 1.3 and a macro one-vs-rest AUC of 92.1. These results demonstrate that explicitly modeling clinical decision structure enables robust and deployable prognostic prediction of metastatic progression and site tropism directly from primary tumor histopathology.
Authors: Gaurang Sharma, Harri Polonen, Juha Pajula, Jutta Suksi, Jussi Tohka
Abstract: Head magnetic resonance imaging (MRI) data are routinely collected and shared for research under strict regulatory frameworks that require the removal of direct identifiers prior to data release. However, even after skull stripping, brain parenchyma may retain participant-specific features that enable linkage of scans acquired from the same individual across datasets, posing a potential privacy risk when combined with auxiliary information. Current regulatory approaches typically assess such risks using qualitative notions of reasonableness. Although prior work has suggested that brain MRI can support subject linkage, existing demonstrations have relied on training-based or computationally intensive methods. Here, we show that reliable linkage of skull-stripped T1-weighted brain MRI is possible using standard preprocessing pipelines followed by direct image similarity computations. Using this simple approach, we achieve near-perfect matching accuracy across datasets acquired at different time points, with varying scanner types, spatial resolutions, and acquisition protocols, and even in the presence of cognitive decline. These experiments simulate realistic scenarios of cross-database matching in large-scale neuroimaging repositories. Our findings highlight a previously underappreciated re-identification risk in shared brain MRI data and provide empirical evidence relevant to the development of informed, forward-looking data-sharing policies in neuroimaging research.
Authors: Riccardo de Lutio, Tobias Fischer, Yen-Yu Chang, Yuxuan Zhang, Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Katarina Tothova, Zan Gojcic, Haithem Turki
Abstract: Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas hold promise but currently suffer from two shortcomings. The first is scalability, as existing methods use image diffusion models or bidirectional video models that are limited in the number of views they can generate in a single pass (and thus require a costly iterative distillation process for consistency). The second is quality itself, as generators used in prior work tend to produce outputs that are inconsistent with existing scene content and fail entirely in completely unobserved regions. To solve these, we propose a two-stage pipeline that leverages two key insights. First, we train a powerful bidirectional generative model with a novel opacity mixing strategy that encourages consistency with existing observations while retaining the model's ability to extrapolate novel content in unseen areas. Second, we distill it into a causal auto-regressive model that generates hundreds of frames in a single pass. This model can directly produce novel views or serve as pseudo-supervision to improve the underlying 3D representation in a simple and highly efficient manner. We evaluate our method extensively and demonstrate that it can generate plausible reconstructions in scenarios where existing approaches fail completely. When measured on commonly benchmarked datasets, we outperform all existing baselines by a wide margin, exceeding prior state-of-the-art methods by 1-3 dB PSNR.
Authors: Rui Ma, Yifeng Wang, Ziteng Yang, Jing Guo, Naomi Imali Okanda, Xinghui Li
Abstract: Visual analysis and reconstruction of pipeline inner walls remain challenging in industrial inspection scenarios. This paper presents a dedicated reconstruction system for pipeline inner walls via industrial endoscopes, which is built on panoramic image stitching technology. Equipped with a custom graphical user interface (GUI), the system extracts key frames from endoscope video footage, and integrates polar coordinate transformation with image stitching techniques to unwrap annular video frames of pipeline inner walls into planar panoramic images. Experimental results demonstrate that the proposed method enables efficient processing of industrial endoscope videos, and the generated panoramic stitched images preserve all detailed features of pipeline inner walls in their entirety. This provides intuitive and accurate visual support for defect detection and condition assessment of pipeline inner walls. In comparison with the traditional frame-by-frame video review method, the proposed approach significantly elevates the efficiency of pipeline inner wall reconstruction and exhibits considerable engineering application value.
Authors: InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xiaojun Xiang, Xiaoyu Zhang, Xianbin Liu, Yifu Wang, Yipeng Chen, Zhewen Le, Zhichao Ye, Ziqiang Zhao
Abstract: We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation.
Authors: Xuezhen Wang, Li Ma, Yulin Shen, Zeyu Wang, Pedro V. Sander
Abstract: Temporal retiming, the ability to reconstruct and render dynamic scenes at arbitrary timestamps, is crucial for applications such as slow-motion playback, temporal editing, and post-production. However, most existing 4D Gaussian Splatting (4DGS) methods overfit at discrete frame indices but struggle to represent continuous-time frames, leading to ghosting artifacts when interpolating between timestamps. We identify this limitation as a form of temporal aliasing and propose RetimeGS, a simple yet effective 4DGS representation that explicitly defines the temporal behavior of the 3D Gaussian and mitigates temporal aliasing. To achieve smooth and consistent interpolation, we incorporate optical flow-guided initialization and supervision, triple-rendering supervision, and other targeted strategies. Together, these components enable ghost-free, temporally coherent rendering even under large motions. Experiments on datasets featuring fast motion, non-rigid deformation, and severe occlusions demonstrate that RetimeGS achieves superior quality and coherence over state-of-the-art methods.
Authors: Sudip Laudari, Sang Hun Baek
Abstract: Geometric data augmentation is widely used in segmentation workflows, but polygon annotations are often assumed to remain valid after transformation. This assumption can fail in structured domains such as architectural floorplan analysis, where a region may contain an interior void encoded as part of a single ordered polygon chain. Cropping or clipping can remove bridge vertices in this chain, causing one semantic region to split into disconnected components. We propose a lightweight topology-preserving augmentation strategy that repairs missing adjacency relations in index space while preserving the original vertex order. The method adds minimal overhead and can be integrated into existing preprocessing workflows. Experiments show that the proposed approach achieves near-perfect Cyclic Adjacency Preservation (CAP) across common geometric transformations and improves annotation consistency in polygon-based segmentation.
Authors: Hiba Adil Al-kharsan, R\'obert Rajk\'o
Abstract: This work presents a robust multi-class classification framework for handwritten digits that combines diffusion-driven feature denoising with a hybrid feature representation. Inspired by our previous work on brain tumor classification, the proposed approach operates in a feature space to improve the robustness to noise and adversarial attacks. This manuscript is submitted as an extended abstract rather than a full-length press-ready paper. First, the input images are converted into tight, interpretable exemplification using Non-negative Matrix Factorization (NNMF). In parallel, special deep features are extracted using a computational neural network (CNN). These integral features are combined into a united hybrid representation. The main objective of this work is to extend our previously validated two-class framework to a multi-class handwritten digit classification scenario. To improve robustness, a step diffusion operation is used in the feature space by gradually adding Gaussian noise. A feature denoiser network is trained to reverse this operation and rebuild clean representations from tilted inputs. The courteous features are then applied for multi-class classification. The suggested method is evaluated in both baseline and adversarial settings using AutoAttack. The experimental outcome present that the diffusion-based hybrid model is both effective and robust, the CNN baseline models outperforming while maintain powerful classification performance. These results explain the activity of feature-level diffusion defense for reliable multi-class handwritten digit classification.
Authors: Pavan Kumar Anasosalu Vasu, Cem Koc, Fartash Faghri, Chun-Liang Li, Bo Feng, Zhengfeng Lai, Meng Cao, Oncel Tuzel, Hadi Pouransari
Abstract: Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess models in offline settings. In contrast, the performance of a streaming VLM depends on additional metrics beyond pure video understanding, including proactiveness, which reflects the timeliness of the model's responses, and consistency, which captures the robustness of its responses over time. To address this limitation, we propose VSAS-Bench, a new framework and benchmark for Visual Streaming Assistants. In contrast to prior benchmarks that primarily employ single-turn question answering on video inputs, VSAS-Bench features temporally dense annotations with over 18,000 annotations across diverse input domains and task types. We introduce standardized synchronous and asynchronous evaluation protocols, along with metrics that isolate and measure distinct capabilities of streaming VLMs. Using this framework, we conduct large-scale evaluations of recent video and streaming VLMs, analyzing the accuracy-latency trade-off under key design factors such as memory buffer length, memory access policy, and input resolution, yielding several practical insights. Finally, we show empirically that conventional VLMs can be adapted to streaming settings without additional training, and demonstrate that these adapted models outperform recent streaming VLMs. For example, Qwen3-VL-4B surpasses Dispider, the best streaming VLM on our benchmark, by 3% under the asynchronous protocol. The benchmark and code will be available at https://github.com/apple/ml-vsas-bench.
Authors: Xiaoben Li, Jingyi Wu, Zeyu Cai, Siyuan Yu, Boqian Li, Yuliang Xiu
Abstract: Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downstream tasks like animation and texturing. An effective fitting method should be both locally expressive-capturing fine details such as hands and facial features-and globally robust to handle real-world challenges, including clothing dynamics, pose variations, and noisy or partial inputs. Existing approaches typically excel in only one aspect, lacking an all-in-one solution. We upgrade ETCH to ETCH-X, which leverages a tightness-aware fitting paradigm to filter out clothing dynamics ("undress"), extends expressiveness with SMPL-X, and replaces explicit sparse markers (which are highly sensitive to partial data) with implicit dense correspondences ("dense fit") for more robust and fine-grained body fitting. Our disentangled "undress" and "dense fit" modular stages enable separate and scalable training on composable data sources, including diverse simulated garments (CLOTH3D), large-scale full-body motions (AMASS), and fine-grained hand gestures (InterHand2.6M), improving outfit generalization and pose robustness of both bodies and hands. Our approach achieves robust and expressive fitting across diverse clothing, poses, and levels of input completeness, delivering a substantial performance improvement over ETCH on both: 1) seen data, such as 4D-Dress (MPJPE-All, 33.0% ) and CAPE (V2V-Hands, 35.8% ), and 2) unseen data, such as BEDLAM2.0 (MPJPE-All, 80.8% ; V2V-All, 80.5% ). Code and models will be released at https://xiaobenli00.github.io/ETCH-X/.
Authors: Junwoo Park, Jangho Lee, Sunho Lim
Abstract: Pretrained detectors perform well on benchmarks but often suffer performance degradation in real-world deployments due to distribution gaps between training data and target environments. COCO-like benchmarks emphasize category diversity rather than instance density, causing detectors trained under per-class sparsity to struggle in dense, single- or few-class scenes such as surveillance and traffic monitoring. In fixed-camera environments, the quasi-static background provides a stable, label-free prior that can be exploited at inference to suppress spurious detections. To address the issue, we propose Background Embedding Memory (BEM), a lightweight, training-free, weight-frozen module that can be attached to pretrained detectors during inference. BEM estimates clean background embeddings, maintains a prototype memory, and re-scores detection logits with an inverse-similarity, rank-weighted penalty, effectively reducing false positives while maintaining recall. Empirically, background-frame cosine similarity correlates negatively with object count and positively with Precision-Confidence AUC (P-AUC), motivating its use as a training-free control signal. Across YOLO and RT-DETR families on LLVIP and simulated surveillance streams, BEM consistently reduces false positives while preserving real-time performance. Our code is available at https://github.com/Leo-Park1214/Background-Embedding-Memory.git
URLs: https://github.com/Leo-Park1214/Background-Embedding-Memory.git
Authors: Xiangyu Liu, Feng Gao, Xiaomei Zhang, Yong Zhang, Xiaoming Wei, Zhen Lei, Xiangyu Zhu
Abstract: Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propose TurboTalk, a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator. We first adopt Distribution Matching Distillation to obtain a strong and stable 4-step student, and then progressively reduce the denoising steps from 4 to 1 through adversarial distillation. To ensure stable training under extreme step reduction, we introduce a progressive timestep sampling strategy and a self-compare adversarial objective that provides an intermediate adversarial reference that stabilizes progressive distillation. Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.
Authors: Sicheng Chen, Chad Wong, Tianyi Zhang, Enhui Chai, Zeyu Liu, Fei Xia
Abstract: Whole Slide Image (WSI) analysis is pivotal in computational pathology, enabling cancer diagnosis by integrating morphological and architectural cues across magnifications. Multiple Instance Learning (MIL) serves as the standard framework for WSI analysis. Recently, Mamba has become a promising backbone for MIL, overtaking Transformers due to its efficiency and global context modeling capabilities originating from Natural Language Processing (NLP). However, existing Mamba-based MIL approaches face three critical challenges: (1) disruption of 2D spatial locality during 1D sequence flattening; (2) sub-optimal modeling of fine-grained local cellular structures; and (3) high memory peaks during inference on resource-constrained edge devices. Studies like MambaOut reveal that Mamba's SSM component is redundant for local feature extraction, where Gated CNNs suffice. Recognizing that WSI analysis demands both fine-grained local feature extraction akin to natural images, and global context modeling akin to NLP, we propose MambaBack, a novel hybrid architecture that harmonizes the strengths of Mamba and MambaOut. First, we propose the Hilbert sampling strategy to preserve the 2D spatial locality of tiles within 1D sequences, enhancing the model's spatial perception. Second, we design a hierarchical structure comprising a 1D Gated CNN block based on MambaOut to capture local cellular features, and a BiMamba2 block to aggregate global context, jointly enhancing multi-scale representation. Finally, we implement an asymmetric chunking design, allowing parallel processing during training and chunking-streaming accumulation during inference, minimizing peak memory usage for deployment. Experimental results on five datasets demonstrate that MambaBack outperforms seven state-of-the-art methods. Source code and datasets are publicly available.
Authors: Zhiling Yan, Sicheng Chen, Tianyi Zhang, Nan Ying, Yanli Lei, Guanglei Zhang
Abstract: Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervised segmentation data requires significant workload demands from experienced pathologists, limiting the application of deep learning. To overcome this challenge, relaxing the label conditions to image-level classification labels allows for more data to be used and more scenarios to be enabled. One approach is to leverage Class Activation Map (CAM) to generate pseudo pixel-level annotations for semantic segmentation with only image-level labels. However, this method fails to thoroughly explore the essential characteristics of pathology images, thus identifying only small areas that are insufficient for pseudo masking. In this paper, we propose a novel shuffle-based feedback learning method inspired by curriculum learning to generate higher-quality pseudo-semantic segmentation masks. Specifically, we perform patch level shuffle of pathology images, with the model adaptively adjusting the shuffle strategy based on feedback from previous learning. Experimental results demonstrate that our proposed approach outperforms state-of-the-arts on three different datasets.
Authors: Yixiao Zeng, Jianlei Zheng, Chaoda Zheng, Shijia Chen, Mingdian Liu, Tongping Liu, Tengwei Luo, Yu Zhang, Boyang Wang, Linkun Xu, Siyuan Lu, Bo Tian, Xianming Liu
Abstract: Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models built on autoregressive video diffusion achieve high-fidelity, controllable multi-camera generation, but their inference cost remains a bottleneck for interactive deployment. However, existing diffusion caching methods are designed for offline video generation with multiple denoising steps, and do not transfer to this scenario. Few-step distilled models have no inter-step redundancy left for these methods to reuse, and sequence-level parallelization techniques require future conditioning that closed-loop interactive generation does not provide. We present X-Cache, a training-free acceleration method that caches along a different axis: across consecutive generation chunks rather than across denoising steps. X-Cache maintains per-block residual caches that persist across chunks, and applies a dual-metric gating mechanism over a structure- and action-aware block-input fingerprint to independently decide whether each block should recompute or reuse its cached residual. To prevent approximation errors from permanently contaminating the autoregressive KV cache, X-Cache identifies KV update chunks (the forward passes that write clean keys and values into the persistent cache) and unconditionally forces full computation on these chunks, cutting off error propagation. We implement X-Cache on X-world, a production multi-camera action-conditioned driving world model built on multi-block causal DiT with few-step denoising and rolling KV cache. X-Cache achieves 71% block skip rate with 2.6x wall-clock speedup while maintaining minimum degradation.
Authors: Helder Oliveira
Abstract: Breast cancer is a leading cause of cancer-related mortality among women worldwide, with mammography as the primary screening tool. While deep learning models have shown strong performance in lesion segmentation, most rely on computationally intensive architectures that limit their use in resource-constrained environments. This study evaluates the performance and efficiency of lightweight models for mammographic lesion segmentation. Architectures including MobileNetV2, EfficientNet Lite, FPN, and Fast-SCNN were compared against a U-Net baseline using the INbreast dataset with 5-fold cross-validation. Performance was assessed using Dice score, Intersection over Union (IoU), and Recall, alongside model complexity. MobileNetV2 with Squeeze-and-Excitation (SCSE) achieved the best performance, with a Dice score of 0.5766 while using approximately 75% fewer parameters than U-Net. Cross-dataset evaluation on the DMID dataset showed reduced accuracy due to domain shift but preserved recall. These results demonstrate that lightweight architectures offer a practical balance between performance and efficiency for deployable CAD systems.
Authors: Yiming Zhang, Jiacheng Chen, Jiaqi Tan, Yongsen Mao, Wenhu Chen, Angel X. Chang
Abstract: Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated for traditional 3D perception. When such annotations are treated as ground truth for video-based evaluation, reconstruction and annotation artifacts can miss objects that are clearly visible in the video, mislabel object identities, or corrupt geometry-dependent answers (e.g., size), yielding incorrect or ambiguous QA pairs. Second, evaluations often assume full-scene access, while many VLMs operate on sparsely sampled frames (e.g., 16-64), making many questions effectively unanswerable under the actual model inputs. We improve evaluation validity by introducing ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs. To this end, we re-annotate objects and geometry across 381 scenes from 5 datasets to improve data quality, and regenerate all QA pairs with rigorous bias mitigation and human verification using professional 3D annotation tools. We further enhance evaluation controllability by providing variants across multiple frame budgets (16/32/64/all) and fine-grained object visibility metadata, enabling controlled diagnostic analyses. Evaluations of general and domain-specific VLMs on ReVSI reveal systematic failure modes that are obscured by prior benchmarks, yielding a more reliable and diagnostic assessment of spatial intelligence.
Authors: Kidus Zewde, Simiao Ren, Xingyu Shen, Jiaqi Wu, Yuchen Zhou, Tommy Duong, Zikang Zhang, Ethan Traister, Kewen Xie
Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21, 2026 release. Leveraging the Twitter API v2 and a multi-stage curation pipeline spanning multilingual text heuristics (English, Japanese, and Chinese), browser-automated Twitter "Made with AI" badge verification, and model name variant matching, we curate 10,217 confirmed GPT-image-2 images from 27,662 collected records over a six-day window. We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters). A key negative result is that C2PA content credentials are systematically stripped by Twitter's CDN on upload, rendering cryptographic provenance verification infeasible for social-media-sourced AI images. The dataset and all curation code are released publicly.
Authors: V Team, Wenyi Hong, Xiaotao Gu, Ziyang Pan, Zhen Yang, Yuting Wang, Yue Wang, Yuanchang Yue, Yu Wang, Yanling Wang, Yan Wang, Xijun Liu, Wenmeng Yu, Weihan Wang, Wei Li, Shuaiqi Duan, Sheng Yang, Ruiliang Lv, Mingdao Liu, Lihang Pan, Ke Ning, Junhui Ji, Jinjiang Wang, Jing Chen, Jiazheng Xu, Jiale Zhu, Jiale Cheng, Ji Qi, Guobing Gan, Guo Wang, Cong Yao, Zijun Dou, Zihao Zhou, Zihan Wang, Zhiqi Ge, Zhijie Li, Zhenyu Hou, Zhao Xue, Zehui Wang, Zehan Qi, Zehai He, Yutao Zhang, Yusen Liu, Yukuo Cen, Yuchen Li, Yuan Wang, Yu Yang, Yongbin Liu, Yijian Lu, Yifan Xu, Yanzi Wang, Yanxiao Zhao, Yanfeng Wang, Yadong Xue, Yabo Xu, Xinyu Zhang, Xinyu Liu, Xiao Liu, Wenyi Zhao, Wenkai Li, Tianyu Tong, Tianshu Zhang, Shudan Zhang, Shengdong Yan, Qinkai Zheng, Mingde Xu, Licheng Bao, lat Long long, Jiaxing Xu, Jiaxin Fan, Jiawen Qian, Jiali Chen, Jiahui Lin, Jiadai Sun, Haozhi Zheng, Haoran Wang, Haochen Li, Hanyu Liu, Han Xu, Fan Yang, Dan Zhang, Da Yin, Chuangxin Zhao, Chengcheng Wu, Boyan Shi, Bowen Lv, Bowei Jia, Bo Li, Bin Chen, Baoxu Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang
Abstract: We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.
Authors: Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei, Jun Wang
Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue that high-resolution visual reasoning is therefore not only semantic reasoning but also task-relevant evidence acquisition under limited perceptual bandwidth. Inspired by active vision and information foraging, we formalise this process as sequential Bayesian optimal experimental design (S-BOED), where an agent decides which visual evidence to acquire before answering. Since exact Bayesian inference is intractable in continuous gigapixel spaces, we derive a tractable coverage--resolution objective as a proxy for task-relevant information gain. We instantiate this framework with FOVEA, a training-free procedure that refines VLM crop proposals through evidence-oriented probing. Experiments on high-resolution benchmarks show consistent gains over direct and ReAct-style baselines, with particularly strong improvements in search-dominated remote-sensing settings.
Authors: Ruize He, Dongchen Han, Gao Huang
Abstract: Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we demonstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters. Through this lens, we explain attention's global modeling power not as explicit token-wise aggregation, but as an implicit process where dynamically generated parameters act as a compressed representation of the global context. Inspired by this insight, we investigate a fundamental question: can we achieve Transformer-level sequence global modeling entirely through dynamic parameterization while maintaining linear complexity, effectively replacing explicit attention? To explore this, we design various dynamic parameter prediction strategies and integrate them into standard network layers. Extensive empirical studies on vision models demonstrate that dynamic parameterization can indeed serve as a highly effective, linear-complexity alternative to explicit attention, opening new pathways for efficient sequence modeling. Code is available at https://github.com/LeapLabTHU/WeightFormer.
Authors: Sen Fang, Hongbin Zhong, Yanxin Zhang, Dimitris N. Metaxas
Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings. While such resources are important for semantic understanding, they do not directly provide a unified interface for open-world recognition and translation, or for modern pose-driven sign language video generation frameworks: 1. RGB-based pretrained recognition models depend heavily on fixed backgrounds or clothing conditions during recording, and are less robust in open-world settings than style-agnostic pose-processing models. 2. Recent pose-guided image/video generation models mostly use a unified keypoint representation such as DWPose as their control interface. At present, the sign language field still lacks a data resource that can directly interface with this modern pose-native paradigm while also targeting real-world open scenarios. We present SignVerse-2M, a large-scale multilingual pose-native dataset for sign language pose modeling and evaluation. Built from publicly available multilingual sign language video resources, it applies DWPose in a unified preprocessing pipeline to convert raw videos into 2D pose sequences that can be used directly for modeling, resulting in a consolidated corpus of about two million clips covering more than 55 sign languages. Unlike many laboratory datasets, this resource preserves the recording conditions and speaker diversity of real-world videos while reducing appearance variation through a unified pose representation. Toward this goal, we further provide the data construction pipeline, task definitions, and a simple SignDW Transformer baseline, demonstrating the feasibility of this resource for multilingual pose-space modeling and its compatibility with modern pose-driven pipelines, while discussing the evaluation claims it can support as well as its current limitations.
Authors: Tzu-Yu Liu, Duan-Shin Lee
Abstract: Accurate badminton stroke prediction is crucial for fine-grained sports analysis and tactical decision support. However, existing methods struggle to model rich temporal context. This paper introduces TemPose-TF-ASF (Adjacent-Stroke Fusion), a context-aware extension of TemPose. It enhances stroke recognition by incorporating stroke-type information from both preceding and subsequent strokes. A two-stage training and inference strategy is adopted. Preliminary predictions from the baseline model are reused as estimated temporal context. These predictions guide the joint optimization of the ASF module and the classifier. By explicitly modeling bidirectional temporal stroke dependencies, the proposed method can be seamlessly integrated into existing state-of-the-art models. Experiments on a large-scale badminton match dataset show consistent improvements over the baseline and its variants in terms of Accuracy and Macro-F1. Moreover, integrating ASF into other advanced methods yields notable performance gains. These results demonstrate strong transferability and generalization capability.
Authors: Jonas V. Funk
Abstract: Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient. To shift the focus of UQ evaluation toward a more operationally relevant approach, the Fire-Centered Evaluation Region (FCER) framework is introduced as a spatially conditioned protocol to characterize UQ within critical fire zones. Using FCER, an Ensemble is compared against an distilled single-pass student model on the WildfireSpreadTS dataset. The student model demonstrates comparable calibration and complementary uncertainty ranking in boundary-relevant regimes. Code is available at https://github.com/jonasvilhofunk/WildfireUQ-FCER
Authors: Haibo Xiao, Hanzhe Liang, Jie Zhou, Jinbao Wang, Can Gao
Abstract: Detecting anomalies from 3D point clouds has received increasing attention in the field of computer vision, with some group-based or point-based methods achieving impressive results in recent years. However, learning accurate point-wise representations for 3D anomaly detection faces great challenges due to the large scale and sparsity of point clouds. In this study, a surface-based method is proposed for 3D anomaly detection, which learns a discriminative signed distance function using multi-scale level-of-detail features. We first present a Noisy Points Generation (NPG) module to generate different types of noise, thereby facilitating the learning of discriminative features by exposing abnormal points. Then, we introduce a Multi-scale Level-of-detail Feature (MLF) module to capture multi-scale information from a point cloud, which provides both fine-grained local and coarse-grained global feature information. Finally, we design an Implicit Surface Discrimination (ISD) module that leverages the extracted multi-scale features to learn an implicit surface representation of point clouds, which effectively trains a signed distance function to distinguish between abnormal and normal points. Experimental results demonstrate that the proposed method achieves an average object-level AUROC of 92.1\% and 85.9\% on the Anomaly-ShapeNet and Real3D-AD datasets, outperforming the current best approach by 2.1\% and 3.6\%, respectively. Codes are available at https://anonymous.4open.science/r/DLF-3AD-DA61.
Authors: Chih-Chung Liu, Zhiwei Lin, Yongtao Wang
Abstract: Open-world object detection aims to localize and recognize objects beyond a fixed closed-set label space. It is commonly divided into two categories, i.e., open-vocabulary detection, which assumes a predefined category list at test time, and open-ended detection, which requires generating candidate categories during the inference. Existing methods rely primarily on coarse textual semantics and parametric knowledge, which often provide insufficient visual evidence for fine-grained appearance variation, rare categories, and cluttered scenes. In this paper, we propose VL-SAM-v3, a unified framework that augments open-world detection with retrieval-grounded external visual memory. Specifically, once candidate categories are available, VL-SAM-v3 retrieves relevant visual prototypes from a non-parametric memory bank and transforms them into two complementary visual priors, i.e., sparse priors for instance-level spatial anchoring and dense priors for class-aware local context. These priors are integrated with the original detection prompts via Memory-Guided Prompt Refinement, enabling a shared retrieval-and-refinement mechanism that supports open-vocabulary and open-ended inference.Extensive zero-shot experiments on LVIS show that VL-SAM-v3 consistently improves detection performance under both open-vocabulary and open-ended inference, with particularly strong gains on rare categories.Moreover, experiments with a stronger open-vocabulary detector (i.e., SAM3) validate the generality of the proposed retrieval-and-refinement mechanism.
Authors: Karthik Inbasekar, Guy Rom, Omer Shlomovits
Abstract: Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet Video Distance (FVD) favors distributional textures over physical plausibility. Binary Visual Question Answering (VQA) based benchmarks like VBench~2.0 are prone to yes-bias and rely on low-resolution auditors that miss temporal failures. Moreover, their prompts target a single dimension at a time, multiplying the number of videos required while still not guaranteeing reliable results. WorldJen addresses these limitations directly. Binary VQA is replaced with Likert-scale questionnaires graded by a VLM that receives frames at native video resolution. Video generation costs are addressed by using adversarially curated prompts that are designed to exercise up to 16 quality dimensions simultaneously. The framework is built around two interlocking contributions. First, A blind human preference study is conducted, accumulating (2,696 pairwise annotations from 7 annotators with 100% pair coverage over 50 of the curated prompts $\times$ 6 state-of-the-art video models. A mean inter-annotator agreement of 66.9% is achieved and the study establishes a human ground-truth Bradley-Terry (BT) rating with a three-tier structure. Second, A VLM-as-a-judge evaluation engine using prompt-specific, dimension-specific Likert questionnaires (10 questions per dimension, 47,160 scored responses) judges the videos and reproduces the human-established three-tier BT rating structure independently. The VLM achieves a Spearman $\hat{\rho}=1.000,~p=0.0014$ that is interpreted as tier agreement with the human results. Six focused ablation studies validate the robustness of the VLM evaluation framework. Project page: https://moonmath.ai/worldjen/
Authors: Jianjie Fang, Yingshan Lei, Qin Wan, Ziyou Wang, Yuchao Huang, Yongyan Xu, Baining Zhao, Weichen Zhang, Chen Gao, Xinlei Chen, Yong Li
Abstract: Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.
Authors: Hongyuan Zhang, Yanchen Xu, Sida Huang, Xuelong Li
Abstract: Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this paper. By converting the contrastive loss to an auxiliary Gaussian distribution to quantitatively measure the difficulty of the specific contrastive model under the information theory framework, we properly define the task entropy, the core concept of $\pi$-noise, of contrastive learning. It is further proved that the predefined data augmentation in the standard contrastive learning paradigm can be regarded as a kind of point estimation of $\pi$-noise. Inspired by the theoretical study, a framework that develops a $\pi$-noise generator to learn the beneficial noise (instead of estimation) as data augmentations for contrast is proposed. The designed framework can be applied to diverse types of data and is also completely compatible with the existing contrastive models. From the visualization, we surprisingly find that the proposed method successfully learns effective augmentations. Our code is available at https://github.com/hyzhang98/PiNDA.
Authors: Hanyeol Yang, Sunggyu Kim, Mi Kyung Kim, Yongseon Yoo, Yu-Mi Kim, Min-Ho Shin, Insung Chung, Sang Baek Koh, Hyeon Chang Kim, Jong-Min Lee
Abstract: Multi-modal brain MRI provides essential complementary information for clinical diagnosis. However, acquiring all modalities in practice is often constrained by time and cost. To address this, various methods have been proposed to generate missing modalities from available ones. Existing approaches can be broadly categorized into two types: paired and unpaired methods. While paired methods achieve high synthesis accuracy, obtaining large-scale paired datasets is typically impractical. In contrast, unpaired methods, though more scalable, often fail to preserve critical anatomical features, such as lesions. In this paper, we propose Fully Guided Schr\"odinger Bridge (FGSB), a novel framework designed to overcome these limitations by enabling high-fidelity generation with extremely limited paired data. When lesion-specific information, such as expert annotations or segmentation masks, is available, FGSB preserves clinically relevant lesions during missing modality synthesis. Our model comprises two stages: (1) a generation stage that iteratively refines synthetic images using paired source images and Gaussian noise, and (2) a training stage that learns optimal transformation pathways by modeling intermediate states to ensure consistent, high-fidelity synthesis. Experimental results across multiple datasets demonstrate that FGSB achieves reliable synthesis performance across diverse imaging resolutions and data acquisition environments. In addition, incorporating lesion-specific priors further enhances the preservation of clinically relevant features.
Authors: Hongwu Wang, Shiwei Lian, Feitian Zhang
Abstract: Object-goal visual navigation aims to reach a specific target object using egocentric visual observations. Recent deep reinforcement learning (DRL) approaches have achieved promising success rates but often neglect collisions during evaluation, limiting real-world deployment. To address this issue, this letter introduces a collision-aware evaluation metric, namely collision-free success rate (CF-SR), to explicitly measure navigation performance under collision constraints. In addition, collision-free success weighted by path length (CF-SPL) is adopted to further evaluate navigation efficiency. Furthermore, a two-stage DRL training framework with collision prediction is proposed to improve collision-free navigation performance. In the first stage, a collision prediction module is trained by supervising the agent's collision states during exploration. In the second stage, leveraging the trained collision prediction, the agent learns to navigate toward target objects while avoiding collision. Extensive experiments across multiple navigation models in the AI2-THOR environment demonstrate consistent improvements in both CF-SR and CF-SPL. Real-world experiments further validate the effectiveness and generalization capability of the proposed framework.
Authors: Stefano Cerri, Asbj{\o}rn Munk, Sebastian N{\o}rgaard Llambias, Jakob Ambsdorf, Julia Machnio, Vardan Nersesjan, Christian Hedeager Krag, Peirong Liu, Pablo Rocamora Garc\'ia, Mostafa Mehdipour Ghazi, Mikael Boesen, Michael Eriksen Benros, Juan Eugenio Iglesias, Mads Nielsen
Abstract: We present FOMO260K, a large-scale, heterogeneous dataset of 260,927 brain Magnetic Resonance Imaging (MRI) scans from 77,589 MRI sessions and 55,378 subjects, aggregated from 910 publicly available sources. The dataset includes both clinical- and research-grade images, multiple MRI sequences, and a wide range of anatomical and pathological variability, including scans with large brain anomalies. Minimal preprocessing was applied to preserve the original image characteristics while reducing entry barriers for new users. Companion code for self-supervised pretraining and finetuning is provided, along with pretrained models. FOMO260K is intended to support the development and benchmarking of self-supervised learning methods in medical imaging at scale.
Authors: Ajay Mittal, Raghav Mehta, Omar Todd, Philipp Seeb\"ock, Georg Langs, Ben Glocker
Abstract: Automatic detection and classification of Cardiovascular disease (CVD) from Computed Tomography (CT) images play an important part in facilitating better-informed clinical decisions. However, most of the recent deep learning based methods either directly work on raw CT data or utilize it in pair with anatomical cardiac structure segmentation by training an end-to-end classifier. As such, these approaches become much more difficult to interpret from a clinical perspective. To address this challenge, in this work, we break down the CVD classification pipeline into three components: (i) image segmentation, (ii) image registration, and (iii) downstream CVD classification. Specifically, we utilize the Atlas-ISTN framework and recent segmentation foundational models to generate anatomical structure segmentation and a normative healthy atlas. These are further utilized to extract clinically interpretable radiomic features as well as deformation field based geometric features (through atlas registration) for CVD classification. Our experiments on the publicly available ASOCA dataset show that utilizing these features leads to better CVD classification accuracy (87.50\%) when compared against classification model trained directly on raw CT images (67.50\%). Our code is publicly available: https://github.com/biomedia-mira/grc-net
Authors: Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
Abstract: Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on labeled target-domain data improves performance, existing approaches typically rely on randomly selected samples, which may fail to identify the most informative data and thus hinder adaptation. To address the limitations, we propose an Active Selective Semi-supervised Fine-tuning framework for efficient adaptation of Med-VFMs to generalize across volumetric medical image segmentation. ASSFT integrates a novel active learning strategy with selective semi-supervised learning to maximize adaptation performance under a limited annotation budget, without requiring access to source data. Specifically, we introduce an Active Test-Time Sample Query strategy that identifies informative samples from the target domain using two complementary query metrics: Diversified Knowledge Divergence and Anatomical Segmentation Difficulty. DKD quantifies both the knowledge gap between pre-training and target domains and the semantic diversity within the target dataset, enabling the selection of samples that contain previously unlearned knowledge while maintaining intra-domain diversity. ASD estimates the segmentation difficulty of target anatomical structures by measuring predictive uncertainty within foreground regions of interest, allowing the model to prioritize samples with complex anatomical patterns rather than those dominated by background uncertainty. Second, we propose a Selective Semi-supervised Fine-tuning strategy to further improve adaptation performance by leveraging unlabeled target samples. Instead of utilizing all pseudo-labeled data, the proposed method selectively incorporates reliable unlabeled samples based on predictive confidence and semantic distance to labeled samples, enabling stable semi-supervised training while avoiding noisy pseudo-labels.
Authors: Taisei Hanyu, Nhat Chung, Huy Le, Toan Nguyen, Yuki Ikebe, Anthony Gunderman, Duy Nguyen Ho Minh, Khoa Vo, Tung Kieu, Kashu Yamazaki, Chase Rainwater, Anh Nguyen, Ngan Le
Abstract: Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation representations can form a foundation for multitask robotic manipulation. Most existing robotic multitask models rely on dense embeddings that entangle both object and background cues, raising concerns about both efficiency and interpretability. In contrast, we study object-relation-centric representations as a pathway to more structured, efficient, and explainable visuomotor control. Our contributions are two-fold. First, we introduce LIBERO+, a fine-grained benchmark dataset designed to enable and evaluate object-relation reasoning in robotic manipulation. Unlike prior datasets, LIBERO+ provides object-centric annotations that enrich demonstrations with box- and mask-level labels as well as instance-level temporal tracking, supporting compact and interpretable visuomotor representations. Second, we propose SlotVLA, a slot-attention-based framework that captures both objects and their relations for action decoding. It uses a slot-based visual tokenizer to maintain consistent temporal object representations, a relation-centric decoder to produce task-relevant embeddings, and an LLM-driven module that translates these embeddings into executable actions. Experiments on LIBERO+ demonstrate that object-centric slot and object-relation slot representations drastically reduce the number of required visual tokens, while providing competitive generalization. Together, LIBERO+ and SlotVLA provide a compact, interpretable, and effective foundation for advancing object-relation-centric robotic manipulation.
Authors: Hao Li, Fabian Deuser, Wenping Yin, Steffen Knoblauch, Wufan Zhao, Filip Biljecki, Yong Xue, Wei Huang
Abstract: As Earth's climate changes, it is impacting disasters and extreme weather events across the planet. Record-breaking heat waves, drenching rainfalls, extreme wildfires, and widespread flooding during hurricanes are all becoming more frequent and more intense. Rapid and efficient response to disaster events is essential for climate resilience and sustainability. A key challenge in disaster response is to accurately and quickly identify disaster locations to support decision-making and resources allocation. In this paper, we propose a Probabilistic Cross-view Geolocalization approach, called ProbGLC, exploring new pathways towards generative location awareness for rapid disaster response. Herein, we combine probabilistic and deterministic geolocalization models into a unified framework to simultaneously enhance model explainability (via uncertainty quantification) and achieve state-of-the-art geolocalization performance. Designed for rapid diaster response, the ProbGLC is able to address cross-view geolocalization across multiple disaster events as well as to offer unique features of probabilistic distribution and localizability score. To evaluate the ProbGLC, we conduct extensive experiments on two cross-view disaster datasets (i.e., MultiIAN and SAGAINDisaster), consisting diverse cross-view imagery pairs of multiple disaster types (e.g., hurricanes, wildfires, floods, to tornadoes). Preliminary results confirms the superior geolocalization accuracy (i.e., 0.86 in Acc@1km and 0.97 in Acc@25km) and model explainability (i.e., via probabilistic distributions and localizability scores) of the proposed ProbGLC approach, highlighting the great potential of leveraging generative cross-view approach to facilitate location awareness for better and faster disaster response. The data and code is publicly available at https://github.com/bobleegogogo/ProbGLC
Authors: Guo Ye, Zexi Zhang, Xu Zhao, Shang Wu, Haoran Lu, Shihan Lu, Han Liu
Abstract: Vision-Language-Action (VLA) models have shown remarkable generalization by mapping web-scale knowledge to robotic control, yet they remain blind to physical contact. Consequently, they struggle with contact-rich manipulation tasks that require reasoning about force, texture, and slip. While some approaches incorporate low-dimensional tactile signals, they fail to capture the high-resolution dynamics essential for such interactions. To address this limitation, we introduce DreamTacVLA, a framework that grounds VLA models in contact physics by learning to feel the future. Our model adopts a hierarchical perception scheme in which high-resolution tactile images serve as micro-vision inputs coupled with wrist-camera local vision and third-person macro vision. To reconcile these multi-scale sensory streams, we first train a unified policy with a Hierarchical Spatial Alignment (HSA) loss that aligns tactile tokens with their spatial counterparts in the wrist and third-person views. To further deepen the model's understanding of fine-grained contact dynamics, we finetune the system with a tactile world model that predicts future tactile signals. To mitigate tactile data scarcity and the wear-prone nature of tactile sensors, we construct a hybrid large-scale dataset sourced from both high-fidelity digital twin and real-world experiments. By anticipating upcoming tactile states, DreamTacVLA acquires a rich model of contact physics and conditions its actions on both real observations and imagined consequences. Across contact-rich manipulation tasks, it outperforms state-of-the-art VLA baselines, achieving up to 95% success, highlighting the importance of understanding physical contact for robust, touch-aware robotic agents.
Authors: Xiaofan Wang, Junyi Wang, Yuqian Chen, Lauren J. O' Donnell, Fan Zhang
Abstract: Multimodal image registration between diffusion MRI (dMRI) and T1-weighted (T1w) MRI images is a critical step for aligning diffusion-weighted imaging (DWI) data with structural anatomical space. Traditional registration methods often struggle to ensure accuracy due to the large intensity differences between diffusion data and high-resolution anatomical structures. This paper proposes an unsupervised registration framework based on a generative registration network, which transforms the original multimodal registration problem between b0 and T1w images into a unimodal registration task between a generated image and the real T1w image. This effectively reduces the complexity of cross-modal registration. The framework first employs an image synthesis model to generate images with T1w-like contrast, and then learns a deformation field from the generated image to the fixed T1w image. The registration network jointly optimizes local structural similarity and cross-modal statistical dependency to improve deformation estimation accuracy. Experiments conducted on two independent datasets demonstrate that the proposed method outperforms several state-of-the-art approaches in multimodal registration tasks.
Authors: I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang, Connor Schenck
Abstract: Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information about objects and scenes that is essential for precise manipulation. In this work, we introduce Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining (CLAMP), a novel 3D pre-training framework that utilizes point clouds and robot actions. From the merged point cloud computed from RGB-D images and camera extrinsics, we re-render multi-view four-channel image observations with depth and 3D coordinates, including dynamic wrist views, to provide clearer views of target objects for high-precision manipulation tasks. The pre-trained encoders learn to associate the 3D geometric and positional information of objects with robot action patterns via contrastive learning on large-scale simulated robot trajectories. During encoder pre-training, we pre-train a Diffusion Policy to initialize the policy weights for fine-tuning, which is essential for improving fine-tuning sample efficiency and performance. After pre-training, we fine-tune the policy on a limited amount of task demonstrations using the learned image and action representations. We demonstrate that this pre-training and fine-tuning design substantially improves learning efficiency and policy performance on unseen tasks. Furthermore, we show that CLAMP outperforms state-of-the-art baselines across six simulated tasks and five real-world tasks. The project website and videos can be found at https://clamp3d.github.io/CLAMP/.
Authors: Gorkem Yildiz
Abstract: We present Helmlab, a family of two purpose-built color spaces for UI design systems sharing a common 11-stage analytical structure: MetricSpace, a 72-parameter space optimized for color-difference prediction, and GenSpace, a 44-parameter space optimized for gradient and palette generation. The forward transform maps CIE XYZ to a perceptually-organized Lab representation through learned matrices, per-channel power compression, Fourier hue correction, and embedded Helmholtz-Kohlrausch lightness adjustment. A post-pipeline neutral correction holds gray-axis chroma below 1e-5 on a 21-step ramp, and a rigid rotation of the chromatic plane improves hue-angle alignment without affecting the distance metric (which is invariant under isometries). On COMBVD (3,813 color pairs), MetricSpace v21 achieves STRESS 22.48, a 23 percent reduction from CIEDE2000 (29.20). On the held-out MacAdam 1974 dataset it scores 19.51 (CIEDE2000: 22.13; CAM16-UCS leads at 18.71). On a self-collected 3,552-judgement screen-condition set it scores 23.26 vs 62.54 for CIEDE2000. On academic He et al. 2022 (82 3D-printed pairs) MetricSpace scores 35.9 vs CIEDE2000 32.6, a regression we own. Averaging the three primary datasets, MetricSpace scores 21.75 vs the next-best baseline CIECAM02-UCS at 35.98. GenSpace v0.11.1 trades distance accuracy for generation quality: on a 90-metric, 3,038-pair gradient/palette benchmark across sRGB, P3, and Rec.2020, it wins 65 of 90 vs OKLab. The transform is invertible with round-trip errors below 1e-13. Production implementations ship on PyPI, npm, Color.js (PR 722, merged), and as a PostCSS plugin.
Authors: Jiamin Zheng, Jingwen Yu, Guangcheng Chen, Hong Zhang
Abstract: Indoor robot navigation is often compromised by glass surfaces, which severely corrupt depth sensor measurements. While foundation models like Depth Anything 3 provide excellent geometric priors, they lack an absolute metric scale. We propose a training-free framework that leverages depth foundation models as a structural prior, employing a robust local RANSAC-based alignment to fuse it with raw sensor depth. This naturally avoids contamination from erroneous glass measurements and recovers an accurate metric scale. Furthermore, we introduce \ti{GlassRecon}, a novel RGB-D dataset with geometrically derived ground truth for glass regions. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art baselines, especially under severe sensor depth corruption. The dataset and related code will be released at https://github.com/jarvisyjw/GlassRecon.
Authors: Tianwei Ye, Yifan Mao, Minwen Liao, Jian Liu, Chunchao Guo, Dazhao Du, Quanxin Shou, Fangqi Zhu, Song Guo
Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for simulation-based training and real-world deployment. While 3D generative modeling has advanced rapidly, embodied applications impose requirements far beyond visual realism: generated objects must carry kinematic structure and material properties, scenes must support interaction and task execution, and the resulting content must bridge the gap between simulation and reality. This survey reviews 3D generation for embodied AI and organizes the literature around three roles that 3D generation plays in embodied systems. In Data Generator, 3D generation produces simulation-ready objects and assets, including articulated, physically grounded, and deformable content for downstream interaction; in Simulation Environments, it constructs interactive and task-oriented worlds, spanning structure-aware, controllable, and agentic scene generation; and in Sim2Real Bridge, it supports digital twin reconstruction, data augmentation, and synthetic demonstrations for downstream robot learning and real-world transfer. We also show that the field is shifting from visual realism toward interaction readiness, and we identify the main bottlenecks, including limited physical annotations, the gap between geometric quality and physical validity, fragmented evaluation, and the persistent sim-to-real divide, that must be addressed for 3D generation to become a dependable foundation for embodied intelligence. Our project page is at https://3dgen4robot.github.io.
Authors: Kenneth J. K. Ong
Abstract: As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effects of visual priming on VLMs' cooperative behavior using the Iterated Prisoner's Dilemma (IPD) as a test scenario. We examine whether exposure to images depicting behavioral concepts (kindness/helpfulness vs. aggressiveness/selfishness) and color-coded reward matrices alters VLM decision patterns. Experiments were conducted across multiple state-of-the-art VLMs. We further explore mitigation strategies including prompt modifications, Chain of Thought (CoT) reasoning, and visual token reduction. Results show that VLM behavior can be influenced by both image content and color cues, with varying susceptibility and mitigation effectiveness across models. These findings not only underscore the importance of robust evaluation frameworks for VLM deployment in visually rich and safety-critical environments, but also highlight how architectural and training differences among models may lead to distinct behavioral responses-an area worthy of further investigation.
Authors: Hao Chen, Jiaming Liu, Zhonghao Yan, Nuowei Han, Renrui Zhang, Chenyang Gu, Jialin Gao, Ziyu Guo, Siyuan Qian, Yinxi Wang, Peng Jia, Shanghang Zhang, Pheng-Ann Heng
Abstract: Robotic foundation models require reasoning over complex visual scenes to execute adaptive actions in dynamic environments. While recent studies on latent-reasoning Vision-Language-Action (VLA) models have demonstrated the capability to capture fine-grained physical dynamics, they remain predominantly confined to static imitation learning, severely limiting their adaptability and generalization. In this paper, we present LaST-R1, a novel reinforcement learning (RL) post-training framework designed to effectively harness "latent reasoning-before-acting" policies. Specifically, we propose Latent-to-Action Policy Optimization (LAPO), a core RL algorithm that jointly optimizes the latent reasoning process and the action generation. By explicitly embedding latent Chain-of-Thought (CoT) reasoning directly within the RL optimization loop, LAPO stimulates profound physical world modeling, which in turn drives robust execution in interactive environments. Furthermore, an adaptive latent CoT mechanism is introduced, allowing the policy to dynamically modulate its reasoning horizon based on diverse environment states. Experiments show that LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark with only one-shot supervised warm-up, significantly improving convergence speed and performance over prior state-of-the-art (SOTA) methods. In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach across four complex tasks, including both single-arm and dual-arm settings. Finally, LaST-R1 demonstrates strong generalization across simulated and real-world environments.
Authors: Yida Xue, Ningyu Zhang, Tingwei Wu, Zhe Ma, Daxiong Ji, Zhao Wang, Guozhou Zheng, Huajun Chen
Abstract: The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.
Authors: Soyeon Kim, Seongwoo Lim, Kyowoon Lee, Jaesik Choi
Abstract: Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield unreliable explanations when the integration path between a baseline and the input passes through regions with noisy gradients. While Guided Integrated Gradients reduces this sensitivity by adaptively updating low-gradient-magnitude features, input-space guidance still produces intermediate inputs that deviate from the data manifold. To address this limitation, we propose \emph{Manifold-Aligned Guided Integrated Gradients} (MA-GIG), which constructs attribution paths in the latent space of a pre-trained variational autoencoder. By decoding intermediate latent states, MA-GIG biases the path toward the learned generative manifold and reduces exposure to implausible input-space regions. Through qualitative and quantitative evaluations, we demonstrate that MA-GIG produces faithful explanations by aggregating gradients on path features proximal to the input. Consequently, our method reduces off-manifold noise and outperforms prior path-based attribution methods across multiple datasets and classifiers. Our code is available at https://github.com/leekwoon/ma-gig/.
Authors: Mahmoud Hanouneh, Radu Timofte, Dmitry Ignatov
Abstract: Automated Machine Learning (AutoML) frameworks increasingly leverage Large Language Models (LLMs) for tasks such as hyperparameter optimization and neural architecture code generation. However, current LLM-based approaches focus on generative outputs and evaluate them by training the produced artifacts. Whether LLMs can learn to reason about neural network performance across datasets remains underexplored. We present a classification task integrated into the NNGPT framework, in which a fine-tuned LLM predicts which of two image classification datasets a given neural network architecture achieves higher accuracy on. The task is built on the LEMUR dataset, which provides standardized PyTorch implementations with reproducible performance metrics. Three prompt configurations of increasing difficulty are evaluated: a normalized-accuracy baseline (trivially reaching 100%), a metadata-enriched prompt replacing accuracies with dataset properties, and a code-only prompt presenting only architecture source code and dataset names. Using DeepSeek-Coder-7B-Instruct fine-tuned with LoRA, the code-only prompt reaches 80% peak accuracy over 15 epochs, while the metadata prompt peaks at 70%. Perdataset analysis reveals complementary strengths: metadata excels for datasets with distinctive properties (CelebAGender at 90.9%) but degrades for overlapping characteristics, whereas the code-only prompt shows more balanced performance. A comparison with DeepSeek-Coder1.3B confirms that model capacity affects this form of architectural reasoning. The results establish that LLMs can be fine-tuned to predict cross-dataset suitability from neural network code, suggesting that architecture source code contains richer discriminative signal than dataset metadata alone.