Attention
-
AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving
2026-04-16 17:54:53Fabrizio Genilotti, Arianna Stropeni, Gionata Grotto, Francesco Borsatti, Manuel Barusco, Davide Dalle Pezze, Gian Antonio SustoAbstract
The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significantly different conditions, such as atypical obstacles, its perceptual capabilities can degrade substantially. Unlike many domains where errors carry limited consequences, failures in autonomous driving translate directly into physical risk for passengers, pedestrians, and other road users. To address this challenge, we explore Visual Anomaly Detection (VAD) as a solution. VAD enables the identification of anomalous objects not present during training, allowing the system to alert the driver when an unfamiliar situation is detected. Crucially, VAD models produce pixel-level anomaly maps that can guide driver attention to specific regions of concern without requiring any prior assumptions about the nature or form of the hazard. We benchmark eight state-of-the-art VAD methods on AnoVox, the largest synthetic dataset for anomaly detection in autonomous driving. In particular, we evaluate performance across four backbone architectures spanning from large networks to lightweight ones such as MobileNet and DeiT-Tiny. Our results demonstrate that VAD transfers effectively to road scenes. Notably, Tiny-Dinomaly achieves the best accuracy-efficiency trade-off for edge deployment, matching full-scale localization performance at a fraction of the memory cost. This study represents a concrete step toward safer, more responsible deployment of autonomous vehicles, ultimately improving protection for passengers, pedestrians, and all road users.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15291
PDF
-
Why Do Vision Language Models Struggle To Recognize Human Emotions?
2026-04-16 17:49:58Madhav Agarwal, Sotirios A. Tsaftaris, Laura Sevilla-Lara, Steven McDonaghAbstract
Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans. Vision-language models (VLMs) have made tremendous progress in the last few years for many visual tasks, potentially offering a promising solution for understanding emotions. However, it is surprising that even the most sophisticated contemporary VLMs struggle to recognize human emotions or to outperform even specialized vision-only classifiers. In this paper we ask the question "Why do VLMs struggle to recognize human emotions?", and observe that the inherently continuous and dynamic task of facial expression recognition (DFER) exposes two critical VLM vulnerabilities. First, emotion datasets are naturally long-tailed, and the web-scale data used to pre-train VLMs exacerbates this head-class bias, causing them to systematically collapse rare, under-represented emotions into common categories. We propose alternative sampling strategies that prevent favoring common concepts. Second, temporal information is critical for understanding emotions. However, VLMs are unable to represent temporal information over dense frame sequences, as they are limited by context size and the number of tokens that can fit in memory, which poses a clear challenge for emotion recognition. We demonstrate that the sparse temporal sampling strategy used in VLMs is inherently misaligned with the fleeting nature of micro-expressions (0.25-0.5 seconds), which are often the most critical affective signal. As a diagnostic probe, we propose a multi-stage context enrichment strategy that utilizes the information from "in-between" frames by first converting them into natural language summaries. This enriched textual context is provided as input to the VLM alongside sparse keyframes, preventing attentional dilution from excessive visual data while preserving the emotional trajectory.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15280
PDF
-
Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography
2026-04-16 14:55:28Simon B\"ohi, Irene Cannistraci, Sergio Mu\~noz Gonzalez, Moritz Vandenhirtz, Sonia Laguna, Samuel Ruiperez-Campillo, Max Kr\"ahenmann, Andrea Agostini, Ece Ozkan, Thomas M. Sutter, Julia E. VogtAbstract
Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective nature, but the sparse and heterogeneous spatiotemporal views of the heart pose distinct challenges. Existing masked autoencoder (MAE) approaches typically process images or short clips independently, failing to capture the inherent multi-view structure required for coherent cardiac representation. We introduce Latent Attention Masked Autoencoder (LAMAE), a foundation model architecture tailored to the multi-view nature of medical imaging. LAMAE augments the standard MAE with a latent attention module that enables information exchange across frames and views directly in latent space. This allows the model to aggregate variable-length sequences and distinct views, reconstructing a holistic representation of cardiac function from partial observations. We pretrain LAMAE on MIMIC-IV-ECHO, a large-scale, uncurated dataset reflecting real-world clinical variability. To the best of our knowledge, we present the first results for predicting ICD-10 codes from MIMIC-IV-ECHO videos. Furthermore, we empirically demonstrate that representations learned from adult data transfer effectively to pediatric cohorts despite substantial anatomical differences. These results provide evidence that incorporating structural priors, such as multi-view attention, yields significantly more robust and transferable representations.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15096
PDF
-
Building Extraction from Remote Sensing Imagery under Hazy and Low-light Conditions: Benchmark and Baseline
2026-04-16 14:49:18Feifei Sang, Wei Lu, Hongruixuan Chen, Sibao Chen, Bin LuoAbstract
Building extraction from optical Remote Sensing (RS) imagery suffers from performance degradation under real-world hazy and low-light conditions. However, existing optical methods and benchmarks focus primarily on ideal clear-weather conditions. While SAR offers all-weather sensing, its side-looking geometry causes geometric distortions. To address these challenges, we introduce HaLoBuilding, the first optical benchmark specifically designed for building extraction under hazy and low-light conditions. By leveraging a same-scene multitemporal pairing strategy, we ensure pixel-level label alignment and high fidelity even under extreme degradation. Building upon this benchmark, we propose HaLoBuild-Net, a novel end-to-end framework for building extraction in adverse RS scenarios. At its core, we develop a Spatial-Frequency Focus Module (SFFM) to effectively mitigate meteorological interference on building features by coupling large receptive field attention with frequency-aware channel reweighting guided by stable low-frequency anchors. Additionally, a Global Multi-scale Guidance Module (GMGM) provides global semantic constraints to anchor building topologies, while a Mutual-Guided Fusion Module (MGFM) implements bidirectional semantic-spatial calibration to suppress shallow noise and sharpen weather-induced blurred boundaries. Extensive experiments demonstrate that HaLoBuild-Net significantly outperforms state-of-the-art methods and conventional cascaded restoration-segmentation paradigms on the HaLoBuilding dataset, while maintaining robust generalization on WHU, INRIA, and LoveDA datasets. The source code and datasets are publicly available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15088
PDF
-
Attention-Gated Convolutional Networks for Scanner-Agnostic Quality Assessment
Abstract
Motion artifacts present a significant challenge in structural MRI (sMRI), often compromising clinical diagnostics and large-scale automated analysis. While manual quality control (QC) remains the gold standard, it is increasingly unscalable for massive longitudinal studies. To address this, we propose a hybrid CNN-Attention framework designed for robust, site-invariant MRI quality assessment. Our architecture integrates a hierarchical 2D CNN encoder for local spatial feature extraction with a multi-head cross-attention mechanism to model global dependencies. This synergy enables the model to prioritize motion relevant artifact signatures, such as ringing and blurring, while dynamically filtering out site-specific intensity variations and background noise. The framework was trained end-to-end on the MR-ART dataset using a balanced cohort of 200 subjects. Performance was evaluated across two tiers: Seen Site Evaluation on a held-out MR-ART partition and Unseen Site Evaluation using 200 subjects from 17 heterogeneous sites in the ABIDE archive. On seen sites, the model achieved a scan-level accuracy of 0.9920 and an F1-score of 0.9919. Crucially, it maintained strong generalization across unseen ABIDE sites (Acc = 0.755) without any retraining or fine-tuning, demonstrating high resilience to domain shift. These results indicate that attention-based feature re-weighting successfully captures universal artifact descriptors, bridging the performance gap between diverse imaging environments and scanner manufacturers.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15059
PDF
-
FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection
2026-04-16 11:22:13Jianchao Huang, Fengming Zhang, Haibo Zhu, Tao YanAbstract
Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a frequency-spatial feature enhancement framework built upon the RT-DETR baseline. By establishing a collaborative modeling mechanism, the method effectively leverages complementary structural information. Specifically, a Spatial Hierarchical Attention Block (SHAB) captures both local details and global dependencies to strengthen semantic representation. Furthermore, to mitigate occlusion in dense scenes, the Deformable Attention-based Intra-scale Feature Interaction (DA-AIFI) focuses on informative regions via dynamic sampling. Finally, the Frequency-Spatial Feature Pyramid Network (FSFPN) integrates frequency filtering with spatial edge extraction via the Cross-domain Frequency-Spatial Block (CFSB) to preserve fine-grained details. Experimental results show that with only 14.7M parameters, FSDETR achieves 13.9% APS on VisDrone 2019 and 48.95% AP50 tiny on TinyPerson, showing strong performance on small-object benchmarks. The code and models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14884
PDF
-
Efficient Search of Implantable Adaptive Cells for Medical Image Segmentation
2026-04-16 10:34:57Emil Benedykciuk, Marcin Denkowski, Grzegorz M. W\'ojcikAbstract
Purpose: Adaptive skip modules can improve medical image segmentation, but searching for them is computationally costly. Implantable Adaptive Cells (IACs) are compact NAS modules inserted into U-Net skip connections, reducing the search space compared with full-network NAS. However, the original IAC framework still requires a 200-epoch differentiable search for each backbone and dataset. Methods: We analyzed the temporal behavior of operations and edges within IAC cells during differentiable search on public medical image segmentation benchmarks. We found that operations selected in the final discrete cell typically emerge among the strongest candidates early in training, and their architecture parameters stabilize well before the final epoch. Based on this, we propose a Jensen--Shannon-divergence-based stability criterion that tracks per-edge operation-importance distributions and progressively prunes low-importance operations during search. The accelerated framework is called IAC-LTH. Results: Across four public benchmarks (ACDC, BraTS, KiTS, AMOS), several 2-D U-Net backbones, and a 2-D nnU-Net pipeline, IAC-LTH discovers IAC cells whose patient-level segmentation performance matches and sometimes slightly exceeds that of cells found by the original full-length search, while reducing wall-clock NAS cost by 3.7x to 16x across datasets and backbones. These results are consistent across architectures, benchmarks, and both non-augmented and augmented training settings, while preserving the gains of IAC-equipped U-Nets over strong attention-based and dense-skip baselines. Conclusion: Competitive IAC architectures can be identified from early-stabilizing operations without running the full search, making adaptive skip-module design more practical for medical image segmentation under realistic computational constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14849
PDF
-
MS-SSE-Net: A Multi-Scale Spatial Squeeze-and-Excitation Network for Structural Damage Detection in Civil and Geotechnical Engineering
2026-04-16 07:21:32Saif ur Rehman Khan, Imad Ahmed Waqar, Arooj Zaib, Saad Ahmed, Sebastian Vollmer, Andreas Dengel, Muhammad Nabeel AsimAbstract
Structural damage detection is essential for maintaining the safety and reliability of civil infrastructure. However, accurately identifying different types of structural damage from images remains challenging due to variations in damage patterns and environmental conditions. To address these challenges, this paper proposes MS-SSE-Net, a novel deep learning (DL) framework for structural damage classification. The proposed model is built upon the DenseNet201 backbone and integrates novel multi-scale feature extraction with channel and spatial attention mechanisms (MS-SSE-Net). Specifically, parallel depthwise convolutions capture both local and contextual features, while squeeze-and-excitation style channel attention and spatial attention emphasize informative regions and suppress irrelevant noise. The refined features are then processed through global average pooling and a fully connected classification layer to generate the final predictions. Experiments are conducted on the StructDamage dataset containing multiple structural damage categories. The proposed MS-SSE-Net demonstrates superior performance compared with the baseline DenseNet201 and other comparative approaches. Specifically, the proposed method achieves 99.31% precision, 99.25% recall, 99.27% F1-score, and 99.26% accuracy, outperforming the baseline model which achieved 98.62% precision, 98.53% recall, 98.58% F1-score, and 98.53% accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14711
PDF
-
Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
2026-04-16 05:47:57Weiwei Zhuang, Wangze Xie, Qi Zhang, Xia Du, Zihan Lin, Zheng Lin, Hanlin Cai, Jizhe Zhou, Zihan Fang, Chi-man Pun, Wei Ni, Jun LuoAbstract
Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods rely on direct pixel-wise perturbations, failing to exploit the inherent atmospheric characteristics of RS imagery or survive real-world image degradations. In this paper, we propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations by iteratively optimizing atmospheric patterns based on Perlin noise. By modeling fog formations with natural, irregular structures, FogFool generates adversarial examples that are not only visually consistent with authentic RS scenes but also deceptive. By leveraging the spatial coherence and mid-to-low-frequency nature of atmospheric phenomena, FogFool embeds adversarial information into structural features shared across diverse architectures. Extensive experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance: not only does it exceed in white-box settings, but also exhibits exceptional black-box transferability (reaching 83.74% TASR) and robustness against common preprocessing-based defenses such as JPEG compression and filtering. Detailed analyses, including confusion matrices and Class Activation Map (CAM) visualizations, reveal that our atmospheric-driven perturbations induce a universal shift in model attention. These results indicate that FogFool represents a practical, stealthy, and highly persistent threat to RS classification systems, providing a robust benchmark for evaluating model reliability in complex environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14643
PDF
-
Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models
2026-04-16 03:47:35Amir El-Ghoussani, Marc H\"olle, Gustavo Carneiro, Vasileios BelagiannisAbstract
We address the problem of prompt-guided image editing in visual autoregressive models. Given a source image and a target text prompt, we aim to modify the source image according to the target prompt, while preserving all regions which are unrelated to the requested edit. To this end, we present Masked Logit Nudging, which uses the source image token maps to introduce a guidance step that aligns the model's predictions under the target prompt with these source token maps. Specifically, we convert the fixed source encodings into logits using the VAR encoding, nudging the model's predicted logits towards the targets along a semantic trajectory defined by the source-target prompts. Edits are applied only within spatial masks obtained through a dedicated masking scheme that leverages cross-attention differences between the source and edited prompts. Then, we introduce a refinement to correct quantization errors and improve reconstruction quality. Our approach achieves the best image editing performance on the PIE benchmark at 512px and 1024px resolutions. Beyond editing, our method delivers faithful reconstructions and outperforms previous methods on COCO at 512px and OpenImages at 1024px. Overall, our method outperforms VAR-related approaches and achieves comparable or even better performance than diffusion models, while being much faster. Code is available at 'this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14591
PDF
-
M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection
2026-04-16 03:06:23Haotian Wu, Yue Cheng, Shan BianAbstract
With the rapid advancement of deep learning in image generation, facial forgery techniques have achieved unprecedented realism, posing serious threats to cybersecurity and information authenticity. Most existing deepfake detection approaches rely on the reconstruction of isolated facial attributes without fully exploiting the complementary nature of multi-modal feature representations. To address these challenges, this paper proposes a novel Multi-Modal 3D Facial Feature Reconstruction Network (M3D-Net) for deepfake detection. Our method leverages an end-to-end dual-stream architecture that reconstructs fine-grained facial geometry and reflectance properties from single-view RGB images via a self-supervised 3D facial reconstruction module. The network further enhances detection performance through a 3D Feature Pre-fusion Module (PFM), which adaptively adjusts multi-scale features, and a Multi-modal Fusion Module (MFM) that effectively integrates RGB and 3D-reconstructed features using attention mechanisms. Extensive experiments on multiple public datasets demonstrate that our approach achieves state-of-the-art performance in terms of detection accuracy and robustness, significantly outperforming existing methods while exhibiting strong generalization across diverse scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14574
PDF
-
Deepfake Detection Generalization with Diffusion Noise
2026-04-16 03:02:04Hongyuan Qi, Wenjin Hou, Hehe Fan, Jun XiaoAbstract
Deepfake detectors face growing challenges in generalization as new image synthesis techniques emerge. In particular, deepfakes generated by diffusion models are highly photorealistic and often evade detectors trained on GAN-based forgeries. This paper addresses the generalization problem in deepfake detection by leveraging diffusion noise characteristics. We propose an Attention-guided Noise Learning (ANL) framework that integrates a pre-trained diffusion model into the deepfake detection pipeline to guide the learning of more robust features. Specifically, our method uses the diffusion model's denoising process to expose subtle artifacts: the detector is trained to predict the noise contained in an input image at a given diffusion step, forcing it to capture discrepancies between real and synthetic images, while an attention-guided mechanism derived from the predicted noise is introduced to encourage the model to focus on globally distributed discrepancies rather than local patterns. By harnessing the frozen diffusion model's learned distribution of natural images, the ANL method acts as a form of regularization, improving the detector's generalization to unseen forgery types. Extensive experiments demonstrate that ANL significantly outperforms existing methods on multiple benchmarks, achieving state-of-the-art accuracy in detecting diffusion-generated deepfakes. Notably, the proposed framework boosts generalization performance (e.g., improving ACC/AP by a substantial margin on unseen models) without introducing additional overhead during inference. Our results highlight that diffusion noise provides a powerful signal for generalizable deepfake detection.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14570
PDF
-
Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs
2026-04-16 01:21:14Ziyang Luo, Nian Liu, Junwei HanAbstract
Omni-modal Large Language Models (Omni-MLLMs) promise a unified integration of diverse sensory streams. However, recent evaluations reveal a critical performance paradox: unimodal baselines frequently outperform joint multimodal inference. We trace this perceptual fragility to the static fusion topologies universally employed by current models, identifying two structural pathologies: positional bias in sequential inputs and alignment traps in interleaved formats, which systematically distort attention regardless of task semantics. To resolve this functional rigidity, we propose Chain of Modality (CoM), an agentic framework that transitions multimodal fusion from passive concatenation to dynamic orchestration. CoM adaptively orchestrates input topologies, switching among parallel, sequential, and interleaved pathways to neutralize structural biases. Furthermore, CoM bifurcates cognitive execution into two task-aligned pathways: a streamlined ``Direct-Decide'' path for direct perception and a structured ``Reason-Decide'' path for analytical auditing. Operating in either a training-free or a data-efficient SFT setting, CoM achieves robust and consistent generalization across diverse benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14520
PDF
-
H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection
2026-04-16 00:47:45Jianghong Huang, Luping Ji, Weiwei Duan, Mao YeAbstract
As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is attracting increasing attention. In recent years, beyond traditional visual paradigm, Vision-Language Model (VLM) has been extensively explored to boost this field. However, in currently-existing VLM-based FSAD schemes, almost all perform anomaly inference only by pairwise feature matching, ignoring structural dependencies and global consistency. To further redound to FSAD via VLM, we propose a Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR) framework. It reformulates the FSAD as a high-order inference problem of visual-semantic relations, by jointly modeling visual regions and semantic concepts in a unified hypergraph. Experimental comparisons verify the effectiveness and advantages of H2VLR. It could often achieve state-of-the-art (SOTA) performance on representative industrial and medical benchmarks. Our code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14507
PDF
-
Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images
2026-04-16 00:43:39Jue Jiang, Aneesh Rangnekar, Harini VeeraraghavanAbstract
Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images due to the contextual similarity of neighboring patches, leading to information leakage and SSL simplification. Hierarchical shifted window (Swin) transformer, a highly effective approach for medical images cannot use advanced masking methods as it lacks a global [CLS] token. Hence, we introduced an attention guided masking mechanism for Swin within a co-distillation learning framework to selectively mask semantically co-occurring and discriminative patches, to reduce information leakage and increase the difficulty of SSL pretraining. However, attention guided masking inevitably reduces the diversity of attention heads, which negatively impacts downstream task performance. To address this, we for the first time, integrate a noisy teacher into the co-distillation framework (termed DAGMaN) that performs attentive masking while preserving high attention head diversity. We demonstrate the capability of DAGMaN on multiple tasks including full- and few-shot lung nodule classification, immunotherapy outcome prediction, tumor segmentation, and unsupervised organs clustering.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14506
PDF
-
SatBLIP: Context Understanding and Feature Identification from Satellite Imagery with Vision-Language Learning
2026-04-15 19:43:20Xue Wu, Shengting Cao, Jiaqi GongAbstract
Rural environmental risks are shaped by place-based conditions (e.g., housing quality, road access, land-surface patterns), yet standard vulnerability indices are coarse and provide limited insight into risk contexts. We propose SatBLIP, a satellite-specific vision-language framework for rural context understanding and feature identification that predicts county-level Social Vulnerability Index (SVI). SatBLIP addresses limitations of prior remote sensing pipelines-handcrafted features, manual virtual audits, and natural-image-trained VLMs-by coupling contrastive image-text alignment with bootstrapped captioning tailored to satellite semantics. We use GPT-4o to generate structured descriptions of satellite tiles (roof type/condition, house size, yard attributes, greenery, and road context), then fine-tune a satellite-adapted BLIP model to generate captions for unseen images. Captions are encoded with CLIP and fused with LLM-derived embeddings via attention for SVI estimation under spatial aggregation. Using SHAP, we identify salient attributes (e.g., roof form/condition, street width, vegetation, cars/open space) that consistently drive robust predictions, enabling interpretable mapping of rural risk environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14373
PDF
-
Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
2026-04-15 18:00:45Ahmed Bourouis, Savas Ozkan, Andrea Maracani, Yi-Zhe Song, Mete OzayAbstract
We tackle a new problem: generating geometrically consistent multi-view scenes from a single freehand sketch. Freehand sketches are the most geometrically impoverished input one could offer a multi-view generator. They convey scene intent through abstract strokes while introducing spatial distortions that actively conflict with any consistent 3D interpretation. No prior method attempts this; existing multi-view approaches require photographs or text, while sketch-to-3D methods need multiple views or costly per-scene optimisation. We address three compounding challenges; absent training data, the need for geometric reasoning from distorted 2D input, and cross-view consistency, through three mutually reinforcing contributions: (i) a curated dataset of $\sim$9k sketch-to-multiview samples, constructed via an automated generation and filtering pipeline; (ii) Parallel Camera-Aware Attention Adapters (CA3) that inject geometric inductive biases into the video transformer; and (iii) a Sparse Correspondence Supervision Loss (CSL) derived from Structure-from-Motion reconstructions. Our framework synthesizes all views in a single denoising process without requiring reference images, iterative refinement, or per-scene optimization. Our approach significantly outperforms state-of-the-art two-stage baselines, improving realism (FID) by over 60% and geometric consistency (Corr-Acc) by 23%, while providing up to a 3.7$\times$ inference speedup.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14302
PDF
-
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
2026-04-15 17:59:52Zheyu Zhang, Ziqi Pang, Shixing Chen, Xiang Hao, Vimal Bhat, Yu-Xiong WangAbstract
Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames sparsely and lose temporal information. To address this, we explore extreme video token compression towards \emph{one token per frame} at the final LLM layer. Our key insight is that heuristic-based compression, widely adopted by previous methods, is prone to information loss, and this necessitates supervising LLM layers into \emph{learnable} and \emph{progressive} modules for \emph{token-level compression} (LP-Comp). Such compression enables our VLM to digest 2x-4x more frames with improved performance. To further increase the token efficiency, we investigate \emph{frame-level compression}, which selects the frames most relevant to the queries via the internal attention scores of the LLM layers, named \emph{question-conditioned compression} (QC-Comp). As a notable distinction from previous studies, we mitigate the position bias of LLM attention in long contexts, \emph{i.e.}, the over-concentration on the beginning and end of a sequence, by splitting long videos into short segments and employing local attention. Collectively, our combined \emph{token-level} and \emph{frame-level} leads to an e\textbf{x}treme compression model for long video understanding, named \textbf{\name}, achieving a significantly larger compression ratio and enabling denser frame sampling. Our \name is finetuned from VideoChat-Flash with a data-efficient \emph{supervised compression tuning} stage that only requires 2.5\% of the supervised fine-tuning data, yet boosts the accuracy from 42.9\% to 46.2\% on LVBench and enhances multiple other long video benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14149
PDF
-
Geometric Context Transformer for Streaming 3D Reconstruction
2026-04-15 17:58:13Lin-Zhuo Chen, Jian Gao, Yihang Chen, Ka Leong Cheng, Yipengjing Sun, Liangxiao Hu, Nan Xue, Xing Zhu, Yujun Shen, Yao Yao, Yinghao XuAbstract
Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles of Simultaneous Localization and Mapping (SLAM), we introduce LingBot-Map, a feed-forward 3D foundation model for reconstructing scenes from streaming data, built upon a geometric context transformer (GCT) architecture. A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory to address coordinate grounding, dense geometric cues, and long-range drift correction, respectively. This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs over long sequences exceeding 10,000 frames. Extensive evaluations across a variety of benchmarks demonstrate that our approach achieves superior performance compared to both existing streaming and iterative optimization-based approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14141
PDF
-
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
2026-04-15 17:50:07Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, Ping LuoAbstract
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14125
PDF
