Searching for objects in unfamiliar scenarios is a challenging task for blind people. It involves specifying the target object, detecting it, and then gathering detailed information according to the user's intent. However, existing description- and detection-based assistive technologies do not sufficiently support the multifaceted nature of interactive object search tasks. We present ObjectFinder, an open-vocabulary wearable assistive system for interactive object search by blind people. ObjectFinder allows users to query target objects using flexible wording. Once the target object is detected, it provides egocentric localization information in real-time, including distance and direction. Users can then initiate different branches to gather detailed information based on their intent towards the target object, such as navigating to it or perceiving its surroundings. ObjectFinder is powered by a seamless combination of open-vocabulary models, namely an open-vocabulary object detector and a multimodal large language model. The ObjectFinder design concept and its development were carried out in collaboration with a blind co-designer. To evaluate ObjectFinder, we conducted an exploratory user study with eight blind participants. We compared ObjectFinder to BeMyAI and Google Lookout, popular description- and detection-based assistive applications. Our findings indicate that most participants felt more independent with ObjectFinder and preferred it for object search, as it enhanced scene context gathering and navigation, and allowed for active target identification. Finally, we discuss the implications for future assistive systems to support interactive object search.

Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M6Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches.

Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract patch-level features that are robust to viewpoint, illumination, and seasonal variations, which are then aggregated into a compact global descriptor for retrieval. Most existing aggregation methods uniformly pool patch tokens into learned clusters, despite the fact that different clusters often encode distinct spatial or semantic patterns and contribute unequally to VPR performance. To address this limitation, we propose Weighted Aggregated Descriptor (WeiAD), which assigns weights to clusters during aggregation, producing more discriminative global representations. Beyond accuracy, retrieval latency is a critical concern for large-scale deployments and resource-constrained edge devices. Prior work mainly reduces latency by compressing global descriptors, while overlooking the cost of feature extraction, an issue exacerbated by ViT-based backbones. We therefore introduce WeiToP, a VPR-oriented token pruning framework that reduces feature extraction cost via self-distillation, where aggregation-induced token importance supervises a lightweight pruning module attached to an early transformer layer, enabling inference-time token pruning. After a single joint training phase, WeiToP enables plug-and-play token pruning at inference time, allowing flexible and on-demand control over the accuracy-efficiency trade-off without additional training. Moreover, WeiToP outperforms existing token pruning methods adapted from general vision tasks.

Guide dogs offer independence to Blind and Low-Vision (BLV) individuals, yet their limited availability leaves the vast majority of BLV users without access. Quadruped robotic guide dogs present a promising alternative, but existing systems rely solely on the robot's ground-level sensors for navigation, overlooking a critical class of hazards: obstacles that are transparent to the robot yet dangerous at human body height, such as bent branches. We term this the viewpoint asymmetry problem and present the first system to explicitly address it. Our Co-Ego system adopts a dual-branch obstacle avoidance framework that integrates the robot-centric ground sensing with the user's elevated egocentric perspective to ensure comprehensive navigation safety. Deployed on a quadruped robot, the system is evaluated in a controlled user study with sighted participants under blindfold across three conditions: unassisted, single-view, and cross-view fusion. Results demonstrate that cross-view fusion significantly reduces collision times and cognitive load, verifying the necessity of viewpoint complementarity for safe robotic guide dog navigation.

3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitively understandable to humans. Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs). However, such pipelines require multi-modal data that may not always be available, and their reliance on heuristic graph construction can constrain the prediction of relationship triplets. In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model), a training-free framework that leverages multi-modal large language models (MLLMs) with retrieval-augmented generation (RAG) for semantic scene graph generation. SGR3 Model bypasses the need for explicit 3D reconstruction. Instead, it enhances relational reasoning by incorporating semantically aligned scene graphs retrieved via a ColPali-style cross-modal framework. To improve retrieval robustness, we further introduce a weighted patch-level similarity selection mechanism that mitigates the negative impact of blurry or semantically uninformative regions. Experiments demonstrate that SGR3 Model achieves competitive performance compared to training-free baselines and on par with GNN-based expert models. Moreover, an ablation study on the retrieval module and knowledge base scale reveals that retrieved external information is explicitly integrated into the token generation process, rather than being implicitly internalized through abstraction.

Fusing sensors with complementary modalities is crucial for maintaining a stable and comprehensive understanding of abnormal driving scenes. However, Multimodal Large Language Models (MLLMs) are underexplored for leveraging multi-sensor information to understand adverse driving scenarios in autonomous vehicles. To address this gap, we propose the DriveXQA, a multimodal dataset for autonomous driving VQA. In addition to four visual modalities, five sensor failure cases, and five weather conditions, it includes 102,505 QA pairs categorized into three types: global scene level, allocentric level, and ego-vehicle centric level. Since no existing MLLM framework adopts multiple complementary visual modalities as input, we design MVX-LLM, a token-efficient architecture with a Dual Cross-Attention (DCA) projector that fuses the modalities to alleviate information redundancy. Experiments demonstrate that our DCA achieves improved performance under challenging conditions such as foggy (GPTScore: 53.5 vs. 25.1 for the baseline). The established dataset and source code will be made publicly available.

Bird's-Eye-View (BEV) perception, crucial for holistic scene understanding, faces limitations with narrow field-of-view sensors (indoors) and complex multi-camera setups (outdoors). To address these limitations and enable omni-range perception with a single image, we propose a new pipeline called panoramic-to-BEV semantic mapping. We extend existing household-related and driving-scene datasets to create four benchmarks for Panoramic BEV in both indoor and outdoor settings. As ground-breaking solutions, the 360BEV (indoor) and OneBEV (outdoor) methods have shown promise in their respective domains. Moreover, we propose a new framework OneBEV++, generating BEV semantic maps from a single panoramic image across indoor and outdoor environments. Extensive experiments on our four panoramic datasets demonstrate that OneBEV++ outperforms previous methods with consistent accuracy gains and improved efficiency. By simplifying complexity while enhancing performance, OneBEV++ enables scalable applications across diverse environments from outdoor autonomous vehicles to indoor robots, paving the way for more holistic cross-environment autonomous systems.

Assistive agents for Blind and Visually Impaired (BVI) users require accessibility alignment as a first-class design objective. Despite rapid progress in agentic AI, most systems are designed and evaluated under assumptions of sighted interaction, low-cost verification, and tolerable trial-and-error, leading to systematic failures in assistive scenarios that cannot be resolved by model scaling or post-hoc interface adaptations alone. Drawing on an analysis of 778 assistance task instances from prior work, we show that current agentic AI remain prone to failure in assistive scenarios due to mismatches between sighted-user design assumptions and the verification, risk, and interaction constraints faced by BVI users. We argue that accessibility should be treated as an alignment problem rather than a peripheral usability concern. To this end, we introduce accessibility alignment and propose a lifecycle-oriented design pipeline for accessibility-aligned assistive agents, spanning user research, system design, deployment and post-deployment iteration. We conclude that BVI-centered assistive tasks provide a critical stress test for agentic AI and motivate a broader shift toward inclusive agent design.

Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions. As a result, mistakes in spatiotemporal perception are only observed in the final caption, making it difficult to identify the underlying perceptual errors directly. To address these issues, we present PercepCap, a perception-aware video captioning framework that makes perceptual evidence explicit before producing the final caption. Specifically, PercepCap follows a perceive-describe generation chain, where the model first produces a spatiotemporal perception trace comprising object trajectories and temporal events, and then generates the final caption conditioned on the perceived evidence. To support this, we design a two-stage training strategy. Perceive-then-Describe Supervised Fine-tuning adapts the model from caption-only generation to the proposed perceive-describe chain, while Perception-Grounded Reinforcement Learning optimizes perception trace and caption quality with joint rewards over perception chain and the final caption. To support our two-stage training, we introduce Caption-Anchored Perception Data Construction. This pipeline builds the SFT and RL training data by first generating a caption-only description, extracting the objects and events it mentions, and grounding them back in the video with boxes and timestamps. This yields caption-aligned perception data that provides solid training ground truth, ensuring that the explicit perception trace and final caption refer to the same objects and events. Across direct caption and caption-to-QA evaluation, PercepCap consistently improves upon the Qwen3-VL baseline and demonstrates leading caption quality.

Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length inputs and post-hoc refinement, hindering online-oriented localization under partial or dynamic observations. In this work, we formulate Progressive Cross-view Video Geo-localization (PCVG) as a deployment-oriented extension and evaluation protocol of CVG, enabling localization under varying temporal budgets, prefix-based inference, random-start evaluation, and long-range localization with interruptions. To explore PCVG, we introduce X^2Localizer, a cross-grained alignment framework that jointly supervises global prefix-to-aerial retrieval and token-aggregated frame–aerial-tile matching with a budget-dependent asymmetric objective. Furthermore, we introduce a Sliding-Window Re-Localization (SWRL) strategy that dynamically refreshes candidate regions for failure recovery and long-range deployment without full-sequence reprocessing. Extensive experiments show that X^2Localizer preserves conventional full-video performance, with marginal gains of +0.1 Recall@1 and +0.3 Recall@10, while substantially improving early localization. In the challenging single-frame setting, X^2Localizer improves coarse retrieval by +4.7 Recall@1 and +11.5 Recall@10 over the previous state-of-the-art method. With SWRL, our approach further enables robust progressive localization under random-start and long-distance scenarios, narrowing the gap between benchmark evaluation and real-world deployment.

Most existing vision-language models (VLMs) are tailored for pinhole imagery, stitching multiple narrow field-of-view inputs to piece together a complete omni-scene understanding. Yet, such multi-view perception overlooks the holistic spatial and contextual relationships that a single panorama inherently preserves. In this work, we propose that panoramic vision-language understanding is more than the sum of its pinhole counterparts. We introduce Panorama-Language Modeling (PLM), a unified 360° visual-language reasoning. Besides, we present PanoVQA, a large-scale panoramic VQA dataset that integrates diverse and adverse omni-scenes, enabling comprehensive reasoning under occlusion, accidents, and challenging conditions. To establish a foundation for PLM, we develop a plug-and-play panoramic adaptation module that allows existing pinhole-based VLMs to process equirectangular panoramas without retraining. Extensive experiments demonstrate that our PLM achieves superior robustness and holistic reasoning under adverse omni-scenes, revealing that a full panorama yields understanding greater than the sum of its parts. All datasets and code will be publicly released.

Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes such as rural roads. To study this failure mode, in this work, we introduce CV-FSS, a benchmark that pairs sequential panoramas from five rural regions with aligned OSM maps, on which single-frame methods degrade drastically. We then propose SeqLoc, an online test-time sequence aggregation mechanism that recursively maintains a log-belief volume with three key components: (1) Entropy-Tempered Uncertainty (ETU) tempers each incoming pose likelihood volume by its normalized entropy; (2) Map-Guided Relocalization (MGR) mixes a map-shaped recovery distribution into the belief so that a suppressed true pose can recover; (3) Peak-Anchored Smoothing (PAS) derives the final pose at sub-grid precision. Extensive experiments on CV-FSS and CV-RHO demonstrate that SeqLoc outperforms single-frame localization by a large margin, improving both position and orientation recall by over 50

Situated reasoning often relies on active exploration, yet in many real-world scenarios such exploration is infeasible due to physical constraints of robots or safety concerns of visually impaired users. Given only a limited observation, can an agent mentally simulate a future trajectory toward a target situation and answer spatial what-if questions? We introduce WanderDream, the first large-scale dataset designed for the emulative simulation of mental exploration, enabling models to reason without active exploration. WanderDream-Gen comprises 15.8K panoramic videos across 1,088 real scenes from HM3D, ScanNet++, and real-world captures, depicting imagined trajectories from current viewpoints to target situations. WanderDream-QA contains 158K question-answer pairs, covering starting states, paths, and end states along each trajectory to comprehensively evaluate exploration-based reasoning. Extensive experiments with world models and MLLMs demonstrate (1) that mental exploration is essential for situated reasoning, (2) that world models achieve compelling performance on WanderDream-Gen, (3) that imagination substantially facilitates reasoning on WanderDream-QA, and (4) that WanderDream data exhibit remarkable transferability to real-world scenarios. The source code and all data will be released.

Charts play a critical role in data analysis and visualization, yet real-world applications often present charts with challenging or noisy features. However, "outlier charts" pose a substantial challenge even for Multimodal Large Language Models (MLLMs), which can struggle to interpret perturbed charts. In this work, we introduce CHAOS (CHart Analysis with Outlier Samples), a robustness benchmark to systematically evaluate MLLMs against chart perturbations. CHAOS encompasses five types of textual and ten types of visual perturbations, each presented at three levels of severity (easy, mid, hard) inspired by the study result of human evaluation. The benchmark includes 13 state-of-the-art MLLMs divided into three groups (i.e., general-, document-, and chart-specific models) according to the training scope and data. Comprehensive analysis involves two downstream tasks (ChartQA and Chart-to-Text). Extensive experiments and case studies highlight critical insights into robustness of models across chart perturbations, aiming to guide future research in chart understanding domain. Data and code are publicly available at: http://huggingface.co/datasets/omoured/CHAOS.

Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole and satellite images, we study robust MCVGL using holistic panoramas and OpenStreetMap (OSM). To this end, we establish a large-scale MCVGL benchmark dataset, CV-RHO, with over 2.7M images under different weather and lighting conditions, as well as sensor noise. Furthermore, we propose a model termed RHO with a two-branch Pin-Pan architecture for accurate visual localization. A Split-Undistort-Merge (SUM) module is introduced to address the panoramic distortion, and a Position-Orientation Fusion (POF) mechanism is designed to enhance the localization accuracy. Extensive experiments prove the value of our CV-RHO dataset and the effectiveness of the RHO model, with a significant performance gain up to 20% compared with the state-of-the-art baselines. The dataset, model, and code will be made publicly available.

Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocentric and exocentric videos. EgoExoMem contains $2.6K$ high-quality MCQs across eight temporal, spatial, and cross-view QA types. To support dual-view retrieval, we propose E$^2$-Select, a training-free frame selection method for synchronized ego-exo videos. It combines relevance-based budget allocation with per-view k-DPP sampling to handle view asymmetry and cross-view temporal consistency. Experiments show that ego and exo views provide complementary memory cues, while existing MLLMs remain far from solving the benchmark: the best model reaches only $55.3\%$. E$^2$-Select achieves state-of-the-art performance of $58.2\%$ over frame-selection and RAG-based memory baselines. Further analysis reveals systematic view-preference conflicts between question framing and answer grounding, underscoring the novelty and challenge of cross-view memory reasoning.

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories with small sample sizes, which are difficult to handle by existing networks. In this regard, we propose a point cloud segmentation network that fuses local attention based on density perception with global attention. The core idea is to increase the effective receptive field of each point while reducing the loss of information about small objects in dense areas. Specifically, we divide different sized windows for local areas with different densities to compute attention within the window. Furthermore, we consider each local area as an independent token for the global attention of the entire input. A category-response loss is also proposed to balance the processing of different categories and sizes of objects. In particular, we set up an additional fully connected layer in the middle of the network for prediction of the presence of object categories, and construct a binary cross-entropy loss to respond to the presence of categories in the scene. In experiments, our method achieves competitive results in semantic segmentation and part segmentation tasks on several publicly available datasets. Experiments on point cloud data obtained from complex real-world scenes filled with tiny objects also validate the strong segmentation capability of our method for small objects as well as small sample categories.

Panoramic perception holds significant potential for autonomous driving, enabling vehicles to acquire a comprehensive 360° surround view in a single shot. However, autonomous driving is a data-driven task. Complete panoramic data acquisition requires complex sampling systems and annotation pipelines, which are time-consuming and labor-intensive. Although existing street view generation models have demonstrated strong data regeneration capabilities, they can only learn from the fixed data distribution of existing datasets and cannot achieve high-quality, controllable panoramic generation. In this paper, we propose the first panoramic generation method, Percep360, for autonomous driving. Percep360 enables coherent generation of panoramic data with control signals based on the stitched panoramic data. Percep360 focuses on two key aspects: coherence and controllability. Specifically, to overcome the inherent information loss caused by the pinhole sampling process, we propose the Local Scenes Diffusion Method (LSDM). LSDM reformulates the panorama generation as a spatially continuous diffusion process, bridging the gaps between different data distributions. Additionally, to achieve the controllable generation of panoramic images, we propose a Probabilistic Prompting Method (PPM). PPM dynamically selects the most relevant control cues, enabling controllable panoramic image generation. We evaluate the effectiveness of the generated images from three perspectives: image quality assessment (i.e.,no-reference and with reference), controllability, and their utility in real-world Bird’s Eye View (BEV) segmentation. Notably, the generated data consistently outperforms the original stitched images in no-reference quality metrics and enhances downstream perception models, leading to an improvement of 2.5% in mIoU for panoramic BEV segmentation. The source code will be publicly available.

Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understanding. However, its application to visualizations such as charts remains under-explored due to the inherent complexity of interleaved visual-numerical relationships in chart images. Existing chart understanding methods primarily focus on answering questions without explicitly identifying the visual elements that support their predictions. To bridge this gap, we introduce RefChartQA, a novel benchmark that integrates Chart Question Answering (ChartQA) with visual grounding, enabling models to refer elements at multiple granularities within chart images. Furthermore, we conduct a comprehensive evaluation by instruction-tuning 6 state-of-the-art VLMs across different categories. Our experiments demonstrate that incorporating spatial awareness via grounding improves response accuracy by over 15 https://github.com/moured/RefChartQA .

Accurately identifying and refining building contours in high-resolution remote sensing images remains a significant technical challenge. Despite the advancements brought by deep learning techniques, particularly convolutional neural networks, issues such as tree occlusion, shading, and spectral heterogeneity hinder the accuracy of building extraction. To address these limitations, this study proposes an adaptive cluster segmentation algorithm to optimize semantic segmentation results and enhance building extraction. By leveraging advanced image matrix operations and unified color space analysis, the algorithm effectively removes abnormal regions and standardizes building contours using corner detection and geometric-mathematical principles. Compared to existing methods, this approach significantly improves contour extraction accuracy, aligning more closely with real-world segmentation requirements. Moreover, integrating this algorithm with deep learning models enhances boundary precision, providing a robust solution for high-resolution image processing.