While vision language models (VLMs) excel in 2D semantic visual understanding, their ability to quantitatively reason about 3D spatial relationships remains under-explored, due to the deficiency of 2D images' spatial representation ability. In this paper, we analyze the problem hindering VLMs' spatial understanding abilities and propose SD-VLM, a novel framework that significantly enhances fundamental spatial perception abilities of VLMs through two key contributions: (1) propose Massive Spatial Measuring and Understanding (MSMU) dataset with precise spatial annotations, and (2) introduce a simple depth positional encoding method strengthening VLMs' spatial awareness. MSMU dataset covers massive quantitative spatial tasks with 700K QA pairs, 2.5M physical numerical annotations, and 10K chain-of-thought augmented samples. We have trained SD-VLM, a strong generalist VLM which shows superior quantitative spatial measuring and understanding capability. SD-VLM not only achieves state-of-the-art performance on our proposed MSMU-Bench, but also shows spatial generalization abilities on other spatial understanding benchmarks including Q-Spatial and SpatialRGPT-Bench. Extensive experiments demonstrate that SD-VLM outperforms GPT-4o and Intern-VL3-78B by 26.91% and 25.56% respectively on MSMU-Bench. Code and models are released at https://github.com/cpystan/SD-VLM.

This work introduces TraceHiding, a scalable, importance-aware machine unlearning framework for mobility trajectory data. Motivated by privacy regulations such as GDPR and CCPA granting users "the right to be forgotten," TraceHiding removes specified user trajectories from trained deep models without full retraining. It combines a hierarchical data-driven importance scoring scheme with teacher-student distillation. Importance scores--computed at token, trajectory, and user levels from statistical properties (coverage diversity, entropy, length)--quantify each training sample's impact, enabling targeted forgetting of high-impact data while preserving common patterns. The student model retains knowledge on remaining data and unlearns targeted trajectories through an importance-weighted loss that amplifies forgetting signals for unique samples and attenuates them for frequent ones. We validate on Trajectory--User Linking (TUL) tasks across three real-world higher-order mobility datasets (HO-Rome, HO-Geolife, HO-NYC) and multiple architectures (GRU, LSTM, BERT, ModernBERT, GCN-TULHOR), against strong unlearning baselines including SCRUB, NegGrad, NegGrad+, Bad-T, and Finetuning. Experiments under uniform and targeted user deletion show TraceHiding, especially its entropy-based variant, achieves superior unlearning accuracy, competitive membership inference attack (MIA) resilience, and up to 40\times speedup over retraining with minimal test accuracy loss. Results highlight robustness to adversarial deletion of high-information users and consistent performance across models. To our knowledge, this is the first systematic study of machine unlearning for trajectory data, providing a reproducible pipeline with public code and preprocessing tools.

Low-cost mobile sensors can be used to collect PM$_{2.5}$ concentration data throughout an entire city. However, identifying air pollution hotspots from the data is challenging due to the uneven spatial sampling, temporal variations in the background air quality, and the dynamism of urban air pollution sources. This study proposes a method to identify urban PM$_{2.5}$ hotspots that addresses these challenges, involving four steps: (1) equip citizen scientists with mobile PM$_{2.5}$ sensors while they travel; (2) normalise the raw data to remove the influence of background ambient pollution levels; (3) fit a Gaussian process regression model to the normalised data and (4) calculate a grid of spatially explicit 'hotspot scores' using the probabilistic framework of Gaussian processes, which conveniently summarise the relative pollution levels throughout the city. We apply our method to create the first ever map of PM$_{2.5}$ pollution in Kigali, Rwanda, at a 200m resolution. Our results suggest that the level of ambient PM$_{2.5}$ pollution in Kigali is dangerously high, and we identify the hotspots in Kigali where pollution consistently exceeds the city-wide average. We also evaluate our method using simulated mobile sensing data for Beijing, China, where we find that the hotspot scores are probabilistically well calibrated and accurately reflect the 'ground truth' spatial profile of PM$_{2.5}$ pollution. Thanks to the use of open-source software, our method can be re-applied in cities throughout the world with a handful of low-cost sensors. The method can help fill the gap in urban air quality information and empower public health officials.

Enabling agents to understand and interact with complex 3D scenes is a fundamental challenge for embodied artificial intelligence systems. While Multimodal Large Language Models (MLLMs) have achieved significant progress in 2D image understanding, extending such capabilities to 3D scenes remains difficult: 1) 3D environment involves richer concepts such as spatial relationships, affordances, physics, layout, and so on, 2) the absence of large-scale 3D vision-language datasets has posed a significant obstacle. In this paper, we introduce Text-Scene, a framework that automatically parses 3D scenes into textual descriptions for scene understanding. Given a 3D scene, our model identifies object attributes and spatial relationships, and then generates a coherent summary of the whole scene, bridging the gap between 3D observation and language without requiring human-in-the-loop intervention. By leveraging both geometric analysis and MLLMs, Text-Scene produces descriptions that are accurate, detailed, and human-interpretable, capturing object-level details and global-level context. Experimental results on benchmarks demonstrate that our textual parses can faithfully represent 3D scenes and benefit downstream tasks. To evaluate the reasoning capability of MLLMs, we present InPlan3D, a comprehensive benchmark for 3D task planning, consisting of 3174 long-term planning tasks across 636 indoor scenes. We emphasize clarity and accessibility in our approach, aiming to make 3D scene content understandable through language. Code and datasets will be released.

3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they remain constrained by insufficient multi-view spatial interaction and limited multi-frame temporal consistency. To overcome these issues, in this paper, we propose a novel Spatial-Temporal Gaussian Splatting (ST-GS) framework to enhance both spatial and temporal modeling in existing Gaussian-based pipelines. Specifically, we develop a guidance-informed spatial aggregation strategy within a dual-mode attention mechanism to strengthen spatial interaction in Gaussian representations. Furthermore, we introduce a geometry-aware temporal fusion scheme that effectively leverages historical context to improve temporal continuity in scene completion. Extensive experiments on the large-scale nuScenes occupancy prediction benchmark showcase that our proposed approach not only achieves state-of-the-art performance but also delivers markedly better temporal consistency compared to existing Gaussian-based methods.

Recently,vision-based robotic manipulation has garnered significant attention and witnessed substantial advancements. 2D image-based and 3D point cloud-based policy learning represent two predominant paradigms in the field, with recent studies showing that the latter consistently outperforms the former in terms of both policy performance and generalization, thereby underscoring the value and significance of 3D information. However, 3D point cloud-based approaches face the significant challenge of high data acquisition costs, limiting their scalability and real-world deployment. To address this issue, we propose a novel framework NoReal3D: which introduces the 3DStructureFormer, a learnable 3D perception module capable of transforming monocular images into geometrically meaningful pseudo-point cloud features, effectively fused with the 2D encoder output features. Specially, the generated pseudo-point clouds retain geometric and topological structures so we design a pseudo-point cloud encoder to preserve these properties, making it well-suited for our framework. We also investigate the effectiveness of different feature fusion strategies.Our framework enhances the robot's understanding of 3D spatial structures while completely eliminating the substantial costs associated with 3D point cloud acquisition.Extensive experiments across various tasks validate that our framework can achieve performance comparable to 3D point cloud-based methods, without the actual point cloud data.

Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-world deployment. While foundation models, particularly Vision-Language Models (VLMs), offer powerful semantic understanding, effectively adapting their web-scale knowledge for embodied decision-making remains a key challenge. We present FiLM-Nav (Fine-tuned Language Model for Navigation), an approach that directly fine-tunes pre-trained VLM as the navigation policy. In contrast to methods that use foundation models primarily in a zero-shot manner or for map annotation, FiLM-Nav learns to select the next best exploration frontier by conditioning directly on raw visual trajectory history and the navigation goal. Leveraging targeted simulated embodied experience allows the VLM to ground its powerful pre-trained representations in the specific dynamics and visual patterns relevant to goal-driven navigation. Critically, fine-tuning on a diverse data mixture combining ObjectNav, OVON, ImageNav, and an auxiliary spatial reasoning task proves essential for achieving robustness and broad generalization. FiLM-Nav sets a new state-of-the-art in both SPL and success rate on HM3D ObjectNav among open-vocabulary methods, and sets a state-of-the-art SPL on the challenging HM3D-OVON benchmark, demonstrating strong generalization to unseen object categories. Our work validates that directly fine-tuning VLMs on diverse simulated embodied data is a highly effective pathway towards generalizable and efficient semantic navigation capabilities.

We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities like depth or point clouds to improve spatial reasoning, purely visualspatial understanding remains underexplored. SEE&TREK addresses this gap by focusing on two core principles: increasing visual diversity and motion reconstruction. For visual diversity, we conduct Maximum Semantic Richness Sampling, which employs an off-the-shell perception model to extract semantically rich keyframes that capture scene structure. For motion reconstruction, we simulate visual trajectories and encode relative spatial positions into keyframes to preserve both spatial relations and temporal coherence. Our method is training&GPU-free, requiring only a single forward pass, and can be seamlessly integrated into existing MLLM'S. Extensive experiments on the VSI-B ENCH and STI-B ENCH show that S EE &T REK consistently boosts various MLLM S performance across diverse spatial reasoning tasks with the most +3.5% improvement, offering a promising path toward stronger spatial intelligence.

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D geometry-aware robotic manipulation policy that leverages multi-view input. GP3 employs a spatial encoder to infer dense spatial features from RGB observations, which enable the estimation of depth and camera parameters, leading to a compact yet expressive 3D scene representation tailored for manipulation. This representation is fused with language instructions and translated into continuous actions via a lightweight policy head. Comprehensive experiments demonstrate that GP3 consistently outperforms state-of-the-art methods on simulated benchmarks. Furthermore, GP3 transfers effectively to real-world robots without depth sensors or pre-mapped environments, requiring only minimal fine-tuning. These results highlight GP3 as a practical, sensor-agnostic solution for geometry-aware robotic manipulation.

Recent advances in vision-language models (VLMs) have enabled powerful multimodal reasoning, but state-of-the-art approaches typically rely on extremely large models with prohibitive computational and memory requirements. This makes their deployment challenging in resource-constrained environments such as warehouses, robotics, and industrial applications, where both efficiency and robust spatial understanding are critical. In this work, we present SmolRGPT, a compact vision-language architecture that explicitly incorporates region-level spatial reasoning by integrating both RGB and depth cues. Smol-RGPT employs a three-stage curriculum that progressively align visual and language features, enables spatial relationship understanding, and adapts to task-specific datasets. W e demonstrate that with only 600M parameters, SmolRGPT achieves competitive results on challenging warehouse spatial reasoning benchmarks, matching or exceeding the performance of much larger alternatives.