Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understanding. Existing spatio-temporal methods primarily focus on the video itself, while overlooking the physical information within the video, such as multi-object layouts and motion. Such limitations restrict the use of MLLMs in downstream applications that demand high precision, including embodied intelligence and VR. To address this issue, we present Video-STR, a novel graph-based reinforcement method for precise Video Spatio-Temporal Reasoning. Building upon the capacity of Reinforcement Learning with V erifi-able Reward (RL VR) to improve model abilities, we introduce a reasoning mechanism using graph-based Group Relative Policy Optimization (GRPO) method to guide the model in inferring the underlying spatio-temporal topology of scenarios during the thinking process. To resolve the lack of spatio-temporal training data, we construct the STV-205k dataset with 205k question-answering pairs, covering dynamic multi-object scenes in both indoor and outdoor environments, to support the model training. Experiments show that Video-STR achieves state-of-the-art results on various benchmarks, outperforming the base model by 13% on STI-Bench, and demonstrating the effectiveness of our approach and dataset. Code, model, and data will be released.

General-purpose spatial representations are essential for building transferable geospatial foundation models (GFMs). Among them, the AlphaEarth Foundation (AE) represents a major step toward a global, unified representation of the Earth's surface, learning 10-meter embeddings from multi-source Earth Observation (EO) data that capture rich physical and environmental patterns across diverse landscapes. However, such EO-driven representations remain limited in capturing the functional and socioeconomic dimensions of cities, as they primarily encode physical and spectral patterns rather than human activities or spatial functions. We propose AETHER (AlphaEarth-POI Enriched Representation Learning), a lightweight framework that adapts AlphaEarth to human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs). AETHER aligns AE embeddings with textual representations of POIs, enriching physically grounded EO features with semantic cues about urban functions and socioeconomic contexts. In Greater London, AETHER achieves consistent gains over the AE baseline, with a 7.2% relative improvement in land-use classification F1 and a 23.6% relative reduction in Kullback-Leibler divergence for socioeconomic mapping. Built upon pretrained AE, AETHER leverages a lightweight multimodal alignment to enrich it with human-centered semantics while remaining computationally efficient and scalable for urban applications. By coupling EO with human-centered semantics, it advances geospatial foundation models toward general-purpose urban representations that integrate both physical form and functional meaning. Introduction Understanding the spatial organization and functional dynamics of cities remains a long-standing challenge in GIScience and urban computing. Addressing this challenge requires spatial representations that generalize across scales, modalities, and urban contexts.

Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative denoising. In contrast, AR models enable efficient optimization and flexible sequence construction, making them better suited for large-scale pretraining. To further improve AR efficiency, particularly when action chunks induce extended and high-dimensional sequences, prior work applies entropy-guided and token-frequency techniques to shorten the sequence length. However, such compression struggled with \textit{poor reconstruction or inefficient compression}. Motivated by this, we introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation. Specifically, we first normalize value ranges and temporal horizons to obtain a consistent representation with B-Spline encoding. Then, we apply multi-stage residual quantization to the position, rotation, and gripper subspaces, producing compressed discrete tokens with coarse-to-fine granularity for each part. After pre-training on the large-scale dataset Droid, the resulting discrete tokenization shortens the training sequence by 6.8$\times$, and lowers the target entropy. To further explore the potential of OmniSAT, we develop a cross-embodiment learning strategy that builds on the unified action-pattern space and jointly leverages robot and human demonstrations. It enables scalable auxiliary supervision from heterogeneous egocentric videos. Across diverse real-robot and simulation experiments, OmniSAT encompasses higher compression while preserving reconstruction quality, enabling faster AR training convergence and model performance.

It is increasingly important to generate synthetic populations with explicit coordinates rather than coarse geographic areas, yet no established methods exist to achieve this. One reason is that latitude and longitude differ from other continuous variables, exhibiting large empty spaces and highly uneven densities. To address this, we propose a population synthesis algorithm that first maps spatial coordinates into a more regular latent space using Normalizing Flows (NF), and then combines them with other features in a Variational Autoencoder (VAE) to generate synthetic populations. This approach also learns the joint distribution between spatial and non-spatial features, exploiting spatial autocorrelations. We demonstrate the method by generating synthetic homes with the same statistical properties of real homes in 121 datasets, corresponding to diverse geographies. We further propose an evaluation framework that measures both spatial accuracy and practical utility, while ensuring privacy preservation. Our results show that the NF+VAE architecture outperforms popular benchmarks, including copula-based methods and uniform allocation within geographic areas. The ability to generate geolocated synthetic populations at fine spatial resolution opens the door to applications requiring detailed geography, from household responses to floods, to epidemic spread, evacuation planning, and transport modeling.

How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predicts future observation sequences based on current visual inputs and motion intentions. Specifically, we construct a dataset for aerial world model training and testing, which consists of 11k video-intention pairs. This dataset includes first-person-view videos capturing diverse drone actions across a wide range of scenarios, with over 1,000 hours spent annotating the corresponding motion intentions. Then we develop a two-phase schedule to train a foundation model--initially devoid of embodied spatial knowledge--into a world model that is controllable by motion intentions and adheres to physical spatio-temporal constraints. Experimental results demonstrate that AirScape significantly outperforms existing foundation models in 3D spatial imagination capabilities, especially with over a 50% improvement in metrics reflecting motion alignment. The project is available at: https://embodiedcity.github.io/AirScape/.

Understanding environmental ecosystems is vital for the sustainable management of our planet. However,existing physics-based and data-driven models often fail to generalize to varying spatial regions and scales due to the inherent data heterogeneity presented in real environmental ecosystems. This generalization issue is further exacerbated by the limited observation samples available for model training. To address these issues, we propose Geo-STARS, a geo-aware spatio-temporal modeling framework for predicting stream water temperature across different watersheds and spatial scales. The major innovation of Geo-STARS is the introduction of geo-aware embedding, which leverages geographic information to explicitly capture shared principles and patterns across spatial regions and scales. We further integrate the geo-aware embedding into a gated spatio-temporal graph neural network. This design enables the model to learn complex spatial and temporal patterns guided by geographic and hydrological context, even with sparse or no observational data. We evaluate Geo-STARS's efficacy in predicting stream water temperature, which is a master factor for water quality. Using real-world datasets spanning 37 years across multiple watersheds along the eastern coast of the United States, Geo-STARS demonstrates its superior generalization performance across both regions and scales, outperforming state-of-the-art baselines. These results highlight the promise of Geo-STARS for scalable, data-efficient environmental monitoring and decision-making.

By building and updating internal cognitive maps, animals exhibit extraordinary navigation abilities in complex, dynamic environments. Inspired by these biological mechanisms, we present a real time robotic navigation system grounded in the Active Inference Framework (AIF). Our model incrementally constructs a topological map, infers the agent's location, and plans actions by minimising expected uncertainty and fulfilling perceptual goals without any prior training. Integrated into the ROS2 ecosystem, we validate its adaptability and efficiency across both 2D and 3D environments (simulated and real world), demonstrating competitive performance with traditional and state of the art exploration approaches while offering a biologically inspired navigation approach.

Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack geometric and spatial reasoning, which is essential for capturing the physical structure of the 3D world. To address this limitation, we introduce iMoWM, a novel interactive world model designed to generate color images, depth maps, and robot arm masks in an autoregressive manner conditioned on actions. To overcome the high computational cost associated with three-dimensional information, we propose MMTokenizer, which unifies multi-modal inputs into a compact token representation. This design enables iMoWM to leverage large-scale pretrained VideoGPT models while maintaining high efficiency and incorporating richer physical information. With its multi-modal representation, iMoWM not only improves the visual quality of future predictions but also serves as an effective simulator for model-based reinforcement learning (MBRL) and facilitates real-world imitation learning. Extensive experiments demonstrate the superiority of iMoWM across these tasks, showcasing the advantages of multi-modal world modeling for robotic manipulation. Homepage: https://xingyoujun.github.io/imowm/

Embodied capabilities refer to a suite of fundamental abilities for an agent to perceive, comprehend, and interact with the physical world. While multimodal large language models (MLLMs) show promise as embodied agents, a thorough and systematic evaluation of their embodied capabilities remains underexplored, as existing benchmarks primarily focus on specific domains such as planning or spatial understanding. To bridge this gap, we introduce BEAR, a comprehensive and fine-grained benchmark that evaluates MLLMs on atomic embodied capabilities. BEAR comprises 4,469 interleaved image-video-text entries across 14 domains in 6 categories, including tasks from low-level pointing, trajectory understanding, spatial reasoning, to high-level planning. Extensive evaluation results of 20 representative MLLMs reveal their persistent limitations across all domains of embodied capabilities. To tackle the shortfall, we propose BEAR-Agent, a multimodal conversable agent that integrates pretrained vision models to strengthen MLLM perception, 3D understanding, and planning capabilities. It substantially enhances MLLM performance across diverse embodied capabilities on BEAR, yielding a 9.12% absolute gain and a relative improvement of 17.5% on GPT-5. Furthermore, our experiments indicate that improving MLLM embodied capabilities can benefit embodied tasks in simulated environments. Project website: https://bear-official66.github.io/

To this end, we propose SpatialPIN, a framework that utilizes progressive prompting and interactions between VLMs and 2D/3D foundation models as "free lunch" to enhance spatial reasoning capabilities