Spatial representations that capture both structural and semantic characteristics of urban environments are essential for urban modeling. Traditional spatial embeddings often prioritize spatial proximity while underutilizing fine-grained contextual information from places. To address this limitation, we introduce CaLLiPer+, an extension of the CaLLiPer model that systematically integrates Point-of-Interest (POI) names alongside categorical labels within a multimodal contrastive learning framework. We evaluate its effectiveness on two downstream tasks, land use classification and socioeconomic status distribution mapping, demonstrating consistent performance gains of 4% to 11% over baseline methods. Additionally, we show that incorporating POI names enhances location retrieval, enabling models to capture complex urban concepts with greater precision. Ablation studies further reveal the complementary role of POI names and the advantages of leveraging pretrained text encoders for spatial representations. Overall, our findings highlight the potential of integrating fine-grained semantic attributes and multimodal learning techniques to advance the development of urban foundation models.

Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the common-sense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches, inspired by Kahneman's theory, have been proposed to leverage a VLM-based System 2 model handling high-level reasoning and a separate System 1 action model ensuring real-time control. However, existing designs maintain both systems as separate models, limiting System 1 from fully leveraging the rich pretrained knowledge from the VLM-based System 2. In this work, we propose Fast-in-Slow (FiS), a unified dual-system vision-language-action (VLA) model that embeds the System 1 execution module within the VLM-based System 2 by partially sharing parameters. This innovative paradigm not only enables high-frequency execution in System 1 but also facilitates coordination between the reasoning and execution components within a single foundation model of System 2. Given their fundamentally distinct roles within FiS-VLA, we design the two systems to incorporate heterogeneous modality inputs alongside asynchronous operating frequencies, enabling both fast and precise manipulation. To enable coordination between the two systems, a dual-aware co-training strategy is proposed that equips System 1 with action generation capabilities while preserving System 2's contextual reasoning representation. For evaluation, FiS-VLA outperforms previous state-of-the-art methods by 8% in simulation and 11% in real-world tasks in terms of average success rate, while achieving a 117.7 Hz control frequency with action chunk set to eight. Project web page: fast-in-slow.github.io.

Image mass cytometry (IMC) enables high-dimensional spatial profiling by combining mass cytometry's analytical power with spatial distributions of cell phenotypes. Recent studies leverage large language models (LLMs) to extract cell states by translating gene or protein expression into biological context. However, existing single-cell LLMs face two major challenges: (1) Integration of spatial information: they struggle to generalize spatial coordinates and effectively encode spatial context as text, and (2) Treating each cell independently: they overlook cell-cell interactions, limiting their ability to capture biological relationships. To address these limitations, we propose Spatial2Sentence, a novel framework that integrates single-cell expression and spatial information into natural language using a multi-sentence approach. Spatial2Sentence constructs expression similarity and distance matrices, pairing spatially adjacent and expressionally similar cells as positive pairs while using distant and dissimilar cells as negatives. These multi-sentence representations enable LLMs to learn cellular interactions in both expression and spatial contexts. Equipped with multi-task learning, Spatial2Sentence outperforms existing single-cell LLMs on preprocessed IMC datasets, improving cell-type classification by 5.98% and clinical status prediction by 4.18% on the diabetes dataset while enhancing interpretability. The source code can be found here: https://github.com/UNITES-Lab/Spatial2Sentence.

Autonomous operation of service robotics in human-centric scenes remains challenging due to the need for understanding of changing environments and context-aware decision-making. While existing approaches like topological maps offer efficient spatial priors, they fail to model transient object relationships, whereas dense neural representations (e.g., NeRF) incur prohibitive computational costs. Inspired by the hierarchical scene representation and video scene graph generation works, we propose Hi-Dyna Graph, a hierarchical dynamic scene graph architecture that integrates persistent global layouts with localized dynamic semantics for embodied robotic autonomy. Our framework constructs a global topological graph from posed RGB-D inputs, encoding room-scale connectivity and large static objects (e.g., furniture), while environmental and egocentric cameras populate dynamic subgraphs with object position relations and human-object interaction patterns. A hybrid architecture is conducted by anchoring these subgraphs to the global topology using semantic and spatial constraints, enabling seamless updates as the environment evolves. An agent powered by large language models (LLMs) is employed to interpret the unified graph, infer latent task triggers, and generate executable instructions grounded in robotic affordances. We conduct complex experiments to demonstrate Hi-Dyna Grap's superior scene representation effectiveness. Real-world deployments validate the system's practicality with a mobile manipulator: robotics autonomously complete complex tasks with no further training or complex rewarding in a dynamic scene as cafeteria assistant. See https://anonymous.4open.science/r/Hi-Dyna-Graph-B326 for video demonstration and more details.

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial understanding comparable to human capabilities poses significant challenges in model encoding and data acquisition. Existing methods frequently depend on external depth sensors for geometry capture or utilize off-the-shelf algorithms for pre-constructing 3D maps, thereby limiting their scalability, especially with prevalent monocular video inputs and for time-sensitive applications. In this work, we introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning. VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding. Leveraging our Spatial-Visual-View Fusion and over 200K curated 3D reconstructive instruction tuning question-answer (QA) pairs, VLM-3R effectively aligns real-world spatial context with language instructions. This enables monocular 3D spatial assistance and embodied reasoning. To facilitate the evaluation of temporal reasoning, we introduce the Vision-Spatial-Temporal Intelligence benchmark, featuring over 138.6K QA pairs across five distinct tasks focused on evolving spatial relationships. Extensive experiments demonstrate that our model, VLM-3R, not only facilitates robust visual-spatial reasoning but also enables the understanding of temporal 3D context changes, excelling in both accuracy and scalability.

To enhance immersive experiences, binaural audio offers spatial awareness of sounding objects in AR, VR, and embodied AI applications. While existing audio spatialization methods can generally map any available monaural audio to binaural audio signals, they often lack the flexible and interactive control needed in complex multi-object user-interactive environments. To address this, we propose a Text-guided Audio Spatialization (TAS) framework that utilizes flexible text prompts and evaluates our model from unified generation and comprehension perspectives. Due to the limited availability of premium and large-scale stereo data, we construct the SpatialTAS dataset, which encompasses 376,000 simulated binaural audio samples to facilitate the training of our model. Our model learns binaural differences guided by 3D spatial location and relative position prompts, augmented by flipped-channel audio. It outperforms existing methods on both simulated and real-recorded datasets, demonstrating superior generalization and accuracy. Besides, we develop an assessment model based on Llama-3.1-8B, which evaluates the spatial semantic coherence between our generated binaural audio and text prompts through a spatial reasoning task. Results demonstrate that text prompts provide flexible and interactive control to generate binaural audio with excellent quality and semantic consistency in spatial locations. Dataset is available at \href{https://github.com/Alice01010101/TASU}

Cooperative perception enables vehicles to share sensor readings and has become a new paradigm to improve driving safety, where the key enabling technology for realizing this vision is to real-time and accurately align and fuse the perceptions. Recent advances to align the views rely on high-density LiDAR data or fine-grained image feature representations, which however fail to meet the requirements of accuracy, real-time, and adaptability for autonomous driving. To this end, we present MMatch, a lightweight system that enables accurate and real-time perception fusion with mmWave radar point clouds. The key insight is that fine-grained spatial information provided by the radar present unique associations with all the vehicles even in two separate views. As a result, by capturing and understanding the unique local and global position of the targets in this association, we can quickly find out all the co-visible vehicles for view alignment. We implement MMatch on both the datasets collected from the CARLA platform and the real-world traffic with over 15,000 radar point cloud pairs. Experimental results show that MMatch achieves decimeter-level accuracy within 59ms, which significantly improves the reliability for autonomous driving.

Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. However, when spatial information is obscured, these models struggle to capture purely temporal patterns. We introduce $\textbf{SpookyBench}$, a benchmark where information is encoded solely in temporal sequences of noise-like frames, mirroring natural phenomena from biological signaling to covert communication. Interestingly, while humans can recognize shapes, text, and patterns in these sequences with over 98% accuracy, state-of-the-art VLMs achieve 0% accuracy. This performance gap highlights a critical limitation: an over-reliance on frame-level spatial features and an inability to extract meaning from temporal cues. Furthermore, when trained in data sets with low spatial signal-to-noise ratios (SNR), temporal understanding of models degrades more rapidly than human perception, especially in tasks requiring fine-grained temporal reasoning. Overcoming this limitation will require novel architectures or training paradigms that decouple spatial dependencies from temporal processing. Our systematic analysis shows that this issue persists across model scales and architectures. We release SpookyBench to catalyze research in temporal pattern recognition and bridge the gap between human and machine video understanding. Dataset and code has been made available on our project website: https://timeblindness.github.io/.

The ability to simulate the world in a spatially consistent manner is a crucial requirements for effective world models. Such a model enables high-quality visual generation, and also ensures the reliability of world models for downstream tasks such as simulation and planning. Designing a memory module is a crucial component for addressing spatial consistency: such a model must not only retain long-horizon observational information, but also enables the construction of explicit or implicit internal spatial representations. However, there are no dataset designed to promote the development of memory modules by explicitly enforcing spatial consistency constraints. Furthermore, most existing benchmarks primarily emphasize visual coherence or generation quality, neglecting the requirement of long-range spatial consistency. To bridge this gap, we construct a dataset and corresponding benchmark by sampling 150 distinct locations within the open-world environment of Minecraft, collecting about 250 hours (20 million frames) of loop-based navigation videos with actions. Our dataset follows a curriculum design of sequence lengths, allowing models to learn spatial consistency on increasingly complex navigation trajectories. Furthermore, our data collection pipeline is easily extensible to new Minecraft environments and modules. Four representative world model baselines are evaluated on our benchmark. Dataset, benchmark, and code are open-sourced to support future research.

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or 2.5D data to incorporate spatial awareness, restricting their utility in scenarios with only 2D inputs, such as images or videos. In this paper, we present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations. Unlike conventional video MLLMs which rely on CLIP-based visual encoders optimized for semantic understanding, our key insight is to unleash the strong structure prior from the feed-forward visual geometry foundation model. Specifically, we propose a dual-encoder architecture: a pretrained 2D visual encoder to extract semantic features, and a spatial encoder-initialized from the backbone of the visual geometry model-to extract 3D structure features. A connector then integrates both features into unified visual tokens for enhanced spatial understanding. Furthermore, we propose a space-aware frame sampling strategy at inference time, which selects the spatially informative frames of a video sequence, ensuring that even under limited token length, the model focuses on frames critical for spatial reasoning. Beyond architecture improvements, we construct the Spatial-MLLM-120k dataset and train the model on it using supervised fine-tuning and GRPO. Extensive experiments on various real-world datasets demonstrate that our spatial-MLLM achieves state-of-the-art performance in a wide range of visual-based spatial understanding and reasoning tasks. Project page: https://diankun-wu.github.io/Spatial-MLLM/.