Navigating dynamic urban environments presents significant challenges for embodied agents, requiring advanced spatial reasoning and adherence to common-sense norms. Despite progress, existing visual navigation methods struggle in map-free or off-street settings, limiting the deployment of autonomous agents like last-mile delivery robots. To overcome these obstacles, we propose a scalable, data-driven approach for human-like urban navigation by training agents on thousands of hours of in-the-wild city walking and driving videos sourced from the web. We introduce a simple and scalable data processing pipeline that extracts action supervision from these videos, enabling large-scale imitation learning without costly annotations. Our model learns sophisticated navigation policies to handle diverse challenges and critical scenarios. Experimental results show that training on large-scale, diverse datasets significantly enhances navigation performance, surpassing current methods. This work shows the potential of using abundant online video data to develop robust navigation policies for embodied agents in dynamic urban settings. Project homepage is at https://ai4ce.github.io/CityWalker/.
Recent advances in multimodal models have demonstrated impressive capabilities in object recognition and scene understanding. However, these models often struggle with precise spatial localization - a critical capability for real-world applications. Inspired by how humans use grid-based references like chess boards and maps, we propose introducing explicit visual position encoding through a simple grid overlay approach. By adding a 9x9 black grid pattern onto input images, our method provides visual spatial guidance analogous to how positional encoding works in transformers, but in an explicit, visual form. Experiments on the COCO 2017 dataset demonstrate that our grid-based approach achieves significant improvements in localization accuracy, with a 107.4% increase in IoU (from 0.27 to 0.56) and a 194.4% improvement in GIoU (from 0.18 to 0.53) compared to baseline performance. Through attention visualization analysis, we show how this visual position encoding helps models better ground spatial relationships. Our method's simplicity and effectiveness make it particularly valuable for applications requiring accurate spatial reasoning, such as robotic manipulation, medical imaging, and autonomous navigation.
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP). We evaluate our approach on two benchmark datasets: StepGame and SparQA, implementing three distinct strategies: (1) direct prompting baseline, (2) Facts+Rules prompting, and (3) DSPy-based LLM+ASP pipeline with iterative refinement. Our experimental results demonstrate that the LLM+ASP pipeline significantly outperforms baseline methods, achieving an average 82% accuracy on StepGame and 69% on SparQA, marking improvements of 40-50% and 8-15% respectively over direct prompting. The success stems from three key innovations: (1) effective separation of semantic parsing and logical reasoning through a modular pipeline, (2) iterative feedback mechanism between LLMs and ASP solvers that improves program rate, and (3) robust error handling that addresses parsing, grounding, and solving failures. Additionally, we propose Facts+Rules as a lightweight alternative that achieves comparable performance on complex SparQA dataset, while reducing computational overhead.Our analysis across different LLM architectures (Deepseek, Llama3-70B, GPT-4.0 mini) demonstrates the framework's generalizability and provides insights into the trade-offs between implementation complexity and reasoning capability, contributing to the development of more interpretable and reliable AI systems.
Recent advancements in artificial intelligence have sparked interest in scientific assistants that could support researchers across the full spectrum of scientific workflows, from literature review to experimental design and data analysis. A key capability for such systems is the ability to process and reason about scientific information in both visual and textual forms - from interpreting spectroscopic data to understanding laboratory setups. Here, we introduce MaCBench, a comprehensive benchmark for evaluating how vision-language models handle real-world chemistry and materials science tasks across three core aspects: data extraction, experimental understanding, and results interpretation. Through a systematic evaluation of leading models, we find that while these systems show promising capabilities in basic perception tasks - achieving near-perfect performance in equipment identification and standardized data extraction - they exhibit fundamental limitations in spatial reasoning, cross-modal information synthesis, and multi-step logical inference. Our insights have important implications beyond chemistry and materials science, suggesting that developing reliable multimodal AI scientific assistants may require advances in curating suitable training data and approaches to training those models.
We present APT, an advanced Large Language Model (LLM)-driven framework that enables autonomous agents to construct complex and creative structures within the Minecraft environment. Unlike previous approaches that primarily concentrate on skill-based open-world tasks or rely on image-based diffusion models for generating voxel-based structures, our method leverages the intrinsic spatial reasoning capabilities of LLMs. By employing chain-of-thought decomposition along with multimodal inputs, the framework generates detailed architectural layouts and blueprints that the agent can execute under zero-shot or few-shot learning scenarios. Our agent incorporates both memory and reflection modules to facilitate lifelong learning, adaptive refinement, and error correction throughout the building process. To rigorously evaluate the agent's performance in this emerging research area, we introduce a comprehensive benchmark consisting of diverse construction tasks designed to test creativity, spatial reasoning, adherence to in-game rules, and the effective integration of multimodal instructions. Experimental results using various GPT-based LLM backends and agent configurations demonstrate the agent's capacity to accurately interpret extensive instructions involving numerous items, their positions, and orientations. The agent successfully produces complex structures complete with internal functionalities such as Redstone-powered systems. A/B testing indicates that the inclusion of a memory module leads to a significant increase in performance, emphasizing its role in enabling continuous learning and the reuse of accumulated experience. Additionally, the agent's unexpected emergence of scaffolding behavior highlights the potential of future LLM-driven agents to utilize subroutine planning and leverage the emergence ability of LLMs to autonomously develop human-like problem-solving techniques.
Spatial understanding is a crucial capability that enables robots to perceive their surroundings, reason about their environment, and interact with it meaningfully. In modern robotics, these capabilities are increasingly provided by vision-language models. However, these models face significant challenges in spatial reasoning tasks, as their training data are based on general-purpose image datasets that often lack sophisticated spatial understanding. For example, datasets frequently do not capture reference frame comprehension, yet effective spatial reasoning requires understanding whether to reason from ego-, world-, or object-centric perspectives. To address this issue, we introduce RoboSpatial, a large-scale dataset for spatial understanding in robotics. It consists of real indoor and tabletop scenes, captured as 3D scans and egocentric images, and annotated with rich spatial information relevant to robotics. The dataset includes 1M images, 5k 3D scans, and 3M annotated spatial relationships, and the pairing of 2D egocentric images with 3D scans makes it both 2D- and 3D- ready. Our experiments show that models trained with RoboSpatial outperform baselines on downstream tasks such as spatial affordance prediction, spatial relationship prediction, and robot manipulation.
The Zero-Shot Object Navigation (ZSON) task requires embodied agents to find a previously unseen object by navigating in unfamiliar environments. Such a goal-oriented exploration heavily relies on the ability to perceive, understand, and reason based on the spatial information of the environment. However, current LLM-based approaches convert visual observations to language descriptions and reason in the linguistic space, leading to the loss of spatial information. In this paper, we introduce TopV-Nav, an MLLM-based method that directly reasons on the top-view map with sufficient spatial information. To fully unlock the MLLM's spatial reasoning potential in top-view perspective, we propose the Adaptive Visual Prompt Generation (AVPG) method to adaptively construct semantically-rich top-view map. It enables the agent to directly utilize spatial information contained in the top-view map to conduct thorough reasoning. Besides, we design a Dynamic Map Scaling (DMS) mechanism to dynamically zoom top-view map at preferred scales, enhancing local fine-grained reasoning. Additionally, we devise a Potential Target Driven (PTD) mechanism to predict and to utilize target locations, facilitating global and human-like exploration. Experiments on MP3D and HM3D datasets demonstrate the superiority of our TopV-Nav.
Autonomous driving requires a comprehensive understanding of 3D environments to facilitate high-level tasks such as motion prediction, planning, and mapping. In this paper, we introduce DriveMLLM, a benchmark specifically designed to evaluate the spatial understanding capabilities of multimodal large language models (MLLMs) in autonomous driving. DriveMLLM includes 880 front-facing camera images and introduces both absolute and relative spatial reasoning tasks, accompanied by linguistically diverse natural language questions. To measure MLLMs' performance, we propose novel evaluation metrics focusing on spatial understanding. We evaluate several state-of-the-art MLLMs on DriveMLLM, and our results reveal the limitations of current models in understanding complex spatial relationships in driving contexts. We believe these findings underscore the need for more advanced MLLM-based spatial reasoning methods and highlight the potential for DriveMLLM to drive further research in autonomous driving. Code will be available at \url{https://github.com/XiandaGuo/Drive-MLLM}.
Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies-areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse set of challenging games. Our benchmark incorporates a range of existing reinforcement learning environments with varying levels of difficulty, including tasks that are solvable by non-expert humans in seconds to extremely challenging ones that may take years to master (e.g., the NetHack Learning Environment). We devise fine-grained metrics to measure performance and conduct an extensive evaluation of several popular open-source and closed-source LLMs and VLMs. Our findings indicate that while current models achieve partial success in the easier games, they struggle significantly with more challenging tasks. Notably, we observe severe deficiencies in vision-based decision-making, as several models perform worse when visual representations of the environments are provided. We release BALROG as an open and user-friendly benchmark to facilitate future research and development in the agentic community. Code and Leaderboard at balrogai.com.
Creating large-scale interactive 3D environments is essential for the development of Robotics and Embodied AI research. Current methods, including manual design, procedural generation, diffusion-based scene generation, and large language model (LLM) guided scene design, are hindered by limitations such as excessive human effort, reliance on predefined rules or training datasets, and limited 3D spatial reasoning ability. Since pre-trained 2D image generative models better capture scene and object configuration than LLMs, we address these challenges by introducing Architect, a generative framework that creates complex and realistic 3D embodied environments leveraging diffusion-based 2D image inpainting. In detail, we utilize foundation visual perception models to obtain each generated object from the image and leverage pre-trained depth estimation models to lift the generated 2D image to 3D space. Our pipeline is further extended to a hierarchical and iterative inpainting process to continuously generate placement of large furniture and small objects to enrich the scene. This iterative structure brings the flexibility for our method to generate or refine scenes from various starting points, such as text, floor plans, or pre-arranged environments.
Multimodal Large Language Models (MLLMs) excel at descriptive tasks within images but often struggle with precise object localization, a critical element for reliable visual interpretation. In contrast, traditional object detection models provide high localization accuracy but frequently generate detections lacking contextual coherence due to limited modeling of inter-object relationships. To address this fundamental limitation, we introduce the \textbf{Visual-Linguistic Agent (VLA), a collaborative framework that combines the relational reasoning strengths of MLLMs with the precise localization capabilities of traditional object detectors. In the VLA paradigm, the MLLM serves as a central Linguistic Agent, working collaboratively with specialized Vision Agents for object detection and classification. The Linguistic Agent evaluates and refines detections by reasoning over spatial and contextual relationships among objects, while the classification Vision Agent offers corrective feedback to improve classification accuracy. This collaborative approach enables VLA to significantly enhance both spatial reasoning and object localization, addressing key challenges in multimodal understanding. Extensive evaluations on the COCO dataset demonstrate substantial performance improvements across multiple detection models, highlighting VLA's potential to set a new benchmark in accurate and contextually coherent object detection.
Spatial intelligence is important in Architecture, Construction, Science, Technology, Engineering, and Mathematics (STEM), and Medicine. Understanding three-dimensional (3D) spatial rotations can involve verbal descriptions and visual or interactive examples, illustrating how objects change orientation in 3D space. Recent studies show Artificial Intelligence (AI) with language and vision capabilities still face limitations in spatial reasoning. In this paper, we have studied generative AI's spatial capabilities of understanding rotations of objects utilizing its image and language processing features. We examined the spatial intelligence of the GPT-4 model with vision in understanding spatial rotation process with diagrams based on the Revised Purdue Spatial Visualization Test: Visualization of Rotations (Revised PSVT:R). Next, we incorporated a layer of coordinate system axes on Revised PSVT:R to study the variations in GPT-4's performance. We also examined GPT-4's understanding of 3D rotations in Augmented Reality (AR) scenes that visualize spatial rotations of an object in 3D space and observed increased accuracy of GPT-4's understanding of the rotations by adding supplementary textual information depicting the rotation process or mathematical representations of the rotation (e.g., matrices). The results indicate that while GPT-4 as a major current Generative AI model lacks the understanding of a spatial rotation process, it has the potential to understand the rotation process with additional information that can be provided by methods such as AR. By combining the potentials in spatial intelligence of AI with AR's interactive visualization abilities, we expect to offer enhanced guidance for students' spatial learning activities. Such spatial guidance can benefit understanding spatial transformations and additionally support processes like assembly, fabrication, and manufacturing.
Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. % Moreover, spatial reasoning steps are much less accurate than non-spatial ones across MLLMs. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. Spatial-MM benchmark is available at: https://github.com/FatemehShiri/Spatial-MM
We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison to baseline prompting methods. In addition, we perform a design analysis to understand the most impactful design decisions. Visual examples and code for our project can be found at https://jirl-upenn.github.io/VLMnav/
In August 2023, Scott Aaronson and I reported the results of testing GPT4 with the Wolfram Alpha and Code Interpreter plug-ins over a collection of 105 original high-school level and college-level science and math problems (Davis and Aaronson, 2023). In September 2024, I tested the recently released model GPT-4o1-preview on the same collection. Overall I found that performance had significantly improved, but was still considerably short of perfect. In particular, problems that involve spatial reasoning are often stumbling blocks.
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
Geospatial Knowledge Graphs (GeoKGs) model geoentities (e.g., places and natural features) and spatial relationships in an interconnected manner, providing strong knowledge support for geographic applications, including data retrieval, question-answering, and spatial reasoning. However, existing methods for mining and reasoning from GeoKGs, such as popular knowledge graph embedding (KGE) techniques, lack geographic awareness. This study aims to enhance general-purpose KGE by developing new strategies and integrating geometric features of spatial relations, including topology, direction, and distance, to infuse the embedding process with geographic intuition. The new model is tested on downstream link prediction tasks, and the results show that the inclusion of geometric features, particularly topology and direction, improves prediction accuracy for both geoentities and spatial relations. Our research offers new perspectives for integrating spatial concepts and principles into the GeoKG mining process, providing customized GeoAI solutions for geospatial challenges.
Spatial intelligence is the ability of a machine to perceive, reason, and act in three dimensions within space and time. Recent advancements in large-scale auto-regressive models have demonstrated remarkable capabilities across various reasoning tasks. However, these models often struggle with fundamental aspects of spatial reasoning, particularly in answering questions like "Where am I?" and "What will I see?". While some attempts have been done, existing approaches typically treat them as separate tasks, failing to capture their interconnected nature. In this paper, we present Generative Spatial Transformer (GST), a novel auto-regressive framework that jointly addresses spatial localization and view prediction. Our model simultaneously estimates the camera pose from a single image and predicts the view from a new camera pose, effectively bridging the gap between spatial awareness and visual prediction. The proposed innovative camera tokenization method enables the model to learn the joint distribution of 2D projections and their corresponding spatial perspectives in an auto-regressive manner. This unified training paradigm demonstrates that joint optimization of pose estimation and novel view synthesis leads to improved performance in both tasks, for the first time, highlighting the inherent relationship between spatial awareness and visual prediction.
Spatial expressions in situated communication can be ambiguous, as their meanings vary depending on the frames of reference (FoR) adopted by speakers and listeners. While spatial language understanding and reasoning by vision-language models (VLMs) have gained increasing attention, potential ambiguities in these models are still under-explored. To address this issue, we present the COnsistent Multilingual Frame Of Reference Test (COMFORT), an evaluation protocol to systematically assess the spatial reasoning capabilities of VLMs. We evaluate nine state-of-the-art VLMs using COMFORT. Despite showing some alignment with English conventions in resolving ambiguities, our experiments reveal significant shortcomings of VLMs: notably, the models (1) exhibit poor robustness and consistency, (2) lack the flexibility to accommodate multiple FoRs, and (3) fail to adhere to language-specific or culture-specific conventions in cross-lingual tests, as English tends to dominate other languages. With a growing effort to align vision-language models with human cognitive intuitions, we call for more attention to the ambiguous nature and cross-cultural diversity of spatial reasoning.
Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective planning. A common solution is building hierarchical agents, where VLMs serve as high-level reasoners that break down tasks into executable sub-tasks, typically specified using language. However, language suffers from the inability to communicate detailed spatial information. We propose visual-temporal context prompting, a novel communication protocol between VLMs and policy models. This protocol leverages object segmentation from past observations to guide policy-environment interactions. Using this approach, we train ROCKET-1, a low-level policy that predicts actions based on concatenated visual observations and segmentation masks, supported by real-time object tracking from SAM-2. Our method unlocks the potential of VLMs, enabling them to tackle complex tasks that demand spatial reasoning. Experiments in Minecraft show that our approach enables agents to achieve previously unattainable tasks, with a $\mathbf{76}\%$ absolute improvement in open-world interaction performance. Codes and demos are now available on the project page: https://craftjarvis.github.io/ROCKET-1.