Related papers: Dual-Pathway Geometry-Aware MLLM for Spatial Intel…

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning…

Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world…

Multimodal large language models (MLLMs) have achieved impressive performance across various tasks such as image captioning and visual question answer(VQA); however, they often struggle to accurately interpret depth information inherent in…

Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, especially specialized small models, exhibit poor…

We introduce GSU, a text-only grid dataset to evaluate the spatial reasoning capabilities of LLMs over 3 core tasks: navigation, object localization, and structure composition. By forgoing visual inputs, isolating spatial reasoning from…

The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their…

Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…

Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in…

Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native…

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenarios, their ability to…

While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making…

While Multimodal Large Language Models (MLLMs) have achieved impressive performance on semantic tasks, their spatial intelligence--crucial for robust and grounded AI systems--remains underdeveloped. Existing benchmarks fall short of…

Recent advances in natural-domain multi-modal large language models (MLLMs) have demonstrated effective spatial reasoning through visual and textual prompting. However, their direct transfer to remote sensing (RS) is hindered by…

Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for…

Although multi-modal large language models (MLLMs) have shown strong capabilities across diverse domains, their application in generating fine-grained 3D perception and prediction outputs in autonomous driving remains underexplored. In this…

Real-world applications, such as autonomous driving and humanoid robot manipulation, require precise spatial perception. However, it remains underexplored how Vision-Language Models (VLMs) recognize spatial relationships and perceive…

Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal…