Related papers: FoREST: Frame of Reference Evaluation in Spatial R…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, while spatial intelligence is fundamental for Vision-Language Models (VLMs) in real-world…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large…

Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical spatial reasoning, defined as the capacity to parse and manipulate two- and three-dimensional…

Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing "under" or "behind" relationships between only two objects, pose significant…

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…

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT)…

For human cognitive process, spatial reasoning and perception are closely entangled, yet the nature of this interplay remains underexplored in the evaluation of multimodal large language models (MLLMs). While recent MLLM advancements show…

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment…

Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that…

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the…

Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial…

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial…

While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…

Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone?…

Recent advances in multimodal large language models (MLLMs) have shown remarkable capabilities in integrating vision and language for complex reasoning. While most existing benchmarks evaluate models under offline settings with a fixed set…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they are for. While existing benchmarks effectively evaluate the geometric perception…

Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems. As a result, recent work…