Related papers: Do Vision--Language Models Understand 3D Scenes or…

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the…

Vision-Language Models (VLMs) excel at complex visual tasks such as VQA and chart understanding, yet recent work suggests they struggle with simple perceptual tests. We present an evaluation of vision-language models' capacity for nonlocal…

Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding,…

Visual language is a system of communication that conveys information through symbols, shapes, and spatial arrangements. Diagrams are a typical example of a visual language depicting complex concepts and their relationships in the form of…

The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to…

What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual…

Recent vision-language (VL) models are powerful, but can they reliably distinguish "right" from "left"? We curate three new corpora to quantify model comprehension of such basic spatial relations. These tests isolate spatial reasoning more…

Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a comprehensive evaluation…

Vision-language models (VLMs) show great promise for 3D scene understanding but are mainly applied to indoor spaces or autonomous driving, focusing on low-level tasks like segmentation. This work expands their use to urban-scale…

Multimodal Large Language Models (MLLMs) have made significant progress in tasks such as image captioning and question answering. However, while these models can generate realistic captions, they often struggle with providing precise…

Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving representations of 3D space. While modern Vision-Language Models (VLMs) demonstrate emergent…

Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely used as foundation backbones:…

Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding…

The lack of a large-scale 3D-text corpus has led recent works to distill open-vocabulary knowledge from vision-language models (VLMs). However, these methods typically rely on a single VLM to align the feature spaces of 3D models within a…

Vision-Language Models (VLMs) combine a vision encoder and a large language model (LLM) through alignment training, showing strong performance on multimodal tasks. A central component in this architecture is the projection layer, which maps…

Recently, Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have shown promise in instruction following and 2D image understanding. While these models are powerful, they have not yet been developed to comprehend the…

This paper explores capabilities of Vision Language Models on spreadsheet comprehension. We propose three self-supervised challenges with corresponding evaluation metrics to comprehensively evaluate VLMs on Optical Character Recognition…

Does language help make sense of the visual world? How important is it to actually see the world rather than having it described with words? These basic questions about the nature of intelligence have been difficult to answer because we…