Related papers: What's "up" with vision-language models? Investiga…

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

Contrastive vision-language models like CLIP have been found to lack spatial understanding capabilities. In this paper we discuss the possible causes of this phenomenon by analysing both datasets and embedding space. By focusing on simple…

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

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:…

Joint vision-language models have shown great performance over a diverse set of tasks. However, little is known about their limitations, as the high dimensional space learned by these models makes it difficult to identify semantic errors.…

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide…

Single-vehicle Vision-Language Models (VLMs) are fundamentally constrained by sensor occlusions. While Vehicle-to-Everything (V2X) systems mitigate this, current benchmarks lack the cooperative reasoning required for resolving ambiguities…

Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

Multimodal Large Language Models (MLLMs) have shown remarkable proficiency on general-purpose vision-language benchmarks, reaching or even exceeding human-level performance. However, these evaluations typically rely on standard…

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability…

Multimodal large language models (MLLMs) have demonstrated remarkable abilities in comprehending visual input alongside text input. Typically, these models are trained on extensive data sourced from the internet, which are sufficient for…

When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the…

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…

Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities. Inspired by the prevalent use of the Cookie Theft task in human cognitive tests, we propose a novel…

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an…

Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual…

Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability encourage automated approaches. We investigate whether Vision Language Models (VLMs) can…

Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich…