Related papers: Diagnosing Bottlenecks in Data Visualization Under…

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…

Why do Vision Language Models (VLMs), despite success on standard benchmarks, often fail to match human performance on surprisingly simple visual reasoning tasks? While the underlying computational principles are still debated, we…

Visual Language Models (VLMs) are now sufficiently advanced to support a broad range of applications, including answering complex visual questions, and are increasingly expected to interact with images in varied ways. To evaluate them,…

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition…

Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant…

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks, particularly for visual question answering (VQA). However, existing…

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this…

Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still…

Recent advances in the development of vision-language models (VLMs) are yielding remarkable success in recognizing visual semantic content, including impressive instances of compositional image understanding. Here, we introduce the novel…

While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain performance. In this work, we present the first large-scale study…

Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization…

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the…

Where someone looks is a nonverbal communication cue that children and adults readily use. How well can Vision-Language Models (VLMs) infer gaze targets? To construct evaluation stimuli, we captured 1,360 real-world photos of scenes in…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects among distractions. While these errors mirror human cognitive…