Related papers: A Study of Commonsense Reasoning over Visual Objec…

Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions,…

Occlusion perception, a critical foundation for human-level spatial understanding, embodies the challenge of integrating visual recognition and reasoning. Though multimodal large language models (MLLMs) have demonstrated remarkable…

Large language models have shown impressive results for multi-hop mathematical reasoning when the input question is only textual. Many mathematical reasoning problems, however, contain both text and image. With the ever-increasing adoption…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual…

Despite their impressive performance on multi-modal tasks, large vision-language models (LVLMs) tend to suffer from hallucinations. An important type is object hallucination, where LVLMs generate objects that are inconsistent with the…

Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and…

The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This…

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question…

Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level multimodal reasoning benchmarks for these models often emphasize single-image analysis and…

In our work, we explore the synergistic capabilities of pre-trained vision-and-language models (VLMs) and large language models (LLMs) on visual commonsense reasoning (VCR) problems. We find that VLMs and LLMs-based decision pipelines are…

Bridging the semantic gap between image and question is an important step to improve the accuracy of the Visual Question Answering (VQA) task. However, most of the existing VQA methods focus on attention mechanisms or visual relations for…

In this work, we introduce SPLICE, a human-curated benchmark derived from the COIN instructional video dataset, designed to probe event-based reasoning across multiple dimensions: temporal, causal, spatial, contextual, and general…

Visual reasoning is critical for a wide range of computer vision tasks that go beyond surface-level object detection and classification. Despite notable advances in relational, symbolic, temporal, causal, and commonsense reasoning, existing…

Vision-language models (VLMs) have demonstrated impressive capabilities in understanding and reasoning about visual and textual content. However, their robustness to common image corruptions remains under-explored. In this work, we present…

Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal…

Large vision-language models (VLMs), such as CLIP, learn rich joint image-text representations, facilitating advances in numerous downstream tasks, including zero-shot classification and text-to-image generation. Nevertheless, existing VLMs…

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…

Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness. While these are remarkable…

Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models'…