相关论文: SUGARCREPE++ Dataset: Vision-Language Model Sensit…

Several recent works seek to adapt general-purpose large language models (LLMs) and vision-language models (VLMs) for medical applications through continued pretraining on publicly available biomedical corpora. These works typically claim…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions. The…

The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding, enriching Vision-Language Models (VLMs) with more…

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

This paper introduces the ColorSwap dataset, designed to assess and improve the proficiency of multimodal models in matching objects with their colors. The dataset is comprised of 2,000 unique image-caption pairs, grouped into 1,000…

The visual commonsense reasoning (VCR) task is to choose an answer and provide a justifying rationale based on the given image and textural question. Representative works first recognize objects in images and then associate them with key…

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information.…

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work,…

Multimodal Large Language Models (MLLMs) show reasoning promise, yet their visual perception is a critical bottleneck. Strikingly, MLLMs can produce correct answers even while misinterpreting crucial visual elements, masking these…

The interpretation of multi-temporal remote sensing imagery is critical for monitoring Earth's dynamic processes-yet previous change detection methods, which produce binary or semantic masks, fall short of providing human-readable insights…

Music-text multimodal systems have enabled new approaches to Music Information Research (MIR) applications such as audio-to-text and text-to-audio retrieval, text-based song generation, and music captioning. Despite the reported success,…

Modern Vision-Language Models (VLMs) exhibit a critical flaw in compositional reasoning, often confusing "a red cube and a blue sphere" with "a blue cube and a red sphere". Disentangling the visual and linguistic roots of these failures is…

Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks. We offer an under-studied perspective by examining how…

Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the…

Large language models (LLMs) have demonstrated significant capabilities in mathematical reasoning, particularly with text-based mathematical problems. However, current multi-modal large language models (MLLMs), especially those specialized…

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…

Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute…

Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always…

Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extending these visual foundations to multi-modal reasoning tasks is severely bottlenecked by…