Related papers: Better Language Models Exhibit Higher Visual Align…

Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model (LLM) with a vision encoder. However, both the LLM and the…

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework…

Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based…

The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3. In particular, averaging over LLM-generated class…

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still…

Vision-language models (VLMs) achieve remarkable performance through large-scale image-text pretraining. However, their reliance on labeled image datasets limits scalability and leaves vast amounts of unlabeled image data underutilized. To…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or…

This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have…

CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle…

Vision-language models (VLMs) such as CLIP have shown promising performance on a variety of recognition tasks using the standard zero-shot classification procedure -- computing similarity between the query image and the embedded words for…

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…

Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and…

Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to…

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

Multilingual vision-language models exhibit systematic performance gaps across languages, but the mechanism remains ambiguous: cross-language divergence could arise from the visual encoder, the text branch, or their interaction. We resolve…

In this paper, we introduce Cross-View Language Modeling, a simple and effective pre-training framework that unifies cross-lingual and cross-modal pre-training with shared architectures and objectives. Our approach is motivated by a key…

The extent to which text-only language models (LMs) learn to represent features of the non-linguistic world is an open question. Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are…

Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…