相关论文: NLLB-CLIP -- train performant multilingual image r…

The current trend of scaling language models involves increasing both parameter count and training dataset size. Extrapolating this trend suggests that training dataset size may soon be limited by the amount of text data available on the…

Massive web datasets play a key role in the success of large vision-language models like CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to reduce noise often come at the expense of data diversity. Our…

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the…

This paper is a technical report to share our experience and findings building a Korean and English bilingual multimodal model. While many of the multimodal datasets focus on English and multilingual multimodal research uses…

Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL…

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for…

Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to…

Multimodal retrieval systems typically employ Vision Language Models (VLMs) that encode images and text independently into vectors within a shared embedding space. Despite incorporating text encoders, VLMs consistently underperform…

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…

In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models…

This work introduces CAPIVARA, a cost-efficient framework designed to enhance the performance of multilingual CLIP models in low-resource languages. While CLIP has excelled in zero-shot vision-language tasks, the resource-intensive nature…

Vision-Language Pre-training (VLP) models have achieved remarkable success by leveraging large-scale image-text pairs. While English-centric models like CLIP and SigLIP benefit from massive datasets (e.g., LAION-400M), the development of…

Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise…

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on…

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…

Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for image-based…

There has been a significant progress in text conditional image generation models. Recent advancements in this field depend not only on improvements in model structures, but also vast quantities of text-image paired datasets. However,…

Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture. However, multimodal models still often consist of many task- and modality-specific pieces and training…

The evaluation of image captions, looking at both linguistic fluency and semantic correspondence to visual contents, has witnessed a significant effort. Still, despite advancements such as the CLIPScore metric, multilingual captioning…