Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training
paradigm, successfully introduces text supervision to vision models. It has shown promising …

With the exponential surge in diverse multimodal data, traditional unimodal retrieval
methods struggle to meet the needs of users seeking access to data across various …

As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …

The development of Artificial Intelligence Generated Content (AIGC) has been facilitated by
advancements in model algorithms, scalable foundation model architectures, and the …

Recent multimodal models such as DALL-E and CM3 have achieved remarkable progress
in text-to-image and image-to-text generation. However, these models store all learned …

Multimodal LLMs are the natural evolution of LLMs and enlarge their capabilities so as to
work beyond the pure textual modality. As research is being carried out to design novel …

Zero-shot image captioning (IC) without well-paired image-text data can be categorized into
two main types: training-free and text-only-training methods. While both types integrate pre …

Image-to-text generation aims to describe images using natural language. Recently, zero-
shot image captioning based on pre-trained vision-language models (VLMs) and large …

Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for
unseen classes which is an effective way to advance ZSL. However existing generative …

Abstract After discovering that Language Models (LMs) can be good in-context few-shot
learners, numerous strategies have been proposed to optimize in-context sequence …