LAVIS - A One-stop Library for Language-Vision Intelligence
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Languag...
DeepSeek-VL: Towards Real-World Vision-Language Understanding
日本語LLMまとめ - Overview of Japanese LLMs
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Ima...
Paddle Multimodal Integration and eXploration, supporting mainstream mul...
[CVPR2023] The code for 《Position-guided Text Prompt for Vision-Languag...
Recognize Any Regions
This repository provides a comprehensive collection of research papers f...