Large Vision-Language Models -

. .

Résumé :
Part 1: Pre-training and Datasets.- Chapter 1: LAION-5B: A Massive Open Image-Text Dataset.- Chapter 2: Efficient Training of Large-Scale Vision-Language Models.- Chapter 3: Scaling Laws for Contrastive Language-Image Learning.- Chapter 4: Scaling Up Vision-Language Models for Generic Tasks.- Chapter 5: Searching for Next-Gen Multimodal Datasets.- Part 2: Prompting and Generalization.- Chapter 6: Soft Prompt Learning for Vision-Language Models.- Chapter 7: Unified Prompting for Vision and Language.- Chapter 8: Zero-Shot Image Classification with Custom Prompts.- Chapter 9: Enhancing Vision-Language Models with Feature Adapters.- Chapter 10: Automatic Optimization of Prompting Architectures.- Chapter 11: Open-Vocabulary Calibration for VL Models.- Part 3: Applications.- Chapter 12: Open-Vocabulary DETR with Conditional Matching.- Chapter 13: Extracting Dense Labels from CLIP.- Chapter 14: PointCLIP: Understanding Point Clouds with VL.- Chapter 15: Diffusion-Based Relation Inversion from Images.- Chapter 16: Text-to-Video Generation.- Chapter 17: Text-Driven Human Motion Generation.- Chapter 18: Zero-Shot Text-Driven 3D Avatar Generation.- Chapter 19: Zero-Shot Text-Driven HDR Panorama Generation....

Biographie:

Peng Gao is a research scientist at Shanghai Artificial Intelligence Laboratory, working on large language models and vision-language models. His research interests include vision-language models, large language models and diffusion models for contents creation. He has published more than 40 papers in top-tier journals and conferences, including International Journal of Computer Vision (IJCV), ICML, ICLR, NeurIPS, CVPR, ICCV and ECCV, receiving more than 10,000 citations. He has led several influential open-source projects including LLaMa-Adapter and the Lumina series, receiving more than 7000 and 2000 stars, respectively. ...

Sommaire:
The rapid progress in the field of large multimodal foundation models, especially vision-language models, has dramatically transformed the landscape of machine learning, computer vision, and natural language processing. These powerful models, trained on vast amounts of multimodal data mixed with images and text, have demonstrated remarkable capabilities in tasks ranging from image classification and object detection to visual content generation and question answering. This book provides a comprehensive and up-to-date exploration of large vision-language models, covering the key aspects of their pre-training, prompting techniques, and diverse real-world computer vision applications. It is an essential resource for researchers, practitioners, and students in the fields of computer vision, natural language processing, and artificial intelligence.