Chuyển đến nội dung chính
BlogCoursesHL7Cert PrepRoadmapGameDomainAboutMCPNEW
Topics
DatabaseDevOpsKiến trúc hệ thốngLinuxProgrammingSecurity

Multimodal AI: Combining Vision, Language & More

Comprehensive course on Multimodal AI — from Vision-Language Models (CLIP, LLaVA), Visual Question Answering, Image Captioning, to Document AI, Video Understanding. Practice with Python, PyTorch, Hugging Face Transformers, and state-of-the-art models like GPT-4V, Gemini, LLaVA.

Part 1: Multimodal Learning Platform

Lesson 1: What is Multimodal AI? — Cross-modal Learning90 minLesson 2: CLIP & Contrastive Vision-Language Learning150 minLesson 3: Vision Encoders — ViT, DINOv2 & Beyond120 min

Part 2: Vision-Language Models (VLMs)

Lesson 4: Image Captioning — From Attention to Transformer150 minLesson 5: Visual Question Answering (VQA)120 minLesson 6: LLaVA & Open-source VLMs180 minLesson 7: GPT-4V, Gemini & Commercial VLMs120 min

Part 3: Document AI & Video Understanding

Lesson 8: Document AI — OCR, Layout Analysis & Extraction150 minLesson 9: Video Understanding & Temporal AI150 minLesson 10: Text-to-Image Generation & Editing150 min

Part 4: Advanced Multimodal & Production

Lesson 11: Multimodal RAG — Retrieval with Images & Documents150 minLesson 12: Embodied AI & Robotics Vision-Language120 minLesson 13: Deploy Multimodal AI — Optimization & Serving150 minLesson 14: Capstone — Multimodal Assistant Pipeline240 min