Multimodal AI

Models that see, hear, read, and reason across modalities.

Цена: 9 644 ₽

Длительность: 21 ч

Автор: John Jackson

Программа курса

  1. Vision Transformers and the Patch-Token Primitive
  2. CLIP and Contrastive Vision-Language Pretraining
  3. From CLIP to BLIP-2 — Q-Former as Modality Bridge
  4. Flamingo and Gated Cross-Attention for Few-Shot VLMs
  5. LLaVA and Visual Instruction Tuning
  6. Any-Resolution Vision: Patch-n'-Pack and NaFlex
  7. Open-Weight VLM Recipes: What Actually Matters
  8. LLaVA-OneVision: Single-Image, Multi-Image, Video in One Model
  9. Qwen-VL Family and Dynamic-FPS Video
  10. InternVL3: Native Multimodal Pretraining
  11. Chameleon and Early-Fusion Token-Only Multimodal Models
  12. Emu3: Next-Token Prediction for Image and Video Generation
  13. Transfusion: Autoregressive Text + Diffusion Image in One Transformer
  14. Show-o and Discrete-Diffusion Unified Models
  15. Janus-Pro: Decoupled Encoders for Unified Multimodal Models
  16. MIO and Any-to-Any Streaming Multimodal Models
  17. Video-Language Models: Temporal Tokens and Grounding
  18. Long-Video Understanding at Million-Token Context
  19. Audio-Language Models: the Whisper to Audio Flamingo 3 Arc
  20. Omni Models: Qwen2.5-Omni and the Thinker-Talker Split
  21. Embodied VLAs: RT-2, OpenVLA, π0, GR00T
  22. Document and Diagram Understanding
  23. ColPali and Vision-Native Document RAG
  24. Multimodal RAG and Cross-Modal Retrieval
  25. Multimodal Agents and Computer-Use (Capstone)
  26. Итоговое задание