← back to curriculum github ↗

phase 12

Multimodal Ai

25 lessons · click any to read the docs

phase progress

0/ 25 lessons · 0%

Vision Transformer Patch Tokens

01-vision-transformer-patch-tokens

Clip Contrastive Pretraining

02-clip-contrastive-pretraining

Blip2 Qformer Bridge

03-blip2-qformer-bridge

Flamingo Gated Cross Attention

04-flamingo-gated-cross-attention

Llava Visual Instruction Tuning

05-llava-visual-instruction-tuning

Any Resolution Patch N Pack

06-any-resolution-patch-n-pack

Open Weight Vlm Recipes

07-open-weight-vlm-recipes

Llava Onevision Single Multi Video

08-llava-onevision-single-multi-video

Qwen Vl Family Dynamic Fps

09-qwen-vl-family-dynamic-fps

Internvl3 Native Multimodal

10-internvl3-native-multimodal

Chameleon Early Fusion Tokens

11-chameleon-early-fusion-tokens

Emu3 Next Token For Generation

12-emu3-next-token-for-generation

Transfusion Autoregressive Diffusion

13-transfusion-autoregressive-diffusion

Show O Discrete Diffusion Unified

14-show-o-discrete-diffusion-unified

Janus Pro Decoupled Encoders

15-janus-pro-decoupled-encoders

Mio Any To Any Streaming

16-mio-any-to-any-streaming

Video Language Temporal Grounding

17-video-language-temporal-grounding

Long Video Million Token

18-long-video-million-token

Audio Language Whisper To Af3

19-audio-language-whisper-to-af3

Omni Models Thinker Talker

20-omni-models-thinker-talker

Embodied Vlas Openvla Pi0 Groot

21-embodied-vlas-openvla-pi0-groot

Document Diagram Understanding

22-document-diagram-understanding

Colpali Vision Native Rag

23-colpali-vision-native-rag

Multimodal Rag Cross Modal

24-multimodal-rag-cross-modal

Multimodal Agents Computer Use

25-multimodal-agents-computer-use