Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Course · stage 7 of 9

Multimodal & Generative AI

Vision Transformers, CLIP and VLMs, diffusion and flow matching, speech, video and world models.

Start the first unit → All stages

4 unitsabout 38 hours39 algorithms

01Units in this stage

In order. Each unit has goals, algorithms, must-read papers, a project and a self-test.

01 · U70 Vision Transformers & Self-Supervised Vision ViT, SimCLR, MAE, JEPA and SAM. 8 h12 algorithms4 papers 02 · U71 CLIP & Vision-Language Models Contrastive image–text pre-training, SigLIP, LLaVA-style VLMs and Flamingo. 8 h4 algorithms4 papers 03 · U72 Diffusion, Flow Matching & Image Generation VAE/GAN, DDPM/DDIM, score SDEs, latent diffusion, CFG, DiT, flow matching and ControlNet. 14 h15 algorithms6 papers 04 · U73 Speech, Video & World Models Whisper, video diffusion (Sora-style DiT), 3-D reconstruction, world models, Dreamer and Genie. 8 h10 algorithms4 papers

02Algorithms you will meet

Algorithms Atlas →

Vision Transformer (ViT)SimCLRMasked Autoencoders (MAE)Joint-Embedding Predictive Architecture (JEPA)Segment Anything (SAM)Contrastive Learning (InfoNCE)U-NetFaster R-CNN (Object Detection)YOLO (Real-Time Object Detection)DETR (Detection Transformer)Swin TransformerDINOv2 (Self-Supervised Visual Features)CLIP (Contrastive Language–Image Pretraining)SigLIP (Sigmoid Loss)Visual Instruction Tuning (LLaVA)FlamingoVariational Autoencoder (VAE)Generative Adversarial Network (GAN)VQ-VAE (Neural Discrete Representation)Denoising Diffusion Probabilistic Models (DDPM)DDIMScore-Based Models via SDEsLatent Diffusion ModelsClassifier-Free Guidance (CFG)Diffusion Transformer (DiT)Flow MatchingRectified FlowConsistency ModelsControlNetVisual Autoregressive Modeling (VAR)Normalizing Flows (RealNVP / Glow)WhisperNeRF & 3D Gaussian SplattingWorld ModelsDreamer (Latent Imagination)Genie (Generative Interactive Environments)Connectionist Temporal Classification (CTC)wav2vec 2.0VALL-E (Neural Codec Language Model TTS)

Part of these routes: Algorithm Researchers · Domain Scientists

Data updated: AI algorithms & curriculum(UTC+8)