// ✦ Diffusion, Flow Matching & Generative Models
Visual Autoregressive Modeling (VAR)
Autoregressive image generation by next-scale rather than next-token prediction.
视觉自回归 VAR 2024 Advanced extended
IN PLAIN WORDS
Generate a coarse token map, then predict progressively finer scales in parallel within each. It made GPT-style autoregression beat diffusion transformers in quality and speed; NeurIPS 2024 best paper.
Used in: Autoregressive image generation research
TIMELINE · prerequisites → this → what builds on it
01Original paper
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Keyu Tian, Yi Jiang, Zehuan Yuan, et al. · 2024
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
- Nothing in the atlas builds on it yet
Related:Diffusion Transformer (DiT)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Reference code
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
var)