Shared recipe
Frozen visual encoder → future features → perception head
Read → through time; ↓ by representation
Orange: point prediction · Green: stochastic generation
Blue “cites” arrows: verified references, pointing to the cited paper. Other arrows: labeled conceptual/benchmark links.
Multi-layer DINO → PCA
Masked transformer
Deterministic regression
One forecast in PCA space
DINO features → VAE
Last-layer DINOv2 features
Cross-attention predictor
Smooth L1 regression
One feature forecast
Autoregressive flow matching
Generate compressed latents
Sample → VAE decode → features
Full pretrained features
Flow matching
Wide head + timestep scheduling
Multiple feature-space futures
RAE · Oct 2025 💻 📦
Making generation in DINO space practical
Semantic features can support high-quality image generation. Adapt the architecture and training to their high dimensionality:
- Wide, shallow head: avoid a narrow denoising bottleneck.
- Dimension-aware noise schedule: adjust the noise–signal balance.
- Noise-augmented decoder: handle imperfect generated latents.
Strong evidence and a practical recipe—not the first feature-space generator.
Public releases · checked 18 Sep 2026
💻 official code · 📦 trained checkpoints
Only available releases get badges.
Backbone weights and local untrained reproductions do not count.