PrototypeCommon
wmn-231314/diffusion-data-constraint
Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion models are significantly more data-efficient than standard left to right autoregressive models, due to their ability to learn from different token orderings.
- Owner
- wmn-231314 (personal account)
- Stars
- Stars: 128
- Forks
- Forks: 6
- Language
- Python
- License
- None
- Created
- 2025
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- yiboz2001/UltraTexStars: 128PythonPrototype
- LuwuDynamics/xgoduck_runtime_arduinoStars: 128PythonPrototype
- Stellar-Sentinel/sentinel-backendStars: 128PythonPrototype
- alex/pyvcsStars: 128PythonPrototype
- scy/levitationStars: 128PythonPrototype
- dziegler/django-cachebotStars: 128PythonPrototype