CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
Perception prioritized training of diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
TextBoost is a one-shot personalization technique that selectively fine-tunes the text encoder of diffusion models using causality-preserving adaptation and lightweight adapters to reduce parameters and storage.
citing papers explorer
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
-
TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation
TextBoost is a one-shot personalization technique that selectively fine-tunes the text encoder of diffusion models using causality-preserving adaptation and lightweight adapters to reduce parameters and storage.