Replacing CFG's w(r-1) coefficient with r^(1+w)-r removes a sigma_min-divergent residual blow-up on a Gaussian calibration model and stabilizes high-guidance diffusion sampling at zero extra NFE.
Elucidating the design space of diffusion-based generative models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Bell-shaped time sampling — drawing the corruption level near t=0.5 — accelerates masked diffusion language model training by up to ~4× without changing the final loss.
ChunkFlow achieves up to 1.28x step-time speedup and up to 49% lower peak GPU memory for DiT inference by using a first-order model to guide communication-aware chunked prefetching.
citing papers explorer
-
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
Replacing CFG's w(r-1) coefficient with r^(1+w)-r removes a sigma_min-divergent residual blow-up on a Gaussian calibration model and stabilizes high-guidance diffusion sampling at zero extra NFE.
-
Understanding and Accelerating the Training of Masked Diffusion Language Models
Bell-shaped time sampling — drawing the corruption level near t=0.5 — accelerates masked diffusion language model training by up to ~4× without changing the final loss.
-
ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference
ChunkFlow achieves up to 1.28x step-time speedup and up to 49% lower peak GPU memory for DiT inference by using a first-order model to guide communication-aware chunked prefetching.