Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.
One-step diffusion with distribution matching distillation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
PermuQuant lowers per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same group using a calibration-based acceptance rule.
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.
citing papers explorer
-
Representation Fr\'echet Loss for Visual Generation
Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.
-
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
PermuQuant lowers per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same group using a calibration-based acceptance rule.
-
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.