OFA-Diffusion Compression trains diffusion models once to yield multiple size-specific compressed subnetworks via restricted candidate spaces, importance-based channel allocation, and reweighting.
Efficientdm: Efficient quantization-aware fine-tuning of low-bit diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
citing papers explorer
-
OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner
OFA-Diffusion Compression trains diffusion models once to yield multiple size-specific compressed subnetworks via restricted candidate spaces, importance-based channel allocation, and reweighting.
-
Sampling-Aware Quantization for Diffusion Models
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.