Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-554
In Stable Diffusion 1.4, 1.5, 2.0, and 3.0, parameters with the smallest absolute values (below ~10^-3) do not contribute to the generative process, and this ineffectiveness is caused by stochastic training dynamics rather than architectural redundancy.