arXiv (All)
open access
A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation
Distribution-matching distillation enables high-quality image generation in only a few denoising steps. However, distilled student models often map different initial noise samples to similar outputs under the same prompt. To locate where diversity is lost, we compare the teacher and student along th
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Data Unlearning via Inverse Distillation#1130941
- CrossDistill: Balancing Quality and Diversity via Trajectory-Level Hybrid Few-Step Distillation#1160771
- Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation#998806
- Data-free Multistep Diffusion Distillation#1345128
- Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher#974116
Record · ID 1468714
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive