跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分36

透過數據空間迭代實現少步生成

Few-Step Generation via Data-Space Iteration

AI 導讀

研究提出數據空間迭代少步生成框架,直接在數據空間迭代修正生成結果,免除概率流的時間步離散化。於類別條件式 ImageNet 256x256 測試中,方法勝過標準離散化基線,並匹敵或超越經排程搜尋選出的變體,毋須按排程專門訓練。該方法只需對分佈匹配蒸餾(DMD)作少量修改即可整合。

正文

Published on Oct 8

Authors:

,

,

Abstract

Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires many network evaluations. Distillation can reduce this cost to one or a few evaluations; however, one-step generation often sacrifices quality, making few-step generation the practical operating regime. Existing few-step methods perform their iterative computation along the probability flow and therefore require a fixed, manually chosen timestep discretization. This discretization is often chosen heuristically and is expensive to tune; it may also be restrictive when refinement difficulty differs across samples or spatial locations. We introduce data-space iteration, a few-step generation framework that removes flow discretization altogether. Starting from noise, a shared generator directly refines its prediction in data space, with every iteration trained to produce the best sample permitted by its capacity. Our formulation integrates with distribution matching distillation (DMD) with minimal changes, enabling a controlled comparison between iteration methods under matched training settings. On class-conditional ImageNet 256x256, data-space iteration outperforms standard discretization baselines and matches or improves upon variants selected through schedule search, without requiring schedule-specific training. These results show that data-space iteration provides a simple and effective alternative to discretized flow-space iteration for fast generation.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.12102

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12102 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.12102 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12102 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co