让去噪过程更聪明，用可学习的加噪策略提升生成效率
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
- 设计可学习的非马尔可夫加噪过程，让模型更好理解目标分布
- 在相同采样步数下，生成图像质量显著优于传统离散扩散模型
- 适合追求快速高质量生成的场景，如实时内容创作
离散扩散模型在多个领域表现出强大生成能力，但为提升效率，通常采用因子化分布参数化生成（反向）过程，导致模型难以在少步内学习目标分布，需大量计算成本完成采样。为此，本文提出前向可学习离散扩散（FLDD），引入可学习的前向（加噪）过程。不同于固定马尔可夫前向链，采用非马尔可夫形式，学习边缘分布与后验分布。该设计使生成过程保持因子化，同时匹配由加噪过程定义的目标分布。所有参数在标准变分目标下端到端训练。在多个基准测试中，给定相同采样步数时，本方法生成样本质量显著高于使用相同反向参数化的传统离散扩散模型。
原文摘要 · Abstract (English)
Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized distributions, which makes it difficult for the model to learn the target process in a small number of steps and necessitates a long, computationally expensive sampling procedure. To reduce the gap between the target and model distributions and enable few-step generation, we propose Forward-Learned Discrete Diffusion (FLDD), which introduces discrete diffusion with a learnable forward (noising) process. Rather than fixing a Markovian forward chain, we adopt a non-Markovian formulation with learnable marginal and posterior distributions. This allows the generative process to remain factorized while matching the target defined by the noising process. We train all parameters end-to-end under the standard variational objective. Experiments on various benchmarks show that, for a given number of sampling steps, our approach produces a higher quality samples than conventional discrete diffusion models using the same reverse parameterization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。