用双层流模型采样，让生成模型又快又准
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
- 构建内层流模型模拟马尔可夫转移，实现高效采样
- 在文生图任务中提升性能且消除效率与随机性的权衡
- 无需重训练，可直接接入现有生成模型
流匹配和扩散模型在推理时通过奖励对齐算法可显著提升性能，但效率仍是主要瓶颈。我们发现，现有方法普遍依赖SDE采样来生成马尔可夫转移，这比ODE采样更慢且效果更差。为此，我们提出GLASS Flows，一种新采样范式，通过“流匹配模型中的流匹配模型”来模拟马尔可夫转移。研究表明，该“内层”流匹配模型可从预训练模型中直接获取，无需重新训练，兼具ODE的高效性与SDE的随机演化特性。在大规模文生图模型上，GLASS Flows成功消除了随机性与效率之间的权衡。结合Feynman-Kac Steering，其进一步提升了当前最先进的文本到图像生成性能，成为一种简单、可直接替换的推理时扩展方案。
原文摘要 · Abstract (English)
The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While several algorithms were proposed, we demonstrate that a common bottleneck is the sampling method these algorithms rely on: many algorithms require to sample Markov transitions via SDE sampling, which is significantly less efficient and often less performant than ODE sampling. To remove this bottleneck, we introduce GLASS Flows, a new sampling paradigm that simulates a "flow matching model within a flow matching model" to sample Markov transitions. As we show in this work, this "inner" flow matching model can be retrieved from a pre-trained model without any re-training, combining the efficiency of ODEs with the stochastic evolution of SDEs. On large-scale text-to-image models, we show that GLASS Flows eliminate the trade-off between stochastic evolution and efficiency. Combined with Feynman-Kac Steering, GLASS Flows improve state-of-the-art performance in text-to-image generation, making it a simple, drop-in solution for inference-time scaling of flow and diffusion models.
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。