DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

Mashrur M. Morshed

Keywords: Diverse sampling, flow matching, determinantal point processes

TL;DR: Under a fixed sampling budget, covering more modes with flow matching models by using determinantal point processes.

Abstract: Many real-world applications of flow generative models desire a diverse set of samples covering multiple modes of the target distribution. However, the predominant approach for obtaining diverse sets is not sample-efficient, as it involves independently obtaining many samples from the source distribution and mapping them through the flow until the desired mode coverage is achieved. As an alternative to repeated sampling, we introduce DiverseFlow---a training-free, inference-time approach to improve the diversity of flow models. Our key idea is to employ a determinantal point process to induce a coupling between the samples and drive sample diversity under a fixed sampling budget. We demonstrate the efficacy of DiverseFlow for tasks where sample efficient diversity is highly desirable---text-guided image generation with polysemous words, inverse problems like large-hole inpainting, and class-conditional image synthesis.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3905