BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation

Yunhong Min* · Juil Koo* · Seungwoo Yoo · Minhyuk Sung (* Equal Contribution)

KAIST

ICLR 2026

We introduce BézierFlow, a lightweight training approach for few-step generation with pretrained diffusion and flow models. BézierFlow achieves a 2–3× performance improvement for sampling with ≤ 10 NFEs while requiring only 15 minutes of training.

News

• [2026.01.27] 🔥 Our work has been accepted to ICLR 2026.

Code - To be released!