← Back to Benchmarks
simmediummanipulationmetric · varies

One Step Is Enough: Dispersive MeanFlow Policy Optimization

Description

Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limiting deployment in time-critical scenarios. We propose Dispersive MeanFlow Policy Optimization (DMPO), a unified framework that enables true one-step generation through three key components: MeanFlow for mathematically-derived single-step inference without knowledge distillation, dispersive regularization to prev

Source

http://arxiv.org/abs/2601.20701v1