One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies

• URL: http://arxiv.org/abs/2603.12480v1
• Date: Thu, 12 Mar 2026 21:58:12 GMT
• Title: One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
• Abstract summary: One-Step Flow Policy (OFP) is a from-scratch self-distillation framework for high-fidelity, single-step action generation without a pre-trained teacher.<n> Evaluations across 56 diverse simulated manipulation tasks demonstrate that a one-step OFP achieves state-of-the-art results.
• Score: 18.743330791557522
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control frequency and harming performance in time-sensitive manipulation. To address this problem, we propose the One-Step Flow Policy (OFP), a from-scratch self-distillation framework for high-fidelity, single-step action generation without a pre-trained teacher. OFP unifies a self-consistency loss to enforce coherent transport across time intervals, and a self-guided regularization to sharpen predictions toward high-density expert modes. In addition, a warm-start mechanism leverages temporal action correlations to minimize the generative transport distance. Evaluations across 56 diverse simulated manipulation tasks demonstrate that a one-step OFP achieves state-of-the-art results, outperforming 100-step diffusion and flow policies while accelerating action generation by over $100\times$. We further integrate OFP into the $π_{0.5}$ model on RoboTwin 2.0, where one-step OFP surpasses the original 10-step policy. These results establish OFP as a practical, scalable solution for highly accurate and low-latency robot control.

Related papers

• PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation [10.164953732323463]
  PIER-Flow is a lightweight navigation policy for mobile robots.<n>It achieves a 98.85% success rate and zero collisions, with an average inference of $sim$1.29 ms.
  arXiv  Detail & Related papers  (2026-07-11T12:34:28Z)
• High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching [3.5570904967011505]
  Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions.<n>Existing one-step acceleration methods compress the whole generation process into a single large update, leading to spatial deviation, frequency distortion, and mode averaging.<n>This paper proposes a high-fidelity one-step generative visuomotor policy framework that addresses these issues with three complementary mechanisms.
  arXiv  Detail & Related papers  (2026-07-04T13:12:38Z)
• V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think [90.69263509098948]
  We introduce Variational GRPO, a method that integrates ELBO-based surrogates with the Group Relative Policy Optimization algorithm.<n>V-GRPO achieves state-of-the-art performance in text-to-image synthesis, while delivering a $2times$ speedup over MixGRPO and a $3times$ speedup over DiffusionNFT.
  arXiv  Detail & Related papers  (2026-04-25T17:03:21Z)
• A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model [112.9420001646428]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost.<n>We present A1, a fully open-source and transparent VLA framework designed for low-cost, high- throughput inference.<n>A1 achieves state-of-the-art success rates while significantly reducing inference cost.
  arXiv  Detail & Related papers  (2026-04-07T10:18:40Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation [18.70033095161235]
  We propose a framework that distills a Conditional Flow Matching expert into a fast single-step student via Implicit Likelihood Estimation (IMLE)<n>A bi-directional Chamfer distance provides a set-level objective that promotes both mode coverage and fidelity.<n>A unified perception encoder further integrates multi-view RGB, depth, point clouds, and proprioception into a geometry-aware representation.
  arXiv  Detail & Related papers  (2026-03-10T09:30:05Z)
• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation [65.13627721310613]
  Mean velocity policy (MVP) is a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation.<n>MVP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench.
  arXiv  Detail & Related papers  (2026-02-14T14:44:06Z)
• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• OMP: One-step Meanflow Policy with Directional Alignment [26.114675928221974]
  One-step MeanFlow Policy (OMP) designed for high-fidelity, real-time manipulation.<n>Experiments on Adroit and Meta-World benchmarks demonstrate that OMP outperforms state-of-the-art methods in success rate and trajectory accuracy.
  arXiv  Detail & Related papers  (2025-12-22T12:45:35Z)
• Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning [56.47948583452555]
  We introduce the Stepwise Flow Policy (SWFP) framework, founded on the key insight that discretizing the flow matching inference process via a fixed-step Euler scheme aligns it with the variational Jordan-Kinderlehrer-Otto principle from optimal transport.<n>SWFP decomposes the global flow into a sequence of small, incremental transformations between proximate distributions.<n>This decomposition yields an efficient algorithm that fine-tunes pre-trained flows via a cascade of small flow blocks, offering significant advantages.
  arXiv  Detail & Related papers  (2025-10-17T07:43:51Z)
• DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation [23.382067451764396]
  Flow-based generative models have emerged as a promising solution to learning distributions of actions.<n>Existing flow-based policies suffer from representation collapse, the inability to distinguish similar visual representations, leading to failures in precise manipulation tasks.<n>We propose DM1, a novel flow matching framework that integrates dispersive regularization into MeanFlow to prevent collapse while maintaining one-step efficiency.
  arXiv  Detail & Related papers  (2025-10-09T07:12:20Z)
• FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency [34.81668269819768]
  We propose FreqPolicy to exploit temporal information in robotic manipulation.<n>FreqPolicy first imposes frequency consistency constraints on flow-based visuomotor policies.<n>We show efficiency and effectiveness in real-world robotic scenarios with an inference frequency 93.5Hz.
  arXiv  Detail & Related papers  (2025-06-10T14:12:53Z)
• CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction [28.761494362934087]
  Coarse-to-Fine AutoRegressive Policy (CARP) is a novel paradigm for visuomotor policy learning.<n>It redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach.<n>CARP achieves competitive success rates, with up to a 10% improvement, and delivers 10x faster inference compared to state-of-the-art policies.
  arXiv  Detail & Related papers  (2024-12-09T18:59:18Z)
• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation [80.71541671907426]
  OneStep Diffusion Policy (OneDP) is a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator. OneDP significantly accelerates response times for robotic control tasks.
  arXiv  Detail & Related papers  (2024-10-28T17:54:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.