{"ID":5937966,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T13:09:31.386604174Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03865","arxiv_id":"2607.03865","title":"High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching","abstract":"Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions, but their multi-step sampling or ODE solving introduces inference latency. Existing one-step acceleration methods often compress the whole generation process into a single large update, leading to spatial deviation, frequency distortion, and mode averaging. This paper proposes a high-fidelity one-step generative visuomotor policy framework that addresses these issues with three complementary mechanisms. Recursive Consistent Action Flow (RCAF) uses recursive correction to compensate for spatial truncation errors and align one-step predictions with refined flow trajectories. Dual-Timestep Frequency Consistency (DTFC) preserves high-frequency manipulation details through adaptive spectral consistency across flow timesteps. Contrastive Flow Matching (CFM) separates entangled action flows with a margin-based repulsive objective, reducing ambiguous actions in multimodal manipulation. Experiments on RoboTwin, RoboTwin 2.0, Adroit, DexArt, and real-world robot platforms show that the proposed method achieves competitive or superior performance compared with strong 10-step generative policy baselines while requiring only one forward pass (1 NFE), enabling low-latency visuomotor control.","short_abstract":"Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions, but their multi-step sampling or ODE solving introduces inference latency. Existing one-step acceleration methods often compress the whole generation process into a single large u...","url_abs":"https://arxiv.org/abs/2607.03865","url_pdf":"https://arxiv.org/pdf/2607.03865v1","authors":"[\"Yuran Chen\",\"Xinye Cai\",\"Zhonglin Gong\",\"Yang Huang\"]","published":"2026-07-04T13:12:38Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}