STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction

• URL: http://arxiv.org/abs/2602.08245v1
• Date: Mon, 09 Feb 2026 03:50:40 GMT
• Title: STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
• Authors: Jinhao Li, Yuxuan Cong, Yingqiao Wang, Hao Xia, Shan Huang, Yijia Zhang, Ningyi Xu, Guohao Dai,
• Abstract summary: iterative denoising leads to substantial inference latency, limiting control frequency in real-time closed-loop systems.<n>We propose STEP, a lightweighttemporal consistency prediction mechanism to construct high-quality warm-start actions.<n> STEP with 2 steps can achieve an average 21.6% and 27.5% higher success rate than BRIDGER and DDIM on the RoboMimic benchmark and real-world tasks.
• Score: 16.465783114087223
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the distribution of action sequences and capture multimodality. However, iterative denoising leads to substantial inference latency, limiting control frequency in real-time closed-loop systems. Existing acceleration methods either reduce sampling steps, bypass diffusion through direct prediction, or reuse past actions, but often struggle to jointly preserve action quality and achieve consistently low latency. In this work, we propose STEP, a lightweight spatiotemporal consistency prediction mechanism to construct high-quality warm-start actions that are both distributionally close to the target action and temporally consistent, without compromising the generative capability of the original diffusion policy. Then, we propose a velocity-aware perturbation injection mechanism that adaptively modulates actuation excitation based on temporal action variation to prevent execution stall especially for real-world tasks. We further provide a theoretical analysis showing that the proposed prediction induces a locally contractive mapping, ensuring convergence of action errors during diffusion refinement. We conduct extensive evaluations on nine simulated benchmarks and two real-world tasks. Notably, STEP with 2 steps can achieve an average 21.6% and 27.5% higher success rate than BRIDGER and DDIM on the RoboMimic benchmark and real-world tasks, respectively. These results demonstrate that STEP consistently advances the Pareto frontier of inference latency and success rate over existing methods.

Related papers

• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• ForeDiffusion: Foresight-Conditioned Diffusion Policy via Future View Construction for Robot Manipulation [37.67451041903772]
  Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences.<n>This paper proposes Foresight-Conditioned Diffusion (ForeDiffusion), by injecting the predicted future view representation into the diffusion process.<n>ForeDiffusion achieves an average success rate of 80% for the overall task, significantly outperforming the existing mainstream diffusion methods by 23% in complex tasks.
  arXiv  Detail & Related papers  (2026-01-19T10:28:42Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models [64.92045568376705]
  Coherent Contextual Decoding (CCD) is a novel inference framework built upon two core innovations.<n>CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence.<n>Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step.
  arXiv  Detail & Related papers  (2025-11-26T09:49:48Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting [52.6508222408558]
  We introduce Elucidated Rolling Diffusion Models (ERDM)<n>ERDM is the first framework to unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM)<n>On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5circ resolution, ERDM consistently outperforms key diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-06-24T21:44:31Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)
• Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillation [29.90613565503628]
  We propose the Score and Distribution Matching Policy (SDM Policy) for visual-motor policy learning.<n>SDM Policy transforms diffusion-based policies into single-step generators through a two-stage optimization process.<n>It achieves a 6x inference speedup while having state-of-the-art action quality.
  arXiv  Detail & Related papers  (2024-12-12T13:22:02Z)
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling [51.38330727868982]
  We show how action chunking impacts the divergence between a learner and a demonstrator.<n>We propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation.<n>Our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation [48.08416841005715]
  We introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency.
  arXiv  Detail & Related papers  (2024-06-14T14:49:12Z)
• ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertainties [6.865435680843742]
  We propose a novel diffusion-based, acceleratable framework that adeptly predicts future trajectories of agents with enhanced resistance to noise. Our method meets the rigorous real-time operational standards essential for autonomous vehicles. It achieves significant improvement in multi-agent motion prediction on the Argoverse 1 motion forecasting dataset.
  arXiv  Detail & Related papers  (2024-05-01T18:16:55Z)
• GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction [15.731398013255179]
  We propose a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.<n>A two-stage tree sampling algorithm is presented, which leverages common features to reduce the inference time and improve accuracy for multi-modal prediction.<n> Experimental results demonstrate that our proposed framework achieves comparable state-of-the-art performance with real-time inference speed in public datasets.
  arXiv  Detail & Related papers  (2023-11-25T03:55:06Z)

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.