Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies

• URL: http://arxiv.org/abs/2606.03847v1
• Date: Tue, 02 Jun 2026 16:26:32 GMT
• Title: Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
• Abstract summary: Action chunking has become a common inference strategy for flow-based robot policies.<n>We propose DVAC, a test-time method that adaptively determines how many actions to execute from each predicted chunk.<n>Experiments on LIBERO, RoboTwin, CALVIN, and real-world manipulation show that DVAC improves task success while reducing replanning frequency.
• Score: 18.476299874941592
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Action chunking has become a common inference strategy for flow-based robot policies, improving action coherence by modeling multi-step temporal dependencies in demonstrations. However, the execution horizon is still typically set as an empirical fixed value, overlooking that predictable free-space motions and precision-critical interaction phases often require different replanning frequencies. In this work, we first show that the denoising process of flow-based policies contains an intrinsic signal of task phases: clean-action estimates remain stable during predictable motion phases, but fluctuate more strongly around contact-rich or precision-sensitive operations. Motivated by this observation, we propose DVAC (Denoising-Variance Adaptive Chunking), a test-time method that adaptively determines how many actions to execute from each predicted chunk. DVAC measures the variance of clean-action estimates over the final denoising steps, executes the stable low-variance prefix, and replans before high-variance future actions are committed. To transfer across tasks and rollouts, DVAC further calibrates the threshold with a rolling estimate of the local variance scale. Experiments on LIBERO, RoboTwin, CALVIN, and real-world manipulation show that DVAC improves task success while reducing replanning frequency. With a $π_{0.5}$-based policy, DVAC improves LIBERO success from 94.75% to 98.00% and reduces replanning by 43.0%, while also yielding aggregate gains on RoboTwin and CALVIN and improving real-world execution efficiency.

Related papers

• SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies [26.372187124257362]
  Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation.<n>We propose SEAM (Smooth Execution of Action-Chunked Motion), a training-free inference-time method for flow matching VLAs.<n>On LIBERO-10 with pi_0.5, SEAM reduces boundary jerk by 28%, reduces chunk transition discontinuity by 27%, preserves baseline-level task success, and keeps denoising-loop cost near the unguided baseline.
  arXiv  Detail & Related papers  (2026-07-06T02:32:10Z)
• SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending [55.764018145256216]
  We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
  arXiv  Detail & Related papers  (2026-06-27T01:32:16Z)
• QPILOTS: Efficient Test-Time Q-Steering for Flow Policies [20.217020870532686]
  QPILOTS is a method that leaves the original policy unmodified and steers the denoising process at inference time.<n>On a standard offline-to-online RL benchmark, QPILOTS achieves the best aggregate performance, reaching an average success rate of 90% across 50 tasks.
  arXiv  Detail & Related papers  (2026-06-11T18:22:03Z)
• Q-VGM: Q-Guided Value-Gradient Matching for Flow-Matching VLA Policies [14.519898493996891]
  We propose Q-Guided Value-Gradient Matching (Q-VGM) as an off-policy reinforcement learning (RL) method.<n>Q-VGM sidesteps issues by leveraging VGG-Flow, a value-gradient view of flow alignment in generative modeling.<n>On LIBERO, Q-VGM raises the average success rate from 75.0% to 92.5%; on RoboTwin 2.0, from 76.4% to 87.2%; and on two real-robot tabletop tasks, from 40.0% to 67.5%.
  arXiv  Detail & Related papers  (2026-06-06T07:10:25Z)
• Actor-Critic with Active Importance Sampling [61.41272490044518]
  This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm.<n>AISAC is an extension of the Actor-Critic framework for reducing variance in policy gradient estimation.<n> Experiments show improved learning speed, sample efficiency, and training compared to standard Actor-Critic methods.
  arXiv  Detail & Related papers  (2026-05-08T01:21:32Z)
• SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data [49.370849653460716]
  We propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation signal as an automated early-stopping mechanism.<n> evaluated on 25 continuous control tasks from the Minari benchmark suite.<n>SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x.
  arXiv  Detail & Related papers  (2026-05-07T08:32:09Z)
• CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies [26.36935074374452]
  Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency.<n>We propose CF-VLA, a coarse-to-fine two-stage formulation that restructures action generation into a coarse-to-fine step.<n>We show that our method establishes a strong efficiency-performance frontier under low-NFE (Number of Function Evaluations) regimes.
  arXiv  Detail & Related papers  (2026-04-27T15:51:40Z)
• AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models [60.04879435087352]
  Vision-language-action (VLA) policies generate actions within a single unified space.<n>We propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement.<n> Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones.
  arXiv  Detail & Related papers  (2026-04-20T04:25:24Z)
• ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching [14.421249343302028]
  Flow Matching (FM) policies have emerged as an efficient backbone for robotic control.<n>We propose ScoRe-Flow, a score-based RL fine-tuning method to achieve decoupled control over the mean and variance of transitions.
  arXiv  Detail & Related papers  (2026-04-13T03:56:37Z)
• 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)
• STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction [16.465783114087223]
  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.
  arXiv  Detail & Related papers  (2026-02-09T03:50:40Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• 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)

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.