Learning Native Continuation for Action Chunking Flow Policies

• URL: http://arxiv.org/abs/2602.12978v1
• Date: Fri, 13 Feb 2026 14:56:06 GMT
• Title: Learning Native Continuation for Action Chunking Flow Policies
• Abstract summary: Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries.<n>We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies.<n>Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time.
• Score: 40.56048312294812
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries. Real-Time Chunking (RTC) alleviates this issue but is external to the policy, leading to spurious multimodal switching and trajectories that are not intrinsically smooth. We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies. Specifically, Legato initializes denoising from a schedule-shaped mixture of known actions and noise, exposing the model to partial action information. Moreover, Legato reshapes the learned flow dynamics to ensure that the denoising process remains consistent between training and inference under per-step guidance. Legato further uses randomized schedule condition during training to support varying inference delays and achieve controllable smoothness. Empirically, Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time. Extensive real-world experiments show that Legato consistently outperforms RTC across five manipulation tasks, achieving approximately 10% improvements in both trajectory smoothness and task completion time.

Related papers

• StructRL: Structured Action-Space Exploration for Flow-Based VLAs [81.43458629514139]
  Flow-based Vision-Language-Action models are now widely used for continuous robotic manipulation.<n>Online reinforcement learning is emerging as a key technique for adapting them to new tasks.<n>We show that effective robot exploration calls for structured noise: temporally smooth and scaled differently across action groups.
  arXiv  Detail & Related papers  (2026-08-15T09:31:29Z)
• 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)
• VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon [40.99993238069073]
  VLA-Corrector is a lightweight corrective inference framework for action-chunked Vision-Language-Action policies.<n>It can be integrated into different VLA models without further retraining the VLA backbone.<n>It mitigates the trade-off imposed by static horizons between execution and policy-call frequency.
  arXiv  Detail & Related papers  (2026-07-02T07:18:53Z)
• dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models [49.497309561043004]
  We propose textbfdVLA-RL, shifting the learning objective from the marginal action probability to the joint probability of the sampled generation path.<n>Our approach achieves a success rate of textbf99.7% on LIBERO.<n>It also establishes strong VLA-based results on RoboTwin 2.0 by delivering a textbf30.6% improvement over the SFT baseline.
  arXiv  Detail & Related papers  (2026-06-22T17:19:03Z)
• DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors [57.944744187489185]
  We propose DiscreteRTC, which replaces external corrections with native unmasking.<n>DiscreteRTC is simpler to implement with 0 lines of code for async inpainting, faster at inference with only 0.7x computation compared with generating actions from scratch, and better at execution with 50% higher success rate in real-world dynamic pick task compared with flow-based RTC.
  arXiv  Detail & Related papers  (2026-04-27T23:04:03Z)
• AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation [36.801575461006664]
  A central challenge in mobile manipulation is preserving plausible action models while remaining reactive during execution.<n>We present AnchorVLA, a diffusion-based VLA policy for mobile manipulation built on the core insight that when sampling begins near a plausible solution manifold, extensive denoising is unnecessary.
  arXiv  Detail & Related papers  (2026-04-02T03:29:04Z)
• Trust Region Continual Learning as an Implicit Meta-Learner [3.705371747297478]
  We study a hybrid perspective: emphtrust region continual learning that combines generative replay with a Fisher-metric trust region constraint.<n>We show that, under local approximations, the resulting update admits a MAML-style interpretation with a single implicit inner step.<n>This yields an emergent meta-learning property in continual learning.
  arXiv  Detail & Related papers  (2026-02-02T18:19:16Z)
• VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots [5.308743386891208]
  Vision-Language-Action (VLA) models have achieved remarkable breakthroughs in robotics.<n>The strategies for fusing a queue of successive action chunks have a profound impact on the overall performance of VLA models.<n>Existing methods suffer from jitter, stalling, or even pauses in robotic action execution.<n>This paper introduces VLA-RAIL, a novel framework designed to conduct model inference and robot motion control asynchronously.
  arXiv  Detail & Related papers  (2025-12-31T06:59:42Z)
• 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)
• Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings [13.325021114990241]
  Catastrophic forgetting remains a critical challenge in continual learning for large language models.<n>We propose Dynamic Orthogonal Continual (DOC) fine-tuning, a novel approach that tracks the drift of functional directions and dynamically updates them during the fine-tuning process.
  arXiv  Detail & Related papers  (2025-09-28T13:55:05Z)
• Real-Time Execution of Action Chunking Flow Policies [49.1574468325115]
  This paper presents a novel inference-time algorithm that enables asynchronous execution of action interacting systems.<n>It is applicable to any diffusion- or VLA-based systems executing out of the box with no re-training.<n>Results show that RTC is fast, performant, and uniquely robust to inference manipulation.
  arXiv  Detail & Related papers  (2025-06-09T01:01:59Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Boundary-Denoising for Video Activity Localization [57.9973253014712]
  We study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. Experiments show that DenoiseLoc advances %in several video activity understanding tasks.
  arXiv  Detail & Related papers  (2023-04-06T08:48:01Z)
• Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp [119.69304125647785]
  This paper introduces a concise yet powerful method to construct Continuous Transition. Specifically, we propose to synthesize new transitions for training by linearly interpolating the consecutive transitions. To keep the constructed transitions authentic, we also develop a discriminator to guide the construction process automatically.
  arXiv  Detail & Related papers  (2020-11-30T01:20:23Z)

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.