# Real-Time Robot Execution with Masked Action Chunking

arXiv: https://arxiv.org/abs/2601.20130 · HTML: https://mlsanity.com/paper/2601.20130/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2026.

## Built on by (most cited first, 20 of 20)

- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking](https://mlsanity.com/paper/2607.24008/) (2026)
- [PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking](https://mlsanity.com/paper/2606.00537/) (2026)
- [DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors](https://mlsanity.com/paper/2604.25050/) (2026)
- [Noise-Space Attribution and Control of Chunk-Boundary Artifact](https://mlsanity.com/paper/2603.11642/) (2026)
- [BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control](https://mlsanity.com/paper/2608.13924/) (2026)
- [RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution](https://mlsanity.com/paper/2608.15924/) (2026)
- [StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models](https://mlsanity.com/paper/2608.26067/) (2026)
- [RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models](https://mlsanity.com/paper/2609.34170/) (2026)
- [Action Chunking Proximal Policy Optimization with Feedback Correction](https://mlsanity.com/paper/2609.36250/) (2026)
- [Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks](https://mlsanity.com/paper/2609.36471/) (2026)
- [Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control](https://mlsanity.com/paper/2609.37772/) (2026)
- [From Local Whole-Body VLA Behaviors to Scene-Scale Aerial Manipulation](https://mlsanity.com/paper/2609.39670/) (2026)
- [Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation](https://mlsanity.com/paper/2609.39822/) (2026)
- [World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models](https://mlsanity.com/paper/2610.02323/) (2026)
- [Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design](https://mlsanity.com/paper/2610.05062/) (2026)
- [Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control](https://mlsanity.com/paper/2610.06582/) (2026)
- [RealtimeWAM: One-Step Asynchronous World Action Models](https://mlsanity.com/paper/2610.06617/) (2026)
- [REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models](https://mlsanity.com/paper/2610.12007/) (2026)
- [Chronos Policy: Learning Robot Policies on Physical Time](https://mlsanity.com/paper/2610.13929/) (2026)

## Abstract (arXiv)

Real-time execution is essential for cyber-physical systems such as robots. These systems operate in dynamic real-world environments where even small delays can undermine responsiveness and compromise performance. Asynchronous inference has recently emerged as a system-level paradigm for real-time robot manipulation, enabling the next action chunk to be predicted while the current one is being executed. While this approach achieves real-time responsiveness, naive integration often results in execution failure. Previous methods attributed this failure to inter-chunk discontinuity and developed test-time algorithms to smooth chunk boundaries. In contrast, we identify another critical yet overlooked factor: intra-chunk inconsistency, where the robot's executed action chunk partially misaligns with its current perception. To address this, we propose REMAC, which learns corrective adjustments on the pretrained policy through masked action chunking, enabling the policy to remain resilient under mismatches between intended actions and actual execution during asynchronous inference. In addition, we introduce a prefix-preserved sampling procedure to reinforce inter-chunk continuity. Overall, our method delivers more reliable policies without incurring additional latency. Extensive experiments in both simulation and real-world settings demonstrate that our method enables faster task execution, maintains robustness across varying delays, and consistently achieves higher completion rates.