# Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation

arXiv: https://arxiv.org/abs/2603.20658 · HTML: https://mlsanity.com/paper/2603.20658/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 30)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model](https://mlsanity.com/paper/2509.09372/) (2025)
- [ALOHA Unleashed: A Simple Recipe for Robot Dexterity](https://mlsanity.com/paper/2410.13126/) (2024)
- [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [Training-Time Action Conditioning for Efficient Real-Time Chunking](https://mlsanity.com/paper/2512.05964/) (2025)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference](https://mlsanity.com/paper/2512.01031/) (2025)
- [State-wise Safe Reinforcement Learning: A Survey](https://mlsanity.com/paper/2302.03122/) (2023)
- [Running VLAs at Real-time Speed](https://mlsanity.com/paper/2510.26742/) (2025)
- [BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark](https://mlsanity.com/paper/2407.07788/) (2024)
- [SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies](https://mlsanity.com/paper/2506.11948/) (2025)
- [DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration](https://mlsanity.com/paper/2506.05064/) (2025)
- [On-Device Diffusion Transformer Policy for Efficient Robot Manipulation](https://mlsanity.com/paper/2508.00697/) (2025)
- [Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning](https://mlsanity.com/paper/2405.17031/) (2024)
- [Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation](https://mlsanity.com/paper/2511.18950/) (2025)
- [Critically fast pick-and-place with suction cups](https://mlsanity.com/paper/1809.03151/) (2018)
- [Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by Imitation Learning](https://mlsanity.com/paper/2410.16981/) (2024)
- [SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning](https://mlsanity.com/paper/2512.00062/) (2025)
- [ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning](https://mlsanity.com/paper/2512.07371/) (2025)

## Built on by (most cited first, 3 of 3)

- [When to Trust Imagination: Adaptive Action Execution for World Action Models](https://mlsanity.com/paper/2605.06222/) (2026)
- [VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon](https://mlsanity.com/paper/2607.01804/) (2026)
- [TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies](https://mlsanity.com/paper/2606.06491/) (2026)

## Abstract (arXiv)

While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Existing acceleration methods typically require policy retraining or costly online interactions, limiting their scalability for large-scale foundation models. In this paper, we propose Speedup Patch (SuP), a lightweight, policy-agnostic framework that enables plug-and-play acceleration using solely offline data. SuP introduces an external scheduler that adaptively downsamples action chunks provided by embodied policies to eliminate redundancies. Specifically, we formalize the optimization of our scheduler as a Constrained Markov Decision Process (CMDP) aimed at maximizing efficiency without compromising task performance. Since direct success evaluation is infeasible in offline settings, SuP introduces World Model based state deviation as a surrogate metric to enforce safety constraints. By leveraging a learned world model as a virtual evaluator to predict counterfactual trajectories, the scheduler can be optimized via offline reinforcement learning. Empirical results on simulation benchmarks (Libero, Bigym) and real-world tasks validate that SuP achieves an overall 1.8x execution speedup for diverse policies while maintaining their original success rates.