# ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning

arXiv: https://arxiv.org/abs/2512.07371 · HTML: https://mlsanity.com/paper/2512.07371/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 22 of 22)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (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)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets](https://mlsanity.com/paper/2109.13396/) (2021)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [ALOHA Unleashed: A Simple Recipe for Robot Dexterity](https://mlsanity.com/paper/2410.13126/) (2024)
- [TACO: Learning Task Decomposition via Temporal Alignment for Control](https://mlsanity.com/paper/1803.01840/) (2018)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning](https://mlsanity.com/paper/2502.17432/) (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)
- [Subconscious Robotic Imitation Learning](https://mlsanity.com/paper/2412.20368/) (2024)

## Built on by (most cited first, 4 of 4)

- [Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation](https://mlsanity.com/paper/2603.20658/) (2026)
- [TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies](https://mlsanity.com/paper/2606.06491/) (2026)
- [Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Model](https://mlsanity.com/paper/2602.18813/) (2026)
- [EgoSpeedUp: Transferring Human Manipulation Tempo to Robot Policies](https://mlsanity.com/paper/2609.29310/) (2026)

## Abstract (arXiv)

Behavior-cloning based visuomotor policies enable precise manipulation but often inherit the slow, cautious tempo of human demonstrations, limiting practical deployment. However, prior studies on acceleration methods mainly rely on statistical or heuristic cues that ignore task semantics and can fail across diverse manipulation settings. We present ESPADA, a semantic and spatially aware framework that segments demonstrations using a VLM-LLM pipeline with 3D gripper-object relations, enabling aggressive downsampling only in non-critical segments while preserving precision-critical phases, without requiring extra data or architectural modifications, or any form of retraining. To scale from a single annotated episode to the full dataset, ESPADA propagates segment labels via Dynamic Time Warping (DTW) on dynamics-only features. Across both simulation and real-world experiments with ACT and DP baselines, ESPADA achieves approximately a 2x speed-up while maintaining success rates, narrowing the gap between human demonstrations and efficient robot control.