# Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation

arXiv: https://arxiv.org/abs/2609.26672 · HTML: https://mlsanity.com/paper/2609.26672/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Failure recovery and robustness, one of 13 directions in Vision-language-action models.
- Builds on 40 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Placed in

- Vision-language-action models / [Failure recovery and robustness](https://mlsanity.com/vla/failure-recovery-and-robustness/)

## Builds on (most cited first, 30 of 40)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers](https://mlsanity.com/paper/2409.20537/) (2024)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations](https://mlsanity.com/paper/2207.10050/) (2022)
- [DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration](https://mlsanity.com/paper/2303.06885/) (2023)
- [Data Quality in Imitation Learning](https://mlsanity.com/paper/2306.02437/) (2023)
- [Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models](https://mlsanity.com/paper/2406.04806/) (2024)
- [Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning](https://mlsanity.com/paper/2408.14037/) (2024)
- [Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/2503.24361/) (2025)
- [PoCo: Policy Composition from and for Heterogeneous Robot Learning](https://mlsanity.com/paper/2402.02511/) (2024)
- [Robot Data Curation with Mutual Information Estimators](https://mlsanity.com/paper/2502.08623/) (2025)
- [Eliciting Compatible Demonstrations for Multi-Human Imitation Learning](https://mlsanity.com/paper/2210.08073/) (2022)
- [CUPID: Curating Data your Robot Loves with Influence Functions](https://mlsanity.com/paper/2506.19121/) (2025)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [Ambient Diffusion Omni: Training Good Models with Bad Data](https://mlsanity.com/paper/2506.10038/) (2025)
- [Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning](https://mlsanity.com/paper/2310.14196/) (2023)
- [Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation](https://mlsanity.com/paper/2401.08957/) (2024)

## Abstract (arXiv)

Training vision-language-action (VLA) models for high-precision manipulation typically requires task-specific, high-quality data (e.g., teleoperation), which is slow and expensive to collect. To reduce this burden without compromising manipulation precision, we propose varepsilon4P (Imperfection for Precision), a simple yet effective method that "upcycles" two otherwise discarded data sources: (1) low-precision data from the target task and (2) high-precision data from mismatched tasks. Rather than naively mixing these imperfect data sources throughout co-training, varepsilon4P controls where each source contributes along the flow-matching trajectory. Specifically, low-precision, target-task data is used at high noise to preserve high-level task context and high-precision, task-mismatched data is used at low noise to transfer low-level action precision. Through real-robot experiments on both sub-millimeter, high-precision tasks and coarse-grained tasks, we demonstrate that the proposed method (1) effectively leverages additional imperfect data to improve policy performance by up to 31.7 percentage points, and (2) can replace an equal amount of task-specific, high-quality data with an average performance drop of only 4.2 percentage points. Overall, varepsilon4P points toward a scalable paradigm for high-precision manipulation, in which heterogeneous, imperfect data can be systematically repurposed to reduce reliance on costly task-specific, high-quality data. More details are available at https://varepsilon4p.github.io/.