# HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface

arXiv: https://arxiv.org/abs/2609.20659 · HTML: https://mlsanity.com/paper/2609.20659/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models.
- Builds on 36 of its 42 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)

## Builds on (most cited first, 30 of 36)

- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [Human-in-the-Loop Imitation Learning using Remote Teleoperation](https://mlsanity.com/paper/2012.06733/) (2020)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers](https://mlsanity.com/paper/2407.10353/) (2024)
- [TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction](https://mlsanity.com/paper/2405.10315/) (2024)
- [GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2512.01801/) (2025)
- [FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset](https://mlsanity.com/paper/2409.19499/) (2024)
- [Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision](https://mlsanity.com/paper/2206.14349/) (2022)
- [SOP: A Scalable Online Post-Training System for Vision-Language-Action Models](https://mlsanity.com/paper/2601.03044/) (2026)
- [PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection](https://mlsanity.com/paper/2212.04708/) (2022)
- [chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies](https://mlsanity.com/paper/2602.09021/) (2026)
- [Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism](https://mlsanity.com/paper/2506.09176/) (2025)

## Built on by (most cited first, 1 of 1)

- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)

## Abstract (arXiv)

Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuning (SFT) on task-specific demonstrations provides a step toward deployment, but faces two persistent limitations: static data provide limited coverage of out-of-distribution states, and standard imitation objectives do not distinguish progressing behavior from less useful data. Interactive post-training can address these limitations, but typically requires repeated policy execution and human intervention on a physical robot. We introduce HIL-UMI, a policy-guided Universal Manipulation Interface (UMI) framework for robot-free human-in-the-loop VLA post-training. During handheld UMI demonstrations, HIL-UMI queries the current policy on the same observation stream without executing its predictions. The Energy Score compares the human action trajectory with policy inference and triggers collection when their discrepancy indicates an out-of-distribution region. In a separate feedback loop, low online advantage predictions identify essential segments for refining a progress-based advantage estimator. The updated estimator then guides advantage-conditioned behavioral cloning using a balanced mixture of base demonstrations and new policy data. This design preserves the iterative and policy-aware nature of human-in-the-loop learning while decoupling data collection from robot deployment. Experiments on four real-world tasks spanning long-horizon and precise manipulation show that HIL-UMI achieves consistent improvement over SFT and benefits from both targeted collection and advantage refinement. Moreover, HIL-UMI outperforms HG-DAgger on Clean Up Table with lower per-frame collection time, suggesting a scalable path for VLA post-training across operators and locations.