# Scalable Behavior Cloning with Open Data, Training, and Evaluation

arXiv: https://arxiv.org/abs/2606.27375 · HTML: https://mlsanity.com/paper/2606.27375/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2026.

## Built on by (most cited first, 10 of 10)

- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents](https://mlsanity.com/paper/2610.02204/) (2026)
- [Hydra-0: Action Flow for Generalist World Modeling and Control](https://mlsanity.com/paper/2608.18077/) (2026)
- [4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes](https://mlsanity.com/paper/2610.03715/) (2026)
- [InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data](https://mlsanity.com/paper/2609.31394/) (2026)
- [Pre-training Visual Dexterity in Simulation](https://mlsanity.com/paper/2608.15917/) (2026)
- [From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention](https://mlsanity.com/paper/2609.21788/) (2026)
- [EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning](https://mlsanity.com/paper/2610.08726/) (2026)
- [Video Prediction Policy 2: Predict Better, Act Better](https://mlsanity.com/paper/2610.10270/) (2026)
- [WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions](https://mlsanity.com/paper/2610.18826/) (2026)

## Abstract (arXiv)

We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500 hours of data spanning over 130K episodes across 195 diverse tasks. Furthermore, we open-source our accessible hardware setup, training infrastructure, and simulation pipeline. We also release 400 hours of sim-teleop data and provide a co-training recipe that produces correlated simulation and real-world evaluation, offering a reliable proxy for ablating model-design and training decisions before costly real-world evaluation. We explore various training recipes and compare common architectural choices for Diffusion Transformers (DiT) and Vision-Language-Action (VLA) models, grounding our findings in real-world evaluations. The resulting policies successfully execute dexterous tasks such as box folding and extracting credit cards from wallets. By providing a reproducible toolkit, we aim to place researchers on an equal footing, establishing the necessary foundation to learn the ABCs of Behavior Cloning together as a community.