# H2RB co-trains with human demos and robot data to adapt VLA policies

- Source: HuggingFace Daily Papers
- Published: 2026-11-03T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/c5edvr2879uktxxsk99imdsmx
- Original: https://huggingface.co/papers/2611.04391

## Summary

The study proposes H2RB, a human-robot co-training framework that adapts pretrained VLA policies on unpaired human and robot demonstrations through geometry-anchored alignment and a decoupled-decoder tokenizer. In real-world tasks, object transfer performance improved from 8.0 to 51.8, and the skill transfer score reached 62.7, while the co-training baseline completely failed to transfer human demonstration skills. Out-of-distribution transfer under object placement changes also improved from 6.0 to 45.3.