# Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation

arXiv: https://arxiv.org/abs/2604.24681 · HTML: https://mlsanity.com/paper/2604.24681/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2026.

## Built on by (most cited first, 3 of 3)

- [EgoRecovery: Acquiring Failure Recovery Ability Through Human Recovery Demonstration](https://mlsanity.com/paper/2607.19745/) (2026)
- [Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models](https://mlsanity.com/paper/2608.23478/) (2026)
- [GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos](https://mlsanity.com/paper/2609.17099/) (2026)

## Abstract (arXiv)

Human videos contain rich manipulation priors, but using them for robot learning remains difficult because raw observations entangle scene understanding, human motion, and embodiment-specific action. We introduce MoT-HRA, a hierarchical vision-language-action framework that learns human-intention priors from large-scale human demonstrations. We first curate HA-2.2M, a 2.2M-episode action-language dataset reconstructed from heterogeneous human videos through hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment. On top of this dataset, MoT-HRA factorizes manipulation into three coupled experts: a vision-language expert predicts an embodiment-agnostic 3D trajectory, an intention expert models MANO-style hand motion as a latent human-motion prior, and a fine expert maps the intention-aware representation to robot action chunks. A shared-attention trunk and read-only key-value transfer allow downstream control to use human priors while limiting interference with upstream representations. Experiments on hand motion generation, simulated manipulation, and real-world robot tasks show that MoT-HRA improves motion plausibility and robust control under distribution shift.