We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning. We first propose a hierarchical approach, which consists of two successive levels of vector quantization. In particular, the lower level assigns input actions to fine-grained subclusters, while the higher level further maps fine-grained subclusters to clusters. Our hierarchical approach outperforms the non-hierarchical counterpart, while mainly exploiting spatial information by reconstructing input actions. Furthermore, we extend our approach by utilizing both spatial and temporal cues, forming a hierarchical spatiotemporal action tokenizer, namely HiST-AT. Specifically, our hierarchical spatiotemporal approach conducts multi-level clustering, while simultaneously recovering input actions and their associated timestamps. Finally, extensive evaluations on multiple simulation and real robotic manipulation benchmarks show that our approach establishes a new state-of-the-art performance in in-context imitation learning.
@article{arxiv.2604.15215,
title = {A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics},
author = {Fawad Javed Fateh and Ali Shah Ali and Murad Popattia and Usman Nizamani and Andrey Konin and M. Zeeshan Zia and Quoc-Huy Tran},
journal= {arXiv preprint arXiv:2604.15215},
year = {2026}
}