A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fateh, Fawad Javed, Ali, Ali Shah, Popattia, Murad, Nizamani, Usman, Konin, Andrey, Zia, M. Zeeshan, Tran, Quoc-Huy
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917546170515456
author Fateh, Fawad Javed
Ali, Ali Shah
Popattia, Murad
Nizamani, Usman
Konin, Andrey
Zia, M. Zeeshan
Tran, Quoc-Huy
author_facet Fateh, Fawad Javed
Ali, Ali Shah
Popattia, Murad
Nizamani, Usman
Konin, Andrey
Zia, M. Zeeshan
Tran, Quoc-Huy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15215
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics
Fateh, Fawad Javed
Ali, Ali Shah
Popattia, Murad
Nizamani, Usman
Konin, Andrey
Zia, M. Zeeshan
Tran, Quoc-Huy
Robotics
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.
title A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics
topic Robotics
url https://arxiv.org/abs/2604.15215