ArXiv TLDR

M. Zeeshan Zia

2 papers · Latest:

Robotics

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

HiST-AT is a new hierarchical spatiotemporal action tokenizer that achieves state-of-the-art in-context imitation learning for robotics.

2604.15215
Computer Vision

Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization

This paper introduces a hierarchical spatiotemporal vector quantization framework for unsupervised skeleton-based action segmentation, achieving SOTA.

2604.15196

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.