ImageNet Classification with Deep Convolutional Neural Networks
A deep convolutional network demonstrated how data, GPU computation and learned representations could transform visual recognition.
THE RESEARCH ATLAS
UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos
A dataset, VLA policy and capture setup connect human demonstrations to control across different dexterous hands.
Institution and location sources
Location refers to credited institutions or the listed organization, not author citizenship or an exhaustive collaboration list.
Why read this
Pay attention to embodiment alignment and the evidence for transfer between hands.
Citation
@misc{zhang2026unidex,
title = {UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos},
author = {Gu Zhang and Qicheng Xu and Haozhe Zhang and Jianhan Ma and Long He and Yiming Bao and Zeyu Ping and Zhecheng Yuan and Chenhao Lu and Chengbo Yuan and Tianhai Liang and Xiaoyu Tian and Maanping Shao and Feihong Zhang and Mingyu Ding and Yang Gao and Hao Zhao and Hang Zhao and Huazhe Xu},
year = {2026},
eprint = {2603.22264},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2603.22264}
}Rights remain with the original authors. Refer to the original source for citations and licensing.
Related research
Denoising Diffusion Probabilistic Models
A generative model learns to reverse a gradual noise process, establishing an influential approach to image synthesis.
Learning Transferable Visual Models From Natural Language Supervision
Contrastive training aligns images with natural-language descriptions, enabling transfer to new visual categories.