| title | Vesta: A Generalist Embodied Reasoning Model |
|---|---|
| authors | Johan Bjorck, Zhiqi Li, Yunze Man, Jing Wang, An-Chieh Cheng, Sifei Liu, Shihao Wang, Zhiding Yu, Abhishek Badki, Stan Birchfield, Valts Blukis, Yevgen Chebotar, Siyi Chen, Sicong Leng, Yu-Cheng Chou, Tianli Ding, Boyi Li, Zhengyi Luo, Hang Su, Jonathan Tremblay, Tingwu Wang, Bowen Wen, Jimmy Wu, Xianghui Xie, Hanrong Ye, Hongxu Yin, K. R. Zentner, Liangyan Gui, Yu-Xiong Wang, Yuke Zhu, Linxi "Jim" Fan, Jan Kautz |
| date | 2026-06-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.20905 |
| affiliation | NVIDIA |
| upvotes | 13 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at individual tasks, deploying a multi-model stack is computationally expensive and prone to cascading errors. We present Vesta, a unified embodied generalist that consolidates these capabilities into a single foundation model. Our approach combines a diverse and massive curated corpus designed to induce spatial grounding and a simple multimodal memory harness that enables reasoning over extended time horizons. Across diverse benchmarks, Vesta on average beats individual SOTA baselines by >20% and beats an ensemble of per-category-best baselines by >10% -- thus demonstrating that a generalist model can match or exceed specialists. On real-world robotic tasks requiring memory and reasoning, Vesta improves task success by >35\%. Our work thus demonstrates that a single generalist is a feasible, scalable, and arguably preferable alternative to combining specialists. |
cite
@misc{bjorck2026vesta,
title={Vesta: A Generalist Embodied Reasoning Model},
author={Johan Bjorck and Zhiqi Li and Yunze Man and Jing Wang and An-Chieh Cheng and Sifei Liu and Shihao Wang and Zhiding Yu and Abhishek Badki and Stan Birchfield and Valts Blukis and Yevgen Chebotar and Siyi Chen and Sicong Leng and Yu-Cheng Chou and Tianli Ding and Boyi Li and Zhengyi Luo and Hang Su and Jonathan Tremblay and Tingwu Wang and Bowen Wen and Jimmy Wu and Xianghui Xie and Hanrong Ye and Hongxu Yin and K. R. Zentner and Liangyan Gui and Yu-Xiong Wang and Yuke Zhu and Linxi "Jim" Fan and Jan Kautz},
year={2026},
eprint={2606.20905},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.20905}
}