Preprint · 2026 · Open access
GazeVLA: Learning Human Intention for Robotic Manipulation
arXiv (Cornell University) · Published 24 April 2026 · DOI 10.48550/arxiv.2604.22615
In brief
“GazeVLA: Learning Human Intention for Robotic Manipulation” is a 2026 preprint by Chengyang Li and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 10 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 10
- Most cited in
- 2026 (10)
- References
- 84
- Authors
- 6
Abstract
Embodied foundation models have significantly propelled the advancement of artificial general intelligence, yet they rely heavily on large-scale data. Recent studies identify human behavior as one of the most scalable sources for fostering robotic physical intelligence. However, the inherent embodiment gap remains a fundamental challenge for effective human-to-robot learning. In this work, we model human intention to enable efficient learning from human demonstrations. Among human behavioral cues, gaze simultaneously encodes high-level task semantics and exhibits a synergistic coupling with low-level action. By modeling intention through gaze, we derive a mid-level representation that facilitates cross-embodiment knowledge transfer. We demonstrate that robots can internalize human intentions to enhance manipulation, even without robotic intention annotations. To capture the synergy between intention and action, we adopt a Chain-of-Thought reasoning paradigm during inference. Our approach enables the execution of long-horizon and fine-grained tasks across diverse embodiments. Extensive experiments in both simulation and real-world demonstrate that our method consistently outperforms baseline approaches and generalizes to unseen settings. Project page: https://gazevla.github.io .
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, C., Xiong, K., Xu, Y., Qian, L., Wang, Y., & Zhu, W. (2026). GazeVLA: Learning Human Intention for Robotic Manipulation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.22615
MLA 9
Li, Chengyang, et al. “GazeVLA: Learning Human Intention for Robotic Manipulation.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2604.22615.
Chicago
Li, Chengyang, Kaiyi Xiong, Yuan Xu, Lei Qian, Yizhou Wang, and Wentao Zhu. 2026. “GazeVLA: Learning Human Intention for Robotic Manipulation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.22615.
Harvard
Li, C. et al. (2026) ‘GazeVLA: Learning Human Intention for Robotic Manipulation’, arXiv (Cornell University). doi:10.48550/arxiv.2604.22615.
IEEE
C. Li, K. Xiong, Y. Xu, L. Qian, Y. Wang, and W. Zhu, “GazeVLA: Learning Human Intention for Robotic Manipulation,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2604.22615.
BibTeX
@misc{li2026gazevla,
title = {{GazeVLA: Learning Human Intention for Robotic Manipulation}},
author = {Li, Chengyang and Xiong, Kaiyi and Xu, Yuan and Qian, Lei and Wang, Yizhou and Zhu, Wentao},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2604.22615},
url = {https://doi.org/10.48550/arxiv.2604.22615}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- gaze
- robotic manipulation
- chain-of-thought reasoning
- human demonstrations
- long-horizon tasks
Work with this paper
Most-cited papers in Engineering
- A Closed‐form Equation for Predicting the Hydraulic Conductivity of Unsaturated SoilsMartinus Th. van Genuchten · Soil Science Society of America Journal · 1980 · 28,197 citations
- An improved technique for determining hardness and elastic modulus using load and displacement sensing indentation experimentsW. C. Oliver, George M. Pharr · Journal of materials research/Pratt's guide to venture capital sources · 1992 · 27,379 citations
- Digital communicationsOwen Bishop · Routledge eBooks · 2007 · 24,890 citations
- The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysisNorden Eh Huang, Zhengwei Shen, Steven R. Long and 6 more · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · 1998 · 24,008 citations
- Numerical Heat Transfer and Fluid FlowSuhas V. Patankar · CRC Press eBooks · 2018 · 23,491 citations
Questions about this paper
How do I cite this paper in APA style?
Li, C., Xiong, K., Xu, Y., Qian, L., Wang, Y., & Zhu, W. (2026). GazeVLA: Learning Human Intention for Robotic Manipulation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.22615
How many times has this paper been cited?
10 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Chengyang Li, Kaiyi Xiong, Yuan Xu, Lei Qian, Yizhou Wang, Wentao Zhu.
What is the DOI of this paper?
10.48550/arxiv.2604.22615, permanently at https://doi.org/10.48550/arxiv.2604.22615. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.