Yu Guo | Academic Homepage

Yu Guo | 郭语

I received my M.S. in Electrical and Computer Engineering from UCLA, where I worked with Prof. Chenfanfu Jiang and Prof. Richard Wesel on representation learning for robot learning.

My research interests lie in embodied AI, with a focus on learning structured and transferable representations for robust decision-making in the physical world. More broadly, I am interested in systems that turn complex and uncertain observations into reliable actions.

I am always excited to connect with fellow researchers and practitioners—please feel free to reach out if you would like to exchange ideas or explore shared interests!

Education

University of California, Los Angeles, M.S. in Electrical and Computer Engineering, 2026.

University of Electronic Science and Technology of China (UESTC), B.Eng. in Communication Engineering, 2020-2024.

Research Experience

Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation

2026.01 - 2026.06 | UCLA AIVC Lab

Co-advised by Prof. Chenfanfu Jiang and Prof. Richard Wesel

project page / arXiv

Developed a representation learning framework for robot learning that uses task-space end-effector motions as geometric supervision to pretrain reusable sparse 3D encoders for cross-domain and sim-to-real manipulation.

Parameterized Probabilistic Routing for LEO Satellite Networks

2025.04 - 2025.08 | National Key Laboratory of Wireless Communication | ISNCC 2025, WCNC 2026

Advisor: Prof. Lidong Zhu

code / paper

Built a probabilistic routing framework for LEO satellite networks under dynamic link conditions.

Real-Time Cortical Signal Decoding

2025.10 - 2025.12 | UCLA

Advisor: Prof. Jonathan Kao

code

Developed a real-time cortical signal decoding pipeline with consistency-regularized sequence modeling.

Publications

Y. Guo, C. Yu, S. Ma, Y. Chen, Y. Yang, Y. N. Wu, and C. Jiang, "Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation," arXiv preprint arXiv:2606.12759, 2026. [paper]

Y. Guo and L. Zhu, "Turning Reliability into Shortest Path: Parameterized Probabilistic Routing for LEO Satellite Networks," IEEE Wireless Communications and Networking Conference (WCNC), 2026. (Oral Presentation) [paper]

Y. Guo and L. Zhu, "Probabilistic Link Weighting via Feature Fusion for Routing in LEO Satellite Networks," International Symposium on Networks, Computers and Communications (ISNCC), 2025. (Oral Presentation) [paper]

News

Jun 2026: Graduated from UCLA with an M.S. in Electrical and Computer Engineering.

Jun 2026: Completed my research internship at UCLA AIVC Lab and released Sparse2Act.

Jan 2026: Started interning at the UCLA AIVC Lab.

Jan 2026: Our paper on probabilistic routing for LEO satellite networks was accepted to WCNC 2026 as an oral presentation.

Nov 2025: Our paper on probabilistic link weighting for LEO satellite networks was accepted to ISNCC 2025 as an oral presentation.

Yu Guo | 郭语

Education

Research Experience

Publications

News

Interests