Rui Yan

ruy020@ucsd.edu
I am a 1st year Master student at UC San Diego advised by Prof. Xiaolong Wang. I earned my B.S. in Engineering at CQU advised by Prof. Fei Liu. I also worked with Prof. Tianshu Yu at CUHKSZ. I am interested in building practical and deployable robotic systems that bridge research and real-world industrial applications.
Profile Picture

News

[Jun 2025] Gave a Speech and a Demo Presentation at RSS 1st Workshop on Robot Hardware-Aware Intelligence
[Nov 2024] Started my Master’s at UCSD
[Jun 2024] Graduated from CQU

Publications

The Application of Texture Classification Network with Hybrid Adaptive Wavelet in Graves' Disease Ultrasound Diagnosis

The Application of Texture Classification Network with Hybrid Adaptive Wavelet in Graves' Disease Ultrasound Diagnosis

Su-Xi Yu, Jing-Yuan He, Yu Pan, Yi Wang, Jing Wen, Rui Yan

ICWAPR 2023

Evolution of corrosion prediction models for oil and gas pipelines: From empirical-driven to data-driven

Evolution of corrosion prediction models for oil and gas pipelines: From empirical-driven to data-driven

Qinying Wang, Yuhui Song, Xingshou Zhang, Lijin Dong, Yuchen Xi, Dezhi Zeng, Qilin Liu, Huali Zhang, Zhi Zhang, Rui Yan, Hong Luo

Engineering Failure Analysis 2023

Highly Tough and Reliable Poly(Amic Acid) with Ballistic Impact-Resistance through Modulation of Hydrogen Bonding Interactions

Highly Tough and Reliable Poly(Amic Acid) with Ballistic Impact-Resistance through Modulation of Hydrogen Bonding Interactions

Qiang Zhang, Ling Yue, Rui Yan, Der-Jang Liaw, Jianzhong Shi, Zhen Li, Chenyu Liang, Yilong Cheng, Zhishen Ge, Yanfeng Zhang

Macromolecular Rapid Communications 2023

Selected Projects

Attention-Driven Depth Fusion: Leveraging Focus and Single-Image Priors with Self-Cross Attention

Attention-Driven Depth Fusion: Leveraging Focus and Single-Image Priors with Self-Cross Attention

Rui Yan, Zaitian Gongye

We proposes an end-to-end model that fuses a single RGB image and its defocus map using attention mechanisms to estimate depth. Instead of handcrafted fusion, it uses self- and cross-attention for uncertainty-aware refinement.

Generation of Autonomous Driving Scenes

Generation of Autonomous Driving Scenes

Rui Yan, Tianshu Yu

We used a generative model with DDIM to create extra training images from small datasets, improving few-shot learning. Fixed size issues with interpolation and reduced noise for better results.

Work Experience

[Jul 2023 - Aug 2023] Research Assistant at CUHKSZ, advised by Prof. Tianshu Yu
[Jul 2021 - Aug 2021] Robot Engineer at NinboX Institute

Academic Services

Conference Attendee

CES 2025, Las Vegas
RSS 2025, Los Angeles, California | Wednesday, June 25th, 2025

Journal Reviewer

Currently NA