YuntianWang
Los Angeles, CA
I'm a
Passionate about the intersection of deep learning and diffractive optics, interested in physics-enabled deep learning applications in real world.
Get to Know Me
Passionate About Physics-enabled Deep Learning Applications in Real World
My research uses deep learning to design intelligent diffractive optical systems, moving computational tasks from software into physical hardware for faster, more efficient processing.
5+
Years of Experience
4
Publications
3
Conference Presentations
Specialization
Deep Learning & Diffractive Optics
Experience Level
Ph.D. Candidate
Education
Ph.D. in Electrical and Computer Engineering, UCLA
Languages
Chinese (Native), English (Fluent)
Resume
Ph.D. Student in Electrical and Computer Engineering specializing in Deep Learning for Diffractive Optics and Computational Pathology
Short Summary
Passionate about the intersection of deep learning and diffractive optics, interested in physics-enabled deep learning applications in real world
Contact Information
- 420 Westwood Plaza, Los Angeles, CA 90024
- yuntianwww@ucla.edu
- +1 3109030381/+86 13100702939
Technical Skills
Coding Languages:
Python, MATLAB, Java, C for embedding system.
Python, MATLAB, Java, C for embedding system.
Machine Learning Frameworks:
PyTorch, Tensorflow, JAX
PyTorch, Tensorflow, JAX
CAD Tools:
Solidworks (CSWA certificant), Zemax, AutoCAD
Solidworks (CSWA certificant), Zemax, AutoCAD
Language:
Native in Chinese, Fluent in English
Native in Chinese, Fluent in English
Research Experience
Deep Learning based Diffractive Optics Optimization
2023 - Present
UCLA ECE, Advisor: Aydogan Ozcan
- Developed a diffractive surface-based pipeline for universal optical waveguide design, which can be streamed down to various tasks such as redirecting, filtering, splitting, and polarization maintaining.
- Designed a diffractive surface system capable of selectively transmitting different classes of images based on the polarization. Bringing innovative methods for privacy protection.
Structure Health Monitoring using Diffractive Processors
2024 - Present
UCLA ECE, Advisor: Aydogan Ozcan
- Designed a hybrid (optical plus digital) system utilizing deep learning to encode vibration spectrum of a building optically and decode by digital network, providing fast and high accuracy structure health monitoring solutions.
Transferable and Universal Adversarial Attacks on Computational Pathology Models
2024 - Present
UCLA ECE, Advisor: Aydogan Ozcan
- Developed a novel adversarial training framework using universal adversarial perturbations (UAPs) to enhance the robustness and security of ViT-based pathology foundation models.
- Engineered physically-realizable attacks modeling fluorescent particle placement to probe the failure modes of physics-consistency-based safety mechanisms in digital pathology.
Optical Diffusion-based Generative Models
2024 - Present
UCLA ECE, Advisor: Aydogan Ozcan
- Involved in building an optical generative model capable of generative multiple classes of images including simple dataset to Van Gogh style artwork. The optical generative model drastically decrease the computational power required for novel image generation.
Education
Ph.D. student in Electrical and Computer Engineering
2023 - Present
University of California, Los Angeles
Bachelor of Electrical and Electronics Engineering
2019 - 2023
Southern University of Science and Technology
Projects
Here is the selection of my projects
Contact
Feel free to contact me!
Contact Info
My Location
420 Westwood Plaza
Los Angeles, CA 90024
Phone Number
+1 310 903 0381
+86 131 0070 2939
Email Address
yuntianwww@ucla.edu