Interpretable-MTLNet: A Kolmogorov-Arnold Network for Multitask Mental Health Prediction
NeurIPS 2025 Workshop on BrainBodyFM
* Co-first authors. Published on September 23, 2025.
About Me
Hi, I'm Zhenghao Ni. I am an Electrical and Computer Engineering student at the University of Toronto with interests spanning AI systems, embedded hardware, and applied machine learning.
My recent work includes LLM-based teaching assistants at the National University of Singapore and interpretable multi-task learning for mental-health screening from wearable data at the University of Toronto. Outside research, I enjoy building across FPGA systems, RF circuits, PCB design, and end-to-end software workflows.
Download my CV (Updated: Jan 2026)
Education
University of Toronto
3.82/4.0 GPA
Bachelor of Applied Science in Electrical & Computer Engineering
Experience
Tenstorrent
Incoming Applied ML Engineer Intern
Focused on inference across LLM, VLM, video generation, and image generation models.
University of Toronto
Undergraduate Research Student
Worked with the Kundur Research Group on interpretable multi-task learning for wearable-based depression and anxiety detection.
National University of Singapore
Research Assistant Intern
Fine-tuned LLM-based teaching assistants for elementary-school programming competitions and designed prompt strategies and evaluation criteria for beginner C++ support.
Publications
Honors
- Top 30 in the University of Toronto ECE first-year cohort.
- Dean's Honours List, 2023 Fall Session.
- Dean's Honours List, 2024 Winter Session.
- Dean's Honours List, 2024 Fall Session.