Yash Mali

Email: ymali@student.ubc.ca | LinkedIn | GitHub | 📄 CV

About

👋🏼 I am an undergraduate student at the University of British Columbia (UBC) interested in Machine Learning/Artificial Intelligence and Optimization. I have worked as a Undergraduate Researcher applying AI to many fields and as a ML engineer. I am driven by fundamental questions about what deep learning learns and how optimization shapes intelligent behavior in AI systems.

Awards

Advanced Machine Learning Network: AML-TN

April 2025

“AML-TN sponsored internships highlight the value of developing young researchers as the next generation of machine learning specialists.”

2X Undergraduate Research Award: WLIURA

May 2024, 2025

“These awards subsidize professors to hire international undergraduate students to work full-time on their research projects in the Summer Session (May to August).”

Experience

  • Healthcare AI – Undergraduate Research 🩺 | UBC Medicine (co-op) | May 2025 – Sep 2025 (Continuing part-time)

    Bringing safe and interpretable AI into medicine. We build software that ingests medical guidelines and delivers evidence-based recommendations through natural language interfaces. Our work combines computer science, medical, and clinical research. We collaborate with UBC’s Cloud Innovation Centre for certain projects. Current projects include agentic NLP pipelines with UIs hosted on AWS for Bipolar Disorder and Depression. Supervised by Dr. John Jose Nunez.

  • ML Engineer – Undergraduate Research 🏡 | UBC SCARP & ECE (part-time) | May 2025 – Present

    Using latest developments in NLP and Computer Vision to analyze public records from Vancouver’s housing development approval process. This work bridges AI and social science to address Canada’s housing crisis. Supervised by Dr. Julia Harten and Dr. Christos Thrampoulidis.

  • Unpacking AI 🎨 | UBC Arts (part-time) | May 2025 – Present

    Developing modules in existing faculty of arts courses that highlight how AI can be used in their field. For example, sequence modelling in economics or computer vision in archeology. Funded by UBC’s Teaching and Learning Enhancement fund (TELF). Supervised by Dr. Laura Nelson and Dr. Jonathan Graves. More info. Tangentially, working on benchmarking LLMs for historical faithfulness.

  • AI and Automation Developer 🧬 | Lux Bio (co-op) | Sep 2024 – May 2025

    Applied AI-based drug discovery tools like AlphaFold and ProteinMPNN to optimize sequences and 3D structures of enzymes. Revamped automation systems for bioprocess engineering, orchestrating sensors, pumps, motors, and valves.

  • Computer Vision & Automation – Undergraduate Research 🔬 | UBC Engineering @ Frostad Research Group (co-op) | May 2024 – Sep 2024

    Developed particle tracking software using an ensemble of open-source computer vision models along with a UI to correct mistakes. Automated and developed data collection software for new instruments invented by the research group. Helped with some day-to-day lab activities. Supervised by Dr. John Frostad.

Additional Experience

  • Undergrad Thesis 💾 | Sep 2025 – Present

    Researching how data diversity and noise affects autoregressive models learn and the kinds of solutions they find through a controlled synthetic data setting. Supervised by Dr.Christos Thrampoulidis.

  • UBC AI Club 🦾 | Jan 2025 – Present

    President: Leading initiatives to encourage student understanding and future pathways in AI and ML.

  • UBC Uncrewed Aircraft Systems ✈️ | Sep 2024 – Present

    Leading the ML sub-team to explore and tune open-sourced models for object detection and tracking. This is a small piece of the puzzle on our drones that compete in two university-level autonomous drone competitions every year.

  • UBC Biological Internet of Things 🧬 | May 2025 – Present

    Automating brewing/fermentation equipment with IoT-controlled devices while also trying to make glow-in-the-dark beer using green fluorescent protein (GFP).

  • IT Helpdesk Support 👨‍💻 | May 2023 – May 2024

    Provided technical assistance to faculty, staff, and students for tech-related queries and equipment across campus.

Selected Work

BC Cancer Summit: AI for Cancer Care | November 20, 2025

Initial demonstration of a conversational agent that helps patients find cancer support resources and collecting attendee feedback to guide improvements. Agenda: here | Page 9

AttenDence: Maximizing Attention Confidence for Test-Time Adaptation | Graduate course project

CPSC 532: Adaptation and Adaptive Computation | Fall 2025

Developed a test-time adaptation method for attention based models that minimizes the entropy of CLS-to-patch attention distributions so the model attends more confidently to relevant image regions under distribution shift. This attention-entropy minimization improves robustness to diverse corruptions on single-image test streams while preserving performance on clean data. Code and preprint coming soon!

Agentic NLP for Medical Guidelines

Poster: CAIDA/TrustML ICML Visits 2025 | July 15, 2025

Poster: UBC Psychiatry Research Day 2025 | June 5, 2025

Talk: Multidisciplinary Undergraduate Research Conference 2025 | Mar 21, 2025

Preprint on medarxiv: Link coming soon!

Praxis UBC: Developing AI education modules in Faculty of Arts Courses

Website: here

Under review at Conference on Teaching and Research in Economic Education!

Quantification of Starch Gelatinization Properties in Glucose and Sucrose Solutions using ParCS and Deep Learning

Talk: Multidisciplinary Undergraduate Research Conference 2025 | Mar 21, 2025

Under review at Food Hydrocolloids!

Small Projects