Nico Schiavone

I am an M.Sc. student in the Department of Computer Science at the University of Toronto, advised by Sheila McIlraith and Eldan Cohen. I am interested in multi-agent systems and cooperation. Currently working on problems in cooperative AI and at the intersection of computer science, statistics, and economics.

In 2024, I graduated Mathematics and Engineering Physics at the University of Alberta. I was fortunate to be advised by Xingyu Li, Frank Marsiglio, and Tian Tang.

In the past, I was an internal tools software engineer at TELUS and a physics researcher at TRIUMF. Most days, I enjoy drawing, writing, lifting, and mixing house. I'm also currently working on a comic.

In Summer 2025, I will be interning at Microsoft, working on Copilot Agents.

If you are interested in my work or just want to chat, feel free to reach out by any avenue.

cv  /  email  /  github  /  scholar  /  linkedin

uniqlo /  substack

profile photo

Research

project image

Reinforcement Learning with Generative Models for Compact Support Sets


Nico Schiavone, Xingyu Li
arXiv, 2024
arxiv / code /

In this work, we propose a framework utilizing reinforcement learning as a control for foundation models, allowing for the granular generation of small, focused synthetic support sets to augment the performance of neural network models on real data classification tasks.

project image

MyriadAL: Active Few Shot Learning for Histopathology


Nico Schiavone, Jingyi Wang, Shuangzhi Li, Roger Zemp, Xingyu Li
IEEE Conference on Artificial Intelligence, 2024
arxiv / code /

Oral Presentation (Top ~5% of Accepted Papers). In this study, we address this issue in the scenario where the annotation budget is very limited, yet a large amount of unlabelled data for the target task is available. We frame this work in the context of histopathology where labelling is prohibitively expensive.




Other Projects

project image

UNIQLO Web Scraper


personal
2024-06-14
code /

A web scraping project using Scrapy and Playwright, developing into a command-line tool for easy shopping on ecommerce sites. Check it out here.

project image

HUGINN


personal
2024-05-01
code /

Autonomous retrieval drone made for a capstone project. Utilizes ROS and YOLOV8 to autonomously find the object of choice, and magnetic grippers to pick it up.


Ubiquitous researcher template from Jon Barron's website