CV

Name
Yucheng (Steven) Chen
Label
Machine Learning Research & Software Engineering
Email
i@schen.me
Website
schen.me
Summary
Computer science student at the University of Toronto. I work on model reliability: uncertainty estimation for medical image segmentation with Project Neura / UTMIST, and a scaling audit of layer-local training that found Forward-Forward does not hold up on real data. Outside research I build production full-stack systems and my own options analytics tooling.

Work

2024PresentResearch Intern

Medical image analysis, with a focus on uncertainty and reliability.

  • Co-first-authored MIPCandy, a modular PyTorch framework for medical image processing (arXiv:2602.21033, 290+ GitHub stars)
  • Co-authored SegWithU, a post-hoc uncertainty module that lets a frozen segmentation model flag its own failures in a single forward pass (arXiv:2604.15271)
  • Contributed to the SortScrews dataset paper
2025.02PresentAI / Full-Stack Engineer Intern

Part-time. Kabuda runs a multi-service platform for newcomers and international students in the Greater Toronto Area.

  • Built conversational AI features and agent workflows for client-facing web and mobile products
  • Designed and implemented the REST backends those products run on
  • Continuing part-time alongside full-time study
2024PresentFounder
Amplimit

Independent research organization; the affiliation carried on my publications.

  • Sole-authored a scaling audit of Forward-Forward learning, including the first FF-family baseline at ImageNet-100 224x224 (arXiv:2606.06539)
  • Builds Ampdraft, a writing tool that gives documents version control

Education

2026.09 – PresentToronto, Canada
Computer Science, Faculty of Arts & Science (University College)
University of Toronto
2025Ontario, Canada
Ontario Secondary School Diploma
Elton Academy

Awards

  • FBLA Canada National — Coding & Programming5th place / 1,800+ competitors (2025)
  • Euclid Mathematics ContestTop 25% / 27,092 participants worldwide (2025)
  • Diamond Challenge (Round 2)Honorable Mention (2025)
  • Canadian Computing Competition (CCC)Top 120 in Canada (2024)
  • UofT Rotman Commerce Boardroom CompetitionAward Winner (2024)
  • Canadian Senior Mathematics Contest (CSMC)Top 25% / 16,425 registrants (2024)

Publications

2026.04
arXiv preprint; under review at UNSURE 2026 (MICCAI workshop) · Tianhao Fu, Austin Wang, Charles Chen, Roby Aldave-Garza, Yucheng Chen
2026.02
arXiv preprint · Tianhao Fu, Steven Chen

Technical Skills

Languages
Python, Java, C++, Rust, TypeScript
ML/DL
PyTorch, computer vision, medical image segmentation, uncertainty estimation
Web
Next.js, React, NestJS, Tailwind CSS, Prisma
Data
PostgreSQL, Redis, SQLite, Meilisearch
Infrastructure
Docker, Nginx, PM2, Linux, Git

Languages

Mandarin
First Language
English
Fluent

Projects

Options analytics dashboard, built for my own research

  • IV surface, smile, term structure, skew, GEX, open interest walls, max pain, expected move
  • Python/Dash pipeline that pulls and normalizes full option chains across every expiration
  • Exposed as an MCP server so a language model can query the pipeline directly

Version control for writing

  • Snapshots, parallel variants, and word-level diff between any two versions
  • Deliberately avoids Git vocabulary; the model is presented as a timeline you can branch from
  • Next.js + Prisma + Postgres, with client-side PDF export via Typst compiled to WASM
2025ATLAS

Stock market pattern recognition with computer vision methods

  • Encoded price series as images (GASF/GADF/RP/MTF) and classified them
  • 83.4% validation accuracy with 17,081 parameters, 18.5x fewer than the ResNet-style CNN baseline
  • Sub-millisecond inference, validated across 200+ stocks

Portfolio management and analysis tool

  • Built for the Wharton WGHS competition, Python backend with a Next.js frontend
  • Parallel pipeline supporting 60+ assets with sub-3-second response
  • SSE streaming for progressive metric loading

Extracurricular

20242025Vice President
FBLA Canada, Bur Oak Chapter (Econ & Biz Champs Club)
  • Recruited and mentored 50+ members
  • Competed in the Wharton WGHS Investment Competition as an executive