Yi Sui

Machine Learning Scientist, Layer6 AI

Joined

May 2021

Names

Yi Sui (Preferred)

Emails

****@mail.utoronto.ca (Confirmed)

****@layer6.ai (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Machine Learning Scientist

Layer6 AI (layer6.ai)

2021 – Present

MS student

Toronto University (utoronto.ca)

2019 – 2021

Undergrad student

University of Waterloo (uwaterloo.ca)

2013 – 2018

Advisors, Relations & Conflicts

Coauthor

Jesse C. Cresswell

2022 – 2025

Coauthor

Ga Wu

2021 – 2024

master advisor

Scott Sanner

2019 – 2021

Expertise

Self-representation learning

2022 – 2025

Explainable AI

2021 – 2025

Publications

DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
Wei Cui, Tongzi Wu, Jesse C. Cresswell, Yi Sui, Keyvan Golestan
- Submitted to ICLR 2026
- Readers: Everyone
Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
Brendan Leigh Ross, Noël Vouitsis, Atiyeh Ashari Ghomi, Rasa Hosseinzadeh, Ji Xin, Zhaoyan Liu, Yi Sui, Shiyi Hou, Kin Kwan Leung, Gabriel Loaiza-Ganem, Jesse C. Cresswell
- ICLR 2026 Poster
- Readers: Everyone
Self-Supervised Representation Learning As Mutual Information Maximization
Akhlaqur Rahman Sabby, Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Conformal Prediction Sets Can Cause Disparate Impact
Jesse C. Cresswell, Bhargava Kumar, Yi Sui, Mouloud Belbahri
- ICLR 2025 Spotlight
- Readers: Everyone
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
Wei Cui, Yi Sui, Jesse C. Cresswell, Keyvan Golestan
- NeurIPS 2024 Workshop SSL
- Readers: Everyone
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic
- ICML 2024 FM-Wild Workshop Poster
- Readers: Everyone
Conformal Prediction Sets Improve Human Decision Making
Jesse C. Cresswell, Yi Sui, Bhargava Kumar, Noël Vouitsis
- ICML 2024 Poster
- Readers: Everyone
Self-supervised Representation Learning from Random Data Projectors
Yi Sui, Tongzi Wu, Jesse Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs
- TRL @ NeurIPS 2023 Oral
- Readers: Everyone
Self-supervised Representation Learning from Random Data Projectors
Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs
- ICLR 2024 poster
- Readers: Everyone
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
George Stein, Jesse C. Cresswell, Rasa Hosseinzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Zhaoyan Liu, Anthony L. Caterini, Eric Taylor, Gabriel Loaiza-Ganem
- NeurIPS 2023 poster
- Readers: Everyone

View all 16 publications

Co-Authors

View all 33 co-authors