Leo Gagnon

PhD student, DIRO, Department of Computer Science and Operations Research, Université de Montréal

Joined

April 2021

Names

Leo Gagnon (Preferred)

Emails

****@gmail.com (Confirmed)

,

****@umontreal.ca (Confirmed)

,

****@mila.quebec (Confirmed)

Personal Links

Career & Education History

PhD student

DIRO, Department of Computer Science and Operations Research, Université de Montréal (diro.umontreal.ca)

2022 – 2028

Undergrad student

DIRO, Department of Computer Science and Operations Research, Université de Montréal (diro.umontreal.ca)

2019 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Guillaume Lajoie

2022 – 2028

Expertise

No areas of expertise listed

Publications

Next-Token Prediction Should be Ambiguity-Sensitive : A Meta-Learing Perspective
Leo Gagnon, Eric Elmoznino, Sarthak Mittal, Tom Marty, Tejas Kasetty, Dhanya Sridhar, Guillaume Lajoie
- ES-FoMo III
- Readers: Everyone
Does learning the right latent variables necessarily improve in-context learning?
Sarthak Mittal, Eric Elmoznino, Leo Gagnon, Sangnie Bhardwaj, Guillaume Lajoie, Dhanya Sridhar
- ICML 2025 poster
- Readers: Everyone
In-Context Learning and Occam's Razor
Eric Elmoznino, Tom Marty, Tejas Kasetty, Leo Gagnon, Sarthak Mittal, Mahan Fathi, Dhanya Sridhar, Guillaume Lajoie
- ICML 2025 poster
- Readers: Everyone
Does learning the right latent variables necessarily improve in-context learning?
Sarthak Mittal, Eric Elmoznino, Leo Gagnon, Sangnie Bhardwaj, Guillaume Lajoie, Dhanya Sridhar
- Submitted to ICLR 2025
- Readers: Everyone
In-context learning and Occam's razor
Eric Elmoznino, Tom Marty, Tejas Kasetty, Leo Gagnon, Sarthak Mittal, Dhanya Sridhar, Guillaume Lajoie
- Submitted to ICLR 2025
- Readers: Everyone
Explicit Knowledge Factorization Meets In-Context Learning: What Do We Gain?
Sarthak Mittal, Eric Elmoznino, Leo Gagnon, Sangnie Bhardwaj, Dhanya Sridhar, Guillaume Lajoie
- ICLR 2024 R2-FM Workshop Poster
- Readers: Everyone

Co-Authors