Juhan Bae

Joined

November 2019

Names

Juhan Bae (Preferred)

Emails

****@cs.toronto.edu (Confirmed)

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

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Department of Computer Science, University of Toronto (cs.toronto.edu)

2019 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Roger Baker Grosse

2019 – 2025

Expertise

No areas of expertise listed

Publications

Gauss-Newton Unlearning for the LLM Era
Lev E McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei Kheirkhah, Nicolas Papernot, Sheila A. McIlraith, Roger Baker Grosse
- MUGen @ ICML 2025 Poster
- Readers: Everyone
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff Schneider, Eduard Hovy, Roger Baker Grosse, Eric P. Xing
- NeurIPS 2025 poster
- Readers: Everyone
IF-Guide: Influence Function-Guided Detoxification of LLMs
Zachary Coalson, Juhan Bae, Nicholas Carlini, Sanghyun Hong
- NeurIPS 2025 poster
- Readers: Everyone
Better Training Data Attribution via Better Inverse Hessian-Vector Products
Andrew Wang, Elisa Nguyen, Runshi Yang, Juhan Bae, Sheila A. McIlraith, Roger Baker Grosse
- NeurIPS 2025 poster
- Readers: Everyone
Fast Fractional Natural Gradient Descent using Learnable Spectral Factorizations
Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Roger Baker Grosse
- Submitted to ICLR 2025
- Readers: Everyone
Accelerating neural network training: An analysis of the AlgoPerf competition
Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, BOYUAN FENG, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl
- ICLR 2025 Poster
- Readers: Everyone
Large-Scale Training Data Attribution with Efficient Influence Functions
Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Minsoo Kang, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff Schneider, Eduard Hovy, Roger Baker Grosse, Eric P. Xing
- Submitted to ICLR 2025
- Readers: Everyone
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwaraknath Gnaneshwar, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, Max Bartolo
- ICLR 2025 Poster
- Readers: Everyone
Influence Functions for Scalable Data Attribution in Diffusion Models
Bruno Kacper Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard E. Turner
- ICLR 2025 Oral
- Readers: Everyone
Training Data Attribution via Approximate Unrolling
Juhan Bae, Wu Lin, Jonathan Lorraine, Roger Baker Grosse
- NeurIPS 2024 poster
- Readers: Everyone

View all 46 publications

Co-Authors

View all 118 co-authors