Theo Putterman

Joined

May 2024

Names

Theo Putterman (Preferred)

Emails

****@berkeley.edu (Confirmed)

Personal Links

Career & Education History

Undergrad student

Computer Science, University of California, Berkeley (berkeley.edu)

2021 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

Equivariant Learning

2024 – Present

Publications

GL Equivariant Metanetworks for Learning on Low Rank Weight Spaces
Theo Putterman, Derek Lim, Yoav Gelberg, Michael M. Bronstein, Stefanie Jegelka, Haggai Maron
- LOG 2025 Oral
- Readers: Everyone
GradMetaNet: An Equivariant Architecture for Learning on Gradients
Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo Putterman, Michael M. Bronstein, Haggai Maron
- NeurIPS 2025 poster
- Readers: Everyone
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
Theo Putterman, Derek Lim, Yoav Gelberg, Stefanie Jegelka, Haggai Maron
- ICLR 2025 Workshop Weight Space Learning Poster
- Readers: Everyone
GradMetaNet: An Equivariant Architecture for Learning on Gradients
Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo Putterman, Haggai Maron
- ICLR 2025 Workshop Weight Space Learning Poster
- Readers: Everyone
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
Theo Putterman, Derek Lim, Yoav Gelberg, Stefanie Jegelka, Haggai Maron
- Submitted to ICLR 2025
- Readers: Everyone
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka
- HiLD at ICML 2024 Poster
- Readers: Everyone
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka
- NeurIPS 2024 poster
- Readers: Everyone

Co-Authors