Andrey Zhmoginov

Researcher, Google DeepMind

Joined

December 2017

Names

Andrey Zhmoginov

Emails

****@google.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Researcher

Google DeepMind (google.com)

2015 – Present

Postdoc

University of California Berkeley (berkeley.edu)

2012 – 2015

PhD student

Princeton University (princeton.edu)

2004 – 2012

Advisors, Relations & Conflicts

Coauthor

Max Vladymyrov

2021 – Present

Coauthor

Mark Sandler

2016 – Present

Coauthor

Andrew G. Howard

2018 – 2021

Coauthor

Soravit Changpinyo

2019 – 2019

Expertise

No areas of expertise listed

Publications

Long Context In-Context Compression by Getting to the Gist of Gisting
Max Vladymyrov, Aleksandar Petrov, Mark Sandler, Andrey Zhmoginov, Nolan Andrew Miller
- OpenReview Archive Direct Upload
- Readers: Everyone
How new data pollutes LLM knowledge and how to dilute it
Chen Sun, Renat Aksitov, Andrey Zhmoginov, Nolan Andrew Miller, Max Vladymyrov, Ulrich Rueckert, Been Kim, Mark Sandler
- SafeGenAi Poster
- Readers: Everyone
How new data permeates LLM knowledge and how to dilute it
Chen Sun, Renat Aksitov, Andrey Zhmoginov, Nolan Andrew Miller, Max Vladymyrov, Ulrich Rueckert, Been Kim, Mark Sandler
- ICLR 2025 Spotlight
- Readers: Everyone
MELODI: Exploring Memory Compression for Long Contexts
Yinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov, David Racz, Jesper Sparre Andersen
- ICLR 2025 Poster
- Readers: Everyone
Contextually Guided Transformers via Low-Rank Adaptation
Andrey Zhmoginov, Jihwan Lee, Max Vladymyrov, Mark Sandler
- Submitted to ICLR 2025
- Readers: Everyone
Narrowing the Focus: Learned Optimizers for Pretrained Models
Gus Kristiansen, Mark Sandler, Andrey Zhmoginov, Nolan Andrew Miller, Anirudh Goyal, Jihwan Lee, Max Vladymyrov
- Submitted to ICLR 2025
- Readers: Everyone
Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones
Andrey Zhmoginov, Jihwan Lee, Mark Sandler
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Learning and Unlearning of Fabricated Knowledge in Language Models
Chen Sun, Nolan Andrew Miller, Andrey Zhmoginov, Max Vladymyrov, Mark Sandler
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Learning Fast and Slow: Representations for In-Context Weight Modulation
Andrey Zhmoginov, Jihwan Lee, Max Vladymyrov, Mark Sandler
- ICML 2024 Workshop ICL Poster
- Readers: Everyone
Narrowing the Focus: Learned Optimizers for Pretrained Models
Gus Kristiansen, Mark Sandler, Andrey Zhmoginov, Nolan Miller, Anirudh Goyal, Jihwan Lee, Max Vladymyrov
- CoRR 2024
- Readers: Everyone

View all 47 publications

Co-Authors

View all 47 co-authors