Andrew Kyle Lampinen

Research Scientist, Google DeepMind

Joined

October 2017

Names

Andrew Lampinen

Emails

****@stanford.edu (Confirmed)

****@berkeley.edu

****@google.com (Confirmed)

****@gmail.com (Confirmed)

****@deepmind.com (Confirmed)

****@anthropic.com (Confirmed)

Personal Links

Career & Education History

Research Scientist

Google DeepMind (google.com)

2020 – Present

PhD student

Stanford University (stanford.edu)

2015 – 2020

Undergrad student

University of California Berkeley (berkeley.edu)

2010 – 2014

Advisors, Relations & Conflicts

PhD Advisor

James McClelland

2015 – 2020

Expertise

Representation analysis

interpretability

2020 – Present

Language models

LLMs

2020 – Present

Reinforcement learning

2019 – Present

Zero-shot learning

adaptation

zero shot transfer

flexibility

2018 – Present

Natural language processing

2017 – Present

Memory

episodic memory

complementary learning systems

2016 – Present

Cognitive science

cognition

2015 – Present

Multi-task learning

transfer

curricula

2015 – 2022

Publications

Distinct Computations Emerge From Compositional Curricula In-Context
Jin Hwa Lee, Andrew Kyle Lampinen, Aaditya K Singh, Andrew M Saxe
- Submitted to ICLR 2026
- Readers: Everyone
Just-in-time and distributed task representations in language models
Yuxuan Li, Declan Iain Campbell, Stephanie C.Y. Chan, Andrew Kyle Lampinen
- Submitted to ICLR 2026
- Readers: Everyone
Just-in-time and distributed task representations in language models
Yuxuan Li, Declan Iain Campbell, Stephanie C.Y. Chan, Andrew Kyle Lampinen
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew Kyle Lampinen, Arslan Chaudhry, Stephanie C.Y. Chan, Cody Wild, Diane Wan, Alexander Ku, Jörg Bornschein, Razvan Pascanu, Murray Shanahan, James Lloyd McClelland
- FoRLM 2025
- Readers: Everyone
How do language models learn facts? Dynamics, curricula and hallucinations
Nicolas Zucchet, Jorg Bornschein, Stephanie C.Y. Chan, Razvan Pascanu, Andrew Kyle Lampinen, Soham De
- OpenReview Archive Direct Upload
- Readers: Everyone
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller, Andi Peng, Andreea Bobu, Been Kim, Bradley C. Love, Christopher J Cueva, Erin Grant, Iris Groen, Jascha Achterberg, Joshua B. Tenenbaum, Katherine M. Collins, Katherine Hermann, Kerem Oktar, Klaus Greff, Martin N Hebart, Nathan Cloos, Nikolaus Kriegeskorte, Nori Jacoby et al. (13 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
The emergence of sparse attention: impact of data distribution and benefits of repetition
Nicolas Zucchet, Francesco D'Angelo, Andrew Kyle Lampinen, Stephanie C.Y. Chan
- NeurIPS 2025 oral
- Readers: Everyone
How do language models learn facts? Dynamics, curricula and hallucinations
Nicolas Zucchet, Jorg Bornschein, Stephanie C.Y. Chan, Andrew Kyle Lampinen, Razvan Pascanu, Soham De
- COLM 2025
- Readers: Everyone
Language models, like humans, show content effects on reasoning tasks
Andrew Kyle Lampinen, Ishita Dasgupta, Stephanie C.Y. Chan, Hannah Sheahan, Antonia Creswell, Dharshan Kumaran, James Lloyd McClelland, Felix Hill
- PNAS Nexus
- Readers: Everyone
Can Language Models Handle Recursively Nested Grammatical Structures? A Case Study on Comparing Models and Humans
Andrew Kyle Lampinen
- Computational Linguistics
- Readers: Everyone

View all 42 publications

Co-Authors

View all 567 co-authors