Andrew K. Lampinen

Orcid: 0000-0002-6988-8437

Affiliations:

DeepMind
Stanford University, Department of Psychology, CA, USA (former)

According to our database¹, Andrew K. Lampinen authored at least 33 papers between 2017 and 2023.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2023

SODA: Bottleneck Diffusion Models for Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Evaluating Spatial Understanding of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Getting aligned on representational alignment.

[BibT_eX]

[DOI]

CoRR, 2023

Improving neural network representations using human similarity judgments.

[BibT_eX]

[DOI]

Lukas Muttenthaler

Lorenz Linhardt

Jonas Dippel

Robert A. Vandermeulen

Katherine L. Hermann

Andrew K. Lampinen

Simon Kornblith

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Passive learning of active causal strategies in agents and language models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Combining Behaviors with the Successor Features Keyboard.

[BibT_eX]

[DOI]

Danilo Jimenez Rezende

Daniel Zoran

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Symbol tuning improves in-context learning in language models.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Know your audience: specializing grounded language models with listener subtraction.

[BibT_eX]

[DOI]

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

2022

Can language models handle recursively nested grammatical structures? A case study on comparing models and humans.

[BibT_eX]

[DOI]

Andrew Kyle Lampinen

CoRR, 2022

Transformers generalize differently from information stored in context vs in weights.

[BibT_eX]

[DOI]

CoRR, 2022

Language models show human-like content effects on reasoning.

[BibT_eX]

[DOI]

CoRR, 2022

Know your audience: specializing grounded language models with the game of Dixit.

[BibT_eX]

[DOI]

CoRR, 2022

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

[BibT_eX]

[DOI]

CoRR, 2022

Semantic Exploration from Language Abstractions and Pretrained Representations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Data Distributional Properties Drive Emergent In-Context Learning in Transformers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Tell me why! Explanations support learning relational and causal structure.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Can language models learn from explanations in context?

[BibT_eX]

[DOI]

Michael Henry Tessler

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Zipfian Environments for Reinforcement Learning.

[BibT_eX]

[DOI]

Stephanie C. Y. Chan

Andrew Kyle Lampinen

Pierre Harvey Richemond

Felix Hill

Proceedings of the Conference on Lifelong Learning Agents, 2022

2021

Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Symbolic Behaviour in Artificial Intelligence.

[BibT_eX]

[DOI]

CoRR, 2021

Towards mental time travel: a hierarchical memory for reinforcement learning agents.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Transforming task representations to perform novel tasks.

[BibT_eX]

[DOI]

Andrew K. Lampinen

James L. McClelland

Proc. Natl. Acad. Sci. USA, 2020

Transforming task representations to allow deep learning models to perform novel tasks.

[BibT_eX]

[DOI]

Andrew K. Lampinen

James L. McClelland

CoRR, 2020

What shapes feature representations? Exploring datasets, architectures, and training.

[BibT_eX]

[DOI]

Katherine L. Hermann

Andrew K. Lampinen

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Automated curriculum generation through setter-solver interactions.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Environmental drivers of systematicity and generalization in a situated agent.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Emergent Systematic Generalization in a Situated Agent.

[BibT_eX]

[DOI]

CoRR, 2019

Automated curricula through setter-solver interactions.

[BibT_eX]

[DOI]

CoRR, 2019

Embedded Meta-Learning: Toward more flexible deep-learning models.

[BibT_eX]

[DOI]

Andrew K. Lampinen

James L. McClelland

CoRR, 2019

An analytic theory of generalization dynamics and transfer learning in deep linear networks.

[BibT_eX]

[DOI]

Andrew K. Lampinen

Surya Ganguli

Proceedings of the 7th International Conference on Learning Representations, 2019

2017

One-shot and few-shot learning of word embeddings.

[BibT_eX]

[DOI]

Andrew K. Lampinen

James L. McClelland

CoRR, 2017

Improving image generative models with human interactions.

[BibT_eX]

[DOI]

CoRR, 2017

Analogies Emerge from Learning Dyamics in Neural Networks.

[BibT_eX]

[DOI]

Andrew K. Lampinen

Shaw Hsu

James L. McClelland

Proceedings of the 39th Annual Meeting of the Cognitive Science Society, 2017

Andrew K. Lampinen

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...