Theodore Sumers

Researcher, Anthropic

Joined

February 2022

Names

Theodore Sumers (Preferred)

Theodore R. Sumers

Emails

****@gmail.com (Confirmed)

****@princeton.edu

****@anthropic.com (Confirmed)

Personal Links

Career & Education History

Researcher

Anthropic (anthropic.com)

2023 – Present

PhD student

Princeton University (princeton.edu)

2019 – 2023

Advisors, Relations & Conflicts

Coworker

Jesse Mu

Present

Coauthor

Rob Fergus

2022 – Present

Coauthor

Ishita Dasgupta

2022 – Present

Coauthor

Kenny Marino

2022 – Present

Coauthor

Arun Ahuja

2022 – Present

PhD Advisor

Tom Griffiths

2019 – Present

Coauthor

Robert Hawkins

2019 – Present

Coauthor

Mark Ho

2019 – Present

Coauthor

Karthik Narasimhan

2019 – Present

Coauthor

Sreejan Kumar

2019 – Present

Expertise

social learning

embodied language

explanations

Present

Publications

Reconstructing the cascade of language processing in the brain using the internal computations of a transformer-based language model
Sreejan Kumar, Theodore Sumers, Takateru Yamakoshi, Ariel Goldstein, Uri Hasson, Kenneth Norman, Thomas L. Griffiths, Robert D. Hawkins, Sam Nastase
- 11 Apr 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
How to talk so AI will learn: instructions, descriptions, and pragmatics
Theodore Sumers, Robert D. Hawkins, Mark K Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
- Published: 21 Oct 2022, Last Modified: 05 May 2023
- LaReL 2022
- Readers: Everyone
Words are all you need? Language as an approximation for human similarity judgments
Raja Marjieh, Pol Van Rijn, Ilia Sucholutsky, Theodore Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
- Published: 01 Feb 2023, Last Modified: 23 Feb 2023
- ICLR 2023 poster
- Readers: Everyone
Predicting Human Similarity Judgments Using Large Language Models
Raja Marjieh, Ilia Sucholutsky, Theodore Sumers, Nori Jacoby, Thomas L. Griffiths
- 26 May 2022 (modified: 30 Dec 2025)
- ICML 2022 Pre-training Workshop
- Readers: Everyone
How to talk so AI will learn: Instructions, descriptions, and autonomy
Theodore Sumers, Robert D. Hawkins, Mark K Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
- Published: 31 Oct 2022, Last Modified: 15 Dec 2022
- NeurIPS 2022 Accept
- Readers: Everyone
Linguistic communication as (inverse) reward design
Theodore Sumers, Robert D. Hawkins, Mark K Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
- 13 Mar 2022 (modified: 05 May 2023)
- LNLS
- Readers: Everyone
Predicting Human Similarity Judgments Using Large Language Models
Raja Marjieh, Ilia Sucholutsky, Theodore Sumers, Nori Jacoby, Thomas L. Griffiths
- 13 Mar 2022 (modified: 08 Feb 2026)
- LNLS
- Readers: Everyone
Words are all you need? Capturing human sensory similarity with textual descriptors
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
- 2022 (modified: 05 Apr 2023)
- CoRR 2022
- Readers: Everyone
How to talk so your robot will learn: Instructions, descriptions, and pragmatics
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
- 2022 (modified: 05 Apr 2023)
- CoRR 2022
- Readers: Everyone
Predicting Human Similarity Judgments Using Large Language Models
Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers, Nori Jacoby, Thomas L. Griffiths
- 2022 (modified: 05 Apr 2023)
- CoRR 2022
- Readers: Everyone

View all 14 publications

Theodore Sumers

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors