Sreejan Kumar

Joined

September 2020

Names

Sreejan Kumar (Preferred)

Emails

****@princeton.edu (Confirmed)

Personal Links

Career & Education History

PhD student

Neuroscience, Princeton University (princeton.edu)

2019 – 2025

Undergrad student

Computer Science, Yale University (yale.edu)

2015 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Thomas L. Griffiths

2019 – 2024

PhD Advisor

Jonathan D. Cohen

2019 – 2024

Expertise

Cognitive Science

Present

Reinforcement Learning

Present

Meta-Learning

Present

Neuroscience

Present

Publications

From Interaction to Abstraction: Using Behavior and Brain Activity to Evaluate How AI Systems Learn Games
Botos Csaba, Sreejan Kumar, Austin Tudor David Andrews, Rui Ponte Costa, Marcelo G Mattar, Momchil Tomov
- HCAIR 2026
- Readers: Everyone
Visual serial processing deficits explain divergences in human and VLM reasoning
Nicholas Budny, Kia Ghods, Declan Iain Campbell, Raja Marjieh, Amogh Joshi, Sreejan Kumar, Jonathan D. Cohen, Taylor Whittington Webb, Thomas L. Griffiths
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases
Raja Marjieh, Sreejan Kumar, Declan Iain Campbell, Liyi Zhang, Gianluca Bencomo, Jake Snell, Thomas L. Griffiths
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Human-like Geometric Abstraction in Large Pre-Trained Neural Networks
Declan Iain Campbell, Sreejan Kumar, Tyler Giallanza, Jonathan D. Cohen, Thomas L. Griffiths
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
Sreejan Kumar, Raja Marjieh, Byron Zhang, Declan Iain Campbell, Michael Y. Hu, Umang Bhatt, Brenden Lake, Thomas L. Griffiths
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning
Carlos A. Velazquez-Vargas, Isaac Ray Christian, Jordan Taylor, Sreejan Kumar
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Relational Constraints On Neural Networks Reproduce Human Biases towards Abstract Geometric Regularity
Declan Campbell, Sreejan Kumar, Tyler Giallanza, Jonathan D. Cohen, Thomas L. Griffiths
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
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
Using natural language and program abstractions to instill human inductive biases in machines
Sreejan Kumar, Carlos G Correa, Ishita Dasgupta, Raja Marjieh, Michael Hu, Robert D. Hawkins, Jonathan Cohen, Nathaniel Daw, Karthik R Narasimhan, Thomas L. Griffiths
- Published: 31 Oct 2022, Last Modified: 19 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
Using Natural Language to Guide Meta-Learning Agents towards Human-like Inductive Biases
Sreejan Kumar, Ishita Dasgupta, Michael Hu, Raja Marjieh, Robert D. Hawkins, Nathaniel Daw, Jonathan Cohen, Karthik R Narasimhan, Thomas L. Griffiths
- 13 Mar 2022 (modified: 05 May 2023)
- LNLS
- Readers: Everyone

View all 17 publications

Co-Authors

View all 47 co-authors