Sotabase

Career

· PhD in Computer Science, UC Berkeley2022–2027
· Research Intern, Center for Human-Compatible AI at UC Berkeley2021–2021

Publications (11)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models
arXiv.org · 2024
201
cited
imitation: Clean Imitation Learning Implementations
arXiv.org · 2022
46
cited
Steerable Partial Differential Operators for Equivariant Neural Networks
International Conference on Learning Representations · 2021
32
cited
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
Neural Information Processing Systems · 2024
24
cited
STARC: A General Framework For Quantifying Differences Between Reward Functions
International Conference on Learning Representations · 2023
12
cited
Diffusion On Syntax Trees For Program Synthesis
International Conference on Learning Representations · 2024
9
cited
Preprocessing Reward Functions for Interpretability
arXiv.org · 2022
8
cited
Calculus on MDPs: Potential Shaping as a Gradient
arXiv.org · 2022
4
cited
Extensions of Karger’s Algorithm: Why They Fail in Theory and How They Are Useful in Practice
IEEE International Conference on Computer Vision · 2021
Sotabase
Erik Jenner | Researcher Profile | Sotabase | Sotabase