Sotabase
Home
Researchers
Career
·
Member Of Technical Staff
,
OpenAI
2024–
Publications
(17)
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
International Conference on Learning Representations · 2018
232
cited
A StrongREJECT for Empty Jailbreaks
Neural Information Processing Systems · 2024
203
cited
Deliberative Alignment: Reasoning Enables Safer Language Models
Robotics · 2024
199
cited
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
International Conference on Learning Representations · 2023
106
cited
Trading Inference-Time Compute for Adversarial Robustness
arXiv.org · 2025
52
cited
imitation: Clean Imitation Learning Implementations
arXiv.org · 2022
46
cited
OpenAI GPT-5 System Card
2025
46
cited
The MAGICAL Benchmark for Robust Imitation
Neural Information Processing Systems · 2020
38
cited
An Empirical Investigation of Representation Learning for Imitation
NeurIPS Datasets and Benchmarks · 2022
28
cited
A Primer on Maximum Causal Entropy Inverse Reinforcement Learning
arXiv.org · 2022
18
cited
Human Action Anticipation: A Survey
arXiv.org · 2024
9
cited
DERAIL: Diagnostic Environments for Reward And Imitation Learning
arXiv.org · 2020
6
cited
From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluation
Conference on Empirical Methods in Natural Language Processing · 2025
2
cited
Exploring and Addressing Reward Confusion in Offline Preference Learning
arXiv.org · 2024
OpenAI Research Engineer Interviews (Multiple Choice)
QBCov: A Linked Data interface for Discrete Global Grid Systems, a new approach to delivering coverage data on the web
2016
UCSC at SemEval-2025 Task 8: Question Answering over Tabular Data
Sotabase
Sam Toyer | Researcher Profile | Sotabase | Sotabase