Profiles2020-2025
Scott Emmons
Center for Human-Compatible AI, University of California, Berkeley
6Papers
1Last author
3Unique co-authors
4First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- Observation Interference in Partially Observable Assistance GamesAuthor 1 of 4ICML 2025
- Image Hijacks: Adversarial Images can Control Generative Models at RuntimeAuthor 4 of 4ICML 2024 · 171 citations
- When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human FeedbackAuthor 6 of 7NeurIPS 2024 · 18 citations
- RvS: What is Essential for Offline RL via Supervised Learning?Author 1 of 5ICLR 2022 · 225 citations
- For Learning in Symmetric Teams, Local Optima are Global Nash EquilibriaAuthor 1 of 5ICML 2022 · 12 citations
- Sparse Graphical Memory for Robust PlanningAuthor 1 of 6NeurIPS 2020 · 60 citations
