PPaperPicks

Stuart Russell

University of California, Berkeley, Department of Electrical Engineering and Computer Sciences, CA, USA

23 papers at tracked venues · 20 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0000-0001-5252-4306 ↗Google Scholar ↗Homepage ↗

Venues

ICML ×7ICLR ×6NeurIPS ×6ICRA ×2AAAI ×1UAI ×1

Frequent coauthors

Hanlin Zhu
DBLP profile ↗ORCID search ↗
×3
Cassidy Laidlaw
DBLP profile ↗ORCID search ↗
×2
Jiahai Feng
DBLP profile ↗ORCID search ↗
×2
Benjamin Plaut
DBLP profile ↗ORCID search ↗
×1
Aly Lidayan
DBLP profile ↗ORCID search ↗
×1
Shreyas Kapur
DBLP profile ↗ORCID search ↗
×1
Yixiao Huang
DBLP profile ↗ORCID search ↗
×1
Scott Emmons
DBLP profile ↗ORCID search ↗
×1
Michael K. Cohen
DBLP profile ↗ORCID search ↗
×1
Niklas Lauffer
DBLP profile ↗ORCID search ↗
×1
Andrew Garber
DBLP profile ↗ORCID search ↗
×1
Evan Ellis
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AssistanceZero: Scalably Solving Assistance Games
    ICML 2025 ·
    Cassidy Laidlaw
    DBLP profile ↗ORCID search ↗
  2. Avoiding Catastrophe in Online Learning by Asking for Help
    ICML 2025 ·
    Benjamin Plaut
    DBLP profile ↗ORCID search ↗
  3. BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping
    ICLR 2025 ·
    Aly Lidayan
    DBLP profile ↗ORCID search ↗
  4. Diffusion On Syntax Trees For Program Synthesis
    ICLR 2025 ·
    Shreyas Kapur
    DBLP profile ↗ORCID search ↗
  5. Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts
    ICML 2025 ·
    Jiahai Feng
    DBLP profile ↗ORCID search ↗
  6. Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
    NeurIPS 2025 ·
    Yixiao Huang
    DBLP profile ↗ORCID search ↗
  7. Monitoring Latent World States in Language Models with Propositional Probes
    ICLR 2025 ·
    Jiahai Feng
    DBLP profile ↗ORCID search ↗
  8. Observation Interference in Partially Observable Assistance Games
    ICML 2025 ·
    Scott Emmons
    DBLP profile ↗ORCID search ↗
  9. RL, but don't do anything I wouldn't do
    UAI 2025 ·
    Michael K. Cohen
    DBLP profile ↗ORCID search ↗
  10. Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
    NeurIPS 2025 ·
    Hanlin Zhu
    DBLP profile ↗ORCID search ↗
  11. Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
    NeurIPS 2025 ·
    Niklas Lauffer
    DBLP profile ↗ORCID search ↗
  12. The Partially Observable Off-Switch Game
    AAAI 2025 ·
    Andrew Garber
    DBLP profile ↗ORCID search ↗
  13. A Generalized Acquisition Function for Preference-based Reward Learning
    ICRA 2024 ·
    Evan Ellis
    DBLP profile ↗ORCID search ↗
  14. AI Alignment with Changing and Influenceable Reward Functions
    ICML 2024 ·
    Micah Carroll
    DBLP profile ↗ORCID search ↗
  15. Ethically Compliant Autonomous Systems under Partial Observability
    ICRA 2024 ·
    Qingyuan Lu
    DBLP profile ↗ORCID search ↗
  16. Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
    NeurIPS 2024 ·
    Erik Jenner
    DBLP profile ↗ORCID search ↗
  17. Image Hijacks: Adversarial Images can Control Generative Models at Runtime
    ICML 2024 ·
    Luke Bailey
    DBLP profile ↗ORCID search ↗
  18. On Representation Complexity of Model-based and Model-free Reinforcement Learning
    ICLR 2024 ·
    Hanlin Zhu
    DBLP profile ↗ORCID search ↗
  19. Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
    ICML 2024 ·
    Vincent Conitzer
    DBLP profile ↗ORCID search ↗
  20. Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
    ICLR 2024 ·
    Sam Toyer
    DBLP profile ↗ORCID search ↗
  21. The Effective Horizon Explains Deep RL Performance in Stochastic Environments
    ICLR 2024 ·
    Cassidy Laidlaw
    DBLP profile ↗ORCID search ↗
  22. Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
    NeurIPS 2024 ·
    Hanlin Zhu
    DBLP profile ↗ORCID search ↗
  23. When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
    NeurIPS 2024 ·
    Leon Lang
    DBLP profile ↗ORCID search ↗