Oliver E. Richardson

Most-cited papers

1. Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?

   Y. Bengio, Michael K. Cohen, Damiano Fornasiere, J. Ghosn +9 more

   2025arXiv.org93 citations

   Semantic Scholar

   Save

2. Language models recognize dropout and Gaussian noise applied to their activations

   Damiano Fornasiere, Mirko Bronzi, Spencer Kitts, A. Palmas +2 more

   2026arXiv.org5 citations

   Semantic Scholar

   Save

3. Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

   Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D. Viviano +3 more

   2026arXiv.org2 citations

   Semantic Scholar

   Save

4. Qualitative Mechanism Independence

   Oliver E. Richardson, Spencer James Peters, Joseph Y. Halpern

   2025Neural Information Processing Systems2 citations

   Semantic Scholar

   Save

5. The Scientist AI: Safe by Design, by Not Desiring

   Damiano Fornasiere, Oliver E. Richardson, Gaël Gendron, I. Serban +1 more

   2 citations

   Semantic Scholar

   Save

6. Safety from Honesty in a Disinterested AI Predictor

   Y. Bengio, Oliver E. Richardson, Tomáš Gavenčiak, Michael K. Cohen +12 more

   2026arXiv.org1 citations

   Semantic Scholar

   Save

7. Latent Veracity Inference for Identifying Errors in Stepwise Reasoning

   Minsu Kim, Jean-Pierre R. Falet, Oliver E. Richardson, Xiaoyin Chen +4 more

   20251 citations

   Semantic Scholar

   Save

8. How to Verify Probabilistic Consistency of Predictive Models

   Orr Paradise, Oliver E. Richardson, Y. Bengio, S. Goldwasser

   20260 citations

   Semantic Scholar

   Save

9. Inverting the Bellman Equation: From Q-Values to World Models

   Alistair Letcher, Mattie Fellows, A. Goldie, Jonathan Richens +2 more

   2026arXiv.org0 citations

   Semantic Scholar

   Save

10. Learning with Confidence

    Oliver E. Richardson

    2025Conference on Uncertainty in Artificial Intelligence0 citations

    Semantic Scholar

    Save

11. Transformer-Based Observers in Psychotherapy

    Tarun Sunkaraneni, Oliver E. Richardson, Vivek Srikumar, C. ErinParkerThomas +4 more

    20200 citations

    Semantic Scholar

    Save

12. The Local Inconsistency Resolution Algorithm

    Oliver E. Richardson, Oliver E. Richardson

    0 citations

    Semantic Scholar

    Save

13. Complexity and Scale: Understanding the Creative

    Oliver E. Richardson

    0 citations

    Semantic Scholar

    Save