Oliver Richardson

According to our database, Oliver Richardson authored at least 9 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

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

Damiano Fornasiere, Mirko Bronzi, Spencer Kitts, Alessandro Palmas, Yoshua Bengio, Oliver Richardson

CoRR, April, 2026

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

Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D. Viviano, Abdessamad El Kabid, Ali Parviz, Yoshua Bengio

CoRR, April, 2026

2025

Search-Based Correction of Reasoning Chains for Language Models.

Minsu Kim, Jean-Pierre R. Falet, Oliver E. Richardson, Xiaoyin Chen, Moksh Jain, Sungjin Ahn, Sungsoo Ahn, Yoshua Bengio

CoRR, May, 2025

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

Yoshua Bengio, Michael K. Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King

CoRR, February, 2025

Learning with Confidence.

Oliver E. Richardson

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

2024

Qualitative Mechanism Independence.

Oliver Richardson, Spencer J. Peters, Joseph Y. Halpern

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Inference for probabilistic dependency graphs.

Oliver E. Richardson, Joseph Y. Halpern, Christopher De Sa

Proceedings of the Uncertainty in Artificial Intelligence, 2023

2022

Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose Your Model, Not Your Loss Function.

Oliver E. Richardson

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Probabilistic Dependency Graphs.

Oliver Richardson, Joseph Y. Halpern

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021