Blake Richards

Google, Paradigms of Intelligence Team, Mila -Quebec AI Institute, CIFAR, McGill University

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Scalable Oversight & Alignment Theory (1)Tool Use & Agents (1)Architecture Design (Transformers, SSMs, MoE) (1)

Frequent co-authors

Alexander Meulemans (1)Maciej Wołczyk (1)Marissa A. Weis (1)Rajai Nasser (1)

Papers (2)

Aug 4, 2026

Google Research2w ago·also ETH, Mila, Affiliation:, CIFAR +4

A game theory for foundation models shows new paths to rational cooperation through similarity inference

Foundation model agents can achieve stable cooperation in social dilemmas by inferring behavioral similarities, defying classical game theory's expectations of mutual defection.

Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis +11

Constitutional AI & AI Ethics Scalable Oversight & Alignment Theory Tool Use & Agents

Mar 18, 2026

Roy Henha Eyono +4Mar 18, 2026·also Google Research, Mila, CIFAR, McGill +1

Inhibitory normalization of error signals improves learning in neural circuits

Normalizing error signals, not just activations, is the key to unlocking the benefits of inhibition-mediated normalization for learning in neural networks.

Roy Henha Eyono, Daniel Levenstein, Arna Ghosh +2

Architecture Design (Transformers, SSMs, MoE)Training Efficiency & Optimization

Search

Blake Richards

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)