2 papers
cs.LG2026
Learning over Positive and Negative Edges with Contrastive Message Passing
Peter Pao-Huang, Charilaos I. Kanatsoulis, Michael Bereket +1
Conventional approaches to learning on graphs involve message passing along existing (i.e., positive) edges to update node features. However, these approaches often disregard the p…
cs.LG2025
Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
Michael Bereket, Jure Leskovec
Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine…