Patrick Wilhelm
Patrick Wilhelm
Doctoral researcher
Patrick Wilhelm, Odej Kao
Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
Patrick Wilhelm, Thorsten Wittkopp, Odej Kao
Monitoring Emergent Reward Hacking During Generation via Internal Activations
Patrick Wilhelm, Inese Yilmaz, Odej Kao
Noise-Aware Client Selection for Carbon-Efficient Federated Learning via Gradient Norm Thresholding
Patrick Wilhelm, Thorsten Wittkopp, Odej Kao