works on

From the 2 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback

Patrick Wilhelm, Odej Kao

The paper investigates how to best allocate a fixed FLOP budget for reinforcement‑learning post‑training of foundation models, comparing larger policies, longer training, more sear…

cs.AI2026

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents

Patrick Wilhelm, Odej Kao

The paper investigates how internal activation signals, token entropy, and decision-context features can be used to monitor and mitigate reward‑hacking behavior in language‑model a…

cs.LG2026

Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning Aggregation

Patrick Wilhelm, Odej Kao

In asynchronous federated learning (FL), client devices send updates to a central server at varying times based on their computational speed, often using stale versions of the glob…

cs.CL2026

Beyond Test-Time Compute Strategies: Advocating Energy-per-Token in LLM Inference

Patrick Wilhelm, Thorsten Wittkopp, Odej Kao

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenar…

cs.LG2026

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Patrick Wilhelm, Inese Yilmaz, Odej Kao

Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data…

cs.CL2026

Monitoring Emergent Reward Hacking During Generation via Internal Activations

Patrick Wilhelm, Thorsten Wittkopp, Odej Kao

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has…