Norman Mu

5

Papers

31

Total Citations

Papers (5)

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

MoST: Multi-Modality Scene Tokenization for Motion Prediction

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

SLIP: Self-Supervision Meets Language-Image Pre-training