Flavio Calmon

4 papers Harvard University

• HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions
• Inference-Time Reward Hacking in Large Language Models
• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
• Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy