Zico Kolter

8 papers Carnegie Mellon University

• Antidistillation Sampling
• Mean Flows for One-step Generative Modeling
• Mean Flows for One-step Generative Modeling
• OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
• Predicting the Performance of Black-box Language Models with Follow-up Queries
• Safety Pretraining: Toward the Next Generation of Safe AI
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition