Tianyu Pang

This paper conducts the first real-world safety evaluation of the personal AI agent OpenClaw, demonstrating that its broad system access creates inherent vulnerabilities that significantly increase the attack success rate regardless of the underlying large language model.

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime-aware diagnostic approach.

This paper introduces MeanFlowNFT, a method that applies reinforcement learning to MeanFlow generators to improve performance and consistency.