🏢 University of Maryland College Park

ZeroMark revolutionizes dataset ownership verification by enabling copyright protection without exposing watermarks, leveraging the intrinsic properties of DNNs trained on watermarked data.

This paper introduces robust reinforcement learning with general utility, providing novel algorithms with convergence guarantees for training robust policies under environmental uncertainty, significa…

Faster bilevel optimization is achieved via without-replacement sampling, improving convergence rates compared to independent sampling methods.

Model Sensitivity Aware Continual Learning (MACL) tackles the CL challenge by optimizing model performance based on parameter distribution, achieving superior old knowledge retention and new task perf…