Zhuotong Chen

adversarial robustness (2) preference optimization (1) policy learning (1) adversarial training (1) contrastive divergence (1) adversarial attack (1) language model (1) bayesian neural network (1) uncertainty calibration (1) classifier robustness (1) closed-loop control (1) certifiable robustness (1) negative log-likelihood (1) posterior robustness (1) self-healing neural network (1)