Sharath Chandra Raparthy

active learning (1) reinforcement learning (1) continual learning (1) catastrophic forgetting (1) adversarial learning (1) adversarial robustness (1) prompt engineering (1) text generation (1) model safety (1) markov chain (1) mixing time (1) multi-objective optimization (1) adversarial attack (1) generative model (1) prompt generation (1) adversarial prompt (1) open-ended search (1) quality-diversity optimization (1) attack transferability (1) safety fine-tuning (1)