Shang-Tse Chen

Privacy (2)

neural network (2) large language model (2) model merging (2) adversarial learning (1) domain adaptation (1) direct preference optimization (1) online learning (1) knowledge representation (1) distributed learning (1) privacy preservation (1) automatic speech recognition (1) formal verification (1) model safety (1) llm defense (1) reinforcement learning from human feedback (1) prompt engineering (1) multiclass classification (1) model alignment (1) agnostic learning (1) certified robustness (1)