Chan Woo Kim

reinforcement learning (1) domain adaptation (1) feature attribution (1) data valuation (1) reinforcement learning from human feedback (1) amortized inference (1) human feedback (1) synthetic datum (1) reward model (1) noisy label (1) noisy label training (1) model explanation (1) model acceleration (1) explainable machine learning (1) code-switching speech recognition (1) multilingual automatic speech recognition (1) preference ranking (1) amortized model (1) amortized learning (1) trajectory comparison (1)