Robert Kirk

Artificial Intelligence (8) Core AI (8) Machine Learning (7) Optimization & Theory (6) Natural Language Processing (3) Learning Types (2) Reinforcement Learning (1) Applications (1) Generation (1) Learning Paradigms (1) Methods (1) Resources & Methods (1)

large language model (2) reinforcement learning from human feedback (2) network pruning (1) model interpretability (1) proximal policy optimization (1) bradley-terry model (1) heavy-tailed distribution (1) steering vector (1) language model (1) supervised fine-tuning (1) adversarial attack (1) task diversity (1) mechanistic interpretability (1) best-of-n sampling (1) out-of-distribution generalization (1) few-shot prompting (1) procedural knowledge (1) inference-time intervention (1) dataset diversity (1) in-context learning (1)