Sarathkrishna Swaminathan

reinforcement learning (2) attention mechanism (1) long context (1) factuality evaluation (1) policy learning (1) abstract meaning representation (1) model alignment (1) episodic memory (1) human judgment (1) rule learning (1) language model (1) proximal policy optimization (1) evaluation metric (1) retrieval-augmented generation (1) question answering (1) key-value cache (1) human evaluation (1) text-based game (1) abstractive summarization (1) preference learning (1)