Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing T10просмотровгод назад
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM5просмотровгод назад
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models4просмотрагод назад
