[LG]《Can Looped Transformers... 爱可可-爱生活 2024-10-16 16:50:23 [LG]《Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?》K Gatmiry, N Saunshi, S J. Reddi, S Jegelka… [MIT & Google Research] (2024) 机器学习人工智能论文