{"type":"link","version":"1.0","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2212.10559","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2212.10559.png","thumbnail_width":1200,"thumbnail_height":630}