{"type":"link","version":"1.0","title":"Stop-gradients on a cached attention memory cut its effective receptive field far below the theoretical depth × window","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/stop-gradient-cache-truncates-effective-receptive-field","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}