爱可可-爱生活
20-04-26 05:26 微博认证:AI博主 2025微博新锐新知博主

《Attention Module is Not Only a Weight: Analyzing Transformers with Vector Norms》G Kobayashi, T Kuribayashi, S Yokoi, K Inui [Tohoku University] (2020) http://t.cn/A6wFCdkP view:http://t.cn/A6wFCdkv ​