登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

Swarnadeep Saha
@swarnaNLP
Research Scientist @AIatMeta (FAIR) working on co-improvement. Past: @Google PhD fellow @uncnlp. Gooner.
参加 May 2014
826 フォロー中    1.7K ファン
My favorite bits: 1. By *meta-optimizing* rubrics, we learn *features* that make expert-human writing superior & thus RL against those rubrics can produce *superhuman* text too. 2. In an online setting, this co-improves both rubrics+model, so extends beyond this specific task.
もっと見る