註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Baoyu Li ✈️ CoRL 2026
@BaoyuLi6
CS PhD @GeorgiaTech @ICatGT | Prev. MSCS @UofIllinois @siebelschool | Robot Learning 🤖 | Opinions are my own.
加入 March 2022
834 正在關注    794 粉絲
Egocentric human data is abundant, but human motion is not always positive supervision for robot policy due to embodiment gaps. Naive BC co-training can HURT performance ☹️. 🌟Our key finding in **EgoWAM**: the state-prediction branch of a World Action Model effectively bridges this embodiment gap, enabling robot performance to scale with diverse **in-the-wild** human data. 💡The key question then becomes: what world representation transfers best across embodiments? 👇🏻Let’s take a deep dive into it: 🌐 🧵[1/]
顯示更多
0
25
321
58
轉發到社區