註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Yujia Zheng
@YujiaZheng9
Assistant Professor @UofIllinois. PhD @CarnegieMellon. Interested in causal learning and machine learning.
加入 August 2021
266 正在關注    1.7K 粉絲
Is it possible to provably recover individual latent variables of the true world, even without reconstruction (e.g., JEPA)? Yes, with DSReg, a simple regularization that can be applied post hoc to your pretrained model!
顯示更多
0
11
305
45
轉發到社區