注册并分享邀请链接,可获得视频播放与邀请奖励。

Yujia Zheng
@YujiaZheng9
Assistant Professor @UofIllinois. PhD @CarnegieMellon. Interested in causal learning and machine learning.
加入 August 2021
266 正在关注    1.7K 粉丝
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!
显示更多
0
11
305
45
转发到社区