注册并分享邀请链接,可获得视频播放与邀请奖励。

Berker Demirel
@berkerdemirel97
PhD Candidate in Computer Science at IST Austria Working on Computer Vision and Deep Learning
加入 October 2026
355 正在关注    118 粉丝
In JEPA, are we preventing collapse in the representation we actually use downstream? TLDR: not necessarily. A high-rank projected representation does not guarantee a non-collapsed backbone. λ-JEPA is designed to target this gap.
显示更多
0
5
426
59
转发到社区