註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Berker Demirel
@berkerdemirel97
PhD Candidate in Computer Science at IST Austria Working on Computer Vision and Deep Learning
加入 October 2026
355 正在關注    118 粉絲
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.
顯示更多
0
5
426
59
轉發到社區