AnalysisAI Models
3 hours ago
SIGReg JEPA scales to compete with DINO foundation models
Yann LeCun
@ylecunProfessor at NYU & Executive Chairman at AMI Labs. Ex-Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
New Yorkyann.lecun.com
Yann LeCun
@ylecun
RT @randall_balestr: Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer:…
·
3 hours ago