86%Must read
?Must readVote to see the score
Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
Linearizing JEPA gradient flow reveals competing drive and decay effects that unify collapse-avoidance heuristics and predict a stability phase boundary, leading to ResidualPred, which improves rank and accuracy.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
– ReadersNo votes yet
14/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 14 of 20 reviewers recommend it
lenient 2/5
medium 10/10
strict 2/5