AI Frontier Lectures
Nov 20, 2026 · Artificial Intelligence
SADL Loss Eliminates JEPA Collapse Across All Seeds, Boosts Effective Rank 6x
Zhejiang University's SADL (Supply and Demand Loss) adds a single regularizer to JEPA training that reduces collapse rate from 50% to 0% across ten random seeds, increases encoder effective rank 3.4–6.4× after one epoch, cuts latent prediction error to 1/20–1/303, and accelerates convergence on world model and image classification tasks, earning a retweet from Yann LeCun.
JEPALeCunSADL
0 likes · 8 min read
