Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
SR-JEPA: Learning Predictive Latent State in 3D Scenes
Zihan Zhou, Qifu Wen, Xi Zeng
Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they…
cs.CV2026
PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models
Xi Zeng, Haojie Ren, Ziying Song +2
We propose PhyLatent, a dynamics-relevant training objective for Joint-Embedding Predictive Architecture (JEPA) world models. Our key observation is that preventing global latent c…