3 papers
cs.CV2026
Frozen in a Frame: The Velocity Blind Spot in JEPA World Models
Tinghe Zhang, Chunyu Liu, Yu Leon Liu +6
Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next frame's embedding, always from a…
cs.AI2026
Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
Jiaheng Chen, Jiaxing Li, Yucheng Xiao +4
Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance or repre…
cs.LG2026
NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
Tinghe Zhang, Jian Xu, Jiaheng Chen +3
Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attribu…