HamJEPA advances JEPAs with Hamiltonian geometry and symplectic prediction

Researchers have introduced HamJEPA, a novel approach to Joint Embedding Predictive Architectures (JEPAs) that moves beyond isotropic regularization. This new method encodes views as phase-space states and uses a learned Hamiltonian leapfrog map for cross-view prediction. Experiments on CIFAR-100 and ImageNet-100 show significant improvements in kNN and linear probe accuracy compared to existing methods like SIGReg. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a new method for representation learning that improves performance on downstream tasks.

RANK_REASON The cluster contains an academic paper detailing a new method and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CIFAR-100
• HamJEPA
• ImageNet-100
• JEPAs
• Robert Jenkinson Alvarez
• SIGReg

• paper
• other