HamJEPA advances JEPAs with Hamiltonian geometry and symplectic prediction

By PulseAugur Editorial · [1 sources] · 2026-05-19 16:57

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

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 →

paper
other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

HamJEPA advances JEPAs with Hamiltonian geometry and symplectic prediction

COVERAGE [1]

arXiv cs.AI TIER_1 English(EN) · Robert Jenkinson Alvarez · 2026-05-19 16:57

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that this is not merely a benign default. For a known structured downstream geometry $H\succ0$, the minimax and maximum-entropy covarianc…

COVERAGE [1]

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

RELATED ENTITIES

RELATED TOPICS