SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

arXiv:2605.26900 · cs.LG · Submitted 2026-05-26 · Read on arXiv

cs.LG

Submitted: 2026-05-26

Updated: 2026-10-05

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 3× in this paper · explained in 2 episodes
• Kernel Ridge Regression — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes

Sources

• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• k-Nearest neighbor density estimation on Riemannian Manifolds
• DINOv2: Learning Robust Visual Features without Supervision
• Spreading vectors for similarity search
• DINOv3

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks