Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
cs.LG, cs.AI
Submitted: 2026-05-19
Updated: 2026-10-31
Terminology
Sources
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Hamiltonian Neural Networks
- KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning