Good Views Are Not Enough: Global Counterexamples for Gaussian-Regularized JEPAs
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Proving and Improving the Platonic Representation Hypothesis with JEPAs
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
- When Does LeJEPA Learn a World Model?
- On the Identifiability of Controlled World Models
- Anisotropic Representations Improve Planning in JEPA World Models
- On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
- Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
- Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
- Why Self-Supervised Encoders Want to Be Normal
- InfoNCE: Identifying the Gap Between Theory and Practice
- Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
- LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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