lambda-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning
cs.LG, cs.CV
Submitted: 2026-09-28
Updated: 2026-09-29
Code: https://github.com/berkerdemirel/lambda-jepa
Terminology
Sources
- A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- The Kinetics Human Action Video Dataset
- When Does LeJEPA Learn a World Model?
- LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- Fine-Grained Visual Classification of Aircraft
- VISReg: Variance-Invariance-Sketching Regularization for JEPA training
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks