Orthogonal JEPA: Factorized Predictive States for Latent World Models
cs.LG
Submitted: 2026-08-20
Updated: 2026-09-21
Comments: This manuscript has been superseded by a substantially revised version, arXiv:2609.20800. The simultaneous existence of both records has caused significant confusion regarding the relationship and development of the work. To prevent further misunderstanding and maintain a clear scientific record, we request withdrawal of arXiv:2608.20065
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DINOv3
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Cell-JEPA: Latent Representation Learning for Single-Cell Transcriptomics
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