Adaptive Latent Capacity for World Models
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- When Does LeJEPA Learn a World Model?
- Predictive but Not Plannable: RC-aux for Latent World Models
- AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment
- Latent Geometry Beyond Search: Amortizing Planning in World Models
- Cosmos World Foundation Model Platform for Physical AI
- VISReg: Variance-Invariance-Sketching Regularization for JEPA training
- A Control Theory of Predictability in Latent World Models
- On the Identifiability of Controlled World Models
- Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
- KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
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