What Should World Models Forget? Stratified Retention for Continual Adaptation
cs.LG, cs.AI, cs.CV, eess.IV, eess.SP
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Don't forget, there is more than forgetting: new metrics for Continual Learning
- Training Agents Inside of Scalable World Models
- LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- PhyGround: Benchmarking Physical Reasoning in Generative World Models
- stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
- The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
- Critique of World Model
- Augmenting Replay in World Models for Continual Reinforcement 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks