JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
- Finetuning Offline World Models in the Real World
- WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
- The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Training Agents Inside of Scalable World Models
- Self-Supervised Policy Adaptation during Deployment
- RMA: Rapid Motor Adaptation for Legged Robots
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- DeepMind Control Suite
- Tent: Fully Test-time Adaptation by Entropy Minimization
- AdaJEPA: An Adaptive Latent World Model
- Temporal Straightening for Latent Planning
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