EpicWorldModel: Exploration-driven Planning with Latent World Models
cs.LG, cs.AI, cs.RO
Submitted: 2026-10-05
Updated: 2026-10-05
Terminology
Sources
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Revisiting Feature Prediction for Learning Visual Representations from Video
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features
- Multisample Flow Matching: Straightening Flows with Minibatch Couplings
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- World Models
- Ctrl-World: A Controllable Generative World Model for Robot Manipulation
- WorldGym: World Model as An Environment for Policy Evaluation
- IRASim: A Fine-Grained World Model for Robot Manipulation
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- Denoising with a Joint-Embedding Predictive Architecture
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Wan: Open and Advanced Large-Scale Video Generative Models
- LTX-Video: Realtime Video Latent Diffusion
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- Advancing Open-source World Models
- DreamerV3-XP: Optimizing exploration through uncertainty estimation
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