The Planning Limits of Latent World Models
cs.RO, cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Diverse Domains through World Models
- Training Agents Inside of Scalable World Models
- Interpreting Physics in Video World Models
- OpenVLA: An Open-Source Vision-Language-Action Model
- RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models
- Objective Mismatch in Model-based Reinforcement Learning
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
- DINOv2: Learning Robust Visual Features without Supervision
- A Control-Centric Benchmark for Video Prediction
- From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
- What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving