Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- Fast LeWorldModel
- Temporal Difference Learning for Model Predictive Control
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Transformers are Sample-Efficient World Models
- DINOv2: Learning Robust Visual Features without Supervision
- Latent Energy Action Planning with World Models
- Parallel Stochastic Gradient-Based Planning for World Models
- Statistical Efficiency of Single- and Multi-step Models for Forecasting and Control
- Koopman-BoxQP: Solving Large-Scale NMPC at kHz Rates
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
- Grounding Generated Videos in Feasible Plans via World Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems