Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation
cs.AI, cs.RO
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Learning Dexterous Manipulation with Quantized Hand State
- Classifier-Free Diffusion Guidance
- World Model for Robot Learning: A Comprehensive Survey
- The Effectiveness of World Models for Continual Reinforcement Learning
- Flow Matching for Generative Modeling
- mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
- WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
- Wan: Open and Advanced Large-Scale Video Generative Models
- DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo
- Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
- WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation
- LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Learning Manipulation by Predicting Interaction
- Native Video-Action Pretraining for Generalizable Robot Control
- Guided Flows for Generative Modeling and Decision Making
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection