AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control

arXiv:2609.30264 · cs.AI, cs.RO · Submitted 2026-09-24 · Read on arXiv

cs.AI, cs.RO

Submitted: 2026-09-24

Updated: 2026-09-25

Project page: https://ad-wm.github.io

Terminology

• World Model — 17× in this paper · explained in 7 episodes
• Regret — 10× in this paper · explained in 3 episodes
• Latent Dynamics — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Adaptation — 5× in this paper · explained in 1 episode
• Regularization — 4× in this paper · explained in 3 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Latent World Models — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• World Models
• Fast LeWorldModel
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

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