DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

arXiv:2610.12468 · cs.RO, cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/haosulab/MPlib

Project page: https://brave-eai.github.io/DreamTrue

Terminology

• Calibration — 48× in this paper · explained in 7 episodes
• World Model — 41× in this paper · explained in 7 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Consistency — 10× in this paper · explained in 3 episodes
• Fidelity — 8× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Ablation — 2× in this paper · explained in 1 episode
• F1 Score — 2× in this paper · explained in 3 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Latent World Models — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Action-Conditioned World Model — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Embodied AI — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes
• Success-Rate Mean Absolute Error — 1× in this paper

Sources

• Masked Visual Actions for Unified World Modeling
• SAM 3: Segment Anything with Concepts
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
• Evaluating Gemini Robotics Policies in a Veo World Simulator
• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
• VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
• RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence
• PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
• EnerVerse-AC: Envisioning Embodied Environments with Action Condition
• WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
• A Comprehensive Survey on World Models for Embodied AI
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
• World Simulation with Video Foundation Models for Physical AI
• FACT: Failure-Aware Causal Training for World-Action Models
• Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models
• GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
• Qwen3.5-Omni Technical Report
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

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