TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models

arXiv:2609.26314 · cs.RO, cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

Code: https://github.com/TriWorldBench/TriWorldBench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 26× in this paper · explained in 3 episodes
• World Model — 19× in this paper · explained in 7 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Alignment — 10× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Temporal consistency — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Verification — 2× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• WorldModelBench: Judging Video Generation Models As World Models
• Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
• CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors
• WorldSimBench: Towards Video Generation Models as World Simulators
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration
• EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Motus: A Unified Latent Action World Model
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• Rethinking Video Generation Model for the Embodied World
• WorldScore: A Unified Evaluation Benchmark for World Generation
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
• World Models
• RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
• EnerVerse-AC: Envisioning Embodied Environments with Action Condition

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