RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation

arXiv:2606.01600 · cs.CV, cs.CL, cs.RO · Submitted 2026-06-01 · Read on arXiv

cs.CV, cs.CL, cs.RO

Submitted: 2026-06-01

Updated: 2026-08-31

Comments: EMNLP 2026 Findings, Project: https://huiqiongli.github.io/RoboTrustBench/

Project page: https://huiqiongli.github.io/RoboTrustBench

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

Terminology

• World Model — 46× in this paper · explained in 7 episodes
• Consistency — 32× in this paper · explained in 3 episodes
• Benchmark — 27× in this paper · explained in 2 episodes
• Alignment — 20× in this paper · explained in 1 episode
• Visual Quality — 20× in this paper
• Interaction Rationality — 14× in this paper
• Task Execution Quality — 12× in this paper
• Benchmarking — 9× in this paper · explained in 3 episodes
• Evaluation Dimensions — 8× in this paper · explained in 3 episodes
• Grounding — 8× in this paper · explained in 3 episodes
• Safety Risk Identification — 8× in this paper
• Adversarial scenarios — 5× in this paper · explained in 1 episode
• Adversarial Examples — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Temporal consistency — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Action-Conditioned World Model — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes

Sources

• Rethinking Video Generation Model for the Embodied World
• World Simulation with Video Foundation Models for Physical AI
• Qwen3-VL Technical Report
• Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test
• GigaWorld-0: World Models as Data Engine to Empower Embodied AI
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• Large Video Planner Enables Generalizable Robot Control
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• WorldEval: World Model as Real-World Robot Policies Evaluator
• Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
• RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
• Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
• Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions
• Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
• Causal World Modeling for Robot Control
• Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
• Advancing Open-source World Models
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• HunyuanVideo 1.5 Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models