When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations
cs.RO, cs.AI, cs.SY, eess.SY
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://mudhdhoo.github.io/WhenWordModelsLie_project_page
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Gemini Robotics: Bringing AI into the Physical World
- Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis
- Hallucination in World Models is Predictable and Preventable
- Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
- Feedback World Model Enables Precise Guidance of Diffusion Policy
- Foundational World Models Accurately Detect Bimanual Manipulator Failures
- Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
- Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models
- Safe Control using Learned Safety Filters and Adaptive Conformal Inference
- How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
- Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
- Mastering Diverse Domains through 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