ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models
cs.RO, cs.AI
Submitted: 2026-08-26
Updated: 2026-10-02
Project page: https://confal-wm.github.io
Terminology
Sources
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Uncertainty-aware Active Learning of NeRF-based Object Models for Robot Manipulators using Visual and Re-orientation Actions
- DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
- Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation
- Sample Efficient Robot Learning in Supervised Effect Prediction Tasks
- RoboReward: General-Purpose Vision-Language Reward Models for Robotics
- WorldModelBench: Judging Video Generation Models As World Models
- Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
- Being-H0.7: A Latent World-Action Model from Egocentric Videos
- Vision Language Models are In-Context Value Learners
- World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
- Uncertainty Quantification for Flow-Based Generalist Robot Policies
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Causally Debiased Latent Action Model for Embodied Action-Conditioned World Models
- Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
- SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
- PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
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