Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
cs.RO
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 8 pages, 9 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- Octo: An Open-Source Generalist Robot Policy
- TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
- Self-Improving Embodied Foundation Models
- Steering Your Diffusion Policy with Latent Space Reinforcement Learning
- Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
- Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
- GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
- WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
- World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
- RISE: Self-Improving Robot Policy with Compositional World Model
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Soft Actor-Critic Algorithms and Applications
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies