How to Better Train VLAs: Lessons Learned From the REAL-I Challenge at ICRA 2026

arXiv:2609.13679 · cs.RO · Submitted 2026-09-12 · Read on arXiv

cs.RO

Submitted: 2026-09-12

Updated: 2026-09-17

Project page: https://www.kdc.icra.l

Terminology

• Adaptation — 20× in this paper · explained in 1 episode
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Distribution Shift — 4× in this paper · explained in 5 episodes
• Embodied AI — 4× in this paper · explained in 2 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Action Chunking — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hybrid System — 1× in this paper · explained in 2 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• VLA Models — 1× in this paper · explained in 3 episodes

Sources

• Training-free Task-oriented Grasp Generation
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• $\pi^{*}_{0.6}$: a VLA That Learns From Experience

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