NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

TL;DR

NORA-1.5 is an improved vision-language-action model that leverages a flow-matching action expert and reward-based post-training to enhance robustness and generalization for embodied tasks in real-world environments.

Contribution

The paper introduces NORA-1.5 with architectural enhancements and reward-driven post-training, significantly improving performance and reliability over prior models in embodied vision-language tasks.

Findings

NORA-1.5 outperforms previous models on simulated and real-world benchmarks.

Reward-based post-training improves task success and robustness.

Model reliability is significantly enhanced through simple reward models.

Abstract

Vision--language--action (VLA) models have recently shown promising performance on a variety of embodied tasks, yet they still fall short in reliability and generalization, especially when deployed across different embodiments or real-world environments. In this work, we introduce NORA-1.5, a VLA model built from the pre-trained NORA backbone by adding to it a flow-matching-based action expert. This architectural enhancement alone yields substantial performance gains, enabling NORA-1.5 to outperform NORA and several state-of-the-art VLA models across both simulated and real-world benchmarks. To further improve robustness and task success, we develop a set of reward models for post-training VLA policies. Our rewards combine (i) an action-conditioned world model (WM) that evaluates whether generated actions lead toward the desired goal, and (ii) a deviation-from-ground-truth heuristic that distinguishes good actions from poor ones. Using these reward signals, we construct preference datasets and adapt NORA-1.5 to target embodiments through direct preference optimization (DPO). Extensive evaluations show that reward-driven post-training consistently improves performance in both simulation and real-robot settings, demonstrating significant VLA model-reliability gains through simple yet effective reward models. Our findings highlight NORA-1.5 and reward-guided post-training as a viable path toward more dependable embodied agents suitable for real-world deployment.