villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

TL;DR

villa-X introduces a novel framework that enhances latent action modeling in vision-language-action models, enabling zero-shot generalization and superior manipulation performance in diverse robotic tasks.

Contribution

The paper presents villa-X, a new ViLLA framework that improves latent action learning and integration, advancing generalization in robot manipulation policies.

Findings

Zero-shot latent action planning for unseen embodiments

Superior performance on diverse simulation tasks

Effective real-world robotic manipulation

Abstract

Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of latent actions, abstract representations of motion between two frames, into VLA pre-training. In this paper, we introduce villa-X, a novel Vision-Language-Latent-Action (ViLLA) framework that advances latent action modeling for learning generalizable robot manipulation policies. Our approach improves both how latent actions are learned and how they are incorporated into VLA pre-training. We demonstrate that villa-X can generate latent action plans in a zero-shot fashion, even for unseen embodiments and open-vocabulary symbolic understanding. This capability enables villa-X to achieve superior performance across diverse simulation tasks in SIMPLER and on two real-world robotic setups involving both gripper and dexterous hand manipulation. These results establish villa-X as a principled and scalable paradigm for learning generalizable robot manipulation policies. We believe it provides a strong foundation for future research.