VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

TL;DR

VideoVLA leverages large video generation models to enable robots to predict actions and visual outcomes, significantly improving their ability to generalize across new tasks, objects, and environments in manipulation tasks.

Contribution

This work introduces VideoVLA, a novel approach that transforms video generation models into robotic manipulators capable of joint action and visual outcome prediction for better generalization.

Findings

High-quality visual imagination correlates with successful manipulation.

VideoVLA demonstrates strong generalization to new objects and tasks.

The dual-prediction strategy enhances robot learning and adaptability.

Abstract

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy - forecasting both actions and their visual consequences - explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems.