Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models

Read full text
Authors: Huaping Liu, Xinghang Li, Peiyan Li, Long Qian, Minghuan Liu, Dong Wang, Jirong Liu, Bingyi Kang, Xiao Ma, Xinlong Wang, Di Guo, Tao Kong
+1 more Hanbo Zhang
Cited by: 0

Abstract

The dataset contains robotic arm action trajectories with language annotations in simulators and real scenarios. All the demonstration datasets are collected through human tele-operation. We open-source the real-world collected data at https://huggingface.co/datasets/robovlms/bytedance_robot_benchmark_20. Further, we open source the RoboVLMs framework and install guidelines at https://github.com/Robot-VLAs/RoboVLMs.

Fields of Study & Subjects

Robot Manipulation and Learning Multimodal Machine Learning Applications Reinforcement Learning in Robotics

Publication details

Journal / source
Figshare
Publication date
1 January 2026
Language
EN
Document type
Dataset