Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos

• URL: http://arxiv.org/abs/2507.15597v1
• Date: Mon, 21 Jul 2025 13:19:09 GMT
• Title: Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
• Authors: Hao Luo, Yicheng Feng, Wanpeng Zhang, Sipeng Zheng, Ye Wang, Haoqi Yuan, Jiazheng Liu, Chaoyi Xu, Qin Jin, Zongqing Lu,
• Abstract summary: We introduce Being-H0, a dexterous Vision-Language-Action model trained on large-scale human videos.<n>Our approach centers on physical instruction tuning, a novel training paradigm that combines large-scale VLA pretraining from human videos, physical space alignment for 3D reasoning, and post-training adaptation for robotic tasks.<n>We empirically show the excellence of Being-H0 in hand motion generation and instruction following, and it also scales well with model and data sizes.
• Score: 66.62109400603394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Being-H0, a dexterous Vision-Language-Action model (VLA) trained on large-scale human videos. Existing VLAs struggle with complex manipulation tasks requiring high dexterity and generalize poorly to novel scenarios and tasks, primarily due to their reliance on synthetic data with significant sim-to-real gaps or teleoperated demonstrations lacking scale and diversity. To address this data bottleneck, we propose leveraging human hands as a foundation manipulator, capitalizing on the rich dexterity and scalability present in web data. Our approach centers on physical instruction tuning, a novel training paradigm that combines large-scale VLA pretraining from human videos, physical space alignment for 3D reasoning, and post-training adaptation for robotic tasks. Additionally, we introduce a part-level motion tokenization method which achieves millimeter-level reconstruction accuracy to model precise hand trajectories for action learning. To support our proposed paradigm, we further develop a comprehensive data curation pipeline that integrates heterogeneous sources -- including motion capture, VR, and RGB-only videos -- into a large-scale dataset with millions of motion-based instructional instances. We empirically show the excellence of Being-H0 in hand motion generation and instruction following, and it also scales well with model and data sizes. Importantly, we observe the expected gains of Being-H0 in real-world robotic manipulation as physical instruction tuning is applied. More details are available at https://beingbeyond.github.io/Being-H0.

Related papers

• DexVLG: Dexterous Vision-Language-Grasp Model at Scale [59.5613919093295]
  There is little research on functional grasping with large models for human-like dexterous hands.<n>We introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions.<n>We generate a dataset of 170 million dexterous grasp poses mapped to semantic parts across 174,000 objects in simulation, paired with detailed part-level captions.
  arXiv  Detail & Related papers  (2025-07-03T16:05:25Z)
• AMPLIFY: Actionless Motion Priors for Robot Learning from Videos [29.799207502031496]
  We introduce AMPLIFY, a novel framework that leverages large-scale video data.<n>We train a forward dynamics model on abundant action-free videos and an inverse dynamics model on a limited set of action-labeled examples.<n>In downstream policy learning, our dynamics predictions enable a 1.2-2.2x improvement in low-data regimes, a 1.4x average improvement by learning from action-free human videos, and the first generalization to LIBERO tasks from zero in-distribution action data.
  arXiv  Detail & Related papers  (2025-06-17T05:31:42Z)
• ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding [31.481969919049472]
  ActionArt is a fine-grained video-caption dataset designed to advance research in human-centric multimodal understanding.<n>Our dataset comprises thousands of videos capturing a broad spectrum of human actions, human-object interactions, and diverse scenarios.<n>We develop eight sub-tasks to evaluate the fine-grained understanding capabilities of existing large multimodal models across different dimensions.
  arXiv  Detail & Related papers  (2025-04-25T08:05:32Z)
• Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning [71.02843679746563]
  In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature.<n>In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process.<n>We propose EgoVideo, a model with a new lightweight motion adapter to capture fine-grained hand-object motion information.
  arXiv  Detail & Related papers  (2025-03-02T18:49:48Z)
• VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation [79.00294932026266]
  VidMan is a novel framework that employs a two-stage training mechanism to enhance stability and improve data utilization efficiency. Our framework outperforms state-of-the-art baseline model GR-1 on the CALVIN benchmark, achieving a 11.7% relative improvement, and demonstrates over 9% precision gains on the OXE small-scale dataset.
  arXiv  Detail & Related papers  (2024-11-14T03:13:26Z)
• EgoMimic: Scaling Imitation Learning via Egocentric Video [22.902881956495765]
  We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data. EgoMimic achieves this through: (1) a system to capture human embodiment data using the ergonomic Project Aria glasses, (2) a low-cost bimanual manipulator that minimizes the kinematic gap to human data, and (4) an imitation learning architecture that co-trains on human and robot data.
  arXiv  Detail & Related papers  (2024-10-31T17:59:55Z)
• Latent Action Pretraining from Videos [156.88613023078778]
  We introduce Latent Action Pretraining for general Action models (LAPA)<n>LAPA is an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels.<n>We propose a method to learn from internet-scale videos that do not have robot action labels.
  arXiv  Detail & Related papers  (2024-10-15T16:28:09Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.