Processed egocentric human video outperforms teleoperated real-robot trajectories as pretraining data for embodied foundation models, delivering 24% lower validation loss and 52.5-90% higher task success rates under matched post-training protocols.
hub Canonical reference
Being-h0: vision-language-action pretraining from large-scale human videos
Canonical reference. 78% of citing Pith papers cite this work as background.
39
Pith papers citing it
Background
78% of classified citations
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.
hub tools
citation-role summary
background 7
baseline 1
dataset 1
citation-polarity summary
representative citing papers
Dexora is the first open-source VLA system for dual-arm dual-hand high-DoF manipulation, trained on 100K simulated and 10K real teleoperated trajectories with a discriminator-weighted diffusion policy, achieving 66.7% dexterous success versus 51.7% for baselines.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
SFHand presents the first streaming language-guided autoregressive framework for 3D hand forecasting, achieving up to 35.8% gains over prior methods and 13.4% better downstream embodied task performance.
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
Human-as-Humanoid converts ego-exo human videos into executable 60-DoF humanoid actions through embodiment alignment and retargeting, enabling zero-shot real-robot policy deployment without target-task teleoperation data.
A relative wrist translation bridging action with a vision-language-action model using interleaved tokens and attention masking transfers human manipulation skills to robots more effectively than 6DoF actions.
GRA extracts 2D waypoints from synthetic videos to supervise VLA vision while restricting action training to real data, outperforming pseudo-action baselines on real-robot tasks.
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
DO AS I DO reconstructs and retargets hand-object interactions from in-the-wild monocular RGB videos to produce dexterous robot manipulation trajectories, outperforming prior methods on ground-truth and online video datasets.
Qwen-RobotManip applies unified alignment across representation, motion, and behavior to enable large-scale training on heterogeneous manipulation data, yielding emergent generalization on out-of-distribution robotic benchmarks.
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.
A wearable interface with a shared dexterous hand module enables retargeting-free teleoperation and matched data collection, yielding policies with 88.75% average success across eight real-robot tasks that generalize and transfer across embodiments.
X-DiffVLA proposes a diffusion VLA model using Embodiment Forcing and Morphological Tree Diffusion to achieve SOTA cross-embodied performance on simulation benchmarks with 15.3% and 12.5% gains.
HandITL enables seamless human intervention in VLA policies for bimanual dexterous manipulation, cutting jitter by 99.8% and improving refined policies by 19% over standard teleoperation.
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
Sim-and-real co-training for robot policies is driven primarily by balanced cross-domain representation alignment and secondarily by domain-dependent action reweighting.
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
citing papers explorer
-
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Processed egocentric human video outperforms teleoperated real-robot trajectories as pretraining data for embodied foundation models, delivering 24% lower validation loss and 52.5-90% higher task success rates under matched post-training protocols.
-
Dexora: Open-source VLA for High-DoF Bimanual Dexterity
Dexora is the first open-source VLA system for dual-arm dual-hand high-DoF manipulation, trained on 100K simulated and 10K real teleoperated trajectories with a discriminator-weighted diffusion policy, achieving 66.7% dexterous success versus 51.7% for baselines.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting
SFHand presents the first streaming language-guided autoregressive framework for 3D hand forecasting, achieving up to 35.8% gains over prior methods and 13.4% better downstream embodied task performance.
-
EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
-
Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
-
Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments
Human-as-Humanoid converts ego-exo human videos into executable 60-DoF humanoid actions through embodiment alignment and retargeting, enabling zero-shot real-robot policy deployment without target-task teleoperation data.
-
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
A relative wrist translation bridging action with a vision-language-action model using interleaved tokens and attention masking transfers human manipulation skills to robots more effectively than 6DoF actions.
-
Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
GRA extracts 2D waypoints from synthetic videos to supervise VLA vision while restricting action training to real data, outperforming pseudo-action baselines on real-robot tasks.
-
Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
-
Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
DO AS I DO reconstructs and retargets hand-object interactions from in-the-wild monocular RGB videos to produce dexterous robot manipulation trajectories, outperforming prior methods on ground-truth and online video datasets.
-
Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
Qwen-RobotManip applies unified alignment across representation, motion, and behavior to enable large-scale training on heterogeneous manipulation data, yielding emergent generalization on out-of-distribution robotic benchmarks.
-
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
-
$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
-
LARA: Latent Action Representation Alignment for Vision-Language-Action Models
LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.
-
RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
A wearable interface with a shared dexterous hand module enables retargeting-free teleoperation and matched data collection, yielding policies with 88.75% average success across eight real-robot tasks that generalize and transfer across embodiments.
-
X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
X-DiffVLA proposes a diffusion VLA model using Embodiment Forcing and Morphological Tree Diffusion to achieve SOTA cross-embodied performance on simulation benchmarks with 15.3% and 12.5% gains.
-
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
HandITL enables seamless human intervention in VLA policies for bimanual dexterous manipulation, cutting jitter by 99.8% and improving refined policies by 19% over standard teleoperation.
-
HumanNet: Scaling Human-centric Video Learning to One Million Hours
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
-
Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
-
A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
Sim-and-real co-training for robot policies is driven primarily by balanced cross-domain representation alignment and secondarily by domain-dependent action reweighting.
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
-
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
ZeroDex grounds VLM outputs into 3D keypoints via multi-view triangulation and ray voting to enable zero-shot long-horizon dexterous manipulation with closed-loop replanning.
-
LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
-
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
WLA models use an autoregressive Transformer to jointly predict textual subtasks, subgoal images, and robot actions from instructions, images, and states, reporting SOTA success rates on RoboTwin2.0 and RMBench.
-
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
BORA combines offline RL critic training with online chunk-wise residual adaptation to raise average success rates of real-world dexterous VLA policies by 33% and up to 43% on unseen objects across five tasks.
-
Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation
MoT-HRA learns embodiment-agnostic human-intention priors from a curated 2.2M-episode human video dataset via a three-expert hierarchical vision-language-action model to improve robotic manipulation under distribution shift.
-
LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment
LIDEA bridges the human-robot embodiment gap via implicit feature distillation in 2D and explicit geometry alignment in 3D, enabling human data to substitute up to 80% of robot demonstrations with improved out-of-distribution robustness.
-
From Foundation to Application: Improving VLA Models in Practice
LingBot-VLA 2.0 combines 60k hours of multi-embodiment pretraining data, an expanded whole-body action space, and dual-query distillation from depth and video teachers to improve VLA performance on GM-100 and long-horizon mobile manipulation tasks.
-
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
Donk is a unified video-action denoising model that generates dexterous hand trajectories and videos under language, image, and state conditioning while also serving as a text-conditioned data engine.
-
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalization from sparse data.
-
Towards Robotic Dexterous Hand Intelligence: A Survey
A structured survey of dexterous robotic hand research that reviews hardware, control methods, data resources, and benchmarks while identifying major limitations and future directions.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks
EgoLive is presented as the largest open-source annotated egocentric dataset for real-world task-oriented human routines, captured with a custom head-mounted device and multi-modal annotations exclusively in unconstrained environments.
-
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
The paper surveys four classes of techniques that derive action-related supervision from human videos for VLA robot models and identifies three open challenges in episode structuring, embodiment grounding, and evaluation.
-
World Model for Robot Learning: A Comprehensive Survey
A comprehensive survey that organizes the literature on world models in robot learning, their roles in policy learning, planning, simulation, and video-based generation, with connections to navigation, driving, datasets, and benchmarks.
-
AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
AugVLA-3D augments existing VLA models with depth-derived 3D features and action priors to improve generalization and action accuracy in 3D robotic tasks.