MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training

• URL: http://arxiv.org/abs/2512.15411v2
• Date: Fri, 19 Dec 2025 09:10:06 GMT
• Title: MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training
• Abstract summary: We propose MiVLA, a vision-language-action model empowered by human-robot mutual imitation pre-training.<n>We show that MiVLA achieves strong improved generalization capability, outperforming state-of-the-art VLAs.
• Score: 102.850162490626
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While leveraging abundant human videos and simulated robot data poses a scalable solution to the scarcity of real-world robot data, the generalization capability of existing vision-language-action models (VLAs) remains limited by mismatches in camera views, visual appearance, and embodiment morphologies. To overcome this limitation, we propose MiVLA, a generalizable VLA empowered by human-robot mutual imitation pre-training, which leverages inherent behavioral similarity between human hands and robotic arms to build a foundation of strong behavioral priors for both human actions and robotic control. Specifically, our method utilizes kinematic rules with left/right hand coordinate systems for bidirectional alignment between human and robot action spaces. Given human or simulated robot demonstrations, MiVLA is trained to forecast behavior trajectories for one embodiment, and imitate behaviors for another one unseen in the demonstration. Based on this mutual imitation, it integrates the behavioral fidelity of real-world human data with the manipulative diversity of simulated robot data into a unified model, thereby enhancing the generalization capability for downstream tasks. Extensive experiments conducted on both simulation and real-world platforms with three robots (ARX, PiPer and LocoMan), demonstrate that MiVLA achieves strong improved generalization capability, outperforming state-of-the-art VLAs (e.g., $\boldsymbolπ_{0}$, $\boldsymbolπ_{0.5}$ and H-RDT) by 25% in simulation, and 14% in real-world robot control tasks.

Related papers

• AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization [88.25615187835321]
  We propose AnyWorld, a cross-embodiment world modeling framework.<n>Our model factorizes an interaction into action, camera, and embodiment.<n>We train the model with large-scale human interaction pretraining.
  arXiv  Detail & Related papers  (2026-08-29T12:55:15Z)
• H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models [56.60098789696351]
  H2R-Bench is a benchmark for evaluating cross-embodiment human-to-robot manipulation video generation.<n>Each benchmark instance contains a human demonstration video, target embodiment constraints, and source-grounded annotations.<n>We benchmark eleven state-of-the-art video generation models across six manipulation families and two robot embodiments.
  arXiv  Detail & Related papers  (2026-08-13T10:14:33Z)
• WSA$_1$: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control [85.21175469425172]
  Recent advances in embodied AI have established robot foundation models (RFMs) as the dominant approach for generalist robotic systems to date.<n>We present WSA$_1$, a novel RFM built upon proposed 3D-Centric World-Spatial-Action modeling paradigm.<n>It not only learns 3D world-aware visual thought for future robot behaviors, but also models mutual constraints between 3D world state transitions and robotic actions to enhance behavior generalization.
  arXiv  Detail & Related papers  (2026-07-04T16:26:39Z)
• HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model [13.153130497047043]
  Learning generalizable vision-language-action models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies.<n>We propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos.<n>Experiments on feature visualization, simulation, and realworld manipulation show improved human-robot alignment and downstream policy performance.
  arXiv  Detail & Related papers  (2026-05-29T12:36:30Z)
• FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions [147.04372611893032]
  We present FRoM-W1, an open-source framework designed to achieve general humanoid whole-body motion control using natural language.<n>We extensively evaluate FRoM-W1 on Unitree H1 and G1 robots.<n>Results demonstrate superior performance on the HumanML3D-X benchmark for human whole-body motion generation.
  arXiv  Detail & Related papers  (2026-01-19T07:59:32Z)
• Emergence of Human to Robot Transfer in Vision-Language-Action Models [88.76648919814771]
  Vision-language-action (VLA) models can enable broad open world generalization, but require large and diverse datasets.<n>We show that human-to-robot transfer emerges once the VLA is pre-trained on sufficient scenes, tasks, and embodiments.
  arXiv  Detail & Related papers  (2025-12-27T00:13:11Z)
• MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training [40.45924128424013]
  We propose MimicDreamer, a framework that turns low-cost human demonstrations into robot-usable supervision.<n>For visual alignment, we propose H2R Aligner, a video diffusion model that generates high-fidelity robot demonstration videos.<n>For viewpoint stabilization, EgoStabilizer is proposed, which canonicalizes egocentric videos via homography.<n>For action alignment, we map human hand trajectories to the robot frame and apply a constrained inverse kinematics solver.
  arXiv  Detail & Related papers  (2025-09-26T11:05:10Z)
• AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning [5.371855090716962]
  Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations.<n>Existing approaches have employed vision-language pretraining with large-scale data.<n>We propose to learn from large-scale human action video datasets in an explicit way.
  arXiv  Detail & Related papers  (2025-08-11T05:09:58Z)
• H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation [27.585828712261232]
  H-RDT (Human to Robotics Diffusion Transformer) is a novel approach that leverages human manipulation data to enhance robot manipulation capabilities.<n>Our key insight is that large-scale egocentric human manipulation videos with paired 3D hand pose annotations provide rich behavioral priors that capture natural manipulation strategies.<n>We introduce a two-stage training paradigm: (1) pre-training on large-scale egocentric human manipulation data, and (2) cross-embodiment fine-tuning on robot-specific data with modular action encoders and decoders.
  arXiv  Detail & Related papers  (2025-07-31T13:06:59Z)
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models [120.25799361925387]
  DreamGen is a pipeline for training robot policies that generalize across behaviors and environments through neural trajectories.<n>Our work establishes a promising new axis for scaling robot learning well beyond manual data collection.
  arXiv  Detail & Related papers  (2025-05-19T04:55:39Z)
• Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning [3.9738951919572827]
  We propose a framework that explicitly models human demonstrations from RGB video with robot demonstrations in voxelized RGB-D space.<n>Our approach combines ResNet-based visual encoding for human intention modeling and a Perceiver Transformer for voxel-based robot action prediction.
  arXiv  Detail & Related papers  (2025-04-14T21:14:51Z)
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots [133.23509142762356]
  General-purpose robots need a versatile body and an intelligent mind.<n>Recent advancements in humanoid robots have shown great promise as a hardware platform for building generalist autonomy.<n>We introduce GR00T N1, an open foundation model for humanoid robots.
  arXiv  Detail & Related papers  (2025-03-18T21:06:21Z)
• VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
  VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos.<n> VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
  arXiv  Detail & Related papers  (2025-03-10T10:04:58Z)

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.