# MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training arXiv: https://arxiv.org/abs/2512.15411 · HTML: https://mlsanity.com/paper/2512.15411/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models. - Builds on 31 of its 33 references that are in the map. - First posted on arXiv 17 Dec 2025. ## Placed in - Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/) ## Builds on (most cited first, 30 of 31) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023) - [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025) - [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023) - [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024) - [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023) - [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024) - [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025) - [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025) - [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025) - [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024) - [ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations](https://mlsanity.com/paper/2107.14483/) (2021) - [DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control](https://mlsanity.com/paper/2502.05855/) (2025) - [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024) - [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024) - [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024) - [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025) - [RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins](https://mlsanity.com/paper/2504.13059/) (2025) - [H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation](https://mlsanity.com/paper/2507.23523/) (2025) - [Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation](https://mlsanity.com/paper/2406.14235/) (2024) - [ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation](https://mlsanity.com/paper/2509.10952/) (2025) - [RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training](https://mlsanity.com/paper/2411.17662/) (2024) - [Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining](https://mlsanity.com/paper/2506.16475/) (2025) ## Built on by (most cited first, 2 of 2) - [TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation](https://mlsanity.com/paper/2603.12665/) (2026) - [HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing](https://mlsanity.com/paper/2608.12122/) (2026) ## Abstract (arXiv) 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., boldsymbolπ0, boldsymbolπ0.5 and H-RDT) by 25% in simulation, and 14% in real-world robot control tasks.