Cover Image

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Rushuai, Wei, Hangxing, Zhang, Ran, Feng, Zhiyuan, Chen, Xiaoyu, Li, Tong, Zhang, Chuheng, Zhao, Li, Bian, Jiang, Su, Xiu, Chen, Yi
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
by: Yang, Rushuai, et al.
Published: (2025)

How Do VLAs Effectively Inherit from VLMs?
by: Zhang, Chuheng, et al.
Published: (2025)

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
by: Chen, Xiaoyu, et al.
Published: (2025)

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
by: Shi, Liangzhi, et al.
Published: (2026)

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
by: Peng, Yuanfang, et al.
Published: (2026)

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
by: Li, Haoyun, et al.
Published: (2025)

Unified Noise Steering for Efficient Human-Guided VLA Adaptation
by: Lu, Junjie, et al.
Published: (2026)

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
by: Li, Wenhao, et al.
Published: (2026)

IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
by: Chen, Xiaoyu, et al.
Published: (2024)

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
by: Jiang, Yuming, et al.
Published: (2025)

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
by: Jiang, Yuhua, et al.
Published: (2026)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
by: Li, Haozhan, et al.
Published: (2025)

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
by: Yang, Rushuai, et al.
Published: (2026)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
by: Wang, Ruiheng, et al.
Published: (2026)

Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
by: Gao, Yinfeng, et al.
Published: (2026)

PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models
by: Wan, Jiansong, et al.
Published: (2025)

ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration
by: Zhu, Minjie, et al.
Published: (2025)

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
by: Zhang, Hongyin, et al.
Published: (2025)

Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations
by: Tang, Zuojin, et al.
Published: (2024)

Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning
by: Jiang, Ke, et al.
Published: (2025)

VDRive: Leveraging Reinforced VLA and Diffusion Policy for End-to-end Autonomous Driving
by: Guo, Ziang, et al.
Published: (2025)

SimVLA: A Simple VLA Baseline for Robotic Manipulation
by: Luo, Yuankai, et al.
Published: (2026)

Learning Additively Compositional Latent Actions for Embodied AI
by: Wei, Hangxing, et al.
Published: (2026)

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
by: Hu, Yucheng, et al.
Published: (2026)

Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
by: Li, Wenhao, et al.
Published: (2026)

Human-Like Robot Impedance Regulation Skill Learning from Human-Human Demonstrations
by: Li, Chenzui, et al.
Published: (2025)

Learning Gentle Grasping from Human-Free Force Control Demonstration
by: Li, Mingxuan, et al.
Published: (2024)

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
by: Wen, Junjie, et al.
Published: (2025)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
by: Xiao, Junjin, et al.
Published: (2025)

End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection
by: Cui, Yu, et al.
Published: (2025)

CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance
by: Li, Jinming, et al.
Published: (2024)

RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning
by: Zhang, Yuhong, et al.
Published: (2025)

ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation
by: Gu, Chenyang, et al.
Published: (2025)

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
by: Song, Wenxuan, et al.
Published: (2026)

ST4VLA: Spatially Guided Training for Vision-Language-Action Models
by: Ye, Jinhui, et al.
Published: (2026)

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
by: Chen, Zhongxi, et al.
Published: (2026)

Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
by: Chen, Zhuoqun, et al.
Published: (2025)

X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
by: Pace, Maximus A., et al.
Published: (2025)

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
by: Jiang, Zhennan, et al.
Published: (2026)

Human Demonstrations are Generalizable Knowledge for Robots
by: Cui, Te, et al.
Published: (2023)