Copertina

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lyu, Mingyang, Sun, Yinqian, Lin, Erliang, Li, Huangrui, Chen, Ruolin, Zhao, Feifei, Zeng, Yi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
di: Jiang, Yuhua, et al.
Pubblicazione: (2025)

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
di: Huang, Dongchi, et al.
Pubblicazione: (2025)

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
di: Chen, Keyu, et al.
Pubblicazione: (2026)

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
di: Zhang, Tonghe, et al.
Pubblicazione: (2025)

The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
di: Chuang, Bing-Cheng, et al.
Pubblicazione: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
di: Li, Runze, et al.
Pubblicazione: (2026)

Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model
di: Wang, Qianhao, et al.
Pubblicazione: (2024)

Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning
di: Sun, Yinqian, et al.
Pubblicazione: (2025)

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
di: Zhang, Zhilong, et al.
Pubblicazione: (2026)

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

Flow Matching Policy Gradients
di: McAllister, David, et al.
Pubblicazione: (2025)

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
di: Yang, Chenyu, et al.
Pubblicazione: (2026)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
di: Kim, Moo Jin, et al.
Pubblicazione: (2025)

MTDP: A Modulated Transformer based Diffusion Policy Model
di: Wang, Qianhao, et al.
Pubblicazione: (2025)

CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
di: Tong, Haibo, et al.
Pubblicazione: (2026)

Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillation
di: Jia, Bofang, et al.
Pubblicazione: (2024)

ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
di: Fang, Zhou, et al.
Pubblicazione: (2026)

Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation
di: Bofi, Pau Montagut, et al.
Pubblicazione: (2026)

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
di: An, Xinyuan, et al.
Pubblicazione: (2026)

VITA: Vision-to-Action Flow Matching Policy
di: Gao, Dechen, et al.
Pubblicazione: (2025)

STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models
di: Xu, Feng, et al.
Pubblicazione: (2025)

PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
di: Yang, Shunpeng, et al.
Pubblicazione: (2026)

SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning
di: Pan, Xu, et al.
Pubblicazione: (2026)

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
di: Hu, Jiaheng, et al.
Pubblicazione: (2026)

Few-Shot Vision-Language Action-Incremental Policy Learning
di: Song, Mingchen, et al.
Pubblicazione: (2025)

Improving Vision-Language-Action Model with Online Reinforcement Learning
di: Guo, Yanjiang, et al.
Pubblicazione: (2025)

$π_0$: A Vision-Language-Action Flow Model for General Robot Control
di: Black, Kevin, et al.
Pubblicazione: (2024)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
di: Li, Chengmeng, et al.
Pubblicazione: (2025)

Active Fine-Tuning of Multi-Task Policies
di: Bagatella, Marco, et al.
Pubblicazione: (2024)

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

VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation
di: Zhai, Xuanran, et al.
Pubblicazione: (2025)

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
di: Xiao, Wei, et al.
Pubblicazione: (2025)

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving
di: Zhu, Tianze, et al.
Pubblicazione: (2026)

FAST: Efficient Action Tokenization for Vision-Language-Action Models
di: Pertsch, Karl, et al.
Pubblicazione: (2025)

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
di: Li, Zhuofan, et al.
Pubblicazione: (2026)

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
di: Yin, Cheng, et al.
Pubblicazione: (2025)

CRL-VLA: Continual Vision-Language-Action Learning
di: Zeng, Qixin, et al.
Pubblicazione: (2026)

Confidence Calibration in Vision-Language-Action Models
di: Zollo, Thomas P, et al.
Pubblicazione: (2025)

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
di: Hu, Xintong, et al.
Pubblicazione: (2026)

Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
di: Lin, Haitao, et al.
Pubblicazione: (2026)