Cover Image

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Changyu, Liu, Yiyang, Wang, Taowen, Zhuang, Qiao, Liang, James Chenhao, Yang, Wenhao, Xu, Renjing, Wang, Qifan, Liu, Dongfang, Han, Cheng
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
by: Wang, Taowen, et al.
Published: (2024)

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

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
by: Liu, Changyu, 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)

EchoVLA: Synergistic Declarative Memory for VLA-Driven Mobile Manipulation
by: Lin, Min, et al.
Published: (2025)

Flying on Point Clouds with Reinforcement Learning
by: Xu, Guangtong, et al.
Published: (2025)

DEFLECT: Delay-Robust Execution via Flow-matching Likelihood-Estimated Counterfactual Tuning for VLA Policies
by: Zhu, Yixiang, et al.
Published: (2026)

UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
by: Zhang, Jiaxi, et al.
Published: (2026)

Refining Almost-Safe Value Functions on the Fly
by: Tonkens, Sander, et al.
Published: (2026)

$π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation
by: Tucker, Johnathan, et al.
Published: (2026)

Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
by: Tang, Yanchuan, et al.
Published: (2026)

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

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
by: Zang, Hongzhi, et al.
Published: (2025)

Long-Horizon Manipulation via Trace-Conditioned VLA Planning
by: Liu, Isabella, et al.
Published: (2026)

Reflection-Based Task Adaptation for Self-Improving VLA
by: Li, Baicheng, et al.
Published: (2025)

Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning
by: Liu, Chenhao, et al.
Published: (2025)

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

On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning
by: Iannotta, Marco, et al.
Published: (2025)

iFlyBot-VLA Technical Report
by: Zhang, Yuan, et al.
Published: (2025)

DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation
by: Wang, Yunheng, et al.
Published: (2025)

Galaxea Open-World Dataset and G0 Dual-System VLA Model
by: Jiang, Tao, et al.
Published: (2025)

VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
by: Wang, Si-Cheng, et al.
Published: (2025)

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
by: Cao, Jiahang, et al.
Published: (2025)

VLA Knows Its Limits
by: Wang, Haoxuan, et al.
Published: (2026)

Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
by: Pan, Jiahe, et al.
Published: (2025)

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
by: Liu, Yuan, et al.
Published: (2026)

Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
by: Guo, Yihong, et al.
Published: (2024)

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
by: Wang, Taowen, et al.
Published: (2024)

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

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

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

CosFly: Plan in the Matrix, Fly in the World
by: Chen, Hanxuan, et al.
Published: (2026)

VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
by: Zhao, Yongsheng, et al.
Published: (2025)

ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
by: Chen, Yuhui, et al.
Published: (2025)

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
by: Li, Puhao, et al.
Published: (2025)

Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
by: Li, Zhuo, et al.
Published: (2025)

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
by: Guo, Xinyu, et al.
Published: (2026)

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
by: Zhang, Qiang, et al.
Published: (2025)

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
by: Lin, Minghui, et al.
Published: (2025)

CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
by: Li, Dachong, et al.
Published: (2026)