Cover Image

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Yuanfang, Fu, Jingjing, Zhang, Chuheng, Zhao, Li, Bian, Jiang, Liu, Mingyu, Zhang, Ling, Zhang, Jun, Wang, Rui
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

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
by: Yang, Rushuai, et al.
Published: (2025)

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

Focus On What Matters: Separated Models For Visual-Based RL Generalization
by: Zhang, Di, et al.
Published: (2024)

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
by: Yang, Rushuai, 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)

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

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

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
by: Zhang, Dapeng, et al.
Published: (2025)

Mask World Model: Predicting What Matters for Robust Robot Policy Learning
by: Lou, Yunfan, et al.
Published: (2026)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
by: Zhang, Yichi, 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)

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

ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning
by: Van Vo, Tuan, et al.
Published: (2025)

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

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
by: Zhang, Hongyin, et al.
Published: (2025)

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

Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
by: Wang, Runze, et al.
Published: (2026)

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

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
by: Xu, Tianyu, et al.
Published: (2025)

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
by: Jin, Piaopiao, et al.
Published: (2025)

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
by: Lu, Guanxing, et al.
Published: (2025)

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

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
by: Liu, Jiahang, et al.
Published: (2025)

OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
by: Jie, Haoxiang, et al.
Published: (2026)

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
by: Zhong, Zhide, et al.
Published: (2026)

Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
by: Fan, Xianzhe, et al.
Published: (2026)

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)

DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
by: Zhang, Wanpeng, et al.
Published: (2025)

TrackVLA: Embodied Visual Tracking in the Wild
by: Wang, Shaoan, et al.
Published: (2025)

MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent
by: Fu, Yuxia, et al.
Published: (2025)

ActionCodec: What Makes for Good Action Tokenizers
by: Dong, Zibin, et al.
Published: (2026)

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
by: Zhang, Ninghao, et al.
Published: (2026)

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA
by: Tang, Tutian, et al.
Published: (2026)

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

TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
by: Huang, Zhiyu, et al.
Published: (2026)

TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation
by: Zhang, Kaidi, et al.
Published: (2026)

Point What You Mean: Visually Grounded Instruction Policy
by: Yu, Hang, et al.
Published: (2025)

What Foundation Models can Bring for Robot Learning in Manipulation : A Survey
by: Li, Dingzhe, et al.
Published: (2024)

FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models
by: Zhong, Zhide, et al.
Published: (2025)

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
by: Wang, Zixuan, et al.
Published: (2026)