Cover Image

Can VLA Models Learn from Real-World Data Continually without Forgetting?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Jiarun, Hong, Yijun, Sun, Xiaoquan, Xu, Zetian, Yuan, Mingqi, Wang, Zhiyong, Zeng, Wenjun, Chen, Jiayu
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

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
by: Sun, Xiaoquan, et al.
Published: (2026)

AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
by: Fan, Liaoyuan, et al.
Published: (2026)

PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
by: Yuan, Mingqi, et al.
Published: (2025)

Can Aerial VLA Models Cooperate? Evaluating Closed-Loop Air-Ground Coordination with CARLA-Air
by: Zeng, Tianle, et al.
Published: (2026)

Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
by: Liu, Qiqi, et al.
Published: (2026)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
by: Liu, Xiaokang, 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)

A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots
by: Yuan, Mingqi, et al.
Published: (2025)

GazeVLA: Learning Human Intention for Robotic Manipulation
by: Li, Chengyang, et al.
Published: (2026)

WorldVLA: Towards Autoregressive Action World Model
by: Cen, Jun, et al.
Published: (2025)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model
by: Zhu, Xiang, et al.
Published: (2026)

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

How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
by: Jiang, Wenqi, et al.
Published: (2026)

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

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
by: Fu, Yiyang, et al.
Published: (2026)

RynnVLA-002: A Unified Vision-Language-Action and World Model
by: Cen, Jun, et al.
Published: (2025)

Hierarchical Procedural Framework for Low-latency Robot-Assisted Hand-Object Interaction
by: Yuan, Mingqi, et al.
Published: (2024)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
by: Sun, Jingwen, et al.
Published: (2026)

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

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
by: Zhang, Wenyao, et al.
Published: (2025)

VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
by: Huang, Alex S., et al.
Published: (2026)

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

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
by: Liu, Huihan, et al.
Published: (2026)

AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
by: Sun, Jianli, 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)

Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations
by: Liu, Hanqing, et al.
Published: (2025)

Uni-Fusion: Universal Continuous Mapping
by: Yuan, Yijun, et al.
Published: (2023)

VLA Model-Expert Collaboration for Bi-directional Manipulation Learning
by: Xiang, Tian-Yu, et al.
Published: (2025)

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
by: Ni, Chaojun, et al.
Published: (2025)

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

Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
by: Zhang, Hongbo, et al.
Published: (2024)

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
by: Zheng, Zihao, et al.
Published: (2026)

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
by: Xu, Xiaoxu, et al.
Published: (2026)

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
by: Xu, Zonghuan, et al.
Published: (2025)

Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
by: Song, Haolin, et al.
Published: (2025)

Long-Term Memory for VLA-based Agents in Open-World Task Execution
by: Huang, Xu, et al.
Published: (2026)

Learning Agile Quadrotor Flight in the Real World
by: Ren, Yunfan, et al.
Published: (2026)

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
by: Yu, Ming-Ming, et al.
Published: (2025)

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