Cover Image

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Huihan, Kim, Changyeon, Liu, Bo, Liu, Minghuan, Zhu, Yuke
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Model-Based Runtime Monitoring with Interactive Imitation Learning
by: Liu, Huihan, et al.
Published: (2023)

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
by: Kim, Changyeon, et al.
Published: (2025)

Verifier-free Test-Time Sampling for Vision Language Action Models
by: Jang, Suhyeok, et al.
Published: (2025)

PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning
by: Gao, Tian, et al.
Published: (2024)

SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
by: Zhang, Yu, et al.
Published: (2025)

A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
by: Lei, Yu, et al.
Published: (2026)

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

Vision-Language Foundation Models as Effective Robot Imitators
by: Li, Xinghang, et al.
Published: (2023)

Continuous Reasoning for Vision-Language-Action
by: Wu, Yueh-Hua, et al.
Published: (2026)

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
by: Grover, Shresth, et al.
Published: (2025)

Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
by: Kawaharazuka, Kento, et al.
Published: (2025)

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models
by: Liu, Huihan, et al.
Published: (2025)

Trust Region Q Adjoint Matching
by: Dong, Yonghoon, et al.
Published: (2026)

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

Multi-Task Interactive Robot Fleet Learning with Visual World Models
by: Liu, Huihan, et al.
Published: (2024)

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
by: Liu, Zuxin, et al.
Published: (2023)

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

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
by: Zhu, Chuning, et al.
Published: (2025)

Jump-Start Reinforcement Learning with Vision-Language-Action Regularization
by: Moroncelli, Angelo, et al.
Published: (2026)

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
by: Zhang, Zhizhen, et al.
Published: (2025)

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
by: Zhang, Zhengshen, et al.
Published: (2025)

Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
by: Miao, Miranda Muqing, et al.
Published: (2026)

Understanding Asynchronous Inference Methods for Vision-Language-Action Models
by: Agouzoul, Ayoub
Published: (2026)

Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
by: Jin, Ruofan, et al.
Published: (2026)

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

Improved Constrained Generation by Bridging Pretrained Generative Models
by: Liang, Xiaoxuan, et al.
Published: (2026)

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks
by: Xiong, Zheng, et al.
Published: (2025)

Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots
by: Su, Haochen, et al.
Published: (2025)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
by: Wu, Yilin, et al.
Published: (2025)

SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
by: Choi, Hyeonbeom, et al.
Published: (2026)

VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation
by: Castro, Mateo Guaman, et al.
Published: (2025)

Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
by: Shi, Lucy Xiaoyang, et al.
Published: (2025)

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
by: Liang, Anthony, et al.
Published: (2025)

Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
by: Li, Qixiu, et al.
Published: (2025)

Autoregressive Action Sequence Learning for Robotic Manipulation
by: Zhang, Xinyu, et al.
Published: (2024)

DrEureka: Language Model Guided Sim-To-Real Transfer
by: Ma, Yecheng Jason, et al.
Published: (2024)

Model-Based Reinforcement Learning with Multi-Task Offline Pretraining
by: Pan, Minting, et al.
Published: (2023)

SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL
by: Hu, Jiaheng, et al.
Published: (2025)

Eureka: Human-Level Reward Design via Coding Large Language Models
by: Ma, Yecheng Jason, et al.
Published: (2023)

RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
by: Nasiriany, Soroush, et al.
Published: (2026)