Cover Image

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Borong, Zhang, Yuhao, Ji, Jiaming, Lei, Yingshan, Cai, Yishuai, Dai, Josef, Chen, Yuanpei, Yang, Yaodong
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RedVLA: Physical Red Teaming for Vision-Language-Action Models
by: Zhang, Yuhao, et al.
Published: (2026)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
by: Zhang, Borong, et al.
Published: (2025)

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
by: Zhong, Yifan, et al.
Published: (2025)

CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation
by: Cai, Yishuai, et al.
Published: (2026)

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation
by: Yu, Dian, et al.
Published: (2026)

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
by: Zhong, Yifan, et al.
Published: (2025)

TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulation
by: Huang, Yuzhe, et al.
Published: (2026)

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

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
by: Wang, Hanzhen, et al.
Published: (2025)

StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
by: Deng, Shengliang, et al.
Published: (2025)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
by: Zhang, Yichi, et al.
Published: (2026)

AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
by: Kong, Weijie, et al.
Published: (2026)

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
by: Wen, Junjie, et al.
Published: (2025)

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
by: Zhu, Ziyue, et al.
Published: (2026)

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

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

Dexterous Non-Prehensile Manipulation for Ungraspable Object via Extrinsic Dexterity
by: Wang, Yuhan, et al.
Published: (2025)

AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
by: Sun, Jianli, et al.
Published: (2026)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
by: Dai, Josef, et al.
Published: (2024)

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
by: Guo, Jianing, et al.
Published: (2025)

HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
by: Xu, Xinyu, et al.
Published: (2024)

DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
by: Peng, Xiongfeng, et al.
Published: (2026)

Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
by: Bai, Shuanghao, et al.
Published: (2026)

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
by: Hu, Yucheng, et al.
Published: (2026)

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

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
by: Zhong, Linqing, et al.
Published: (2026)

MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
by: Zhang, Rongyu, et al.
Published: (2025)

SafeDreamer: Safe Reinforcement Learning with World Models
by: Huang, Weidong, et al.
Published: (2023)

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
by: Li, Ye, et al.
Published: (2026)

QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
by: Ding, Pengxiang, et al.
Published: (2023)

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

HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
by: Liu, Jiaming, et al.
Published: (2025)

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

AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models
by: Li, Xiaoqi, et al.
Published: (2026)

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation
by: Zhu, Kefei, et al.
Published: (2025)

KineVLA: Towards Kinematics-Aware Vision-Language-Action Models with Bi-Level Action Decomposition
by: Han, Gaoge, et al.
Published: (2026)

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
by: Ye, Angen, et al.
Published: (2025)

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

ST4VLA: Spatially Guided Training for Vision-Language-Action Models
by: Ye, Jinhui, et al.
Published: (2026)

RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model
by: Li, Shunlei, et al.
Published: (2024)