Cover Image

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Wenxuan, Zhao, Han, Li, Fuhao, Zhou, Ziyang, Wang, Xi, Lyu, Jing, Ding, Pengxiang, Wang, Yan, Wang, Donglin, Li, Haoang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
by: Li, Fuhao, et al.
Published: (2025)

CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
by: Song, Wenxuan, et al.
Published: (2025)

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
by: Chen, Jiayi, et al.
Published: (2025)

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
by: Song, Wenxuan, et al.
Published: (2025)

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
by: Zhao, Han, et al.
Published: (2025)

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
by: Song, Wenxuan, et al.
Published: (2025)

MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models
by: Zhao, Han, et al.
Published: (2025)

Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
by: Zhao, Wei, et al.
Published: (2025)

RationalVLA: A Rational Vision-Language-Action Model with Dual System
by: Song, Wenxuan, et al.
Published: (2025)

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

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

FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
by: Zhao, Han, et al.
Published: (2026)

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

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models
by: Ge, Zirui, et al.
Published: (2026)

Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
by: Song, Wenxuan, et al.
Published: (2026)

VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
by: Zhao, Wei, et al.
Published: (2025)

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
by: Lei, Huashuo, et al.
Published: (2026)

GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot
by: Song, Wenxuan, et al.
Published: (2024)

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
by: Wang, Yihao, et al.
Published: (2025)

MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
by: Liu, Yang, et al.
Published: (2026)

Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling
by: Gong, Zhefei, et al.
Published: (2025)

Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
by: Fan, Yiguo, et al.
Published: (2025)

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

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
by: Chen, Jiayi, et al.
Published: (2026)

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation
by: Zhang, Hongyin, et al.
Published: (2025)

SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
by: Huang, Jingzhi, et al.
Published: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
by: Li, Runze, et al.
Published: (2026)

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
by: Li, Hengtao, 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)

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning
by: Zhang, Hongyin, et al.
Published: (2025)

CUBic: Coordinated Unified Bimanual Perception and Control Framework
by: Wang, Xingyu, et al.
Published: (2026)

Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
by: Bai, Shuanghao, et al.
Published: (2025)

Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey
by: Bai, Shuanghao, et al.
Published: (2025)

Unified Vision-Language-Action Model
by: Wang, Yuqi, et al.
Published: (2025)

Dynamic Adaptive Legged Locomotion Policy via Decoupling Reaction Force Control and Gait Control
by: Wang, Renjie, et al.
Published: (2025)

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
by: Wang, Yating, et al.
Published: (2025)

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

Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
by: Bai, Shuanghao, et al.
Published: (2026)

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

Discovering Self-Protective Falling Policy for Humanoid Robot via Deep Reinforcement Learning
by: Shi, Diyuan, et al.
Published: (2025)