Image de couverture de livre

Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Grant, Bryce, Zhao, Xijia, Wang, Peng
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
par: Xu, Yuhao, et autres
Publié: (2026)

Observing and Controlling Features in Vision-Language-Action Models
par: Buurmeijer, Hugo, et autres
Publié: (2026)

Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
par: Grant, Bryce, et autres
Publié: (2025)

Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
par: Liang, Yuanchang, et autres
Publié: (2026)

Embodiment Transfer Learning for Vision-Language-Action Models
par: Li, Chengmeng, et autres
Publié: (2025)

Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
par: Bai, Shuanghao, et autres
Publié: (2026)

Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
par: Wille, Melanie, et autres
Publié: (2025)

StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
par: Deng, Shengliang, et autres
Publié: (2025)

Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
par: Mitra, Chancharik, et autres
Publié: (2025)

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
par: Zhu, Ziyue, et autres
Publié: (2026)

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
par: Zhong, Yifan, et autres
Publié: (2025)

Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
par: Zhao, Wei, et autres
Publié: (2025)

VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
par: Zhao, Wei, et autres
Publié: (2025)

A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter
par: Xu, Kechun, et autres
Publié: (2023)

VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation
par: Zhang, Chaofan, et autres
Publié: (2025)

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
par: Liu, Yudong, et autres
Publié: (2026)

LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models
par: Li, Zuolei, et autres
Publié: (2025)

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
par: Chen, Zixing, et autres
Publié: (2026)

DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
par: Peng, Xiongfeng, et autres
Publié: (2026)

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
par: Wang, Yihao, et autres
Publié: (2025)

RationalVLA: A Rational Vision-Language-Action Model with Dual System
par: Song, Wenxuan, et autres
Publié: (2025)

Stable Language Guidance for Vision-Language-Action Models
par: Zhan, Zhihao, et autres
Publié: (2026)

CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
par: Song, Wenxuan, et autres
Publié: (2025)

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
par: Lin, Yihan, et autres
Publié: (2026)

Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
par: Bai, Shuanghao, et autres
Publié: (2026)

AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
par: Kong, Weijie, et autres
Publié: (2026)

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
par: Hu, Yanbin, et autres
Publié: (2026)

MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation
par: Zhao, Ruihan, et autres
Publié: (2025)

RynnVLA-002: A Unified Vision-Language-Action and World Model
par: Cen, Jun, et autres
Publié: (2025)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
par: Li, Boyu, et autres
Publié: (2026)

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
par: Zhong, Linqing, et autres
Publié: (2026)

Unified Vision-Language-Action Model
par: Wang, Yuqi, et autres
Publié: (2025)

Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
par: Wulff, Theodor, et autres
Publié: (2026)

VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
par: Chen, Guanyan, et autres
Publié: (2024)

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
par: Chen, Xiaoyu, et autres
Publié: (2025)

STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations
par: Xie, Yuhan, et autres
Publié: (2026)

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
par: Zhao, Han, et autres
Publié: (2025)

Action Hallucination in Generative Vision-Language-Action Models
par: Soh, Harold, et autres
Publié: (2026)

SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
par: Li, Meng, et autres
Publié: (2025)

OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
par: Lin, Fanqi, et autres
Publié: (2025)