Image de couverture de livre

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qu, Delin, Song, Haoming, Chen, Qizhi, Yao, Yuanqi, Ye, Xinyi, Ding, Yan, Wang, Zhigang, Gu, JiaYuan, Zhao, Bin, Wang, Dong, Li, Xuelong
Format:	Preprint
Publié:	2025
Sujets:	Robotics Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
par: Gao, Xianqiang, et autres
Publié: (2026)

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation
par: Yao, Yuanqi, et autres
Publié: (2025)

Hume: Introducing System-2 Thinking in Visual-Language-Action Model
par: Song, Haoming, et autres
Publié: (2025)

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
par: Yan, Chi, et autres
Publié: (2023)

Exploring the Potential of Encoder-free Architectures in 3D LMMs
par: Tang, Yiwen, et autres
Publié: (2025)

FreeGaussian: Annotation-free Control of Articulated Objects via 3D Gaussian Splats with Flow Derivatives
par: Chen, Qizhi, et autres
Publié: (2024)

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
par: Liu, Junli, et autres
Publié: (2025)

F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
par: Lv, Qi, et autres
Publié: (2025)

Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation
par: Gao, Yunpeng, et autres
Publié: (2024)

LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control
par: Qu, Delin, et autres
Publié: (2024)

EO-1: An Open Unified Embodied Foundation Model for General Robot Control
par: Qu, Delin, et autres
Publié: (2025)

ST4VLA: Spatially Guided Training for Vision-Language-Action Models
par: Ye, Jinhui, et autres
Publié: (2026)

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
par: Chen, Xinyi, et autres
Publié: (2025)

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
par: Gao, Xianqiang, et autres
Publié: (2024)

MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation
par: Wang, Haoming, et autres
Publié: (2026)

Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy
par: Wu, Pengyuan, et autres
Publié: (2026)

InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity
par: Wang, Haoming, et autres
Publié: (2025)

SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation
par: Shi, Hao, et autres
Publié: (2025)

Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
par: Feng, Yicheng, et autres
Publié: (2025)

FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset
par: Zhaxizhuoma, et autres
Publié: (2024)

Implicit Event-RGBD Neural SLAM
par: Qu, Delin, et autres
Publié: (2023)

FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset
par: Liu, Kehui, et autres
Publié: (2025)

SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning
par: Pan, Xu, et autres
Publié: (2026)

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
par: Wang, Zixuan, et autres
Publié: (2026)

AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
par: Hu, Yutong, et autres
Publié: (2026)

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
par: Li, Fuhao, et autres
Publié: (2025)

OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
par: Jie, Haoxiang, et autres
Publié: (2026)

GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
par: Sun, Lin, et autres
Publié: (2025)

Exploring Spatial Hybrid User Interface for Visual Sensemaking
par: Tong, Wai, et autres
Publié: (2025)

Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding
par: Patratskiy, Maxim A., et autres
Publié: (2025)

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
par: Lin, Minghui, et autres
Publié: (2025)

SurfPatch: Enabling Patch Matching for Exploratory Stream Surface Visualization
par: An, Delin, et autres
Publié: (2025)

AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation
par: Zhu, Juan, et autres
Publié: (2026)

DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
par: Yuan, Tianyuan, et autres
Publié: (2025)

SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
par: Tu, Ruisen, et autres
Publié: (2026)

CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
par: Li, Dachong, et autres
Publié: (2026)

RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models
par: Koo, Jiyeon, et autres
Publié: (2025)

HiST-VLA: A Hierarchical Spatio-Temporal Vision-Language-Action Model for End-to-End Autonomous Driving
par: Wang, Yiru, et autres
Publié: (2026)

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
par: Xu, Xiaoxu, et autres
Publié: (2026)

Trajectory Conditioned Cross-embodiment Skill Transfer
par: Tang, YuHang, et autres
Publié: (2025)