Image de couverture de livre

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ni, Chaojun, Chen, Cheng, Wang, Xiaofeng, Zhu, Zheng, Zheng, Wenzhao, Wang, Boyuan, Chen, Tianrun, Zhao, Guosheng, Li, Haoyun, Dong, Zhehao, Zhang, Qiang, Ye, Yun, Wang, Yang, Huang, Guan, Mei, Wenjun
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
par: Li, Haoyun, et autres
Publié: (2025)

WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration
par: Ni, Chaojun, et autres
Publié: (2025)

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
par: Ni, Chaojun, et autres
Publié: (2025)

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
par: Ye, Angen, et autres
Publié: (2025)

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
par: Zhao, Guosheng, et autres
Publié: (2024)

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
par: Ni, Chaojun, et autres
Publié: (2025)

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
par: Zhao, Guosheng, et autres
Publié: (2025)

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
par: GigaBrain Team, et autres
Publié: (2026)

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
par: Song, Wenxuan, et autres
Publié: (2026)

HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration
par: Wang, Boyuan, et autres
Publié: (2025)

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
par: Wang, Boyuan, et autres
Publié: (2025)

SimVLA: A Simple VLA Baseline for Robotic Manipulation
par: Luo, Yuankai, et autres
Publié: (2026)

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
par: Guo, Peizheng, et autres
Publié: (2026)

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
par: Dong, Zhehao, et autres
Publié: (2025)

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
par: Wang, Boyuan, et autres
Publié: (2026)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
par: Wang, Ruiheng, et autres
Publié: (2026)

Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
par: Tang, Yanchuan, et autres
Publié: (2026)

EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
par: Wang, Boyuan, et autres
Publié: (2025)

AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
par: Zhang, Likui, et autres
Publié: (2026)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
par: Ni, Chaojun, et autres
Publié: (2024)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
par: Zheng, Zihao, et autres
Publié: (2026)

ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
par: Wu, You, et autres
Publié: (2026)

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
par: Jiang, Yuhua, et autres
Publié: (2026)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
par: Liu, Jiahang, et autres
Publié: (2025)

GigaWorld-0: World Models as Data Engine to Empower Embodied AI
par: GigaWorld Team, et autres
Publié: (2025)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
par: Li, Haozhan, et autres
Publié: (2025)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
par: Liu, Xiaokang, et autres
Publié: (2026)

WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control
par: Jiang, Haoran, et autres
Publié: (2025)

StarVLA-$α$: Reducing Complexity in Vision-Language-Action Systems
par: Ye, Jinhui, et autres
Publié: (2026)

WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
par: Wang, Xiaofeng, et autres
Publié: (2024)

A Pragmatic VLA Foundation Model
par: Wu, Wei, et autres
Publié: (2026)

Sci-VLA: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
par: Pang, Yiwen, et autres
Publié: (2026)

VLA-LPAF: Lightweight Perspective-Adaptive Fusion for Vision-Language-Action to Enable More Unconstrained Robotic Manipulation
par: Bian, Jinyue, et autres
Publié: (2025)

DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion
par: Wang, Weijie, et autres
Publié: (2025)

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
par: Li, Ye, et autres
Publié: (2025)

LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
par: Shen, Boyang, et autres
Publié: (2026)

Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
par: Huang, Jialei, et autres
Publié: (2025)

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
par: Cao, Jiajun, et autres
Publié: (2026)

DroneVLA: VLA based Aerial Manipulation
par: Mehboob, Fawad, et autres
Publié: (2026)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
par: Jiang, Feng, et autres
Publié: (2025)