Cover Image

See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Guangyan, Wang, Meiling, Shao, Qi, Zhou, Zichen, Mao, Weixin, Cui, Te, Zhu, Minzhao, Deng, Yinan, Yang, Luojie, Zhang, Zhanqi, Yang, Yi, Chen, Hua, Yue, Yufeng
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Human Demonstrations are Generalizable Knowledge for Robots
by: Cui, Te, et al.
Published: (2023)

FMimic: Foundation Models are Fine-grained Action Learners from Human Videos
by: Chen, Guangyan, et al.
Published: (2025)

Point Tree Transformer for Point Cloud Registration
by: Wang, Meiling, et al.
Published: (2024)

Joint Conditional Diffusion Model for Image Restoration with Mixed Degradations
by: Yue, Yufeng, et al.
Published: (2024)

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
by: Tan, Xudong, et al.
Published: (2025)

VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
by: Chen, Guanyan, et al.
Published: (2024)

Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy
by: Xu, Kechun, et al.
Published: (2025)

GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch Tracking
by: Chen, Ye, et al.
Published: (2025)

Open-RGBT: Open-vocabulary RGB-T Zero-shot Semantic Segmentation in Open-world Environments
by: Yu, Meng, et al.
Published: (2024)

RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation
by: Xiao, Zhanqi, et al.
Published: (2026)

ARM: Advantage Reward Modeling for Long-Horizon Manipulation
by: Mao, Yiming, et al.
Published: (2026)

VAT: Vision Action Transformer by Unlocking Full Representation of ViT
by: Li, Wenhao, et al.
Published: (2025)

OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
by: Deng, Yinan, et al.
Published: (2024)

Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
by: Wang, Jing, et al.
Published: (2025)

You Only Speak Once to See
by: Yang, Wenhao, et al.
Published: (2024)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
by: Zhou, Huayi, et al.
Published: (2025)

Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
by: Bai, Yongjie, et al.
Published: (2025)

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
by: Huang, Chi-Pin, et al.
Published: (2025)

Long-Term Memory for VLA-based Agents in Open-World Task Execution
by: Huang, Xu, et al.
Published: (2026)

Mean-Flow based One-Step Vision-Language-Action
by: Chen, Yang, et al.
Published: (2026)

Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
by: Singhi, Nishad, et al.
Published: (2026)

Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
by: Mitra, Chancharik, et al.
Published: (2025)

The Solution for Temporal Action Localisation Task of Perception Test Challenge 2024
by: Han, Yinan, et al.
Published: (2024)

BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model
by: Li, Haosheng, et al.
Published: (2026)

TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models
by: Yu, Meng, et al.
Published: (2025)

Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning
by: Zhou, Jianyi, et al.
Published: (2026)

LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
by: Liu, Guangyi, et al.
Published: (2025)

Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models
by: Cai, Zhejia, et al.
Published: (2025)

Effects of Family‐Based Intervention for Childhood Obesity on Parental and Offspring Outcomes: A Systematic Review and Meta‐Analysis
by: Ying Zhang, et al.
Published: (2026)

One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented Demonstrations
by: Wu, Shaokang, et al.
Published: (2024)

ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation
by: Chen, Zixuan, et al.
Published: (2025)

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
by: Bu, Qingwen, et al.
Published: (2025)

Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection
by: Wang, Tao, et al.
Published: (2023)

Seeing Double: Calibrating Two Jets at Once
by: Gambhir, Rikab, et al.
Published: (2024)

Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation
by: Yang, Sizhe, et al.
Published: (2025)

DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks
by: Barekatain, Alireza, et al.
Published: (2023)

ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
by: Ye, Wencheng, et al.
Published: (2025)

OpenIN: Open-Vocabulary Instance-Oriented Navigation in Dynamic Domestic Environments
by: Tang, Yujie, et al.
Published: (2025)

OpenObject-NAV: Open-Vocabulary Object-Oriented Navigation Based on Dynamic Carrier-Relationship Scene Graph
by: Tang, Yujie, et al.
Published: (2024)

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
by: Huang, Chi-Pin, et al.
Published: (2026)