Imagen de Portada

MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhi, Heng, Tan, Wentao, Zhu, Lei, Li, Fengling, Li, Jingjing, Yang, Guoli, Shen, Heng Tao
Formato:	Preprint
Publicado:	2026
Materias:	Robotics Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
por: Liu, Chenyv, et al.
Publicado: (2026)

Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
por: Chen, Yipeng, et al.
Publicado: (2026)

BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
por: Tan, Wentao, et al.
Publicado: (2025)

LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
por: Zha, Lihan, et al.
Publicado: (2026)

Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
por: Yang, Ming, et al.
Publicado: (2026)

MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping
por: Zhang, Heng, et al.
Publicado: (2025)

Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
por: Liu, Junjia, et al.
Publicado: (2024)

Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment
por: Wang, Tianyu, et al.
Publicado: (2024)

Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
por: Abe, Haruki, et al.
Publicado: (2026)

DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
por: Xu, Siyuan, et al.
Publicado: (2026)

Generalizing vision-language models to novel domains: A comprehensive survey
por: Li, Xinyao, et al.
Publicado: (2025)

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
por: Zheng, Jinliang, et al.
Publicado: (2025)

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
por: Chen, Yixiang, et al.
Publicado: (2025)

MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment Learning
por: Rayyan, Omar, et al.
Publicado: (2025)

FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators
por: Tao, Heng, et al.
Publicado: (2026)

Composing Diffusion Policies for Few-shot Learning of Movement Trajectories
por: Patil, Omkar, et al.
Publicado: (2024)

Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
por: Davies, Travis, et al.
Publicado: (2025)

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

Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
por: Yang, Jiarui, et al.
Publicado: (2025)

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
por: Wang, Qiuyue, et al.
Publicado: (2026)

Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations
por: Mattson, Connor, et al.
Publicado: (2024)

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
por: Dan, Prithwish, et al.
Publicado: (2025)

Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
por: Cho, Seongwoong, et al.
Publicado: (2024)

OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
por: Ji, Guanhua, et al.
Publicado: (2025)

FAR-Dex: Few-shot Data Augmentation and Adaptive Residual Policy Refinement for Dexterous Manipulation
por: Bai, Yushan, et al.
Publicado: (2026)

Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models
por: Barcellona, Leonardo, et al.
Publicado: (2024)

Minimal Embodiment Enables Efficient Learning of Number Concepts in Robot
por: Shangguan, Zhegong, et al.
Publicado: (2026)

Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation
por: Meng, Yuan, et al.
Publicado: (2025)

Flexible Locomotion Learning with Diffusion Model Predictive Control
por: Huang, Runhan, et al.
Publicado: (2025)

Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
por: Lum, Tyler Ga Wei, et al.
Publicado: (2025)

H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
por: Lin, Yunfeng, et al.
Publicado: (2025)

Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots
por: Su, Haochen, et al.
Publicado: (2025)

DexGrasp-Zero: A Morphology-Aligned Policy for Zero-Shot Cross-Embodiment Dexterous Grasping
por: Wu, Yuliang, et al.
Publicado: (2026)

RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
por: Liu, Songming, et al.
Publicado: (2026)

Cross-Domain Transfer Learning using Attention Latent Features for Multi-Agent Trajectory Prediction
por: Loh, Jia Quan, et al.
Publicado: (2024)

Compose by Focus: Scene Graph-based Atomic Skills
por: Qi, Han, et al.
Publicado: (2025)

AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
por: Yu, Wenda, et al.
Publicado: (2026)

Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning
por: Shen, Weijie, et al.
Publicado: (2025)

Reliable Few-shot Learning under Dual Noises
por: Zhang, Ji, et al.
Publicado: (2025)

Sim-and-Human Co-training for Data-Efficient and Generalizable Robotic Manipulation
por: Fang, Kaipeng, et al.
Publicado: (2026)