Image de couverture de livre

DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Wanpeng, Wang, Ye, Luo, Hao, Yuan, Haoqi, Feng, Yicheng, Zheng, Sipeng, Jin, Qin, Lu, Zongqing
Format:	Preprint
Publié:	2025
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
par: Luo, Hao, et autres
Publié: (2026)

Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting
par: Zhang, Wanpeng, et autres
Publié: (2026)

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
par: Luo, Hao, et autres
Publié: (2025)

Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
par: Wang, Ye, et autres
Publié: (2026)

Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
par: Xu, Haiweng, et autres
Publié: (2026)

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
par: Luo, Hao, et autres
Publié: (2026)

PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking
par: Qin, Weikai, et autres
Publié: (2026)

Being-H0.7: A Latent World-Action Model from Egocentric Videos
par: Luo, Hao, et autres
Publié: (2026)

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

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
par: Huang, Ziye, et autres
Publié: (2024)

Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations
par: Zhou, Bohan, et autres
Publié: (2024)

Cross-Embodiment Dexterous Grasping with Reinforcement Learning
par: Yuan, Haoqi, et autres
Publié: (2024)

VideoOrion: Tokenizing Object Dynamics in Videos
par: Feng, Yicheng, et autres
Publié: (2024)

Unified Multimodal Understanding via Byte-Pair Visual Encoding
par: Zhang, Wanpeng, et autres
Publié: (2025)

DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
par: Yuan, Haoqi, et autres
Publié: (2025)

UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
par: Zhang, Chi, et autres
Publié: (2025)

Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
par: Yuan, Haoqi, et autres
Publié: (2025)

QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds
par: Mei, Yuting, et autres
Publié: (2024)

DiG-Net: Enhancing Human-Robot Interaction through Hyper-Range Dynamic Gesture Recognition in Assistive Robotics
par: Beeri, Eran Bamani, et autres
Publié: (2025)

AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
par: Jiang, Yuhua, et autres
Publié: (2025)

Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
par: Mao, Chuan, et autres
Publié: (2025)

UniCode: Learning a Unified Codebook for Multimodal Large Language Models
par: Zheng, Sipeng, et autres
Publié: (2024)

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

Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
par: Zhang, Zunzhe, et autres
Publié: (2026)

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
par: Zhang, Wanpeng, et autres
Publié: (2024)

SPAFormer: Sequential 3D Part Assembly with Transformers
par: Xu, Boshen, et autres
Publié: (2024)

DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation
par: Fu, Yuhui, et autres
Publié: (2025)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
par: Zhang, Hongyin, et autres
Publié: (2025)

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

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
par: Shi, Yiran, et autres
Publié: (2026)

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
par: Zhu, Lianghui, et autres
Publié: (2024)

Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models
par: Soleymanzadeh, Davood, et autres
Publié: (2026)

ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
par: Zhang, Shuoheng, et autres
Publié: (2026)

Galaxea Open-World Dataset and G0 Dual-System VLA Model
par: Jiang, Tao, et autres
Publié: (2025)

Efficient Trajectory Forecasting and Generation with Conditional Flow Matching
par: Ye, Sean, et autres
Publié: (2024)

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
par: Chen, Jiayi, et autres
Publié: (2026)

FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models
par: Zhong, Zhide, et autres
Publié: (2025)

Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
par: Ahmed, Riad, et autres
Publié: (2026)

ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
par: Wang, Xiyang, et autres
Publié: (2026)