Cover Image

3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Bin, Lian, Shijie, Lin, Xiaopeng, Shen, Zhaolong, Wei, Yuliang, Liu, Haishan, Wu, Changti, Yuan, Hang, Wang, Bailing, Huang, Cong, Chen, Kai
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training
by: Yu, Bin, et al.
Published: (2026)

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
by: Yu, Bin, et al.
Published: (2026)

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
by: Lian, Shijie, et al.
Published: (2026)

PhysBrain 1.0 Technical Report
by: Lian, Shijie, et al.
Published: (2026)

TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model
by: Yu, Bin, et al.
Published: (2025)

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence
by: Lin, Xiaopeng, et al.
Published: (2025)

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
by: Lian, Shijie, et al.
Published: (2025)

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning
by: Wu, Changti, et al.
Published: (2026)

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision
by: Liu, Ruixun, et al.
Published: (2025)

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
by: Chen, Peng, et al.
Published: (2025)

GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
by: Sun, Lin, et al.
Published: (2025)

GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module
by: Zhang, Yichen, et al.
Published: (2024)

3D-VLA: A 3D Vision-Language-Action Generative World Model
by: Zhen, Haoyu, et al.
Published: (2024)

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
by: Jia, Xiaosong, et al.
Published: (2026)

AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
by: Yang, Kai, et al.
Published: (2026)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
by: Li, Chengmeng, et al.
Published: (2025)

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
by: Zhang, Jiahui, et al.
Published: (2025)

ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
by: He, Zeyuan, et al.
Published: (2026)

Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer
by: Peng, Shuai, et al.
Published: (2024)

CLAMP: Majorized Plug-and-Play for Coherent 3D LIDAR Imaging
by: Allen, Tony G., et al.
Published: (2024)

Toward a Plug-and-Play Vision-Based Grasping Module for Robotics
by: Hélénon, François, et al.
Published: (2023)

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models
by: Yu, Bin, et al.
Published: (2025)

DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry
by: Wu, Changti, et al.
Published: (2025)

StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
by: Xiao, Jiasong, et al.
Published: (2026)

SceneVGGT: VGGT-based online 3D semantic SLAM for indoor scene understanding and navigation
by: Gelencsér-Horváth, Anna, et al.
Published: (2026)

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
by: Hu, Songqiao, et al.
Published: (2025)

AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
by: Rao, Zhifeng, et al.
Published: (2026)

OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model
by: Singh, Ishika, et al.
Published: (2025)

Plug-and-Play regularized 3D seismic inversion with 2D pre-trained denoisers
by: Luiken, Nick, et al.
Published: (2024)

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior
by: Guo, Wenhan, et al.
Published: (2025)

VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model
by: Sun, Xiangyu, et al.
Published: (2026)

GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions
by: Huang, Helong, et al.
Published: (2025)

ModalPatch: A Plug-and-Play Module for Robust Multi-Modal 3D Object Detection under Modality Drop
by: Li, Shuangzhi, et al.
Published: (2026)

The Loupe: A Plug-and-Play Attention Module for Amplifying Discriminative Features in Vision Transformers
by: Sengodan, Naren
Published: (2025)

DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
by: Yuan, Tianyuan, et al.
Published: (2025)

DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
by: Wen, Junjie, et al.
Published: (2025)

Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
by: Yu, Qiao, et al.
Published: (2024)

GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models
by: Sarowar, Md Selim, et al.
Published: (2026)

ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
by: Liu, Zhenyang, et al.
Published: (2026)

PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
by: Chen, Yongwei, et al.
Published: (2026)