Image de couverture de livre

MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Jiaxu, Jiang, Yicheng, He, Tianlun, Sun, Jingkai, Zhang, Qiang, He, Junhao, Cao, Jiahang, Gan, Zesen, Sun, Mingyuan, Shao, Qiming, Yue, Xiangyu
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
par: Jiang, Yicheng, et autres
Publié: (2026)

DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
par: Wang, Jiaxu, et autres
Publié: (2024)

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
par: He, Junhao, et autres
Publié: (2025)

Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
par: Sun, Jingkai, et autres
Publié: (2025)

EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
par: Wang, Jiaxu, et autres
Publié: (2024)

Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning
par: Wang, Jiaxu, et autres
Publié: (2024)

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
par: Wang, Jiaxu, et autres
Publié: (2026)

Trinity: A Modular Humanoid Robot AI System
par: Sun, Jingkai, et autres
Publié: (2025)

Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion
par: Zhang, Qiang, et autres
Publié: (2025)

Fully Spiking Neural Network for Legged Robots
par: Jiang, Xiaoyang, et autres
Publié: (2023)

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation
par: Chai, Ying, et autres
Publié: (2025)

WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
par: Qian, Zezhong, et autres
Publié: (2025)

ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation
par: Li, Wei, et autres
Publié: (2026)

DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
par: Sun, Jingkai, et autres
Publié: (2025)

Occupancy World Model for Robots
par: Zhang, Zhang, et autres
Publié: (2025)

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
par: Zhang, Qiang, et autres
Publié: (2025)

RealD$^2$iff: Bridging Real-World Gap in Robot Manipulation via Depth Diffusion
par: Liang, Xiujian, et autres
Publié: (2025)

ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
par: Zhang, Qiang, et autres
Publié: (2025)

Physical Priors Augmented Event-Based 3D Reconstruction
par: Wang, Jiaxu, et autres
Publié: (2024)

3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation
par: He, Yunhong, et autres
Publié: (2025)

3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training
par: Deng, Yicheng, et autres
Publié: (2021)

Reinforcement Learning with Generalizable Gaussian Splatting
par: Wang, Jiaxu, et autres
Publié: (2024)

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models
par: Cao, Jiahang, et autres
Publié: (2024)

ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations
par: Li, Zheng, et autres
Publié: (2025)

AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation
par: Zhu, Juan, et autres
Publié: (2026)

Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning
par: Cao, Jiahang, et autres
Publié: (2024)

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
par: Cao, Jiahang, et autres
Publié: (2025)

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
par: Zhou, Kaichen, et autres
Publié: (2026)

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
par: Zhou, Pengfei, et autres
Publié: (2026)

Never-Ending Behavior-Cloning Agent for Robotic Manipulation
par: Liang, Wenqi, et autres
Publié: (2024)

VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation
par: Zhou, Hanyu, et autres
Publié: (2025)

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining
par: Liu, I-Chun Arthur, et autres
Publié: (2026)

Continual Hand-Eye Calibration for Open-world Robotic Manipulation
par: Li, Fazeng, et autres
Publié: (2026)

E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework
par: Duan, Yiqun, et autres
Publié: (2024)

TesserAct: Learning 4D Embodied World Models
par: Zhen, Haoyu, et autres
Publié: (2025)

PSF-4D: A Progressive Sampling Framework for View Consistent 4D Editing
par: Iqbal, Hasan, et autres
Publié: (2025)

Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
par: Huang, Jingkai, et autres
Publié: (2026)

SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation
par: Xu, Jingkai, et autres
Publié: (2025)

Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation
par: Lv, Kangchen, et autres
Publié: (2025)

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
par: Zhang, Qiang, et autres
Publié: (2025)