Image de couverture de livre

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Zhen, Meng, Zian, Shi, Shuwei, Peng, Wenshuo, Wu, Yuwei, Zheng, Bo, Li, Chuanhao, Zhang, Kaipeng
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

Yume: An Interactive World Generation Model
par: Mao, Xiaofeng, et autres
Publié: (2025)

Sekai: A Video Dataset towards World Exploration
par: Li, Zhen, et autres
Publié: (2025)

SVBench: Evaluation of Video Generation Models on Social Reasoning
par: Peng, Wenshuo, et autres
Publié: (2025)

Yume-1.5: A Text-Controlled Interactive World Generation Model
par: Mao, Xiaofeng, et autres
Publié: (2025)

SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
par: Li, Chuanhao, et autres
Publié: (2024)

World Craft: Agentic Framework to Create Visualizable Worlds via Text
par: Sun, Jianwen, et autres
Publié: (2026)

T3M: Text Guided 3D Human Motion Synthesis from Speech
par: Peng, Wenshuo, et autres
Publié: (2024)

World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild
par: Zheng, Yupeng, et autres
Publié: (2025)

Learning Latent Action World Models In The Wild
par: Garrido, Quentin, et autres
Publié: (2026)

Speech World Model: Causal State-Action Planning with Explicit Reasoning for Speech
par: Zhou, Xuanru, et autres
Publié: (2025)

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
par: Huang, Wenlong, et autres
Publié: (2026)

Multi-Sourced Compositional Generalization in Visual Question Answering
par: Li, Chuanhao, et autres
Publié: (2025)

A Large-Scale Study on Video Action Dataset Condensation
par: Chen, Yang, et autres
Publié: (2024)

MAPF-World: Action World Model for Multi-Agent Path Finding
par: Yang, Zhanjiang, et autres
Publié: (2025)

GigaWorld-Policy: An Efficient Action-Centered World--Action Model
par: Ye, Angen, et autres
Publié: (2026)

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
par: Mao, Xiaofeng, et autres
Publié: (2026)

Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism
par: Chen, Zheyu, et autres
Publié: (2026)

MotionScape: A Large-Scale Real-World Highly Dynamic UAV Video Dataset for World Models
par: Guo, Zile, et autres
Publié: (2026)

OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding
par: Zheng, Minghang, et autres
Publié: (2026)

Generative World Renderer
par: Huang, Zheng-Hui, et autres
Publié: (2026)

Stash, Slot, and Carry: ARPG, Pokémon, PSO, and the Environmental Conditions of Agentic AI
par: Eissens, Raynor
Publié: (2026)

Composition-Incremental Learning for Compositional Generalization
par: Li, Zhen, et autres
Publié: (2025)

3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly
par: Yang, Enquan, et autres
Publié: (2025)

Generalized Dynamics Generation towards Scannable Physical World Model
par: Li, Yichen, et autres
Publié: (2025)

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification
par: Peng, Wenshuo, et autres
Publié: (2024)

LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
par: Zheng, Lianmin, et autres
Publié: (2023)

WebWorld: A Large-Scale World Model for Web Agent Training
par: Xiao, Zikai, et autres
Publié: (2026)

Building Explicit World Model for Zero-Shot Open-World Object Manipulation
par: Li, Xiaotong, et autres
Publié: (2026)

EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks
par: Li, Yihang, et autres
Publié: (2026)

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
par: Shi, Chen, et autres
Publié: (2026)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
par: Zi, Bojia, et autres
Publié: (2021)

Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
par: Ruan, Bo-Kai, et autres
Publié: (2026)

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
par: Zhou, Yang, et autres
Publié: (2025)

Can World Models Benefit VLMs for World Dynamics?
par: Zhang, Kevin, et autres
Publié: (2025)

ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild
par: Liu, Yongxiang, et autres
Publié: (2025)

DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
par: Lyu, Jiangran, et autres
Publié: (2025)

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos
par: Li, Kaining, et autres
Publié: (2025)

Wild Tibetan Macaques Use a Route‐Based Mental Map to Navigate in Large‐Scale Space
par: Shi Cheng, et autres
Publié: (2024)

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
par: Wang, Jiahao, et autres
Publié: (2025)

DDL: A Large-Scale Datasets for Deepfake Detection and Localization in Diversified Real-World Scenarios
par: Miao, Changtao, et autres
Publié: (2025)