世界模型

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

DynamicVerse: 一种具有物理意识的多模态框架用于4D世界建模

Kairun Wen, Yuzhi Huang, Runyu Chen, Hui Zheng, Yunlong Lin, Panwang Pan, Chenxin Li, Wenyan Cong, Jian Zhang, Junbin Lu, Chenguo Lin, Dilin Wang, Zhicheng Yan, Hongyu Xu, Justin Theiss, Yue Huang, Xinghao Ding, Rakesh Ranjan, Zhiwen Fan

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

AI总结 DynamicVerse提出了一种多模态框架，通过整合大规模视觉、几何和多模态模型，实现动态现实世界视频的4D世界建模，提升了对物理尺度测量的全局准确性。

DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments

DREAMer-VXS：一种用于在随机、未观测环境中高效样本AGV探索的潜在世界模型

Agniprabha Chakraborty

机构 * Department of Power Engineering, Jadavpur University（功率工程系，贾瓦德普尔大学） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.RO

AI总结 DREAMer-VXS通过高效样本利用和潜在世界模型，实现AGV在随机未观测环境中的高效探索与鲁棒导航

PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics

Sachin Vashistha, Aryan Bibhuti, Atharva Naik, Martin Tutek, Somak Aditya

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.AI

Comments 23 pages, 15 tables, 10 figures; AAAI 2026 Conference Main Track (oral)

ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling

Golnaz Raja, Ruslan Agishev, Miloš Prágr, Joni Pajarinen, Karel Zimmermann, Arun Kumar Singh, Reza Ghabcheloo

机构 * Tampere University（塔尔皮耶大学） ； Czech Technical University（捷克技术大学） ； University of Tartu（塔尔图大学） ； Aalto University（阿尔托大学） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.RO

Comments This paper is submitted to IEEE International Conference on Robotics and Automation (ICRA) 2026

X-Streamer: Unified Human World Modeling with Audiovisual Interaction

You Xie, Tianpei Gu, Zenan Li, Chenxu Zhang, Guoxian Song, Xiaochen Zhao, Chao Liang, Jianwen Jiang, Hongyi Xu, Linjie Luo

机构 * ByteDance（字节跳动） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments Project Page at https://byteaigc.github.io/X-Streamer

Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach

Xiaoran Yin, Xu Luo, Hao Wu, Lianli Gao, Jingkuan Song

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments Accepted to Findings of EMNLP 2025. This is the camera-ready version

CoEx -- Co-evolving World-model and Exploration

Minsoo Kim, Seung-won Hwang

专题命中 通用世界模型 ：world-model(title)；world-model(title)；world model(abstract)；world model(abstract)

What Does it Mean for a Neural Network to Learn a "World Model"?

Kenneth Li, Fernanda Viégas, Martin Wattenberg

机构 * Harvard University（哈佛大学） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.AI

NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments

Xuan Yao, Junyu Gao, Changsheng Xu

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)（多模态人工智能系统国家重点实验室（MAIS）、自动化研究所、中国科学院（CASIA）） ； School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（人工智能学院、中国科学院大学（UCAS）） ； Peng Cheng Laboratory, ShenZhen, China（鹏城实验室、深圳中国） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis

Yifei Gao, Junhong Ye, Jiaqi Wang, Jitao Sang

机构 * Beijing Jiaotong University（北京交通大学） 纠错

专题命中 通用世界模型 ：world-model(title)；world-model(title)；world model(abstract)；world model(abstract)

Xray2Xray: World Model from Chest X-rays with Volumetric Context

Zefan Yang, Xinrui Song, Xuanang Xu, Yongyi Shi, Ge Wang, Mannudeep K. Kalra, Pingkun Yan

机构 * Department of Biomedical Engineering（生物医学工程系） ； Center for Biotechnology（生物技术中心） ； Interdisciplinary Studies（跨学科研究） ； Rensselaer Polytechnic Institute（伦塞拉尔理工大学） ； Department of Radiology（放射科） ； Massachusetts General Hospital（麻省总医院） ； Harvard Medical School（哈佛医学院） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

DSG-World: Learning a 3D Gaussian World Model from Dual State Videos

Wenhao Hu, Xuexiang Wen, Xi Li, Gaoang Wang

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； ZJU-UIUC Institute, Zhejiang University（浙江大学-伊利诺伊大学联合研究所） 纠错

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval

Yuanmin Tang, Jing Yu, Keke Gai, Jiamin Zhuang, Gang Xiong, Gaopeng Gou, Qi Wu

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments This work has been accepted to CVPR 2025

World Model Agents with Change-Based Intrinsic Motivation

Jeremias Ferrao, Rafael Cunha

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Comments Submitted to Northern Lights Deep Learning Conference 2025

Inter-environmental world modeling for continuous and compositional dynamics

Kohei Hayashi, Masanori Koyama, Julian Jorge Andrade Guerreiro

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

Xiang Li, Pengfei Li, Yupeng Zheng, Wei Sun, Yan Wang, Yilun Chen

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments Accepted by ICLR 2025

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Pedro M B Rezende, Yasaman Haghighi, David Brüggemann, Isinsu Katircioglu, Lin Zhang, Xiaoran Chen, Suman Saha, Marco Cannici, Elie Aljalbout, Botao Ye, Xi Wang, Aram Davtyan, Mathieu Salzmann, Davide Scaramuzza, Marc Pollefeys, Paolo Favaro, Alexandre Alahi

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

UrbanWorld: An Urban World Model for 3D City Generation

Yu Shang, Yuming Lin, Yu Zheng, Hangyu Fan, Jingtao Ding, Jie Feng, Jiansheng Chen, Li Tian, Yong Li

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments 14 pages

Understanding Physical Dynamics with Counterfactual World Modeling

Rahul Venkatesh, Honglin Chen, Kevin Feigelis, Daniel M. Bear, Khaled Jedoui, Klemen Kotar, Felix Binder, Wanhee Lee, Sherry Liu, Kevin A. Smith, Judith E. Fan, Daniel L. K. Yamins

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Comments ECCV 2024. Project page at: https://neuroailab.github.io/cwm-physics/

Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling

Margaret Li, Weijia Shi, Artidoro Pagnoni, Peter West, Ari Holtzman

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.AI

Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model

Zeyu Gao, Yao Mu, Chen Chen, Jingliang Duan, Shengbo Eben Li, Ping Luo, Yanfeng Lu

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Comments 13 pages, 13 figures, 4 tables, this version is accepted by IEEE Transactions on Intelligent Transportation Systems, the workshop version can be found in NeurIPS Deep RL Workshop 2022

Explainable Reinforcement Learning via a Causal World Model

Zhongwei Yu, Jingqing Ruan, Dengpeng Xing

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Comments Accepted by IJCAI 2023

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi, Hannaneh Hajishirzi, Sameer Singh, Roy Fox

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Comments in proceedings of ICML 23

InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views

Mai Nishimura, Shohei Nobuhara, Ko Nishino

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.CV

Reinforcement learning with world model

Jingbin Liu, Xinyang Gu, Shuai Liu

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.AI

Sepsis World Model: A MIMIC-based OpenAI Gym "World Model" Simulator for Sepsis Treatment

Amirhossein Kiani, Chris Wang, Angela Xu

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)；分类 cs.LG

Comments This project was done as a class project for CS221 at Stanford University

ResiliFlow: An Open Transport World Model for Infrastructure Perception and Disaster Resilience

ResiliFlow：面向基础设施感知与灾害韧性的开放交通世界模型

Junxiang Xu, Vinayak Dixit, S. Travis Waller, Divya Jayakumar Nair, Qianwen (Vivian)Guo, Sisi Jian, Xiao Wen, Ashutosh Ashutosh, Sunhyung Yoo, Julius Secadiningrat, Jingni Guo

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)

AI总结 ResiliFlow是面向基础设施感知与灾害韧性的开放交通世界模型平台，整合两类工作空间功能，实现交通模型的可检查复用，支撑研究协作与公众监督。

RFWM: Physics-Guided World Model for Dynamic Wireless Radiance Field Generation

RFWM：用于生成动态无线辐射场的物理引导世界模型

Zijiu Yang, Qianqian Yang

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)

AI总结 本研究针对动态未知环境下RF场建模泛化难的问题，提出物理引导的RF世界模型RFWM，采用两阶段训练策略，在新构建的基准上实现了优于现有最优方法的RF场生成性能。

A JEPA-Based Field-Layer World Model for Bridging Channel Prediction and Estimation

一种基于JEPA的场层世界模型，用于衔接信道预测与估计

Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, MérouaneDebbah

专题命中 通用世界模型 ：world model(title,abstract)；world model(title,abstract)

AI总结 该研究针对MIMO-OFDM无线系统中CSI预测鲁棒性差的问题，提出基于JEPA的场层世界模型，通过多尺度对齐策略实现跨频段重构，显著提升了波束成形增益。

Comments submitted to IEEE trans

Reinforcement Learning: From Algorithms To Foundation Models

强化学习：从算法到基础模型

Zihan Ding

专题命中 通用世界模型 ：world model(abstract)；world models(abstract)；video world model(abstract)；world model(abstract)

AI总结 本文从游戏算法和基础模型时代的RL两个视角展开研究，前者聚焦多智能体RL中相关概念的相互作用，后者利用生成和基础模型丰富序列决策，开发多种模型并进行相关研究，呈现RL在复杂序列域的统一视图，突出其连接多方面的作用。

Comments Princeton University PhD Thesis 2026