World Models

Follow this topic Ask about this topic

Momentum

153 papers in the last four weeks, up 178% on the four weeks before. 1.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 692

All topics

Grounded World Model: Latent Planning with Language Goals
Apr 13, 2026Quanyi Li, Lan Feng, Haonan Zhang +4World Models World
EPFL · NUS
Zero-shot World Models Are Developmentally Efficient Learners
Apr 11, 2026Khai Loong Aw, Klemen Kotar, Wanhee Lee +6World Models Early Layers
Stanford University
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Apr 10, 2026Zile Wang, Zexiang Liu, Jiaxing Li +20Video World Models World Models
Skywork AI
MotionScape: A Motion-Stratified UAV Video Benchmark for World Modeling and Future Video Generation
Apr 9, 2026Zile Guo, Zhan Chen, Xiaoxuan Liu +5Unmanned Aerial Vehicles Unmanned Aerial Vehicle Detection
Aerospace Information Research Institute, Chinese Academy of Sciences · Key Laboratory of Target Cognition and Application Technology, Chinese Academy of Sciences · School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences +1
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
Apr 8, 2026Zhaowen Fan, Rongchao Zhang, Yunxiang HanEmbodied Agents Autonomous Agents
School of Computer Science, Sichuan University, Chengdu 610065, China
ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation
Mar 30, 2026Yu Sun, Meng Cao, Yang Ping +24Robot Systems Evaluation Benchmarks
Sun Yat-sen University · X Square Robot · MBZUAI +2
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Mar 30, 2026Muyang He, Hanzhong Guo, Junxiong Lin +1Generative Video Models Video World Models
School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China · Hong Kong Generative AI Research and Development Center, Hong Kong SAR, China
What if? Emulative Simulation with World Models for Situated Reasoning
Mar 6, 2026Ruiping Liu, Yufan Chen, Yuheng Zhang +8Imagination Spatial Reasoning
Karlsruhe Institute of Technology · Hunan University · ETH Zürich +2
MetaOthello: A Controlled Study of Multiple World Models in Transformers
Feb 26, 2026Aviral Chawla, Galen Hall, Juniper LovatoTransformer Architectures World Models
Vermont Complex Systems Institute, University of Vermont, Burlington, VT · University of Michigan, Ann Arbor, MI
UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
Feb 26, 2026Tianxing Xu, Zixuan Wang, Guangyuan Wang +5Long Video Generation Camera Control
Tsinghua University China · Tongyi Lab, Alibaba China · University of Science and Technology of China China
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Feb 15, 2026Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11Video World Models Simulation-Based Reinforcement Learning
University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy +2
Calculating Mutual Information between a Reward Maximizer and its Environment
Feb 13, 2026Alfred Harwood, Jose Faustino, Alex AltairOptimal Policies Mutual Information
1Dovetail Research · University of Sao Paulo
H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
Feb 11, 2026Jinbang Huang, Wenyuan Chen, Zhiyuan Li +9Efficient World-Action Model Robot State
Huawei Noah’s Ark Lab · University of Toronto · University of British Columbia +1
Neuro-Symbolic Synergy for World Modeling
Feb 11, 2026Hongyu Zhao, Siyu Zhou, Haolin Yang +2Neuro-Symbolic Framework LLM Reasoning Strategies
Department of Computer Science University of Maryland College Park, MD 20742, USA · Faculty of Engineering and IT Australian AI Institute University of Technology Sydney Sydney, Australia · Department of Statistics University of Chicago Chicago, IL 60637, USA +2
PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation
Feb 5, 2026Yushan Liu, Jingjing Fan, Shoujie Li +3Robotic Manipulation Foresight
Tsinghua University · Nanyang Technological University · Xspark AI
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Jan 18, 2026Tianxin Wei, Ting-Wei Li, Zhining Liu +26Agentic Reasoning LLM Reasoning Strategies
University of Illinois Urbana-Champaign · Meta · UCSD +2
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
Jan 13, 2026Youwei Liu, Jian Wang, Hanlin Wang +2Imagination World Models
Central South University · Department of Computing, The Hong Kong Polytechnic University · College of Computer Science, Sichuan University
Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions
Jan 12, 2026Zhiting Mei, Tenny Yin, Ola Shorinwa +9Video World Models Generative Video Models
Princeton University · Temple University
MobileDreamer: Generative Sketch World Model for GUI Agent
Jan 7, 2026Yilin Cao, Yufeng Zhong, Zhixiong Zeng +6Graphical User Interface Agents Device
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences · Meituan · School of Artificial Intelligence, University of Chinese Academy of Sciences
Soft Geometric Inductive Bias for Object Centric Dynamics
Dec 17, 2025Hampus Linander, Conor Heins, Alexander Tschantz +2Rigid-Body Dynamics Equivariance
VERSES AI · University of Sussex, Department of Informatics
AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis
Dec 12, 2025Junjie Ye, Rong Xue, Basile Van Hoorick +4Imitation Learning Human Motion Generation
Toyota Research Institute · USC Physical Superintelligence (PSI) Lab
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
Dec 7, 2025Ruicheng Zhang, Mingyang Zhang, Jun Zhou +6Long-Horizon Manipulation Embodied Artificial Intelligence
Tsinghua University · Sun Yat-sen University · X Square Robot +1
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
Nov 24, 2025Zhantao Gong, Liaoyuan Fan, Qing Guo +3Recent Vision-Language Models Foresight
College of Software, Nankai University, China · The University of Hong Kong, China · NKIARI, Shenzhen Futian, China +2
Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task
Oct 21, 2025Brady Bhalla, Honglu Fan, Nancy Chen +1Transformer Architectures Behavioral Embeddings
California Institute of Technology · Pasadena, CA 91125 · Google DeepMind +3
OmniNWM: Omniscient Driving Navigation World Models
Oct 21, 2025Bohan Li, Zhuang Ma, Dalong Du +10Efficient World-Action Model Autonomous Driving
Shanghai Jiao Tong University · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China · PhiGent +3
A Comprehensive Survey on World Models for Embodied AI
Oct 19, 2025Xinqing Li, Xin He, Le Zhang +3World Models Embodied Artificial Intelligence
Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
Oct 16, 2025Shiqi Chen, Tongyao Zhu, Zian Wang +8Large Language Model Agents Next-State Prediction
City University of Hong Kong · National University of Singapore · The Hong Kong Polytechnic University +5
RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation
Oct 10, 2025Chuanrui Zhang, Zhengxian Wu, Guanxing Lu +2Robotic Manipulation Imitation Learning
Nanyang Technological University, Singapore · Tsinghua University, Beijing, China
PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration
Date pendingHan Wang, Zijun Wang, Shuoshuo Xue +4Efficient World-Action Model World Models
Singapore University of Technology and Design · Sun Yat-sen University
Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Embodiment Adaptation
Date pendingZhidong Wang, Jingsong Liang, Zirui Li +3Autonomous Driving World Models
School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore · Collaborative Initiative, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore
Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping
Date pendingJiahui Zhang, Gongbo Liang, Yu ZhangOccupancy Viewpoint-Dependent Active Perception
Boise State University · Texas A&M University–San Antonio
GameWAM: A World Action Model for Video Games
Date pendingYuncheng Guo, Zhanqiu Zhang, Yiwen Guo +1Efficient World-Action Model World Models
Fudan University · LIGHTSPEED · Independent Researcher +1

Apr 13, 2026, cs.ROJ/K move · Enter open · S save

Grounded World Model: Latent Planning with Language Goals

Quanyi Li, Lan Feng, Haonan Zhang, Wuyang Li+3

EPFL · NUS

World Models World Planning Language Pairs

Open paper AskPDF arXiv

World models such as DINO-WM and LeWM specify the goal with an image, which is difficult to obtain in advance for novel tasks. We present the Grounded World Model (GWM), a latent world model that enables zero-shot planning in the real world from language goals alone. Given a candidate action sequence and the current observation, GWM predicts the future in the visual space of a pretrained video-language embedding model. The frozen readout of this embedding model maps this imagined future and the task description into the same embedding space, where their negative cosine similarity serves as the planning cost. Training GWM requires only offline and task-agnostic video-action pairs and no language labels. In simulated experiments on WISER, planning with GWM, which executes the candidate action of lowest cost, solves 87% of 288 tasks with unseen instructions and visual signals, while ten fine-tuned VLAs average 22%. We then scale GWM up with real robot data, and use it for zero-shot planning in realistic simulation and real scenes. In the IsaacSim evaluation, planning with GWM completes all 70 trials across 14 tasks that require reasoning over referring expressions, matching a modular planner grounded by a frontier VLM, while pi0.5 reaches 37/70. Deployed on a real Franka, the same stack completes 55/60 separately evaluated pick-and-place sub-tasks, comparable to the modular planner's 52/60, with the full system running locally on a single consumer GPU. Project website: https://quanyili.github.io/gwm-wiser/.

Momentum

Related topics

Latest papers 692