World Model Learning

Follow this topic Ask about this topic

Momentum

50 papers in the last four weeks, up 257% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 281

All topics

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
May 22, 2026Jiayi FangRepresentation Learning World Model Learning
1Shanghai University of Finance and Economics
World Machine: Towards Generative World Modeling for Time-Series
May 21, 2026Elton Cardoso do Nascimento, Alexandre da Silva Simões, Esther Luna Colombini +2World Model Learning Latent World Models
Universidade Estadual de Campinas (UNICAMP), {FEEC, IC} · Universidade Estadual Paulista (UNESP), Instituto de Ciˆencia e Tecnologia, Sorocaba
World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks
May 19, 2026Zuyao Lin, Jianhui Zhang, Peidong Jia +4World Model Learning Long-Horizon Robotic Manipulation
Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Zhongguancun Academy +2
HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models
May 19, 2026Hoonhee Cho, Giwon Lee, Jae-Young Kang +3World Model Learning End-to-End Autonomous Driving
1All authors are with KAIST, Daejeon, Republic of Korea.
WorldString: Actionable World Representation
May 18, 2026Kunqi Xu, Jitao Li, Jianglong Ye +4World Model Learning Object-Centric Representation Learning
Tsinghua University - IEI Lab · CalTech · UC San Diego +1
GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning
May 17, 2026Cheng Chen, Hao Huang, Saurabh Bagchi3D Gaussian Splatting World Model Learning
Purdue University · New York University Abu Dhabi
A World Model of Radiologist Reading for Medical Image Representation Learning
May 17, 2026Yiwei Li, Zihao Wu, Huaqin Zhao +5World Model Learning Healthcare
University of Georgia · University of Texas at Arlington · New Jersey Institute of Technology
Self-supervised Hierarchical Visual Reasoning with World Model
May 17, 2026Yuanfei Xu, Lin Liu, Wengang Zhou +2World Model Learning World Models
Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
May 16, 2026SeungWon Seo, DongHeun Han, SeongRae Noh +1Online System Identification World Model Learning
Korea University · Kyung Hee University
SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation
May 15, 2026Ssharvien Kumar Sivakumar, Akwele Johnson, Anirudh Dhingra +3World Model Learning Sim-to-Real Transfer
Technical University Darmstadt, Darmstadt, Germany · Carl Zeiss AG, Munich, Germany · AICM, Medical Faculty of Heidelberg University, Heidelberg University, Germany
WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
May 15, 2026Baining Zhao, Jiacheng Xu, Weicheng Feng +13World Model Learning Vision-Language Navigation
Tsinghua University · Shandong University · Manifold AI +2
Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
May 15, 2026Tianqiu Zhang, Muyang Lyu, Xiao Liu +1Computational Cognitive Modeling World Model Learning
Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, IDG/McGovern Institute for Brain Research, Center of Quantitative Biology, School of Psychological and Cognitive Sciences, Key Laboratory of Machine Perception (Ministry of Education), Peking University. · HHMI Janelia.
DiLA: Disentangled Latent Action World Models
May 15, 2026Tianqiu Zhang, Muyang Lyu, Yufan Zhang +2Action-Conditioned Video Generation Latent Action Learning
Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, IDG/McGovern Institute for Brain Research, Peking University. · Center of Quantitative Biology, Peking University. · School of Psychological and Cognitive Sciences, Key Laboratory of Machine Perception (Ministry of Education), Peking University.
Feedback World Model Enables Precise Guidance of Diffusion Policy
May 15, 2026Tuo An, Jindou Jia, Gen Li +8World Model Learning World Models for Robotics
1MARS Lab, Nanyang Technological University
Identifiable Token Correspondence for World Models
May 15, 2026Youngin Kim, Ray Sun, Inho Kim +2World Model Learning Transformer-Based RL
Interdisciplinary Program in Artificial Intelligence, Seoul National University · Department of Computer Science and Engineering, Seoul National University · KRAFTON
Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction
May 14, 2026Santosh Kumar PaidiWorld Model Learning Causal World Models
Genentech, Inc.
Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics
May 14, 2026Yunfei Luo, Xi Chen, Yuliang Chen +8Multivariate Time Series Forecasting World Model Learning
University of California San Diego · Dartmouth College · Amazon Web Services +3
EponaV2: Driving World Model with Comprehensive Future Reasoning
May 14, 2026Jiawei Xu, Zhizhou Zhong, Zhijian Shu +8World Model Learning World Model-Based Planning
1PCA Lab, VCIP, College of Computer Science, Nankai University · 2Horizon Robotics · 3HKUST +4
Learning POMDP World Models from Observations with Language-Model Priors
May 13, 2026Valentin Six, Frederik Panse, Mathis Fajeau +7World Model Learning Markov Models
1Max Planck Institute for Intelligent Systems · University of Tübingen · 2IRIIS +3
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
May 13, 2026Jing Yu Lim, Rushi Shah, Zarif Ikram +4World Model Learning Joint-Embedding Predictive Architecture
National University of Singapore · usc
Reinforcing VLAs in Task-Agnostic World Models
May 12, 2026Yucen Wang, Rui Yu, Fengming Zhang +5World Model Learning World Models
Nanjing University · Interns at Microsoft · University of Illinois at Urbana-Champaign +4
Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference
May 12, 2026Toru TakahashiWorld Model Learning Cognitive Modeling
Human Informatics and Systems Laboratory, Doshisha University, Kyoto, Japan · Linked Open Data Initiative, NPO, Tokyo, Japan · Keio Research Institute at SFC, Fujisawa, Japan +1
Composition of Memory Experts for Diffusion World Models
May 12, 2026Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan +1World Model Learning Memory-Augmented Agents
Computer Vision Group Department of Computer Science University of Bern
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
May 12, 2026Conglang Zhang, Yifan Zhan, Qingjie Wang +10World Model Learning Long-Horizon Video Generation
Wuhan University · The University of Tokyo · Horizon Robotics +3
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
May 11, 2026Ahmet H. Güzel, Jenny Seidenschwarz, Benjamin Graham +3Adversarial Training World Model Learning
University College London AI Centre · Odyssey · University of Basel
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
May 11, 2026Lingjun Zhang, Changjie Wu, Linzhe Shi +6World Model Learning End-to-End Autonomous Driving
Tsinghua University · Amap, Alibaba Group · Nanyang Technological University
How Mobile World Model Guides GUI Agents?
May 11, 2026Weikai Xu, Kun Huang, Yunren Feng +10World Model Learning GUI Agents
1Nanyang Technological University · 2MiLM Plus, Xiaomi Inc. · 3Independent Researchers +3
Do multimodal models imagine electric sheep?
May 10, 2026Santhosh Kumar Ramakrishnan, Carl Vondrick, Raja Giryes +2Visual Spatial Reasoning World Model Learning
Apple
DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
May 10, 2026Can Li, Zhoujian Li, Ren Li +4World Model Learning World Models
Nankai University · Rightly Robotics, A4X · Zhejiang University +2
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
May 10, 2026Kai Zhao, Dongliang Nie, Yuchen Lin +4Representation Learning Representation Collapse
1Shanghai University · 2The University of Manchester · 3Nankai University

May 22, 2026, cs.LGJ/K move · Enter open · S save

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision

Jiayi Fang

1Shanghai University of Finance and Economics

Representation Learning World Model Learning Geometric Representation Learning Latent World Models Embodied World Models

Open paper AskPDF arXiv

What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random embodied exploration, we find that its latent space develops spatial semantic structure that mirrors physical geometry -- direction accuracy 0.677+-0.029 versus 0.547 for a randomly initialized encoder, and position RSA 0.192+-0.047 versus 0.029 for random encoders (6.6x improvement), showing that training induces genuine structural organization beyond CNN inductive bias. Across 20 temporal checkpoints, prediction performance and semantic alignment co-improve (Spearman r=-0.61, p=0.004), consistent with the shared-driver account. We confirm this through a double knockout: standard KL regularization (beta=0.1) forces the encoder away from geometric structure, and both prediction performance and semantic alignment collapse simultaneously to near-chance by step 50,000 -- exactly as the shared-driver account predicts. Reducing beta to 0.001 restores geometric access and recovers both capabilities together. These findings establish physical world geometry as the organizing principle of world model representations, with direct implications for the design of semantically grounded embodied agents.

Momentum

Related topics

Latest papers 281