World Models papers, 2023–2026

Key findings

• World Models went from 23 papers in 2023 to 250 in 2026, roughly 11x in three years.
• NeurIPS publishes the most World Models work: 159 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 1 in 2023 to 34 in 2026.
• Among the 4 topics under Trending Systems, it ranks #4 by 2026 paper count; the fastest grower in the group, AI Agents, is up 12x versus 11x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Hierarchical World Model for Driving
• ICML 2026A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
• ICLR 2026Astra: General Interactive World Model with Autoregressive Denoising
• CVPR 2026Active Intelligence in Video Avatars via Closed-loop World Modeling
• NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
• ICML 2025A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
• ICLR 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving
• CVPR 2025DIO: Decomposable Implicit 4D Occupancy-Flow World Model
• NeurIPS 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
• ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
• ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
• CVPR 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
• NeurIPS 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
• ICML 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
• ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
• NeurIPS 2026A World Model of Radiologist Reading for Medical Image Representation Learning
• ICML 2026Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
• ICLR 2026Building spatial world models from sparse transitional episodic memories
• CVPR 2026Chain of World World Model Thinking in Latent Motion
• NeurIPS 2025DMWM: Dual-Mind World Model with Long-Term Imagination

All World Models papers

425 papers, page 2 of 9

51. ICLR 2026Dual-Scale World Models for LLM Agents towards Hard-Exploration Problems
52. ICLR 2026Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
53. ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
54. ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
55. ICLR 2026FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
56. ICLR 2026FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
57. ICLR 2026From Observations to Events: Event-Aware World Models for Reinforcement Learning
58. ICLR 2026Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
59. ICLR 2026Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
60. ICLR 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
61. ICLR 2026Learning Human Habits with Rule-Guided Active Inference
62. ICLR 2026Learning Massively Multitask World Models for Continuous Control
63. ICLR 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
64. ICLR 2026Learning to Be Uncertain: Pre-training World Models with Horizon-Calibrated Uncertainty
65. ICLR 2026Mapping Overlaps in Benchmarks through Perplexity in the Wild
66. ICLR 2026Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
67. ICLR 2026Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
68. ICLR 2026OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
69. ICLR 2026One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
70. ICLR 2026One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
71. ICLR 2026Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
72. ICLR 2026R-WoM: Retrieval-augmented World Model For Computer-use Agents
73. ICLR 2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
74. ICLR 2026ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving
75. ICLR 2026Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
76. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
77. ICLR 2026Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
78. ICLR 2026Scalable In-Context Q-Learning
79. ICLR 2026Self-Supervised Learning from Structural Invariance
80. ICLR 2026Sparse Imagination for Efficient Visual World Model Planning
81. ICLR 2026Speech World Model: Causal State–Action Planning with Explicit Reasoning for Speech
82. ICLR 2026TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
83. ICLR 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
84. ICLR 2026Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control
85. ICLR 2026Towards Spatial Supersensing in Video
86. ICLR 2026Unified 3D Scene Understanding Through Physical World Modeling
87. ICLR 2026Unified Vision-Language-Action Model
88. ICLR 2026VCWorld: A Biological World Model for Virtual Cell Simulation
89. ICLR 2026Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
90. ICLR 2026Vid2World: Crafting Video Diffusion Models to Interactive World Models
91. ICLR 2026Video-GPT via Next Clip Diffusion
92. ICLR 2026ViMo: A Generative Visual GUI World Model for App Agents
93. ICLR 2026WIMLE: Uncertainty‑Aware World Models with IMLE for Sample‑Efficient Continuous Control
94. ICLR 2026WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
95. ICLR 2026WorldGym: World Model as An Environment for Policy Evaluation
96. ICLR 2026WoW!: World Models in a Closed-Loop World
97. ICML 2026A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
98. ICML 2026Agent Learning via Early Experience
99. ICML 2026Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
100. ICML 2026Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

FAQ

How many World Models papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

425 in total: 23 in 2023, 46 in 2024, 106 in 2025, 250 in 2026.

How many World Models papers are at NeurIPS 2026?

NeurIPS 2026 has 85 World Models papers, versus 42 the year before.

How many World Models papers are at ICLR 2026?

ICLR 2026 has 56 World Models papers, versus 24 the year before.

How many World Models papers are at ICML 2026?

ICML 2026 has 69 World Models papers, versus 27 the year before.

How many World Models papers are at CVPR 2026?

CVPR 2026 has 40 World Models papers, versus 13 the year before.

Which conference publishes the most World Models papers?

NeurIPS, with 159 papers from 2023 to 2026.