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 8 of 9

351. NeurIPS 2025Video World Models with Long-term Spatial Memory
352. NeurIPS 2025WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
353. NeurIPS 2025World Models as Reference Trajectories for Rapid Motor Adaptation
354. NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
355. NeurIPS 2025WorldModelBench: Judging Video Generation Models As World Models
356. NeurIPS 2025Zero-shot World Models via Search in Memory
357. CVPR 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
358. CVPR 2024Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
359. CVPR 2024ReCoRe: Regularized Contrastive Representation Learning of World Model
360. CVPR 2024UnO: Unsupervised Occupancy Fields for Perception and Forecasting
361. ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
362. ICLR 2024Grounding Multimodal Large Language Models to the World
363. ICLR 2024Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
364. ICLR 2024Locality Sensitive Sparse Encoding for Learning World Models Online
365. ICLR 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
366. ICLR 2024Mastering Memory Tasks with World Models
367. ICLR 2024Neurosymbolic Grounding for Compositional World Models
368. ICLR 2024Reward-Free Curricula for Training Robust World Models
369. ICLR 2024Robust agents learn causal world models
370. ICLR 2024SafeDreamer: Safe Reinforcement Learning with World Models
371. ICLR 2024TD-MPC2: Scalable, Robust World Models for Continuous Control
372. ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
373. ICML 2024AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors
374. ICML 2024Do Transformer World Models Give Better Policy Gradients?
375. ICML 2024Efficient World Models with Context-Aware Tokenization
376. ICML 2024Genie: Generative Interactive Environments
377. ICML 2024HarmonyDream: Task Harmonization Inside World Models
378. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
379. ICML 2024Improving Token-Based World Models with Parallel Observation Prediction
380. ICML 2024Learning Latent Dynamic Robust Representations for World Models
381. ICML 2024Learning to Model the World With Language
382. ICML 2024Learning to Play Atari in a World of Tokens
383. ICML 2024RoboDreamer: Learning Compositional World Models for Robot Imagination
384. NeurIPS 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
385. NeurIPS 2024Diffusion for World Modeling: Visual Details Matter in Atari
386. NeurIPS 2024DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
387. NeurIPS 2024Evaluating the World Model Implicit in a Generative Model
388. NeurIPS 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
389. NeurIPS 2024GenRL: Multimodal-foundation world models for generalization in embodied agents
390. NeurIPS 2024Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
391. NeurIPS 2024In-Context Symmetries: Self-Supervised Learning through Contextual World Models
392. NeurIPS 2024iVideoGPT: Interactive VideoGPTs are Scalable World Models
393. NeurIPS 2024Learning World Models for Unconstrained Goal Navigation
394. NeurIPS 2024Leveraging Separated World Model for Exploration in Visually Distracted Environments
395. NeurIPS 2024Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
396. NeurIPS 2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
397. NeurIPS 2024Operator World Models for Reinforcement Learning
398. NeurIPS 2024PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
399. NeurIPS 2024Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
400. NeurIPS 2024Simplifying Latent Dynamics with Softly State-Invariant World Models

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.