世界模型论文趋势 2023–2026
学习环境动力学、交互式视频世界、latent 动力学与可规划的世界表征
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 425 篇被归入该主题的论文。
主要结论
- 世界模型论文从 2023 年的 23 篇增长到 2026 年的 250 篇，三年间扩大到约 11 倍。
- NeurIPS 是发世界模型论文最多的会议，2023–2026 年共 159 篇，占四个会议总量的 37%。
- 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 34 篇。
- 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 4；同组增长最快的AI 智能体是 12 倍，世界模型是 11 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 13 | 7 | 3 | 0 | 23 |
| 2024 | 19 | 11 | 12 | 4 | 46 |
| 2025 | 42 | 24 | 27 | 13 | 106 |
| 2026 | 85 | 56 | 69 | 40 | 250 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- 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
全部世界模型论文
共 250 篇，第 5 / 5 页
- NeurIPS 2026Hybrid Neural World Models for Physical Dynamics
- NeurIPS 2026ICAT: Incident-Case–Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
- NeurIPS 2026Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction Dynamics
- NeurIPS 2026Imperfect World Models are Exploitable
- NeurIPS 2026Joint Learning of Hierarchical Neural Options and Abstract World Model
- NeurIPS 2026K-PWM: Control-Oriented Structured World Models under Partial Observation
- NeurIPS 2026Language-Conditioned World Modeling for Visual Navigation
- NeurIPS 2026Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
- NeurIPS 2026LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
- NeurIPS 2026Learning Agentic World Vision-Language-Action Models for Autonomous Driving
- NeurIPS 2026Learning POMDP World Models from Observations with Language-Model Priors
- NeurIPS 2026Learning Task-Centric World Models from Visual Foundations
- NeurIPS 2026Learning Visual Feature-Based World Models via Residual Latent Action
- NeurIPS 2026LEIA: Learned Environment for Interactive Architected Materials
- NeurIPS 2026LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
- NeurIPS 2026LoopNav: Benchmarking Spatial Consistency in World Models
- NeurIPS 2026MapShift: Controlled Post-Intervention Evaluation for Embodied World Models
- NeurIPS 2026Masked Visual Actions for Unified World Modeling
- NeurIPS 2026Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search
- NeurIPS 2026MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
- NeurIPS 2026Next Forcing: Causal World Modeling with Multi-Chunk Prediction
- NeurIPS 2026Next-Latent Prediction Transformers Learn Compact World Models
- NeurIPS 2026ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
- NeurIPS 2026PanoWorld: Geometry-Consistent Panoramic Video World Modeling
- NeurIPS 2026Perception for Action in Latent World Models
- NeurIPS 2026Plan4D: Generative Plannable 4D Worlds
- NeurIPS 2026Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning
- NeurIPS 2026Predictive but Not Plannable: RC-aux for Latent World Models
- NeurIPS 2026Q-ARVD: Quantizing Autoregressive Video Diffusion Models
- NeurIPS 2026Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
- NeurIPS 2026ReGen: Agentic Video World Modeling with Synergized Reasoning and Generation
- NeurIPS 2026RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
- NeurIPS 2026SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts
- NeurIPS 2026Solaris: Building a Multiplayer Video World Model in Minecraft
- NeurIPS 2026Sparse Planning in Visual World Models via Cost Gradients
- NeurIPS 2026StarWM: Self-Supervised Trained Attention Routing for Robust World Models
- NeurIPS 2026Stealthy World Model Manipulation via Data Poisoning
- NeurIPS 2026SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics
- NeurIPS 2026TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
- NeurIPS 2026Think Before You Generate: Active Panoramic Exploration for Text-to-3D Scenes
- NeurIPS 2026ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
- NeurIPS 2026Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
- NeurIPS 2026Towards Financial World Modeling
- NeurIPS 2026Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
- NeurIPS 2026Trimming the Long-Tail of Visual World Modeling Evaluation
- NeurIPS 2026When does LeJEPA learn a World Model?
- NeurIPS 2026World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
- NeurIPS 2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
- NeurIPS 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
- NeurIPS 2026WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查世界模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "world-models"}
常见问题
- 2023–2026 年四大会议一共有多少篇世界模型论文？
- 共 425 篇，按年份分别是 2023 年 23 篇、2024 年 46 篇、2025 年 106 篇、2026 年 250 篇。
- NeurIPS 2026 有多少篇世界模型论文？
- NeurIPS 2026 有 85 篇世界模型论文，上一届是 42 篇。
- ICLR 2026 有多少篇世界模型论文？
- ICLR 2026 有 56 篇世界模型论文，上一届是 24 篇。
- ICML 2026 有多少篇世界模型论文？
- ICML 2026 有 69 篇世界模型论文，上一届是 27 篇。
- CVPR 2026 有多少篇世界模型论文？
- CVPR 2026 有 40 篇世界模型论文，上一届是 13 篇。
- 哪个会议的世界模型论文最多？
- NeurIPS，2023–2026 年共 159 篇。