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 425 篇，第 4 / 9 页
- ICML 2026TaskLoom: Weaving Knowledge Across Tasks in World Models
- ICML 2026TimeSpot: Benchmarking Geo-Temporal Understanding in Vision–Language Models in Real-World Settings
- ICML 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
- ICML 2026Uncertainty-Guided Exploration and Stable Planning for Sparse-Reward Manipulation from Limited Demonstrations
- ICML 2026VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
- ICML 2026VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
- ICML 2026VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
- ICML 2026WebWorld: A Large-Scale World Model for Web Agent Training
- ICML 2026WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
- ICML 2026What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
- ICML 2026World Guidance: World Modeling in Condition Space for Action Generation
- ICML 2026World Models in Pieces: Structural Certification of General Agents
- ICML 2026WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
- ICML 2026WorldCompass: Reinforcement Learning for Long-Horizon World Models
- ICML 2026WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- NeurIPS 2026A Hierarchical World Model for Driving
- NeurIPS 2026A World Model of Radiologist Reading for Medical Image Representation Learning
- NeurIPS 2026Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
- NeurIPS 2026ActO: Extracting Action Representations from MLLM Embeddings for Video World Models
- NeurIPS 2026AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes
- NeurIPS 2026Addressable Memory for Video World Models
- NeurIPS 2026AEON: Unifying Video and 3D World Models
- NeurIPS 2026Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
- NeurIPS 2026AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
- NeurIPS 2026AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
- NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
- NeurIPS 2026Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
- NeurIPS 2026Axiomatic World Modeling for Physics Reasoning
- NeurIPS 2026Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
- NeurIPS 2026Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
- NeurIPS 2026Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
- NeurIPS 2026Code2World: A GUI World Model via Renderable Code Generation
- NeurIPS 2026Counterfactual Debugging the World Model Transfer Gap
- NeurIPS 2026CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
- NeurIPS 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- NeurIPS 2026Decomposed Graded Verifier for Generative World Modeling
- NeurIPS 2026Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
- NeurIPS 2026Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
- NeurIPS 2026DRILL: Training World Models to Improve Policies, Not Predict Pixels
- NeurIPS 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
- NeurIPS 2026DriveFuture: Future-Aware Latent World Models for Autonomous Driving
- NeurIPS 2026ECHO: Terminal Agents Learn World Models for Free
- NeurIPS 2026EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
- NeurIPS 2026EpicWorldModel: Exploration-driven Planning with Latent World Models
- NeurIPS 2026Feedback World Model Enables Precise Guidance of Diffusion Policy
- NeurIPS 2026From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
- NeurIPS 2026From Zero to Hero: Training-Free Custom Concept Spawning in World Models
- NeurIPS 2026HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models
- NeurIPS 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
- NeurIPS 2026HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
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。