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

每年论文数

各会议论文数

按年份和会议统计

世界模型论文数,按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231373023
2024191112446
202542242713106
202685566940250

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

全部世界模型论文

共 46 篇,第 1 / 1 页

  1. CVPR 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
  2. CVPR 2024Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
  3. CVPR 2024ReCoRe: Regularized Contrastive Representation Learning of World Model
  4. CVPR 2024UnO: Unsupervised Occupancy Fields for Perception and Forecasting
  5. ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
  6. ICLR 2024Grounding Multimodal Large Language Models to the World
  7. ICLR 2024Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
  8. ICLR 2024Locality Sensitive Sparse Encoding for Learning World Models Online
  9. ICLR 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
  10. ICLR 2024Mastering Memory Tasks with World Models
  11. ICLR 2024Neurosymbolic Grounding for Compositional World Models
  12. ICLR 2024Reward-Free Curricula for Training Robust World Models
  13. ICLR 2024Robust agents learn causal world models
  14. ICLR 2024SafeDreamer: Safe Reinforcement Learning with World Models
  15. ICLR 2024TD-MPC2: Scalable, Robust World Models for Continuous Control
  16. ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
  17. ICML 2024AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors
  18. ICML 2024Do Transformer World Models Give Better Policy Gradients?
  19. ICML 2024Efficient World Models with Context-Aware Tokenization
  20. ICML 2024Genie: Generative Interactive Environments
  21. ICML 2024HarmonyDream: Task Harmonization Inside World Models
  22. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
  23. ICML 2024Improving Token-Based World Models with Parallel Observation Prediction
  24. ICML 2024Learning Latent Dynamic Robust Representations for World Models
  25. ICML 2024Learning to Model the World With Language
  26. ICML 2024Learning to Play Atari in a World of Tokens
  27. ICML 2024RoboDreamer: Learning Compositional World Models for Robot Imagination
  28. NeurIPS 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
  29. NeurIPS 2024Diffusion for World Modeling: Visual Details Matter in Atari
  30. NeurIPS 2024DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
  31. NeurIPS 2024Evaluating the World Model Implicit in a Generative Model
  32. NeurIPS 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
  33. NeurIPS 2024GenRL: Multimodal-foundation world models for generalization in embodied agents
  34. NeurIPS 2024Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
  35. NeurIPS 2024In-Context Symmetries: Self-Supervised Learning through Contextual World Models
  36. NeurIPS 2024iVideoGPT: Interactive VideoGPTs are Scalable World Models
  37. NeurIPS 2024Learning World Models for Unconstrained Goal Navigation
  38. NeurIPS 2024Leveraging Separated World Model for Exploration in Visually Distracted Environments
  39. NeurIPS 2024Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
  40. NeurIPS 2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
  41. NeurIPS 2024Operator World Models for Reinforcement Learning
  42. NeurIPS 2024PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
  43. NeurIPS 2024Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
  44. NeurIPS 2024Simplifying Latent Dynamics with Softly State-Invariant World Models
  45. NeurIPS 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
  46. NeurIPS 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment

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"}

两分钟接入 Paperlist MCP(Claude Code、Cursor、Codex、ChatGPT)

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。

「前沿系统」下的其他主题