视觉-语言-动作论文趋势 2023–2026

VLA 与端到端驾驶

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,639 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

视觉-语言-动作论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023883034105257
20241082962130329
20251086433140345
2026204113126265708

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

全部视觉-语言-动作论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 34 篇，第 1 / 1 页

  1. ICML 2023A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
  2. ICML 2023A Kernel-Based View of Language Model Fine-Tuning
  3. ICML 2023Algorithmic Collective Action in Machine Learning
  4. ICML 2023An Information-Theoretic Analysis of Nonstationary Bandit Learning
  5. ICML 2023Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
  6. ICML 2023Boosting Offline Reinforcement Learning with Action Preference Query
  7. ICML 2023Combinatorial Neural Bandits
  8. ICML 2023COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
  9. ICML 2023Delayed Bandits: When Do Intermediate Observations Help?
  10. ICML 2023Distilling Internet-Scale Vision-Language Models into Embodied Agents
  11. ICML 2023Dynamical Linear Bandits
  12. ICML 2023Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
  13. ICML 2023End-to-end Differentiable Clustering with Associative Memories
  14. ICML 2023End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
  15. ICML 2023For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal
  16. ICML 2023Global Context Vision Transformers
  17. ICML 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
  18. ICML 2023ILLUME: Rationalizing Vision-Language Models through Human Interactions
  19. ICML 2023Improving Visual Prompt Tuning for Self-supervised Vision Transformers
  20. ICML 2023Infinite Action Contextual Bandits with Reusable Data Exhaust
  21. ICML 2023Learning Intuitive Policies Using Action Features
  22. ICML 2023LIV: Language-Image Representations and Rewards for Robotic Control
  23. ICML 2023MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action
  24. ICML 2023Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
  25. ICML 2023Oscillation-free Quantization for Low-bit Vision Transformers
  26. ICML 2023PaLM-E: An Embodied Multimodal Language Model
  27. ICML 2023Quantum Policy Gradient Algorithm with Optimized Action Decoding
  28. ICML 2023Scaling Vision Transformers to 22 Billion Parameters
  29. ICML 2023Short-lived High-volume Bandits
  30. ICML 2023Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
  31. ICML 2023Tuning Computer Vision Models With Task Rewards
  32. ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
  33. ICML 2023Unifying Molecular and Textual Representations via Multi-task Language Modelling
  34. ICML 2023UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

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 查视觉-语言-动作在 CVPR 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": "vision-language-action"}

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视觉-语言-动作论文？
共 1,639 篇，按年份分别是 2023 年 257 篇、2024 年 329 篇、2025 年 345 篇、2026 年 708 篇。
NeurIPS 2026 有多少篇视觉-语言-动作论文？
NeurIPS 2026 有 204 篇视觉-语言-动作论文，上一届是 108 篇。
ICLR 2026 有多少篇视觉-语言-动作论文？
ICLR 2026 有 113 篇视觉-语言-动作论文，上一届是 64 篇。
ICML 2026 有多少篇视觉-语言-动作论文？
ICML 2026 有 126 篇视觉-语言-动作论文，上一届是 33 篇。
CVPR 2026 有多少篇视觉-语言-动作论文？
CVPR 2026 有 265 篇视觉-语言-动作论文，上一届是 140 篇。
哪个会议的视觉-语言-动作论文最多？
CVPR，2023–2026 年共 640 篇。

「机器人与具身」下的其他主题