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 1,639 篇，第 31 / 33 页

  1. ICLR 2023Human MotionFormer: Transferring Human Motions with Vision Transformers
  2. ICLR 2023Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations
  3. ICLR 2023Learning to Estimate Shapley Values with Vision Transformers
  4. ICLR 2023Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models
  5. ICLR 2023LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
  6. ICLR 2023Masked Vision and Language Modeling for Multi-modal Representation Learning
  7. ICLR 2023Mid-Vision Feedback
  8. ICLR 2023MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
  9. ICLR 2023MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
  10. ICLR 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
  11. ICLR 2023PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
  12. ICLR 2023Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
  13. ICLR 2023Quasi-optimal Reinforcement Learning with Continuous Actions
  14. ICLR 2023Sparse Token Transformer with Attention Back Tracking
  15. ICLR 2023Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval
  16. ICLR 2023Vision Transformer Adapter for Dense Predictions
  17. ICLR 2023Write and Paint: Generative Vision-Language Models are Unified Modal Learners
  18. ICML 2023A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
  19. ICML 2023A Kernel-Based View of Language Model Fine-Tuning
  20. ICML 2023Algorithmic Collective Action in Machine Learning
  21. ICML 2023An Information-Theoretic Analysis of Nonstationary Bandit Learning
  22. ICML 2023Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
  23. ICML 2023Boosting Offline Reinforcement Learning with Action Preference Query
  24. ICML 2023Combinatorial Neural Bandits
  25. ICML 2023COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
  26. ICML 2023Delayed Bandits: When Do Intermediate Observations Help?
  27. ICML 2023Distilling Internet-Scale Vision-Language Models into Embodied Agents
  28. ICML 2023Dynamical Linear Bandits
  29. ICML 2023Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
  30. ICML 2023End-to-end Differentiable Clustering with Associative Memories
  31. ICML 2023End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
  32. ICML 2023For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal
  33. ICML 2023Global Context Vision Transformers
  34. ICML 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
  35. ICML 2023ILLUME: Rationalizing Vision-Language Models through Human Interactions
  36. ICML 2023Improving Visual Prompt Tuning for Self-supervised Vision Transformers
  37. ICML 2023Infinite Action Contextual Bandits with Reusable Data Exhaust
  38. ICML 2023Learning Intuitive Policies Using Action Features
  39. ICML 2023LIV: Language-Image Representations and Rewards for Robotic Control
  40. ICML 2023MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action
  41. ICML 2023Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
  42. ICML 2023Oscillation-free Quantization for Low-bit Vision Transformers
  43. ICML 2023PaLM-E: An Embodied Multimodal Language Model
  44. ICML 2023Quantum Policy Gradient Algorithm with Optimized Action Decoding
  45. ICML 2023Scaling Vision Transformers to 22 Billion Parameters
  46. ICML 2023Short-lived High-volume Bandits
  47. ICML 2023Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
  48. ICML 2023Tuning Computer Vision Models With Task Rewards
  49. ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
  50. ICML 2023Unifying Molecular and Textual Representations via Multi-task Language Modelling

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