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 29 / 33 页

  1. CVPR 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
  2. CVPR 2023DeAR: Debiasing Vision-Language Models With Additive Residuals
  3. CVPR 2023Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection
  4. CVPR 2023DETRs With Hybrid Matching
  5. CVPR 2023Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization
  6. CVPR 2023DropKey for Vision Transformer
  7. CVPR 2023Dynamic Inference With Grounding Based Vision and Language Models
  8. CVPR 2023End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve
  9. CVPR 2023Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition
  10. CVPR 2023Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language
  11. CVPR 2023FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training
  12. CVPR 2023Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
  13. CVPR 2023GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods
  14. CVPR 2023Global Vision Transformer Pruning With Hessian-Aware Saliency
  15. CVPR 2023Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos
  16. CVPR 2023How Can Objects Help Action Recognition?
  17. CVPR 2023Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles
  18. CVPR 2023Improving Vision-and-Language Navigation by Generating Future-View Image Semantics
  19. CVPR 2023Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels
  20. CVPR 2023InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions
  21. CVPR 2023Iterative Vision-and-Language Navigation
  22. CVPR 2023Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
  23. CVPR 2023LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
  24. CVPR 2023Latency Matters: Real-Time Action Forecasting Transformer
  25. CVPR 2023Learning Action Changes by Measuring Verb-Adverb Textual Relationships
  26. CVPR 2023Learning Discriminative Representations for Skeleton Based Action Recognition
  27. CVPR 2023Learning Expressive Prompting With Residuals for Vision Transformers
  28. CVPR 2023Learning Imbalanced Data With Vision Transformers
  29. CVPR 2023Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing
  30. CVPR 2023Learning To Name Classes for Vision and Language Models
  31. CVPR 2023Leveraging per Image-Token Consistency for Vision-Language Pre-Training
  32. CVPR 2023MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model
  33. CVPR 2023Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
  34. CVPR 2023Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding
  35. CVPR 2023MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition
  36. CVPR 2023NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action
  37. CVPR 2023Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
  38. CVPR 2023Neural Map Prior for Autonomous Driving
  39. CVPR 2023NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
  40. CVPR 2023NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior
  41. CVPR 2023On the Benefits of 3D Pose and Tracking for Human Action Recognition
  42. CVPR 2023On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks
  43. CVPR 2023Open Set Action Recognition via Multi-Label Evidential Learning
  44. CVPR 2023PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers
  45. CVPR 2023PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization
  46. CVPR 2023Position-Guided Text Prompt for Vision-Language Pre-Training
  47. CVPR 2023Post-Processing Temporal Action Detection
  48. CVPR 2023Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features
  49. CVPR 2023Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
  50. CVPR 2023Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

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