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 257 篇，第 1 / 6 页

  1. CVPR 20233Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
  2. CVPR 2023Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
  3. CVPR 2023AdamsFormer for Spatial Action Localization in the Future
  4. CVPR 2023Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation
  5. CVPR 2023Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
  6. CVPR 2023ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources
  7. CVPR 2023AUNet: Learning Relations Between Action Units for Face Forgery Detection
  8. CVPR 2023BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection
  9. CVPR 2023Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
  10. CVPR 2023Biomechanics-Guided Facial Action Unit Detection Through Force Modeling
  11. CVPR 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
  12. CVPR 2023Boost Vision Transformer With GPU-Friendly Sparsity and Quantization
  13. CVPR 2023Boosting Weakly-Supervised Temporal Action Localization With Text Information
  14. CVPR 2023Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization
  15. CVPR 2023Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
  16. CVPR 2023Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding
  17. CVPR 2023CompletionFormer: Depth Completion With Convolutions and Vision Transformers
  18. CVPR 2023CREPE: Can Vision-Language Foundation Models Reason Compositionally?
  19. CVPR 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
  20. CVPR 2023DeAR: Debiasing Vision-Language Models With Additive Residuals
  21. CVPR 2023Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection
  22. CVPR 2023DETRs With Hybrid Matching
  23. CVPR 2023Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization
  24. CVPR 2023DropKey for Vision Transformer
  25. CVPR 2023Dynamic Inference With Grounding Based Vision and Language Models
  26. CVPR 2023End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve
  27. CVPR 2023Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition
  28. CVPR 2023Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language
  29. CVPR 2023FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training
  30. CVPR 2023Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
  31. CVPR 2023GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods
  32. CVPR 2023Global Vision Transformer Pruning With Hessian-Aware Saliency
  33. CVPR 2023Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos
  34. CVPR 2023How Can Objects Help Action Recognition?
  35. CVPR 2023Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles
  36. CVPR 2023Improving Vision-and-Language Navigation by Generating Future-View Image Semantics
  37. CVPR 2023Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels
  38. CVPR 2023InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions
  39. CVPR 2023Iterative Vision-and-Language Navigation
  40. CVPR 2023Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
  41. CVPR 2023LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
  42. CVPR 2023Latency Matters: Real-Time Action Forecasting Transformer
  43. CVPR 2023Learning Action Changes by Measuring Verb-Adverb Textual Relationships
  44. CVPR 2023Learning Discriminative Representations for Skeleton Based Action Recognition
  45. CVPR 2023Learning Expressive Prompting With Residuals for Vision Transformers
  46. CVPR 2023Learning Imbalanced Data With Vision Transformers
  47. CVPR 2023Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing
  48. CVPR 2023Learning To Name Classes for Vision and Language Models
  49. CVPR 2023Leveraging per Image-Token Consistency for Vision-Language Pre-Training
  50. CVPR 2023MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model

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