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 30 / 33 页

  1. CVPR 2023Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
  2. CVPR 2023ReasonNet: End-to-End Driving With Temporal and Global Reasoning
  3. CVPR 2023Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation
  4. CVPR 2023RGB No More: Minimally-Decoded JPEG Vision Transformers
  5. CVPR 2023RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer
  6. CVPR 2023Search-Map-Search: A Frame Selection Paradigm for Action Recognition
  7. CVPR 2023Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning
  8. CVPR 2023Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention
  9. CVPR 2023Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
  10. CVPR 2023SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
  11. CVPR 2023Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
  12. CVPR 2023STMixer: A One-Stage Sparse Action Detector
  13. CVPR 2023STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
  14. CVPR 2023SVFormer: Semi-Supervised Video Transformer for Action Recognition
  15. CVPR 2023Task Residual for Tuning Vision-Language Models
  16. CVPR 2023TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving
  17. CVPR 2023Teaching Matters: Investigating the Role of Supervision in Vision Transformers
  18. CVPR 2023Teaching Structured Vision & Language Concepts to Vision & Language Models
  19. CVPR 2023The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction
  20. CVPR 2023Therbligs in Action: Video Understanding Through Motion Primitives
  21. CVPR 2023Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving
  22. CVPR 2023TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
  23. CVPR 2023Token Turing Machines
  24. CVPR 2023Trade-Off Between Robustness and Accuracy of Vision Transformers
  25. CVPR 2023Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization
  26. CVPR 2023TriDet: Temporal Action Detection With Relative Boundary Modeling
  27. CVPR 2023TrojViT: Trojan Insertion in Vision Transformers
  28. CVPR 2023Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms
  29. CVPR 2023Uncertainty-Aware Vision-Based Metric Cross-View Geolocalization
  30. CVPR 2023Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
  31. CVPR 2023Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling
  32. CVPR 2023Vision Transformer With Super Token Sampling
  33. CVPR 2023Vision Transformers Are Good Mask Auto-Labelers
  34. CVPR 2023Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves
  35. CVPR 2023What You Can Reconstruct From a Shadow
  36. CVPR 2023X-Pruner: eXplainable Pruning for Vision Transformers
  37. CVPR 2023You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
  38. ICLR 2023$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
  39. ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
  40. ICLR 2023AIM: Adapting Image Models for Efficient Video Action Recognition
  41. ICLR 2023Budgeted Training for Vision Transformer
  42. ICLR 2023CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
  43. ICLR 2023Conditional Positional Encodings for Vision Transformers
  44. ICLR 2023Contextual Convolutional Networks
  45. ICLR 2023Diagnosing and Rectifying Vision Models using Language
  46. ICLR 2023Distributionally Robust Recourse Action
  47. ICLR 2023Efficient Planning in a Compact Latent Action Space
  48. ICLR 2023GAIN: On the Generalization of Instructional Action Understanding
  49. ICLR 2023GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
  50. ICLR 2023Graph Contrastive Learning for Skeleton-based Action Recognition

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