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 28 / 33 页

  1. NeurIPS 2024Reinforcing LLM Agents via Policy Optimization with Action Decomposition
  2. NeurIPS 2024Revisiting the Integration of Convolution and Attention for Vision Backbone
  3. NeurIPS 2024Right this way: Can VLMs Guide Us to See More to Answer Questions?
  4. NeurIPS 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
  5. NeurIPS 2024ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
  6. NeurIPS 2024Scaling White-Box Transformers for Vision
  7. NeurIPS 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
  8. NeurIPS 2024Slicing Vision Transformer for Flexible Inference
  9. NeurIPS 2024SlimSAM: 0.1% Data Makes Segment Anything Slim
  10. NeurIPS 2024SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
  11. NeurIPS 2024Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
  12. NeurIPS 2024Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
  13. NeurIPS 2024Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
  14. NeurIPS 2024TrAct: Making First-layer Pre-Activations Trainable
  15. NeurIPS 2024Transformer Doctor: Diagnosing and Treating Vision Transformers
  16. NeurIPS 2024Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
  17. NeurIPS 2024Unveiling Encoder-Free Vision-Language Models
  18. NeurIPS 2024Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
  19. NeurIPS 2024Unveiling the Tapestry of Consistency in Large Vision-Language Models
  20. NeurIPS 2024V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
  21. NeurIPS 2024VHELM: A Holistic Evaluation of Vision Language Models
  22. NeurIPS 2024Vision Foundation Model Enables Generalizable Object Pose Estimation
  23. NeurIPS 2024Vision Mamba Mender
  24. NeurIPS 2024Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
  25. NeurIPS 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
  26. NeurIPS 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
  27. NeurIPS 2024Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
  28. NeurIPS 2024VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
  29. NeurIPS 2024What matters when building vision-language models?
  30. NeurIPS 2024WikiDO: A New Benchmark Evaluating Cross-Modal Retrieval for Vision-Language Models
  31. NeurIPS 2024Wormhole Loss for Partial Shape Matching
  32. NeurIPS 2024Yo'LLaVA: Your Personalized Language and Vision Assistant
  33. CVPR 20233Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
  34. CVPR 2023Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
  35. CVPR 2023AdamsFormer for Spatial Action Localization in the Future
  36. CVPR 2023Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation
  37. CVPR 2023Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
  38. CVPR 2023ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources
  39. CVPR 2023AUNet: Learning Relations Between Action Units for Face Forgery Detection
  40. CVPR 2023BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection
  41. CVPR 2023Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
  42. CVPR 2023Biomechanics-Guided Facial Action Unit Detection Through Force Modeling
  43. CVPR 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
  44. CVPR 2023Boost Vision Transformer With GPU-Friendly Sparsity and Quantization
  45. CVPR 2023Boosting Weakly-Supervised Temporal Action Localization With Text Information
  46. CVPR 2023Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization
  47. CVPR 2023Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
  48. CVPR 2023Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding
  49. CVPR 2023CompletionFormer: Depth Completion With Convolutions and Vision Transformers
  50. CVPR 2023CREPE: Can Vision-Language Foundation Models Reason Compositionally?

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