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 33 / 33 页

  1. NeurIPS 2023Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
  2. NeurIPS 2023Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection
  3. NeurIPS 2023Lightweight Vision Transformer with Bidirectional Interaction
  4. NeurIPS 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
  5. NeurIPS 2023Lookaround Optimizer: $k$ steps around, 1 step average
  6. NeurIPS 2023LOVM: Language-Only Vision Model Selection
  7. NeurIPS 2023M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
  8. NeurIPS 2023Mass-Producing Failures of Multimodal Systems with Language Models
  9. NeurIPS 2023Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
  10. NeurIPS 2023MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
  11. NeurIPS 2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
  12. NeurIPS 2023MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
  13. NeurIPS 2023Multi-modal Queried Object Detection in the Wild
  14. NeurIPS 2023Normalization Layers Are All That Sharpness-Aware Minimization Needs
  15. NeurIPS 2023On Evaluating Adversarial Robustness of Large Vision-Language Models
  16. NeurIPS 2023On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
  17. NeurIPS 2023PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile
  18. NeurIPS 2023Parts of Speech–Grounded Subspaces in Vision-Language Models
  19. NeurIPS 2023Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
  20. NeurIPS 2023Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
  21. NeurIPS 2023Revealing the unseen: Benchmarking video action recognition under occlusion
  22. NeurIPS 2023Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
  23. NeurIPS 2023RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments
  24. NeurIPS 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policies
  25. NeurIPS 2023Scattering Vision Transformer: Spectral Mixing Matters
  26. NeurIPS 2023Stable and low-precision training for large-scale vision-language models
  27. NeurIPS 2023State-Action Similarity-Based Representations for Off-Policy Evaluation
  28. NeurIPS 2023Text Promptable Surgical Instrument Segmentation with Vision-Language Models
  29. NeurIPS 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Series
  30. NeurIPS 2023Towards Label-free Scene Understanding by Vision Foundation Models
  31. NeurIPS 2023Type-to-Track: Retrieve Any Object via Prompt-based Tracking
  32. NeurIPS 2023UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
  33. NeurIPS 2023VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
  34. NeurIPS 2023VidChapters-7M: Video Chapters at Scale
  35. NeurIPS 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
  36. NeurIPS 2023VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models
  37. NeurIPS 2023VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution
  38. NeurIPS 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
  39. NeurIPS 2023Vocabulary-free Image Classification

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