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 22 / 33 页

  1. NeurIPS 2025What Can RL Bring to VLA Generalization? An Empirical Study
  2. NeurIPS 2025What Do Latent Action Models Actually Learn?
  3. NeurIPS 2025With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You
  4. CVPR 2024A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification
  5. CVPR 2024A Vision Check-up for Language Models
  6. CVPR 2024Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes
  7. CVPR 2024Active Prompt Learning in Vision Language Models
  8. CVPR 2024Adapting Short-Term Transformers for Action Detection in Untrimmed Videos
  9. CVPR 2024AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval
  10. CVPR 2024AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One
  11. CVPR 2024Anchor-based Robust Finetuning of Vision-Language Models
  12. CVPR 2024ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models
  13. CVPR 2024AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
  14. CVPR 2024Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
  15. CVPR 2024BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection
  16. CVPR 2024BigGait: Learning Gait Representation You Want by Large Vision Models
  17. CVPR 2024BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
  18. CVPR 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
  19. CVPR 2024Can't Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models
  20. CVPR 2024Coherent Temporal Synthesis for Incremental Action Segmentation
  21. CVPR 2024ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks
  22. CVPR 2024Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering
  23. CVPR 2024COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
  24. CVPR 2024CPR-Coach: Recognizing Composite Error Actions based on Single-class Training
  25. CVPR 2024Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework
  26. CVPR 2024Dense Vision Transformer Compression with Few Samples
  27. CVPR 2024Distilling Vision-Language Models on Millions of Videos
  28. CVPR 2024Do Vision and Language Encoders Represent the World Similarly?
  29. CVPR 2024DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
  30. CVPR 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
  31. CVPR 2024DUSt3R: Geometric 3D Vision Made Easy
  32. CVPR 2024Efficient Test-Time Adaptation of Vision-Language Models
  33. CVPR 2024Efficient Vision-Language Pre-training by Cluster Masking
  34. CVPR 2024EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
  35. CVPR 2024End-to-End Spatio-Temporal Action Localisation with Video Transformers
  36. CVPR 2024End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
  37. CVPR 2024Enhancing Vision-Language Pre-training with Rich Supervisions
  38. CVPR 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
  39. CVPR 2024Explaining CLIP's Performance Disparities on Data from Blind/Low Vision Users
  40. CVPR 2024FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation
  41. CVPR 2024FairCLIP: Harnessing Fairness in Vision-Language Learning
  42. CVPR 2024FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models
  43. CVPR 2024Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning
  44. CVPR 2024FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment
  45. CVPR 2024FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding
  46. CVPR 2024Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
  47. CVPR 2024Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection
  48. CVPR 2024From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding
  49. CVPR 2024GeoChat: Grounded Large Vision-Language Model for Remote Sensing
  50. CVPR 2024Grounding Everything: Emerging Localization Properties in Vision-Language Transformers

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