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 640 篇，第 3 / 13 页

  1. CVPR 2026LA-Pose Latent Action Pretraining Meets Pose Estimation
  2. CVPR 2026LaDy Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal
  3. CVPR 2026Language-Grounded Decoupled Action Representation for Robotic Manipulation
  4. CVPR 2026Language-guided Frequency Modulation for Large Vision-Language Models
  5. CVPR 2026LAOF Robust Latent Action Learning with Optical Flow Constraints
  6. CVPR 2026LEAD Minimizing Learner-Expert Asymmetry in End-to-End Driving
  7. CVPR 2026Learning a Unified Latent Action Space from Videos with Action-centric
  8. CVPR 2026Learning from Itself Mining Internal Knowledge from Vision Language Models
  9. CVPR 2026Learning Surgical Robotic Manipulation with 3D Spatial Priors
  10. CVPR 2026Learning to Act Robustly with View-Invariant Latent Actions
  11. CVPR 2026Learning to Reason in 4D Dynamic Spatial Understanding for Vision
  12. CVPR 2026Learning What Helps Task-Aligned Context Selection for Vision Tasks
  13. CVPR 2026Lenses Toward Polysemous Vision-Language Understanding
  14. CVPR 2026LIBERO-Plus A Progressive Robustness Benchmark for Visual-Language-Action Models
  15. CVPR 2026LLaVAShield Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
  16. CVPR 2026Localizing Structuring and Rendering Bridging 3D and 2D Vision-Language-Action Models
  17. CVPR 2026LOREAL Mitigating Low-Resolution Challenges in Vision-Language Models with Attribute-driven Prompt
  18. CVPR 2026M3DocDep Multi-modal Multi-page Multi-document Dependency Chunking with Large Vision-Language Models
  19. CVPR 2026MA-Bench Towards Fine-grained Micro-Action Understanding
  20. CVPR 2026Mantis A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
  21. CVPR 2026MAPS Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better
  22. CVPR 2026Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
  23. CVPR 2026Medic-AD Towards Medical Vision-Language Models Clinical Intelligence
  24. CVPR 2026Memory Matters Boosting Training-Free Zero-Shot Temporal Action Localization with a
  25. CVPR 2026MergeVLA Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent
  26. CVPR 2026Models as Lego Builders Assembling Malice from Benign Blocks via
  27. CVPR 2026MODIX A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language
  28. CVPR 2026MoEActok A MoE-based Action Tokenizer for Vision-Language-Action Models
  29. CVPR 2026MonoVLM Monocular 3D Visual Grounding with Vision Language Models
  30. CVPR 2026More than the Sum Panorama-Language Models for Adverse Omni-Scenes
  31. CVPR 2026Mostly Text Smart Visuals Asymmetric Text-Visual Pruning for Large Vision-Language
  32. CVPR 2026Motus A Unified Latent Action World Model
  33. CVPR 2026MoVie Broaden Your Views with Human Motion for Action Detection
  34. CVPR 2026MPL Match-guided Prototype Learning for Few-shot Action Recognition
  35. CVPR 2026Multimodal Distribution Matching for Vision-Language Dataset Distillation
  36. CVPR 2026mVLM A Vision Language Model for mNPUs
  37. CVPR 2026MVLM Template-Free Tracking via Vision-Language Margin Confidence and Memory-Gated Tracking
  38. CVPR 2026NavForesee A Unified Vision-Language World Model for Hierarchical Planning and
  39. CVPR 2026NeuroRule Bridging Vision and Logic with Differentiable Rule Induction
  40. CVPR 2026Nonparametric Deep Fine-grained Clustering with Low-Rank Guided Vision-Language Model
  41. CVPR 2026NoRD A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
  42. CVPR 2026OccuFly A 3D Vision Benchmark for Semantic Scene Completion from
  43. CVPR 2026One Token Two Fates A Unified Framework via Vision Token
  44. CVPR 2026OneSparse A Unified Framework for Sparse Activation Layers in Vision
  45. CVPR 2026OpenMarcie Dataset for Multimodal Action Recognition in Industrial Environments
  46. CVPR 2026ORIC Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language
  47. CVPR 2026PA-Attack Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes
  48. CVPR 2026PACT Phase-Like Transition Constraints in Adapter-Based Continual Learning of Vision-Language
  49. CVPR 2026Pano360 Perspective to Panoramic Vision with Geometric Consistency
  50. CVPR 2026Parse Search and Confirmation Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought

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