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 24 / 33 页

  1. CVPR 2024Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
  2. CVPR 2024SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
  3. CVPR 2024Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
  4. CVPR 2024Semantics-aware Motion Retargeting with Vision-Language Models
  5. CVPR 2024Sequential Modeling Enables Scalable Learning for Large Vision Models
  6. CVPR 2024Situational Awareness Matters in 3D Vision Language Reasoning
  7. CVPR 2024SonicVisionLM: Playing Sound with Vision Language Models
  8. CVPR 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction
  9. CVPR 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks
  10. CVPR 2024SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling
  11. CVPR 2024SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
  12. CVPR 2024Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding
  13. CVPR 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding
  14. CVPR 2024TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
  15. CVPR 2024Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation
  16. CVPR 2024Test-Time Zero-Shot Temporal Action Localization
  17. CVPR 2024Three Pillars Improving Vision Foundation Model Distillation for Lidar
  18. CVPR 2024THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models
  19. CVPR 2024Towards Better Vision-Inspired Vision-Language Models
  20. CVPR 2024Uncertainty-aware Action Decoupling Transformer for Action Anticipation
  21. CVPR 2024Uncertainty-Guided Never-Ending Learning to Drive
  22. CVPR 2024Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action
  23. CVPR 2024VCoder: Versatile Vision Encoders for Multimodal Large Language Models
  24. CVPR 2024ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification
  25. CVPR 2024Vision-and-Language Navigation via Causal Learning
  26. CVPR 2024Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
  27. CVPR 2024ViTamin: Designing Scalable Vision Models in the Vision-Language Era
  28. CVPR 2024VLP: Vision Language Planning for Autonomous Driving
  29. CVPR 2024Volumetric Environment Representation for Vision-Language Navigation
  30. CVPR 2024What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation
  31. CVPR 2024What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
  32. CVPR 2024X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization
  33. CVPR 2024You Only Need Less Attention at Each Stage in Vision Transformers
  34. ICLR 2024A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
  35. ICLR 2024Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
  36. ICLR 2024AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
  37. ICLR 2024Boundary Denoising for Video Activity Localization
  38. ICLR 2024Cascading Reinforcement Learning
  39. ICLR 2024Decoupling regularization from the action space
  40. ICLR 2024Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
  41. ICLR 2024ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
  42. ICLR 2024EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
  43. ICLR 2024EventRPG: Event Data Augmentation with Relevance Propagation Guidance
  44. ICLR 2024Faithful Vision-Language Interpretation via Concept Bottleneck Models
  45. ICLR 2024FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
  46. ICLR 2024How to Fine-Tune Vision Models with SGD
  47. ICLR 2024Image Clustering Conditioned on Text Criteria
  48. ICLR 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  49. ICLR 2024INViTE: INterpret and Control Vision-Language Models with Text Explanations
  50. ICLR 2024Large Language Models as Automated Aligners for benchmarking Vision-Language Models

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