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 15 / 33 页

  1. NeurIPS 2026ViT-AdaLA: Adapting Vision Transformers with Linear Attention
  2. NeurIPS 2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
  3. NeurIPS 2026VLM$^3$: Vision Language Models Are Native 3D Learners
  4. NeurIPS 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
  5. NeurIPS 2026When a Window Is Not an Action: Selective Phase-Script Deliberation for Sliding-Window Human Activity Recognition
  6. NeurIPS 2026When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
  7. NeurIPS 2026Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
  8. NeurIPS 2026World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
  9. CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
  10. CVPR 2025Action Detail Matters: Refining Video Recognition with Local Action Queries
  11. CVPR 2025Active Event-based Stereo Vision
  12. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
  13. CVPR 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
  14. CVPR 2025Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
  15. CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
  16. CVPR 2025Assessing and Learning Alignment of Unimodal Vision and Language Models
  17. CVPR 2025ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
  18. CVPR 2025Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
  19. CVPR 2025BHViT: Binarized Hybrid Vision Transformer
  20. CVPR 2025Bias for Action: Video Implicit Neural Representations with Bias Modulation
  21. CVPR 2025BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models
  22. CVPR 2025Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport
  23. CVPR 2025Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
  24. CVPR 2025Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
  25. CVPR 2025Building Vision Models upon Heat Conduction
  26. CVPR 2025CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
  27. CVPR 2025Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
  28. CVPR 2025Conical Visual Concentration for Efficient Large Vision-Language Models
  29. CVPR 2025Context-Enhanced Memory-Refined Transformer for Online Action Detection
  30. CVPR 2025COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
  31. CVPR 2025CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
  32. CVPR 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
  33. CVPR 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
  34. CVPR 2025Cropper: Vision-Language Model for Image Cropping through In-Context Learning
  35. CVPR 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  36. CVPR 2025DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
  37. CVPR 2025DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
  38. CVPR 2025Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
  39. CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
  40. CVPR 2025DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
  41. CVPR 2025DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
  42. CVPR 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?
  43. CVPR 2025DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models
  44. CVPR 2025DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving
  45. CVPR 2025Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map
  46. CVPR 2025DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
  47. CVPR 2025EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models
  48. CVPR 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
  49. CVPR 2025Evaluating Vision-Language Models as Evaluators in Path Planning
  50. CVPR 2025FastVLM: Efficient Vision Encoding for 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