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 6 / 13 页

  1. CVPR 2026VITAL Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment
  2. CVPR 2026VL-Eraser Vacuum Distillation for Machine Unlearning in Vision-Language Models
  3. CVPR 2026VL-RouterBench A Benchmark for Vision-Language Model Routing
  4. CVPR 2026VLA Models Are More Generalizable Than You Think Revisiting Physical
  5. CVPR 2026VLM-3R Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
  6. CVPR 2026VLM-Loc Localization in Point Cloud Maps via Vision-Language Models
  7. CVPR 2026VLM-PTQ Efficient Post-Training Quantization for Large Vision-Language Models
  8. CVPR 2026VLM4RSDet Collaborative Optimization with Vision-Language Model for Enhancing Remote Sensing
  9. CVPR 2026VOLD Reasoning Transfer from LLMs to Vision-Language Models via On-Policy
  10. CVPR 2026WeMMU Enhanced Bridging of Vision-Language Models and Diffusion Models via
  11. CVPR 2026Where Does Vision Meet Language Understanding and Refining Visual Fusion
  12. CVPR 2026White-Balance First Adjust Later Cross-Camera Color Constancy via Vision-Language Evaluation
  13. CVPR 2026Zero-Shot Depth Completion with Vision-Language Model
  14. CVPR 2026ZOO-Prune Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language
  15. CVPR 2026ZoomEarth Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks
  16. CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
  17. CVPR 2025Action Detail Matters: Refining Video Recognition with Local Action Queries
  18. CVPR 2025Active Event-based Stereo Vision
  19. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
  20. CVPR 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
  21. CVPR 2025Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
  22. CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
  23. CVPR 2025Assessing and Learning Alignment of Unimodal Vision and Language Models
  24. CVPR 2025ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
  25. CVPR 2025Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
  26. CVPR 2025BHViT: Binarized Hybrid Vision Transformer
  27. CVPR 2025Bias for Action: Video Implicit Neural Representations with Bias Modulation
  28. CVPR 2025BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models
  29. CVPR 2025Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport
  30. CVPR 2025Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
  31. CVPR 2025Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
  32. CVPR 2025Building Vision Models upon Heat Conduction
  33. CVPR 2025CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
  34. CVPR 2025Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
  35. CVPR 2025Conical Visual Concentration for Efficient Large Vision-Language Models
  36. CVPR 2025Context-Enhanced Memory-Refined Transformer for Online Action Detection
  37. CVPR 2025COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
  38. CVPR 2025CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
  39. CVPR 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
  40. CVPR 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
  41. CVPR 2025Cropper: Vision-Language Model for Image Cropping through In-Context Learning
  42. CVPR 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  43. CVPR 2025DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
  44. CVPR 2025DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
  45. CVPR 2025Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
  46. CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
  47. CVPR 2025DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
  48. CVPR 2025DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
  49. CVPR 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?
  50. CVPR 2025DPC: Dual-Prompt Collaboration for Tuning 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