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 140 篇，第 3 / 3 页

  1. CVPR 2025SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
  2. CVPR 2025Seeing the Abstract: Translating the Abstract Language for Vision Language Models
  3. CVPR 2025Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition
  4. CVPR 2025ShowUI: One Vision-Language-Action Model for GUI Visual Agent
  5. CVPR 2025Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
  6. CVPR 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment
  7. CVPR 2025Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
  8. CVPR 2025SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling
  9. CVPR 2025SLADE: Shielding against Dual Exploits in Large Vision-Language Models
  10. CVPR 2025SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
  11. CVPR 2025SOAP: Vision-Centric 3D Semantic Scene Completion with Scene-Adaptive Decoder and Occluded Region-Aware View Projection
  12. CVPR 2025SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters
  13. CVPR 2025SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving
  14. CVPR 2025SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
  15. CVPR 2025Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
  16. CVPR 2025Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
  17. CVPR 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
  18. CVPR 2025SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
  19. CVPR 2025TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
  20. CVPR 2025Task-Aware Clustering for Prompting Vision-Language Models
  21. CVPR 2025Taxonomy-Aware Evaluation of Vision-Language Models
  22. CVPR 2025Temporal Action Detection Model Compression by Progressive Block Drop
  23. CVPR 2025TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
  24. CVPR 2025VideoGEM: Training-free Action Grounding in Videos
  25. CVPR 2025VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge
  26. CVPR 2025Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes
  27. CVPR 2025Vision-Language Embodiment for Monocular Depth Estimation
  28. CVPR 2025Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks
  29. CVPR 2025Vision-Language Model IP Protection via Prompt-based Learning
  30. CVPR 2025Vision-Language Models Do Not Understand Negation
  31. CVPR 2025VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
  32. CVPR 2025VisionZip: Longer is Better but Not Necessary in Vision Language Models
  33. CVPR 2025VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
  34. CVPR 2025VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning
  35. CVPR 2025VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models
  36. CVPR 2025Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models
  37. CVPR 2025What's in the Image? A Deep-Dive into the Vision of Vision Language Models
  38. CVPR 2025Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
  39. CVPR 2025Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
  40. CVPR 2025Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model

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