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 708 篇，第 5 / 15 页

  1. CVPR 2026STAR Test-Time Adaptation Can Enhance Universal Prompt Learning for Vision-Language
  2. CVPR 2026StoryTailorA Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives
  3. CVPR 2026Structural Graph Probing of Vision-Language Models
  4. CVPR 2026StructXLIP Enhancing Vision-language Models with Multimodal Structural Cues
  5. CVPR 2026Superman Unifying Skeleton and Vision for Human Motion Perception and
  6. CVPR 2026SwiftVLA Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal
  7. CVPR 2026Synthesizing Visual Concepts as Vision-Language Programs
  8. CVPR 2026TALO Pushing 3D Vision Foundation Models Towards Globally Consistent Online
  9. CVPR 2026TANGO Text-Anchored Guided Optimization for Robust Fine-tuning Vision-Language Models under
  10. CVPR 2026Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
  11. CVPR 2026Test-Time Attention Purification for Backdoored Large Vision Language Models
  12. CVPR 2026Test-Time Perturbation Tuning with Delayed Feedback for Vision-Language-Action Models
  13. CVPR 2026Test-time Sparsity for Extreme Fast Action Diffusion
  14. CVPR 2026The LLM Bottleneck Why Open-Source Vision LLMs Struggle with Hierarchical
  15. CVPR 2026Think Visually Reason Textually Vision-Language Synergy in Abstract Reasoning
  16. CVPR 2026Think-as-You-See Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
  17. CVPR 2026Thinking with Programming Vision Towards a Unified View for Thinking
  18. CVPR 2026ThinkingViT Matryoshka Thinking Vision Transformer for Elastic Inference
  19. CVPR 2026TimeViper A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video
  20. CVPR 2026Towards Calibrating Prompt Tuning of Vision- Language Models
  21. CVPR 2026Towards GUI Agents Vision-Language Diffusion Models for GUI Grounding
  22. CVPR 2026Towards Robust Vision Transformers Path Dependency Analysis and a Simple
  23. CVPR 2026Transform to Transfer Boosting Adversarial Attack Transferability on Vision-Language Pre-training
  24. CVPR 2026TransPrune Token Transition Pruning for Efficient Large Vision-Language Model
  25. CVPR 2026TreeTeaming Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
  26. CVPR 2026TRM-VLA Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models
  27. CVPR 2026TTRV Test-Time Reinforcement Learning for Vision Language Models
  28. CVPR 2026Turning Pre-Trained Vision Transformers into End-to-End Histopathology Whole Slide Image
  29. CVPR 2026UARE A Unified Vision-Language Model for Image Quality Assessment Restoration
  30. CVPR 2026Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language
  31. CVPR 2026Understanding Counting Mechanisms in Large Language and Vision-Language Models
  32. CVPR 2026Understanding Task Transfer in Vision-Language Models
  33. CVPR 2026Unifying Language-Action Understanding and Generation for Autonomous Driving
  34. CVPR 2026Unifying Perception and Action A Hybrid-Modality Pipeline with Implicit Visual
  35. CVPR 2026Unlearning without Forgetting Securely Removing Targeted Concepts from Large-Scale Vision-Language
  36. CVPR 2026Unleashing Vision-Language Semantics for Deepfake Video Detection
  37. CVPR 2026Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from
  38. CVPR 2026Unlocking Motion from Large Vision Models with a Semantic and
  39. CVPR 2026UVU Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
  40. CVPR 2026Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
  41. CVPR 2026VGGDrive Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous
  42. CVPR 2026VideoNet A Large-Scale Dataset for Domain-Specific Action Recognition
  43. CVPR 2026Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion
  44. CVPR 2026VISion On Request Enhanced VLLM efficiency with sparse dynamically selected
  45. CVPR 2026Vision Transformers Need More Than Registers
  46. CVPR 2026Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
  47. CVPR 2026Vision-Language Model Guided Source-Free Domain Adaptation via Optimal Transport
  48. CVPR 2026Vision-Oriented Lightweight Neural Architecture Search with Budget-Adaptive Evaluation
  49. CVPR 2026VisMem Latent Vision Memory Unlocks Potential of Vision-Language Models
  50. CVPR 2026VisPlay Self-Evolving 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