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 329 篇，第 2 / 7 页

  1. CVPR 2024InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
  2. CVPR 2024Investigating Compositional Challenges in Vision-Language Models for Visual Grounding
  3. CVPR 2024Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?
  4. CVPR 2024Iterated Learning Improves Compositionality in Large Vision-Language Models
  5. CVPR 2024Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model
  6. CVPR 2024JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models
  7. CVPR 2024Label Propagation for Zero-shot Classification with Vision-Language Models
  8. CVPR 2024Language Models as Black-Box Optimizers for Vision-Language Models
  9. CVPR 2024Learning Correlation Structures for Vision Transformers
  10. CVPR 2024Learning Vision from Models Rivals Learning Vision from Data
  11. CVPR 2024Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
  12. CVPR 2024LLMs are Good Action Recognizers
  13. CVPR 2024LMDrive: Closed-Loop End-to-End Driving with Large Language Models
  14. CVPR 2024Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation
  15. CVPR 2024Low-power Continuous Remote Behavioral Localization with Event Cameras
  16. CVPR 2024MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
  17. CVPR 2024MAFA: Managing False Negatives for Vision-Language Pre-training
  18. CVPR 2024MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding
  19. CVPR 2024MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
  20. CVPR 2024MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
  21. CVPR 2024MoST: Motion Style Transformer Between Diverse Action Contents
  22. CVPR 2024Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition
  23. CVPR 2024MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
  24. CVPR 2024Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-stage Action Localization
  25. CVPR 2024Narrative Action Evaluation with Prompt-Guided Multimodal Interaction
  26. CVPR 2024Non-autoregressive Sequence-to-Sequence Vision-Language Models
  27. CVPR 2024Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers
  28. CVPR 2024On Scaling Up a Multilingual Vision and Language Model
  29. CVPR 2024On the Faithfulness of Vision Transformer Explanations
  30. CVPR 2024Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
  31. CVPR 2024One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
  32. CVPR 2024OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
  33. CVPR 2024OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation
  34. CVPR 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
  35. CVPR 2024PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
  36. CVPR 2024PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
  37. CVPR 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
  38. CVPR 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
  39. CVPR 2024Pre-training Vision Models with Mandelbulb Variations
  40. CVPR 2024Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos
  41. CVPR 2024PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
  42. CVPR 2024Question Aware Vision Transformer for Multimodal Reasoning
  43. CVPR 2024Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization
  44. CVPR 2024ReGenNet: Towards Human Action-Reaction Synthesis
  45. CVPR 2024RMT: Retentive Networks Meet Vision Transformers
  46. CVPR 2024SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training
  47. CVPR 2024SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
  48. CVPR 2024Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
  49. CVPR 2024SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
  50. CVPR 2024Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

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