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 345 篇，第 2 / 7 页

  1. CVPR 2025HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
  2. CVPR 2025Hyperbolic Safety-Aware Vision-Language Models
  3. CVPR 2025Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
  4. CVPR 2025Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration
  5. CVPR 2025It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data
  6. CVPR 2025LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models
  7. CVPR 2025Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model
  8. CVPR 2025LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
  9. CVPR 2025LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living
  10. CVPR 2025Mamba-Reg: Vision Mamba Also Needs Registers
  11. CVPR 2025MambaOut: Do We Really Need Mamba for Vision?
  12. CVPR 2025MambaVision: A Hybrid Mamba-Transformer Vision Backbone
  13. CVPR 2025MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking
  14. CVPR 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
  15. CVPR 2025MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
  16. CVPR 2025MBQ: Modality-Balanced Quantization for Large Vision-Language Models
  17. CVPR 2025MDP: Multidimensional Vision Model Pruning with Latency Constraint
  18. CVPR 2025MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output
  19. CVPR 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
  20. CVPR 2025Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
  21. CVPR 2025Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks
  22. CVPR 2025Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
  23. CVPR 2025MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation
  24. CVPR 2025Multimodal Autoregressive Pre-training of Large Vision Encoders
  25. CVPR 2025NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
  26. CVPR 2025Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
  27. CVPR 2025Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
  28. CVPR 2025O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models
  29. CVPR 2025Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation
  30. CVPR 2025Olympus: A Universal Task Router for Computer Vision Tasks
  31. CVPR 2025Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants
  32. CVPR 2025Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
  33. CVPR 2025PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models
  34. CVPR 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
  35. CVPR 2025Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction
  36. CVPR 2025Post-pre-training for Modality Alignment in Vision-Language Foundation Models
  37. CVPR 2025Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
  38. CVPR 2025PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
  39. CVPR 2025R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner
  40. CVPR 2025RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models
  41. CVPR 2025RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network
  42. CVPR 2025Realistic Test-Time Adaptation of Vision-Language Models
  43. CVPR 2025Reproducible Vision-Language Models Meet Concepts Out of Pre-Training
  44. CVPR 2025ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
  45. CVPR 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
  46. CVPR 2025Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
  47. CVPR 2025ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
  48. CVPR 2025RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
  49. CVPR 2025RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
  50. CVPR 2025Scaling Vision Pre-Training to 4K Resolution

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