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 236 篇，第 4 / 5 页

  1. ICLR 2025MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
  2. ICLR 2025Model merging with SVD to tie the Knots
  3. ICLR 2025Neural Eulerian Scene Flow Fields
  4. ICLR 2025OS-ATLAS: Foundation Action Model for Generalist GUI Agents
  5. ICLR 2025PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
  6. ICLR 2025PETRA: Parallel End-to-end Training with Reversible Architectures
  7. ICLR 2025POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition
  8. ICLR 2025Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering
  9. ICLR 2025REMEDY: Recipe Merging Dynamics in Large Vision-Language Models
  10. ICLR 2025Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
  11. ICLR 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
  12. ICLR 2025Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
  13. ICLR 2025Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
  14. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
  15. ICLR 2025TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
  16. ICLR 2025Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation
  17. ICLR 2025TLDR: Token-Level Detective Reward Model for Large Vision Language Models
  18. ICLR 2025Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
  19. ICLR 2025TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
  20. ICLR 2025Tree of Attributes Prompt Learning for Vision-Language Models
  21. ICLR 2025TULIP: Token-length Upgraded CLIP
  22. ICLR 2025Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
  23. ICLR 2025VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
  24. ICLR 2025Vision and Language Synergy for Rehearsal Free Continual Learning
  25. ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
  26. ICLR 2025VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation
  27. ICLR 2025VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
  28. ICLR 2024A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
  29. ICLR 2024Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
  30. ICLR 2024AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
  31. ICLR 2024Boundary Denoising for Video Activity Localization
  32. ICLR 2024Cascading Reinforcement Learning
  33. ICLR 2024Decoupling regularization from the action space
  34. ICLR 2024Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
  35. ICLR 2024ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
  36. ICLR 2024EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
  37. ICLR 2024EventRPG: Event Data Augmentation with Relevance Propagation Guidance
  38. ICLR 2024Faithful Vision-Language Interpretation via Concept Bottleneck Models
  39. ICLR 2024FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
  40. ICLR 2024How to Fine-Tune Vision Models with SGD
  41. ICLR 2024Image Clustering Conditioned on Text Criteria
  42. ICLR 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  43. ICLR 2024INViTE: INterpret and Control Vision-Language Models with Text Explanations
  44. ICLR 2024Large Language Models as Automated Aligners for benchmarking Vision-Language Models
  45. ICLR 2024Learning Grounded Action Abstractions from Language
  46. ICLR 2024Learning Optimal Contracts: How to Exploit Small Action Spaces
  47. ICLR 2024Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
  48. ICLR 2024Matrix Manifold Neural Networks++
  49. ICLR 2024Measuring Vision-Language STEM Skills of Neural Models
  50. ICLR 2024MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

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