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 5 / 7 页

  1. ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
  2. ICML 2024Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
  3. ICML 2024Position: A Call to Action for a Human-Centered AutoML Paradigm
  4. ICML 2024Position: Do Not Explain Vision Models Without Context
  5. ICML 2024Position: The Platonic Representation Hypothesis
  6. ICML 2024Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
  7. ICML 2024PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
  8. ICML 2024Revealing Vision-Language Integration in the Brain with Multimodal Networks
  9. ICML 2024Revisiting the Role of Language Priors in Vision-Language Models
  10. ICML 2024RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning
  11. ICML 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
  12. ICML 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
  13. ICML 2024Stochastic Q-learning for Large Discrete Action Spaces
  14. ICML 2024Taylor Videos for Action Recognition
  15. ICML 2024The Role of Learning Algorithms in Collective Action
  16. ICML 2024TVE: Learning Meta-attribution for Transferable Vision Explainer
  17. ICML 2024Using Left and Right Brains Together: Towards Vision and Language Planning
  18. ICML 2024ViP: A Differentially Private Foundation Model for Computer Vision
  19. ICML 2024Vision Transformers as Probabilistic Expansion from Learngene
  20. ICML 2024Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
  21. ICML 2024When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
  22. NeurIPS 20243DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
  23. NeurIPS 2024A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
  24. NeurIPS 2024Accelerating Transformers with Spectrum-Preserving Token Merging
  25. NeurIPS 2024ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
  26. NeurIPS 2024Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
  27. NeurIPS 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
  28. NeurIPS 2024AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
  29. NeurIPS 2024Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
  30. NeurIPS 2024Are We on the Right Way for Evaluating Large Vision-Language Models?
  31. NeurIPS 2024Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
  32. NeurIPS 2024BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
  33. NeurIPS 2024BendVLM: Test-Time Debiasing of Vision-Language Embeddings
  34. NeurIPS 2024Biologically Inspired Learning Model for Instructed Vision
  35. NeurIPS 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
  36. NeurIPS 2024CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
  37. NeurIPS 2024ClevrSkills: Compositional Language And Visual Reasoning in Robotics
  38. NeurIPS 2024Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
  39. NeurIPS 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
  40. NeurIPS 2024Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
  41. NeurIPS 2024Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
  42. NeurIPS 2024ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
  43. NeurIPS 2024Demystify Mamba in Vision: A Linear Attention Perspective
  44. NeurIPS 2024DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
  45. NeurIPS 2024Depth Anything V2
  46. NeurIPS 2024Dissecting Query-Key Interaction in Vision Transformers
  47. NeurIPS 2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
  48. NeurIPS 2024Efficient Temporal Action Segmentation via Boundary-aware Query Voting
  49. NeurIPS 2024Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers
  50. NeurIPS 2024Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking

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