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 1,639 篇，第 19 / 33 页

  1. ICLR 2025Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation
  2. ICLR 2025TLDR: Token-Level Detective Reward Model for Large Vision Language Models
  3. ICLR 2025Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
  4. ICLR 2025TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
  5. ICLR 2025Tree of Attributes Prompt Learning for Vision-Language Models
  6. ICLR 2025TULIP: Token-length Upgraded CLIP
  7. ICLR 2025Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
  8. ICLR 2025VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
  9. ICLR 2025Vision and Language Synergy for Rehearsal Free Continual Learning
  10. ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
  11. ICLR 2025VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation
  12. ICLR 2025VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
  13. ICML 2025Action Dubber: Timing Audible Actions via Inflectional Flow
  14. ICML 2025Action-Constrained Imitation Learning
  15. ICML 2025Action-Dependent Optimality-Preserving Reward Shaping
  16. ICML 2025ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation
  17. ICML 2025Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
  18. ICML 2025Do Vision-Language Models Really Understand Visual Language?
  19. ICML 2025Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering
  20. ICML 2025DVI:A Derivative-based Vision Network for INR
  21. ICML 2025Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
  22. ICML 2025ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
  23. ICML 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
  24. ICML 2025Feasible Action Search for Bandit Linear Programs via Thompson Sampling
  25. ICML 2025From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
  26. ICML 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
  27. ICML 2025Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
  28. ICML 2025Large Displacement Motion Transfer with Unsupervised Anytime Interpolation
  29. ICML 2025Latent Action Learning Requires Supervision in the Presence of Distractors
  30. ICML 2025LieRE: Lie Rotational Positional Encodings
  31. ICML 2025OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
  32. ICML 2025On the Convergence of Continuous Single-timescale Actor-critic
  33. ICML 2025OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction
  34. ICML 2025RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
  35. ICML 2025S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking
  36. ICML 2025SafeMap: Robust HD Map Construction from Incomplete Observations
  37. ICML 2025SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
  38. ICML 2025Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
  39. ICML 2025Targeted Unlearning with Single Layer Unlearning Gradient
  40. ICML 2025Test-time Adapted Reinforcement Learning with Action Entropy Regularization
  41. ICML 2025Textural or Textual: How Vision-Language Models Read Text in Images
  42. ICML 2025The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
  43. ICML 2025Vintix: Action Model via In-Context Reinforcement Learning
  44. ICML 2025Vision Graph Prompting via Semantic Low-Rank Decomposition
  45. ICML 2025Zero Shot Generalization of Vision-Based RL Without Data Augmentation
  46. NeurIPS 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
  47. NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
  48. NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
  49. NeurIPS 2025Active Test-time Vision-Language Navigation
  50. NeurIPS 2025AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents

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