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 18 / 33 页

  1. ICLR 2025Action abstractions for amortized sampling
  2. ICLR 2025Action Sequence Augmentation for Action Anticipation
  3. ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
  4. ICLR 2025Are Large Vision Language Models Good Game Players?
  5. ICLR 2025Asymmetric Factorized Bilinear Operation for Vision Transformer
  6. ICLR 2025Attribute-based Visual Reprogramming for Vision-Language Models
  7. ICLR 2025Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
  8. ICLR 2025BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
  9. ICLR 2025Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortex
  10. ICLR 2025C-CLIP: Multimodal Continual Learning for Vision-Language Model
  11. ICLR 2025Can We Talk Models Into Seeing the World Differently?
  12. ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
  13. ICLR 2025Compositional Entailment Learning for Hyperbolic Vision-Language Models
  14. ICLR 2025Control-oriented Clustering of Visual Latent Representation
  15. ICLR 2025DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models
  16. ICLR 2025Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities
  17. ICLR 2025Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding
  18. ICLR 2025Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
  19. ICLR 2025Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
  20. ICLR 2025Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs
  21. ICLR 2025Efficient Off-Policy Learning for High-Dimensional Action Spaces
  22. ICLR 2025ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
  23. ICLR 2025Enhancing End-to-End Autonomous Driving with Latent World Model
  24. ICLR 2025ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
  25. ICLR 2025Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
  26. ICLR 2025GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation
  27. ICLR 2025Improving Large Language Model Planning with Action Sequence Similarity
  28. ICLR 2025Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
  29. ICLR 2025Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
  30. ICLR 2025Kronecker Mask and Interpretive Prompts are Language-Action Video Learners
  31. ICLR 2025Latent Action Pretraining from Videos
  32. ICLR 2025Locality Alignment Improves Vision-Language Models
  33. ICLR 2025Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
  34. ICLR 2025MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
  35. ICLR 2025Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models
  36. ICLR 2025MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
  37. ICLR 2025Model merging with SVD to tie the Knots
  38. ICLR 2025Neural Eulerian Scene Flow Fields
  39. ICLR 2025OS-ATLAS: Foundation Action Model for Generalist GUI Agents
  40. ICLR 2025PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
  41. ICLR 2025PETRA: Parallel End-to-end Training with Reversible Architectures
  42. ICLR 2025POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition
  43. ICLR 2025Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering
  44. ICLR 2025REMEDY: Recipe Merging Dynamics in Large Vision-Language Models
  45. ICLR 2025Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
  46. ICLR 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
  47. ICLR 2025Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
  48. ICLR 2025Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
  49. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
  50. ICLR 2025TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data

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