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 108 篇，第 1 / 3 页

  1. NeurIPS 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
  2. NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
  3. 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
  4. NeurIPS 2025Active Test-time Vision-Language Navigation
  5. NeurIPS 2025AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
  6. NeurIPS 2025AGI-Elo: How Far Are We From Mastering A Task?
  7. NeurIPS 2025AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
  8. NeurIPS 2025Approximate Domain Unlearning for Vision-Language Models
  9. NeurIPS 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
  10. NeurIPS 2025BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
  11. NeurIPS 2025Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
  12. NeurIPS 2025BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
  13. NeurIPS 2025Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
  14. NeurIPS 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
  15. NeurIPS 2025BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
  16. NeurIPS 2025Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks
  17. NeurIPS 2025ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
  18. NeurIPS 2025Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
  19. NeurIPS 2025CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
  20. NeurIPS 2025CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
  21. NeurIPS 2025Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
  22. NeurIPS 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
  23. NeurIPS 2025CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification
  24. NeurIPS 2025Computational Budget Should Be Considered in Data Selection
  25. NeurIPS 2025Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect
  26. NeurIPS 2025DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models
  27. NeurIPS 2025Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
  28. NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
  29. NeurIPS 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  30. NeurIPS 2025DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
  31. NeurIPS 2025Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
  32. NeurIPS 2025Each Complexity Deserves a Pruning Policy
  33. NeurIPS 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
  34. NeurIPS 2025EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation
  35. NeurIPS 2025Embodied Cognition Augmented End2End Autonomous Driving
  36. NeurIPS 2025Emerging Risks from Embodied AI Require Urgent Policy Action
  37. NeurIPS 2025End-to-End Vision Tokenizer Tuning
  38. NeurIPS 2025Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
  39. NeurIPS 2025Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
  40. NeurIPS 2025ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
  41. NeurIPS 2025Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
  42. NeurIPS 2025Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
  43. NeurIPS 2025Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
  44. NeurIPS 2025Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
  45. NeurIPS 2025FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
  46. NeurIPS 2025FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
  47. NeurIPS 2025FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
  48. NeurIPS 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
  49. NeurIPS 2025From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D
  50. NeurIPS 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction

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