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 8 / 33 页

  1. ICLR 2026Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
  2. ICLR 2026SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild?
  3. ICLR 2026Spatially Guided Training for Vision-Language-Action Model
  4. ICLR 2026Subspace Kernel Learning on Tensor Sequences
  5. ICLR 2026Time Optimal Execution of Action Chunk Policies Beyond Demonstration Speed
  6. ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
  7. ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
  8. ICLR 2026TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
  9. ICLR 2026Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process
  10. ICLR 2026Unified Vision-Language-Action Model
  11. ICLR 2026Unifying Diffusion and Autoregression for Generalizable Vision-Language-Action Model
  12. ICLR 2026VADv2: End-to-End Autonomous Driving via Probabilistic Planning
  13. ICLR 2026VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
  14. ICLR 2026Verifier-free Test-Time Sampling for Vision Language Action Models
  15. ICLR 2026Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
  16. ICLR 2026villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
  17. ICLR 2026ViPRA: Video Prediction for Robot Actions
  18. ICLR 2026Vision-Language-Action Instruction Tuning: From Understanding to Manipulation
  19. ICLR 2026VITA: Vision-to-Action Flow Matching Policy
  20. ICLR 2026ViTSP: A Vision Language Models Guided Framework for Large-Scale Traveling Salesman Problems
  21. ICLR 2026VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
  22. ICLR 2026Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
  23. ICLR 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
  24. ICLR 2026VLMgineer: Vision-Language Models as Robotic Toolsmiths
  25. ICLR 2026Vulcan: Crafting Compact Class-Specific Vision Transformers For Edge Intelligence
  26. ICLR 2026WRING Out The Bias: A Rotation-Based Alternative To Projection Debiasing
  27. ICLR 2026WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
  28. ICLR 2026X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  29. ICML 2026A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
  30. ICML 2026Action Manifold Smoothing: A Lipschitz Pathway Perspective on High-Dimensional Reinforcement Learning
  31. ICML 2026Action-Sufficient Goal Representations
  32. ICML 2026Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision-Language Models
  33. ICML 2026Adaptive Token Refinement in Long-Tailed Large Vision-Language Models Fine-Tuning
  34. ICML 2026AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
  35. ICML 2026AlignedNorm: Prompting Vision–Language Models via Coupled Prompt Field
  36. ICML 2026Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial Alignment
  37. ICML 2026AURA: Visually Interpretable Affective Understanding via Robust Archetypes
  38. ICML 2026AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving
  39. ICML 2026Benign Overfitting in Adversarial Training for Vision Transformers
  40. ICML 2026Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
  41. ICML 2026Bring Future Vision: Dynamic Computation Allocation Guided by Lightweight Feature Forecaster
  42. ICML 2026Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting
  43. ICML 2026BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
  44. ICML 2026CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
  45. ICML 2026Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
  46. ICML 2026Chunk-Guided Q-Learning
  47. ICML 2026Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models
  48. ICML 2026Co-Evolving Latent Action World Models
  49. ICML 2026Compass-RoPE: Isotropic Rotary Position Embeddings for Vision Transformers
  50. ICML 2026Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

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