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 708 篇，第 7 / 15 页

  1. ICLR 2026From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeurons
  2. ICLR 2026From Pixels to Semantics: Unified Facial Action Representation Learning for Micro-Expression Analysis
  3. ICLR 2026From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
  4. ICLR 2026From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
  5. ICLR 2026Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-Language Navigation
  6. ICLR 2026Hallucination-aware Intermediate Representation Editing in Large Vision-Lanugage Models
  7. ICLR 2026HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy
  8. ICLR 2026Hybrid Training for Vision-Language-Action Models
  9. ICLR 2026iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
  10. ICLR 2026Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language Models
  11. ICLR 2026Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization
  12. ICLR 2026InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI Research
  13. ICLR 2026Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
  14. ICLR 2026IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
  15. ICLR 2026Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
  16. ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
  17. ICLR 2026Learning Robust Intervention Representations with Delta Embeddings
  18. ICLR 2026Learning to Reason as Action Abstractions with Scalable Mid-Training RL
  19. ICLR 2026Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions
  20. ICLR 2026Long-tailed Test-Time Adaptation for Vision-Language Models
  21. ICLR 2026M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro Experts
  22. ICLR 2026MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
  23. ICLR 2026Naming to Learn: Class Incremental Learning for Vision-Language Model with Unlabeled Data
  24. ICLR 2026On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
  25. ICLR 2026On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
  26. ICLR 2026OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
  27. ICLR 2026Online Decision Making with Generative Action Sets
  28. ICLR 2026Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
  29. ICLR 2026PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
  30. ICLR 2026PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
  31. ICLR 2026Pose-RFT: Aligning MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
  32. ICLR 2026Post-hoc Probabilistic Vision-Language Models
  33. ICLR 2026Primary-Fine Decoupling for Action Generation in Robotic Imitation
  34. ICLR 2026Procedural Mistake Detection via Action Effect Modeling
  35. ICLR 2026Real-Time Robot Execution with Masked Action Chunking
  36. ICLR 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
  37. ICLR 2026ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
  38. ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
  39. ICLR 2026Revisiting Multimodal Positional Encoding in Vision–Language Models
  40. ICLR 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
  41. ICLR 2026Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging
  42. ICLR 2026Rodrigues Network for Learning Robot Actions
  43. ICLR 2026Scaling up Memory for Robotic Control via Experience Retrieval
  44. ICLR 2026Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
  45. ICLR 2026Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
  46. ICLR 2026Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
  47. ICLR 2026Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization
  48. ICLR 2026Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation
  49. ICLR 2026SiNGER: A Clearer Voice Distills Vision Transformers Further
  50. ICLR 2026SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

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