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 21 / 33 页

  1. NeurIPS 2025HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
  2. NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
  3. NeurIPS 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
  4. NeurIPS 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
  5. NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
  6. NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
  7. NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
  8. NeurIPS 2025Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
  9. NeurIPS 2025MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes
  10. NeurIPS 2025More effort is needed to protect pedestrian privacy in the era of AI
  11. NeurIPS 2025Normalize Filters! Classical Wisdom for Deep Vision
  12. NeurIPS 2025On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
  13. NeurIPS 2025Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
  14. NeurIPS 2025Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving
  15. NeurIPS 2025Prompt-guided Disentangled Representation for Action Recognition
  16. NeurIPS 2025QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
  17. NeurIPS 2025Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers
  18. NeurIPS 2025Quantization-Free Autoregressive Action Transformer
  19. NeurIPS 2025Reinforcement Learning with Action Chunking
  20. NeurIPS 2025REOrdering Patches Improves Vision Models
  21. NeurIPS 2025Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
  22. NeurIPS 2025SAFE: Multitask Failure Detection for Vision-Language-Action Models
  23. NeurIPS 2025SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
  24. NeurIPS 2025Seeing the Wind from a Falling Leaf
  25. NeurIPS 2025SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
  26. NeurIPS 2025Sherlock: Self-Correcting Reasoning in Vision-Language Models
  27. NeurIPS 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
  28. NeurIPS 2025SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
  29. NeurIPS 2025Structured Initialization for Vision Transformers
  30. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
  31. NeurIPS 2025SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
  32. NeurIPS 2025The Underappreciated Power of Vision Models for Graph Structural Understanding
  33. NeurIPS 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
  34. NeurIPS 2025Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models
  35. NeurIPS 2025Towards Self-Refinement of Vision-Language Models with Triangular Consistency
  36. NeurIPS 2025UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
  37. NeurIPS 2025UniViT: Unifying Image and Video Understanding in One Vision Encoder
  38. NeurIPS 2025Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action
  39. NeurIPS 2025VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning
  40. NeurIPS 2025Vision Function Layer in Multimodal LLMs
  41. NeurIPS 2025Vision Transformers Don't Need Trained Registers
  42. NeurIPS 2025Vision Transformers with Self-Distilled Registers
  43. NeurIPS 2025Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It
  44. NeurIPS 2025Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models
  45. NeurIPS 2025Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
  46. NeurIPS 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
  47. NeurIPS 2025VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution
  48. NeurIPS 2025VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
  49. NeurIPS 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
  50. NeurIPS 2025VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking

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