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 508 篇，第 6 / 11 页

  1. NeurIPS 2025FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
  2. NeurIPS 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
  3. NeurIPS 2025From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D
  4. NeurIPS 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
  5. NeurIPS 2025From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging
  6. NeurIPS 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
  7. NeurIPS 2025Glance2Gaze: Efficient Vision-Language Models from Glance Fusion to Gaze Compression
  8. NeurIPS 2025GoalLadder: Incremental Goal Discovery with Vision-Language Models
  9. NeurIPS 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
  10. NeurIPS 2025HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
  11. NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
  12. NeurIPS 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
  13. NeurIPS 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
  14. NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
  15. NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
  16. NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
  17. NeurIPS 2025Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
  18. NeurIPS 2025MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes
  19. NeurIPS 2025More effort is needed to protect pedestrian privacy in the era of AI
  20. NeurIPS 2025Normalize Filters! Classical Wisdom for Deep Vision
  21. NeurIPS 2025On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
  22. NeurIPS 2025Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
  23. NeurIPS 2025Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving
  24. NeurIPS 2025Prompt-guided Disentangled Representation for Action Recognition
  25. NeurIPS 2025QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
  26. NeurIPS 2025Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers
  27. NeurIPS 2025Quantization-Free Autoregressive Action Transformer
  28. NeurIPS 2025Reinforcement Learning with Action Chunking
  29. NeurIPS 2025REOrdering Patches Improves Vision Models
  30. NeurIPS 2025Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
  31. NeurIPS 2025SAFE: Multitask Failure Detection for Vision-Language-Action Models
  32. NeurIPS 2025SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
  33. NeurIPS 2025Seeing the Wind from a Falling Leaf
  34. NeurIPS 2025SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
  35. NeurIPS 2025Sherlock: Self-Correcting Reasoning in Vision-Language Models
  36. NeurIPS 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
  37. NeurIPS 2025SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
  38. NeurIPS 2025Structured Initialization for Vision Transformers
  39. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
  40. NeurIPS 2025SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
  41. NeurIPS 2025The Underappreciated Power of Vision Models for Graph Structural Understanding
  42. NeurIPS 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
  43. NeurIPS 2025Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models
  44. NeurIPS 2025Towards Self-Refinement of Vision-Language Models with Triangular Consistency
  45. NeurIPS 2025UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
  46. NeurIPS 2025UniViT: Unifying Image and Video Understanding in One Vision Encoder
  47. NeurIPS 2025Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action
  48. NeurIPS 2025VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning
  49. NeurIPS 2025Vision Function Layer in Multimodal LLMs
  50. NeurIPS 2025Vision Transformers Don't Need Trained Registers

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