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 140 篇，第 1 / 3 页

  1. CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
  2. CVPR 2025Action Detail Matters: Refining Video Recognition with Local Action Queries
  3. CVPR 2025Active Event-based Stereo Vision
  4. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
  5. CVPR 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
  6. CVPR 2025Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
  7. CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
  8. CVPR 2025Assessing and Learning Alignment of Unimodal Vision and Language Models
  9. CVPR 2025ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
  10. CVPR 2025Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
  11. CVPR 2025BHViT: Binarized Hybrid Vision Transformer
  12. CVPR 2025Bias for Action: Video Implicit Neural Representations with Bias Modulation
  13. CVPR 2025BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models
  14. CVPR 2025Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport
  15. CVPR 2025Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
  16. CVPR 2025Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
  17. CVPR 2025Building Vision Models upon Heat Conduction
  18. CVPR 2025CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
  19. CVPR 2025Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
  20. CVPR 2025Conical Visual Concentration for Efficient Large Vision-Language Models
  21. CVPR 2025Context-Enhanced Memory-Refined Transformer for Online Action Detection
  22. CVPR 2025COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
  23. CVPR 2025CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
  24. CVPR 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
  25. CVPR 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
  26. CVPR 2025Cropper: Vision-Language Model for Image Cropping through In-Context Learning
  27. CVPR 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  28. CVPR 2025DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
  29. CVPR 2025DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
  30. CVPR 2025Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
  31. CVPR 2025DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
  32. CVPR 2025DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
  33. CVPR 2025DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
  34. CVPR 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?
  35. CVPR 2025DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models
  36. CVPR 2025DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving
  37. CVPR 2025Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map
  38. CVPR 2025DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
  39. CVPR 2025EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models
  40. CVPR 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
  41. CVPR 2025Evaluating Vision-Language Models as Evaluators in Path Planning
  42. CVPR 2025FastVLM: Efficient Vision Encoding for Vision Language Models
  43. CVPR 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
  44. CVPR 2025GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
  45. CVPR 2025Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision
  46. CVPR 2025Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision
  47. CVPR 2025H-MoRe: Learning Human-centric Motion Representation for Action Analysis
  48. CVPR 2025HalLoc: Token-level Localization of Hallucinations for Vision Language Models
  49. CVPR 2025Heterogeneous Skeleton-Based Action Representation Learning
  50. CVPR 2025HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language 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