应用 · computer vision论文趋势 2023–2026

应用方向：computer_vision

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,538 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

应用 · computer vision论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233420844106
2024891522568334
202516533820168772
2026168538554661,326

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

全部应用 · computer vision论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 456 篇，第 5 / 10 页

  1. NeurIPS 2025Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models
  2. NeurIPS 2025Discovering Compositional Hallucinations in LVLMs
  3. NeurIPS 2025Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation
  4. NeurIPS 2025Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
  5. NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
  6. NeurIPS 2025DOTA: Distributional Test-time Adaptation of Vision-Language Models
  7. NeurIPS 2025Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning
  8. NeurIPS 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
  9. NeurIPS 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
  10. NeurIPS 2025Each Complexity Deserves a Pruning Policy
  11. NeurIPS 2025Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
  12. NeurIPS 2025Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark
  13. NeurIPS 2025Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
  14. NeurIPS 2025EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning
  15. NeurIPS 2025Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
  16. NeurIPS 2025Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
  17. NeurIPS 2025Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
  18. NeurIPS 2025Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
  19. NeurIPS 2025FACE: Faithful Automatic Concept Extraction
  20. NeurIPS 2025Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
  21. NeurIPS 2025FastJAM: a Fast Joint Alignment Model for Images
  22. NeurIPS 2025Fix False Transparency by Noise Guided Splatting
  23. NeurIPS 2025FLAME: Fast Long-context Adaptive Memory for Event-based Vision
  24. NeurIPS 2025FlowFeat: Pixel-Dense Embedding of Motion Profiles
  25. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
  26. NeurIPS 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
  27. NeurIPS 2025Frequency-Aware Token Reduction for Efficient Vision Transformer
  28. NeurIPS 2025From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging
  29. NeurIPS 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
  30. NeurIPS 2025Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span
  31. NeurIPS 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
  32. NeurIPS 2025GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
  33. NeurIPS 2025GLVD: Guided Learned Vertex Descent
  34. NeurIPS 2025GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
  35. NeurIPS 2025Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges
  36. NeurIPS 2025GSPN-2: Efficient Parallel Sequence Modeling
  37. NeurIPS 2025HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
  38. NeurIPS 2025Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
  39. NeurIPS 2025HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
  40. NeurIPS 2025Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models
  41. NeurIPS 2025High Dynamic Range Imaging with Time-Encoding Spike Camera
  42. NeurIPS 2025HMVLM:Human Motion-Vision-Language Model via MoE LoRA
  43. NeurIPS 2025HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
  44. NeurIPS 2025IBGS: Image-Based Gaussian Splatting
  45. NeurIPS 2025InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
  46. NeurIPS 2025Instance-Level Composed Image Retrieval
  47. NeurIPS 2025Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
  48. NeurIPS 2025InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition
  49. NeurIPS 2025Interactive Anomaly Detection for Articulated Objects via Motion Anticipation
  50. NeurIPS 2025InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

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 查应用 · computer vision在 ICLR 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": "app-computer-vision"}

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应用 · computer vision论文？
共 2,538 篇，按年份分别是 2023 年 106 篇、2024 年 334 篇、2025 年 772 篇、2026 年 1,326 篇。
NeurIPS 2026 有多少篇应用 · computer vision论文？
NeurIPS 2026 有 168 篇应用 · computer vision论文，上一届是 165 篇。
ICLR 2026 有多少篇应用 · computer vision论文？
ICLR 2026 有 538 篇应用 · computer vision论文，上一届是 338 篇。
ICML 2026 有多少篇应用 · computer vision论文？
ICML 2026 有 554 篇应用 · computer vision论文，上一届是 201 篇。
CVPR 2026 有多少篇应用 · computer vision论文？
CVPR 2026 有 66 篇应用 · computer vision论文，上一届是 68 篇。
哪个会议的应用 · computer vision论文最多？
ICLR，2023–2026 年共 1,048 篇。

「应用领域」下的其他主题