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 1,048 篇，第 8 / 21 页

  1. ICLR 2026PointRePar : SpatioTemporal Point Relation Parsing for Robust Category-Unified 3D Tracking
  2. ICLR 2026PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity
  3. ICLR 2026PoSh: Using Scene Graphs to Guide LLMs-as-a-Judge for Detailed Image Descriptions
  4. ICLR 2026Post-hoc Probabilistic Vision-Language Models
  5. ICLR 2026PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models
  6. ICLR 2026PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
  7. ICLR 2026Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
  8. ICLR 2026Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction
  9. ICLR 2026Prompt-Robust Vision-Language Models via Meta-Finetuning
  10. ICLR 2026ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection
  11. ICLR 2026ProxyAttn: Guided Sparse Attention via Representative Heads
  12. ICLR 2026Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
  13. ICLR 2026Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression
  14. ICLR 2026PT$^2$-LLM: Post-Training Ternarization for Large Language Models
  15. ICLR 2026PTNET: A PROPOSAL-CENTRIC TRANSFORMER NET- WORK FOR 3D OBJECT DETECTION
  16. ICLR 2026Purrception: Variational Flow Matching for Vector-Quantized Image Generation
  17. ICLR 2026QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
  18. ICLR 2026QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining
  19. ICLR 2026QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
  20. ICLR 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
  21. ICLR 2026Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
  22. ICLR 2026Quantized Visual Geometry Grounded Transformer
  23. ICLR 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
  24. ICLR 2026Query-Level Uncertainty in Large Language Models
  25. ICLR 2026QVGen: Pushing the Limit of Quantized Video Generative Models
  26. ICLR 2026Radiometrically Consistent Gaussian Surfels for Inverse Rendering
  27. ICLR 2026Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification
  28. ICLR 2026RATE-DISTORTION OPTIMIZED COMMUNICATION FOR COLLABORATIVE PERCEPTION
  29. ICLR 2026RayI2P: Learning Rays for Image-to-Point Cloud Registration
  30. ICLR 2026Realtime Video Frame Interpolation using One-Step Diffusion Sampling
  31. ICLR 2026ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
  32. ICLR 2026Reconstructing KV Caches with Cross-Layer Fusion for Enhanced Transformers
  33. ICLR 2026Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
  34. ICLR 2026ReFocusEraser: Refocusing for Small Object Removal with Robust Context-Shadow Repair
  35. ICLR 2026ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
  36. ICLR 2026REMem: Reasoning with Episodic Memory in Language Agent
  37. ICLR 2026Repurposing Synthetic Data for Fine-grained Search Agent Supervision
  38. ICLR 2026ReSplat: Degradation-agnostic Feed-forward Gaussian Splatting via Self-guided Residual Diffusion
  39. ICLR 2026Rethinking Causal Mask Attention for Vision-Language Inference
  40. ICLR 2026Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts
  41. ICLR 2026Revisiting Multimodal Positional Encoding in Vision–Language Models
  42. ICLR 2026RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
  43. ICLR 2026Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
  44. ICLR 2026Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging
  45. ICLR 2026RoRE: Rotary Ray Embedding for Generalised Multi-Modal Scene Understanding
  46. ICLR 2026RPM: Reasoning-Level Personalization for Black-Box Large Language Models
  47. ICLR 2026S2GO: Streaming Sparse Gaussian Occupancy
  48. ICLR 2026SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
  49. ICLR 2026Salient Object Ranking via Cyclical Perception-Viewing Interaction Modeling
  50. ICLR 2026Sapiens2

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