稠密检索论文趋势 2023–2026

主要结论

• 稠密检索论文从 2023 年的 60 篇增长到 2026 年的 162 篇，三年间扩大到约 2.7 倍。
• CVPR 是发稠密检索论文最多的会议，2023–2026 年共 147 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是检索记忆：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 21 篇。
• 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的交叉编码重排是 3.0 倍，稠密检索是 2.7 倍。

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

• NeurIPS 2026Half-Truths Break Similarity-Based Retrieval
• ICML 2026Deep Discriminative Structure Proxy Hashing for Cross-modal Retrieval
• ICLR 2026A Dense Subset Index for Collective Query Coverage
• CVPR 2026Beyond Caption-Based Queries in Video Moment Retrieval
• NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
• ICML 2025Nonparametric Modern Hopfield Models
• ICLR 2025Contextual Document Embeddings
• CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
• NeurIPS 2024CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
• ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
• ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
• CVPR 2024Dense Optical Tracking: Connecting the Dots
• NeurIPS 2023Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes
• ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
• ICLR 2023Automating Nearest Neighbor Search Configuration with Constrained Optimization
• CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
• NeurIPS 2026Hyperparameter Transfer for Dense Associative Memories
• ICML 2026Dense associative memory for Gaussian distributions
• ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
• CVPR 2026Beyond Tie Points Satellite Image Block Adjustment based on Dense

全部稠密检索论文

共 92 篇，第 1 / 2 页

1. CVPR 2024Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability
2. CVPR 2024Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
3. CVPR 2024BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
4. CVPR 2024Composed Video Retrieval via Enriched Context and Discriminative Embeddings
5. CVPR 2024Dense Optical Tracking: Connecting the Dots
6. CVPR 2024Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes
7. CVPR 2024DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
8. CVPR 2024Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
9. CVPR 2024Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval
10. CVPR 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
11. CVPR 2024Efficient Multitask Dense Predictor via Binarization
12. CVPR 2024Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods
13. CVPR 2024Exploiting Diffusion Prior for Generalizable Dense Prediction
14. CVPR 2024FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking
15. CVPR 2024Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models
16. CVPR 2024How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?
17. CVPR 2024Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
18. CVPR 2024KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
19. CVPR 2024Learning to Produce Semi-dense Correspondences for Visual Localization
20. CVPR 2024Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
21. CVPR 2024Loopy-SLAM: Dense Neural SLAM with Loop Closures
22. CVPR 2024Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging
23. CVPR 2024READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning
24. CVPR 2024Retrieval-Augmented Embodied Agents
25. CVPR 2024RoMa: Robust Dense Feature Matching
26. CVPR 2024Self-Supervised Dual Contouring
27. CVPR 2024SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM
28. CVPR 2024Streaming Dense Video Captioning
29. CVPR 2024Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
30. CVPR 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Space
31. CVPR 2024TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light
32. CVPR 2024UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity
33. CVPR 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence
34. ICLR 2024A Fast and Provable Algorithm for Sparse Phase Retrieval
35. ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
36. ICLR 2024BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
37. ICLR 2024Diffusion Model for Dense Matching
38. ICLR 2024Dual-Encoders for Extreme Multi-label Classification
39. ICLR 2024Learning to Act from Actionless Videos through Dense Correspondences
40. ICLR 2024Making Retrieval-Augmented Language Models Robust to Irrelevant Context
41. ICLR 2024Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
42. ICLR 2024Neural Architecture Retrieval
43. ICLR 2024RA-DIT: Retrieval-Augmented Dual Instruction Tuning
44. ICLR 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
45. ICLR 2024Retrieval meets Long Context Large Language Models
46. ICLR 2024Retrieval-based Disentangled Representation Learning with Natural Language Supervision
47. ICLR 2024Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
48. ICML 2024A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
49. ICML 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
50. ICML 2024Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation

常见问题

2023–2026 年四大会议一共有多少篇稠密检索论文？

共 401 篇，按年份分别是 2023 年 60 篇、2024 年 92 篇、2025 年 87 篇、2026 年 162 篇。

NeurIPS 2026 有多少篇稠密检索论文？

NeurIPS 2026 有 51 篇稠密检索论文，上一届是 35 篇。

ICLR 2026 有多少篇稠密检索论文？

ICLR 2026 有 26 篇稠密检索论文，上一届是 12 篇。

ICML 2026 有多少篇稠密检索论文？

ICML 2026 有 35 篇稠密检索论文，上一届是 10 篇。

CVPR 2026 有多少篇稠密检索论文？

CVPR 2026 有 50 篇稠密检索论文，上一届是 30 篇。

哪个会议的稠密检索论文最多？

CVPR，2023–2026 年共 147 篇。