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 87 篇，第 1 / 2 页

1. CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
2. CVPR 2025Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation
3. CVPR 2025Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
4. CVPR 2025CoLLM: A Large Language Model for Composed Image Retrieval
5. CVPR 2025DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
6. CVPR 2025Dense Dispersed Structured Light for Hyperspectral 3D Imaging of Dynamic Scenes
7. CVPR 2025Dense Match Summarization for Faster Two-view Estimation
8. CVPR 2025Dense-SfM: Structure from Motion with Dense Consistent Matching
9. CVPR 2025Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
10. CVPR 2025EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
11. CVPR 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
12. CVPR 2025Event-Equalized Dense Video Captioning
13. CVPR 2025Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
14. CVPR 2025From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting
15. CVPR 2025Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval
16. CVPR 2025GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation
17. CVPR 2025Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
18. CVPR 2025ILIAS: Instance-Level Image retrieval At Scale
19. CVPR 2025Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
20. CVPR 2025Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models
21. CVPR 2025LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
22. CVPR 2025Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
23. CVPR 2025MaRI: Material Retrieval Integration across Domains
24. CVPR 2025Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions
25. CVPR 2025NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
26. CVPR 2025ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos
27. CVPR 2025PerLA: Perceptive 3D Language Assistant
28. CVPR 2025PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval
29. CVPR 2025RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
30. CVPR 2025Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
31. ICLR 2025Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
32. ICLR 2025Contextual Document Embeddings
33. ICLR 2025CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning
34. ICLR 2025Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
35. ICLR 2025Making Transformer Decoders Better Differentiable Indexers
36. ICLR 2025Memory Efficient Transformer Adapter for Dense Predictions
37. ICLR 2025MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
38. ICLR 2025NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
39. ICLR 2025ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing
40. ICLR 2025Retrieval Head Mechanistically Explains Long-Context Factuality
41. ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
42. ICLR 2025Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks
43. ICML 2025Contradiction Retrieval via Contrastive Learning with Sparsity
44. ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
45. ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
46. ICML 2025In-Context Learning as Conditioned Associative Memory Retrieval
47. ICML 2025Learnware Specification via Dual Alignment
48. ICML 2025Locality Preserving Markovian Transition for Instance Retrieval
49. ICML 2025MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
50. ICML 2025Nonparametric Modern Hopfield Models

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。