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 22 篇，第 1 / 1 页

1. ICML 2024A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
2. ICML 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
3. ICML 2024Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation
4. ICML 2024Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
5. ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
6. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
7. ICML 2024DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval
8. ICML 2024Dual Operating Modes of In-Context Learning
9. ICML 2024DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
10. ICML 2024Exploring the Benefit of Activation Sparsity in Pre-training
11. ICML 2024Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval
12. ICML 2024Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs
13. ICML 2024InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
14. ICML 2024Parsimonious Learning-Augmented Approximations for Dense Instances of $\mathcal{NP}$-hard Problems
15. ICML 2024Repoformer: Selective Retrieval for Repository-Level Code Completion
16. ICML 2024Retrieval Across Any Domains via Large-scale Pre-trained Model
17. ICML 2024Semantically-correlated memories in a dense associative model
18. ICML 2024Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network
19. ICML 2024SqueezeLLM: Dense-and-Sparse Quantization
20. ICML 2024Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces
21. ICML 2024Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
22. ICML 2024USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval

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。