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 35 篇，第 1 / 1 页

1. ICML 2026``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
2. ICML 2026$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
3. ICML 2026AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation
4. ICML 2026Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
5. ICML 2026Beyond Hamming: Query-Aware Decoding of Binary Cosine Sketches
6. ICML 2026Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
7. ICML 2026Deep Discriminative Structure Proxy Hashing for Cross-modal Retrieval
8. ICML 2026Dense associative memory for Gaussian distributions
9. ICML 2026DenseMLLM: Standard Multimodal LLMs for Dense Prediction
10. ICML 2026Dual Quaternion SE(3) Synchronization with Recovery Guarantees
11. ICML 2026Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
12. ICML 2026ElicitR: Unlocking Latent Reasoning in Dense Retrievers via Generative Regularization
13. ICML 2026Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
14. ICML 2026Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory
15. ICML 2026GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval
16. ICML 2026Hierarchical Retrieval at Scale: Bridging Interpretability and Efficiency
17. ICML 2026HOBIT: Hardness Optimized Batch Sampling for InfoNCE Training
18. ICML 2026HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
19. ICML 2026Improving Topic Modeling by Distilling Soft Labels from Language Models
20. ICML 2026Language Model Networks: Supervision-Efficient Learning through Dense Communication
21. ICML 2026Learning with Admissibility: Robust Fuzzy Hashing for Cross-Modal Retrieval with Noisy Labels
22. ICML 2026mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
23. ICML 2026Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
24. ICML 2026No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
25. ICML 2026PCA of Probability Measures: Sparse and Dense Sampling Regimes
26. ICML 2026RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated Inference
27. ICML 2026Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label
28. ICML 2026Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models
29. ICML 2026SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
30. ICML 2026Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
31. ICML 2026Temporal Preference Optimization for Unsupervised Retrieval
32. ICML 2026The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents
33. ICML 2026TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
34. ICML 2026Unifying Adversarial Robustness and Training Across Text Scoring Models
35. ICML 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

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。