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 2 / 2 页

51. ICML 2024Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
52. ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
53. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
54. ICML 2024DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval
55. ICML 2024Dual Operating Modes of In-Context Learning
56. ICML 2024DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
57. ICML 2024Exploring the Benefit of Activation Sparsity in Pre-training
58. ICML 2024Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval
59. ICML 2024Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs
60. ICML 2024InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
61. ICML 2024Parsimonious Learning-Augmented Approximations for Dense Instances of $\mathcal{NP}$-hard Problems
62. ICML 2024Repoformer: Selective Retrieval for Repository-Level Code Completion
63. ICML 2024Retrieval Across Any Domains via Large-scale Pre-trained Model
64. ICML 2024Semantically-correlated memories in a dense associative model
65. ICML 2024Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network
66. ICML 2024SqueezeLLM: Dense-and-Sparse Quantization
67. ICML 2024Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces
68. ICML 2024Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
69. ICML 2024USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval
70. NeurIPS 2024A Gradient Accumulation Method for Dense Retriever under Memory Constraint
71. NeurIPS 2024Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
72. NeurIPS 2024An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
73. NeurIPS 2024Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
74. NeurIPS 2024CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
75. NeurIPS 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAG
76. NeurIPS 2024Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
77. NeurIPS 2024Dense Associative Memory Through the Lens of Random Features
78. NeurIPS 2024Dense Connector for MLLMs
79. NeurIPS 2024Dual Critic Reinforcement Learning under Partial Observability
80. NeurIPS 2024Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
81. NeurIPS 2024Generative Retrieval Meets Multi-Graded Relevance
82. NeurIPS 2024Language Models as Hierarchy Encoders
83. NeurIPS 2024MatFormer: Nested Transformer for Elastic Inference
84. NeurIPS 2024Multi-Group Proportional Representation in Retrieval
85. NeurIPS 2024MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
86. NeurIPS 2024On Affine Homotopy between Language Encoders
87. NeurIPS 2024Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes
88. NeurIPS 2024Retrieval & Fine-Tuning for In-Context Tabular Models
89. NeurIPS 2024SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
90. NeurIPS 2024Semi-Open 3D Object Retrieval via Hierarchical Equilibrium on Hypergraph
91. NeurIPS 2024Skinned Motion Retargeting with Dense Geometric Interaction Perception
92. NeurIPS 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

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。