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 115 篇，第 2 / 3 页

51. NeurIPS 2026Your Embedding Model Is SMARTer Than You Think
52. NeurIPS 2025CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
53. NeurIPS 2025Contextual Tokenization for Graph Inverted Indices
54. NeurIPS 2025CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
55. NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
56. NeurIPS 2025Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
57. NeurIPS 2025Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting
58. NeurIPS 2025Dense SAE Latents Are Features, Not Bugs
59. NeurIPS 2025Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation
60. NeurIPS 2025Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
61. NeurIPS 2025Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks
62. NeurIPS 2025Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
63. NeurIPS 2025EUGens: Efficient, Unified and General Dense Layers
64. NeurIPS 2025Exploring Structural Degradation in Dense Representations for Self-supervised Learning
65. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
66. NeurIPS 2025FlowFeat: Pixel-Dense Embedding of Motion Profiles
67. NeurIPS 2025Generalized Contrastive Learning for Universal Multimodal Retrieval
68. NeurIPS 2025Global Minimizers of Sigmoid Contrastive Loss
69. NeurIPS 2025Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
70. NeurIPS 2025Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
71. NeurIPS 2025JAFAR: Jack up Any Feature at Any Resolution
72. NeurIPS 2025Learning Dense Hand Contact Estimation from Imbalanced Data
73. NeurIPS 2025MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
74. NeurIPS 2025Optimal community detection in dense bipartite graphs
75. NeurIPS 2025Optimizing Retrieval for RAG via Reinforced Contrastive Learning
76. NeurIPS 2025Reconciling Geospatial Prediction and Retrieval via Sparse Representations
77. NeurIPS 2025REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
78. NeurIPS 2025Results of the Big ANN: NeurIPS’23 competition
79. NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
80. NeurIPS 2025STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
81. NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
82. NeurIPS 2025UFM: A Simple Path towards Unified Dense Correspondence with Flow
83. NeurIPS 2025Understanding protein function with a multimodal retrieval-augmented foundation model
84. NeurIPS 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
85. NeurIPS 2025VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection
86. NeurIPS 2025When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions
87. NeurIPS 2024A Gradient Accumulation Method for Dense Retriever under Memory Constraint
88. NeurIPS 2024Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
89. NeurIPS 2024An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
90. NeurIPS 2024Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
91. NeurIPS 2024CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
92. NeurIPS 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAG
93. NeurIPS 2024Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
94. NeurIPS 2024Dense Associative Memory Through the Lens of Random Features
95. NeurIPS 2024Dense Connector for MLLMs
96. NeurIPS 2024Dual Critic Reinforcement Learning under Partial Observability
97. NeurIPS 2024Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
98. NeurIPS 2024Generative Retrieval Meets Multi-Graded Relevance
99. NeurIPS 2024Language Models as Hierarchy Encoders
100. NeurIPS 2024MatFormer: Nested Transformer for Elastic Inference

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。