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 64 篇，第 1 / 2 页

1. ICLR 2026A Biologically Plausible Dense Associative Memory with Exponential Capacity
2. ICLR 2026A Dense Subset Index for Collective Query Coverage
3. ICLR 2026Avey-B
4. ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
5. ICLR 2026Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
6. ICLR 2026Dynamical properties of dense associative memory
7. ICLR 2026Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
8. ICLR 2026Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
9. ICLR 2026Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
10. ICLR 2026Fast Proteome-Scale Protein Interaction Retrieval via Residue-Level Factorization
11. ICLR 2026Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
12. ICLR 2026Grasp Any Region: Prompting MLLM to Understand the Dense World
13. ICLR 2026Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
14. ICLR 2026Hybrid Reinforcement: when reward is sparse, better to be dense
15. ICLR 2026Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
16. ICLR 2026LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference
17. ICLR 2026LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
18. ICLR 2026MILCO: Learned Sparse Retrieval Across Languages via a Multilingual Connector
19. ICLR 2026Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
20. ICLR 2026On the Theoretical Limitations of Embedding-Based Retrieval
21. ICLR 2026Pisces: Cryptography-based Private Retrieval-Augmented Generation with Dual-Path Retrieval
22. ICLR 2026RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference
23. ICLR 2026Revela: Dense Retriever Learning via Language Modeling
24. ICLR 2026Seq vs Seq: An Open Suite of Paired Encoders and Decoders
25. ICLR 2026SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
26. ICLR 2026Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval
27. ICLR 2025Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
28. ICLR 2025Contextual Document Embeddings
29. ICLR 2025CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning
30. ICLR 2025Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
31. ICLR 2025Making Transformer Decoders Better Differentiable Indexers
32. ICLR 2025Memory Efficient Transformer Adapter for Dense Predictions
33. ICLR 2025MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
34. ICLR 2025NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
35. ICLR 2025ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing
36. ICLR 2025Retrieval Head Mechanistically Explains Long-Context Factuality
37. ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
38. ICLR 2025Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks
39. ICLR 2024A Fast and Provable Algorithm for Sparse Phase Retrieval
40. ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
41. ICLR 2024BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
42. ICLR 2024Diffusion Model for Dense Matching
43. ICLR 2024Dual-Encoders for Extreme Multi-label Classification
44. ICLR 2024Learning to Act from Actionless Videos through Dense Correspondences
45. ICLR 2024Making Retrieval-Augmented Language Models Robust to Irrelevant Context
46. ICLR 2024Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
47. ICLR 2024Neural Architecture Retrieval
48. ICLR 2024RA-DIT: Retrieval-Augmented Dual Instruction Tuning
49. ICLR 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
50. ICLR 2024Retrieval meets Long Context Large Language 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。