Dense Retrieval papers, 2023–2026

Key findings

• Dense Retrieval went from 60 papers in 2023 to 162 in 2026, roughly 2.7x in three years.
• CVPR publishes the most Dense Retrieval work: 147 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Retrieval Memory: papers tagged with both rose from 1 in 2023 to 21 in 2026.
• Among the 5 topics under Information Retrieval, it ranks #1 by 2026 paper count; the fastest grower in the group, Cross-Encoder Reranking, is up 3.0x versus 2.7x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Dense Retrieval papers

22 papers, page 1 of 1

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

FAQ

How many Dense Retrieval papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

401 in total: 60 in 2023, 92 in 2024, 87 in 2025, 162 in 2026.

How many Dense Retrieval papers are at NeurIPS 2026?

NeurIPS 2026 has 51 Dense Retrieval papers, versus 35 the year before.

How many Dense Retrieval papers are at ICLR 2026?

ICLR 2026 has 26 Dense Retrieval papers, versus 12 the year before.

How many Dense Retrieval papers are at ICML 2026?

ICML 2026 has 35 Dense Retrieval papers, versus 10 the year before.

How many Dense Retrieval papers are at CVPR 2026?

CVPR 2026 has 50 Dense Retrieval papers, versus 30 the year before.

Which conference publishes the most Dense Retrieval papers?

CVPR, with 147 papers from 2023 to 2026.