Dense Retrieval papers, 2023–2026
Dual encoders and ANN
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 401 papers are tagged with this topic.
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.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 6 | 12 | 8 | 34 | 60 |
| 2024 | 23 | 14 | 22 | 33 | 92 |
| 2025 | 35 | 12 | 10 | 30 | 87 |
| 2026 | 51 | 26 | 35 | 50 | 162 |
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
92 papers, page 1 of 2
- CVPR 2024Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability
- CVPR 2024Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
- CVPR 2024BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
- CVPR 2024Composed Video Retrieval via Enriched Context and Discriminative Embeddings
- CVPR 2024Dense Optical Tracking: Connecting the Dots
- CVPR 2024Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes
- CVPR 2024DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
- CVPR 2024Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
- CVPR 2024Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval
- CVPR 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
- CVPR 2024Efficient Multitask Dense Predictor via Binarization
- CVPR 2024Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods
- CVPR 2024Exploiting Diffusion Prior for Generalizable Dense Prediction
- CVPR 2024FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking
- CVPR 2024Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models
- CVPR 2024How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?
- CVPR 2024Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
- CVPR 2024KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
- CVPR 2024Learning to Produce Semi-dense Correspondences for Visual Localization
- CVPR 2024Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
- CVPR 2024Loopy-SLAM: Dense Neural SLAM with Loop Closures
- CVPR 2024Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging
- CVPR 2024READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning
- CVPR 2024Retrieval-Augmented Embodied Agents
- CVPR 2024RoMa: Robust Dense Feature Matching
- CVPR 2024Self-Supervised Dual Contouring
- CVPR 2024SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM
- CVPR 2024Streaming Dense Video Captioning
- CVPR 2024Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
- CVPR 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Space
- CVPR 2024TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light
- CVPR 2024UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity
- CVPR 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence
- ICLR 2024A Fast and Provable Algorithm for Sparse Phase Retrieval
- ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
- ICLR 2024BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
- ICLR 2024Diffusion Model for Dense Matching
- ICLR 2024Dual-Encoders for Extreme Multi-label Classification
- ICLR 2024Learning to Act from Actionless Videos through Dense Correspondences
- ICLR 2024Making Retrieval-Augmented Language Models Robust to Irrelevant Context
- ICLR 2024Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
- ICLR 2024Neural Architecture Retrieval
- ICLR 2024RA-DIT: Retrieval-Augmented Dual Instruction Tuning
- ICLR 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- ICLR 2024Retrieval meets Long Context Large Language Models
- ICLR 2024Retrieval-based Disentangled Representation Learning with Natural Language Supervision
- ICLR 2024Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
- ICML 2024A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
- ICML 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
- ICML 2024Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Dense Retrieval papers grew at CVPR from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "dense-retrieval"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
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.