Retrieval Memory papers, 2023–2026

Key findings

• Retrieval Memory went from 23 papers in 2023 to 151 in 2026, roughly 6.6x in three years.
• NeurIPS publishes the most Retrieval Memory work: 120 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 25 in 2026.
• Among the 5 topics under Long Context and Memory, it ranks #3 by 2026 paper count; the fastest grower in the group, Long Context, is up 5.2x versus 6.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
• ICML 2026Attention with Routed-Memory for Learnable Sparse Control
• ICLR 2026AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
• CVPR 2026DREAM Document Recognition with Explicit Adaptive Memory
• NeurIPS 2025EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
• ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
• ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
• CVPR 2025MAD: Memory-Augmented Detection of 3D Objects
• NeurIPS 2024A Gradient Accumulation Method for Dense Retriever under Memory Constraint
• ICML 2024Think Before You Act: Decision Transformers with Working Memory
• ICLR 2024STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
• CVPR 2024Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
• NeurIPS 2023Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
• ICML 2023Memory-Based Meta-Learning on Non-Stationary Distributions
• ICLR 2023Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
• CVPR 2023Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
• NeurIPS 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
• ICML 2026Dense associative memory for Gaussian distributions
• ICLR 2026FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
• CVPR 2026Interactive Tracking A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation

All Retrieval Memory papers

72 papers, page 1 of 2

1. CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
2. CVPR 2025MAD: Memory-Augmented Detection of 3D Objects
3. CVPR 2025RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
4. CVPR 2025RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
5. CVPR 2025SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
6. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
7. ICLR 2025An Evolved Universal Transformer Memory
8. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
9. ICLR 2025DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
10. ICLR 2025ESE: Espresso Sentence Embeddings
11. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
12. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
13. ICLR 2025LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
14. ICLR 2025MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory
15. ICLR 2025RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
16. ICLR 2025RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
17. ICLR 2025RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression
18. ICLR 2025RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
19. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
20. ICLR 2025SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
21. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
22. ICLR 2025Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
23. ICLR 2025STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
24. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
25. ICML 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
26. ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
27. ICML 2025In-Context Learning as Conditioned Associative Memory Retrieval
28. ICML 2025LAuReL: Learned Augmented Residual Layer
29. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
30. ICML 2025M+: Extending MemoryLLM with Scalable Long-Term Memory
31. ICML 2025MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification
32. ICML 2025Nonparametric Modern Hopfield Models
33. ICML 2025PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
34. ICML 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
35. ICML 2025Position: Retrieval-augmented systems can be dangerous medical communicators
36. ICML 2025RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding
37. ICML 2025Retrieval Augmented Time Series Forecasting
38. ICML 2025Towards flexible perception with visual memory
39. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
40. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
41. NeurIPS 2025Chain-of-Retrieval Augmented Generation
42. NeurIPS 2025Cross City Traffic Flow Generation via Retrieval Augmented Diffusion Model
43. NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
44. NeurIPS 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
45. NeurIPS 2025EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation
46. NeurIPS 2025EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
47. NeurIPS 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
48. NeurIPS 2025Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
49. NeurIPS 2025HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
50. NeurIPS 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

FAQ

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

290 in total: 23 in 2023, 44 in 2024, 72 in 2025, 151 in 2026.

How many Retrieval Memory papers are at NeurIPS 2026?

NeurIPS 2026 has 64 Retrieval Memory papers, versus 34 the year before.

How many Retrieval Memory papers are at ICLR 2026?

ICLR 2026 has 31 Retrieval Memory papers, versus 19 the year before.

How many Retrieval Memory papers are at ICML 2026?

ICML 2026 has 38 Retrieval Memory papers, versus 14 the year before.

How many Retrieval Memory papers are at CVPR 2026?

CVPR 2026 has 18 Retrieval Memory papers, versus 5 the year before.

Which conference publishes the most Retrieval Memory papers?

NeurIPS, with 120 papers from 2023 to 2026.