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

290 papers, page 2 of 6

51. ICML 2026Attention with Routed-Memory for Learnable Sparse Control
52. ICML 2026CiteGuard: Conformal False-Discovery Control for Faithful Retrieval-Augmented Generation
53. ICML 2026CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval
54. ICML 2026Dense associative memory for Gaussian distributions
55. ICML 2026E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
56. ICML 2026From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
57. ICML 2026From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
58. ICML 2026GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
59. ICML 2026Generalized Linear Bandits with Memory
60. ICML 2026Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory
61. ICML 2026Global Merger-Arbitrage Forecasting with Language Models
62. ICML 2026GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
63. ICML 2026HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
64. ICML 2026Hyperbolic Associative Memory Networks
65. ICML 2026HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
66. ICML 2026LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
67. ICML 2026Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
68. ICML 2026MemIncept: Steering LLM Agents via Cooperative Stealthy Memory Injections
69. ICML 2026Memory Caching: RNNs with Growing Memory
70. ICML 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
71. ICML 2026Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
72. ICML 2026Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
73. ICML 2026No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
74. ICML 2026Panini: Continual Learning in Token Space via Structured Memory
75. ICML 2026Predictive Prefetching for Retrieval-Augmented Generation
76. ICML 2026RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
77. ICML 2026RADAR: Defending RAG Dynamically against Retrieval Corruption
78. ICML 2026RAG without Forgetting: Continual Query-Infused Key Memory
79. ICML 2026Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
80. ICML 2026Retrieval-Aware Distillation for Transformer-SSM Hybrids
81. ICML 2026Retriever Portfolios: A Principled Approach to Adaptive RAG
82. ICML 2026RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
83. ICML 2026SE-GA: Memory-Augmented Self-Evolution for GUI Agents
84. ICML 2026SimpleMem: Efficient Lifelong Memory for LLM Agents
85. ICML 2026The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents
86. ICML 2026Token-Free Hierarchical Indexing for RAG beyond LLM-based Summarization
87. ICML 2026Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
88. NeurIPS 2026ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
89. NeurIPS 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
90. NeurIPS 2026Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
91. NeurIPS 2026Augmented Lagrangian Predictive Coding
92. NeurIPS 2026Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
93. NeurIPS 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
94. NeurIPS 2026AUTOMEM: Automated Learning of Memory as a Cognitive Skill
95. NeurIPS 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
96. NeurIPS 2026Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
97. NeurIPS 2026BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
98. NeurIPS 2026Block Sparse Flash Attention
99. NeurIPS 2026Block Sphere Vector Quantization
100. NeurIPS 2026Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation

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.