External Memory papers, 2023–2026

Key findings

• External Memory went from 21 papers in 2023 to 56 in 2026, roughly 2.7x in three years.
• NeurIPS publishes the most External Memory work: 46 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 9 in 2026.
• Among the 5 topics under Long Context and Memory, it ranks #5 by 2026 paper count; the fastest grower in the group, Retrieval Memory, is up 6.6x versus 2.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
• ICML 2026A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
• ICLR 2026Pre-training Limited Memory Language Models with Internal and External Knowledge
• CVPR 2026Spatial-SAM Spatially Consistent 3D Electron Microscopy Segmentation with SDF Memory
• NeurIPS 2025Future Link Prediction Without Memory or Aggregation
• ICML 2025Agent Workflow Memory
• ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
• CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
• NeurIPS 2024Pipeline Parallelism with Controllable Memory
• ICML 2024Graph External Attention Enhanced Transformer
• ICLR 2024The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
• CVPR 2024RTracker: Recoverable Tracking via PN Tree Structured Memory
• NeurIPS 2023Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity
• ICML 2023Memory-Based Meta-Learning on Non-Stationary Distributions
• ICLR 2023Mass-Editing Memory in a Transformer
• CVPR 2023Bilateral Memory Consolidation for Continual Learning
• NeurIPS 2026Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
• ICML 2026Generalized Linear Bandits with Memory
• ICLR 2026QKV Projections Require a Fraction of Their Memory
• CVPR 2026Captain Safari A World Engine with Pose-Aligned 3D Memory

All External Memory papers

130 papers, page 2 of 3

51. NeurIPS 2026Spectral Quantum Memory for Implicit Neural Representations
52. NeurIPS 2026Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
53. NeurIPS 2026StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems
54. NeurIPS 2026The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
55. NeurIPS 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
56. NeurIPS 2026V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
57. CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
58. CVPR 2025MatAnyone: Stable Video Matting with Consistent Memory Propagation
59. CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
60. ICLR 20253D-SPATIAL MULTIMODAL MEMORY
61. ICLR 2025Adam-mini: Use Fewer Learning Rates To Gain More
62. ICLR 2025An Evolved Universal Transformer Memory
63. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
64. ICLR 2025Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information
65. ICLR 2025ELICIT: LLM Augmentation Via External In-context Capability
66. ICLR 2025Learning Successor Features with Distributed Hebbian Temporal Memory
67. ICLR 2025Memory Mosaics
68. ICLR 2025MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory
69. ICLR 2025Track-On: Transformer-based Online Point Tracking with Memory
70. ICML 2025Agent Workflow Memory
71. ICML 2025Deep Unsupervised Hashing via External Guidance
72. ICML 2025Dynamical phases of short-term memory mechanisms in RNNs
73. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
74. NeurIPS 2025BMW: Bidirectionally Memory bank reWriting for Unsupervised Person Re-Identification
75. NeurIPS 2025CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
76. NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
77. NeurIPS 2025EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction
78. NeurIPS 2025FEEDBACK FRICTION: LLMs Struggle to Fully Incorporate External Feedback
79. NeurIPS 2025Future Link Prediction Without Memory or Aggregation
80. NeurIPS 2025Memory Mosaics at scale
81. NeurIPS 2025Memory-Efficient Training with In-Place FFT Implementation
82. NeurIPS 2025Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
83. NeurIPS 2025Nested Learning: The Illusion of Deep Learning Architectures
84. NeurIPS 2025Robust Ego-Exo Correspondence with Long-Term Memory
85. CVPR 2024Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
86. CVPR 2024Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
87. CVPR 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
88. CVPR 2024EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
89. CVPR 2024Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names
90. CVPR 2024MemFlow: Optical Flow Estimation and Prediction with Memory
91. CVPR 2024Memory-based Adapters for Online 3D Scene Perception
92. CVPR 2024RTracker: Recoverable Tracking via PN Tree Structured Memory
93. ICLR 2024LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
94. ICLR 2024Memory-Consistent Neural Networks for Imitation Learning
95. ICLR 2024STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
96. ICLR 2024The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
97. ICML 2024GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
98. ICML 2024Graph External Attention Enhanced Transformer
99. ICML 2024Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks
100. ICML 2024Image Clustering with External Guidance

FAQ

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

130 in total: 21 in 2023, 25 in 2024, 28 in 2025, 56 in 2026.

How many External Memory papers are at NeurIPS 2026?

NeurIPS 2026 has 26 External Memory papers, versus 12 the year before.

How many External Memory papers are at ICLR 2026?

ICLR 2026 has 13 External Memory papers, versus 10 the year before.

How many External Memory papers are at ICML 2026?

ICML 2026 has 13 External Memory papers, versus 3 the year before.

How many External Memory papers are at CVPR 2026?

CVPR 2026 has 4 External Memory papers, versus 3 the year before.

Which conference publishes the most External Memory papers?

NeurIPS, with 46 papers from 2023 to 2026.