外部记忆论文趋势 2023–2026

主要结论

• 外部记忆论文从 2023 年的 21 篇增长到 2026 年的 56 篇，三年间扩大到约 2.7 倍。
• NeurIPS 是发外部记忆论文最多的会议，2023–2026 年共 46 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 9 篇。
• 在「长上下文与记忆」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的检索记忆是 6.6 倍，外部记忆是 2.7 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部外部记忆论文

共 26 篇，第 1 / 1 页

1. NeurIPS 2026A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory
2. NeurIPS 2026Approximate Memory Suffices for Universal Approximation with State Space Models
3. NeurIPS 2026AUTOMEM: Automated Learning of Memory as a Cognitive Skill
4. NeurIPS 2026Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
5. NeurIPS 2026BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
6. NeurIPS 2026Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
7. NeurIPS 2026Driving on Memory
8. NeurIPS 2026Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
9. NeurIPS 2026Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
10. NeurIPS 2026Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
11. NeurIPS 2026Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
12. NeurIPS 2026HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
13. NeurIPS 2026LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
14. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
15. NeurIPS 2026MemDLM: Memory-Enhanced DLM Training
16. NeurIPS 2026Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
17. NeurIPS 2026MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
18. NeurIPS 2026Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
19. NeurIPS 2026PREPING: Building Agent Memory without Tasks
20. NeurIPS 2026Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
21. NeurIPS 2026Spectral Quantum Memory for Implicit Neural Representations
22. NeurIPS 2026Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
23. NeurIPS 2026StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems
24. NeurIPS 2026The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
25. NeurIPS 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
26. NeurIPS 2026V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models

常见问题

2023–2026 年四大会议一共有多少篇外部记忆论文？

共 130 篇，按年份分别是 2023 年 21 篇、2024 年 25 篇、2025 年 28 篇、2026 年 56 篇。

NeurIPS 2026 有多少篇外部记忆论文？

NeurIPS 2026 有 26 篇外部记忆论文，上一届是 12 篇。

ICLR 2026 有多少篇外部记忆论文？

ICLR 2026 有 13 篇外部记忆论文，上一届是 10 篇。

ICML 2026 有多少篇外部记忆论文？

ICML 2026 有 13 篇外部记忆论文，上一届是 3 篇。

CVPR 2026 有多少篇外部记忆论文？

CVPR 2026 有 4 篇外部记忆论文，上一届是 3 篇。

哪个会议的外部记忆论文最多？

NeurIPS，2023–2026 年共 46 篇。