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 130 篇，第 1 / 3 页

1. CVPR 2026Affordance Field Intervention Enabling VLAs to Escape Memory Traps in
2. CVPR 2026Captain Safari A World Engine with Pose-Aligned 3D Memory
3. CVPR 2026Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual
4. CVPR 2026Spatial-SAM Spatially Consistent 3D Electron Microscopy Segmentation with SDF Memory
5. ICLR 2026A Biologically Plausible Dense Associative Memory with Exponential Capacity
6. ICLR 2026Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
7. ICLR 2026ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
8. ICLR 2026Fresh in memory: Training-order recency is linearly encoded in language model activations
9. ICLR 2026Hippoformer: Integrating Hippocampus-inspired Spatial Memory with Transformers
10. ICLR 2026Improving Code Localization with Repository Memory
11. ICLR 2026MLP Memory: A Retriever-Pretrained Memory for Large Language Models
12. ICLR 2026Muon Outperforms Adam in Tail-End Associative Memory Learning
13. ICLR 2026Not All Bits Are Equal: How Model Scale Changes Memory-Optimal Reasoning
14. ICLR 2026Pre-training Limited Memory Language Models with Internal and External Knowledge
15. ICLR 2026QKV Projections Require a Fraction of Their Memory
16. ICLR 2026Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
17. ICLR 2026Sublinear Spectral Clustering Oracle with Little Memory
18. ICML 2026A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
19. ICML 2026Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
20. ICML 2026E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
21. ICML 2026Generalized Linear Bandits with Memory
22. ICML 2026Hyperbolic Associative Memory Networks
23. ICML 2026Investigating Memory in Model-Free RL with POPGym Arcade
24. ICML 2026LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining
25. ICML 2026Memory Caching: RNNs with Growing Memory
26. ICML 2026Memory Savings at What Cost? A Study of Alternatives to Backpropagation
27. ICML 2026Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs
28. ICML 2026ParamMem: Augmenting Language Agents with Parametric Reflective Memory
29. ICML 2026Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners
30. ICML 2026Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents
31. NeurIPS 2026A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory
32. NeurIPS 2026Approximate Memory Suffices for Universal Approximation with State Space Models
33. NeurIPS 2026AUTOMEM: Automated Learning of Memory as a Cognitive Skill
34. NeurIPS 2026Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
35. NeurIPS 2026BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
36. NeurIPS 2026Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
37. NeurIPS 2026Driving on Memory
38. NeurIPS 2026Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
39. NeurIPS 2026Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
40. NeurIPS 2026Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
41. NeurIPS 2026Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
42. NeurIPS 2026HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
43. NeurIPS 2026LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
44. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
45. NeurIPS 2026MemDLM: Memory-Enhanced DLM Training
46. NeurIPS 2026Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
47. NeurIPS 2026MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
48. NeurIPS 2026Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
49. NeurIPS 2026PREPING: Building Agent Memory without Tasks
50. NeurIPS 2026Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory

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。