检索记忆论文趋势 2023–2026

检索增强记忆

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 290 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

检索记忆论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023873523
202414715844
2025341914572
202664313818151

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

全部检索记忆论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 120 篇，第 2 / 3 页

  1. NeurIPS 2026Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
  2. NeurIPS 2026Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
  3. NeurIPS 2026SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
  4. NeurIPS 2026Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
  5. NeurIPS 2026Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
  6. NeurIPS 2026TailCon: Mitigating Tail Signal Erosion through Memory Consolidation for Long-Tailed Recognition
  7. NeurIPS 2026The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
  8. NeurIPS 2026Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
  9. NeurIPS 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
  10. NeurIPS 2026TRIM: A Theory of Retrieval with Incremental Memory -- Defect, Benefit, and Critical Horizon
  11. NeurIPS 2026V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
  12. NeurIPS 2026When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG
  13. NeurIPS 2026When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
  14. NeurIPS 2026When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift
  15. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
  16. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
  17. NeurIPS 2025Chain-of-Retrieval Augmented Generation
  18. NeurIPS 2025Cross City Traffic Flow Generation via Retrieval Augmented Diffusion Model
  19. NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
  20. NeurIPS 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
  21. NeurIPS 2025EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation
  22. NeurIPS 2025EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
  23. NeurIPS 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
  24. NeurIPS 2025Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
  25. NeurIPS 2025HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
  26. NeurIPS 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
  27. NeurIPS 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
  28. NeurIPS 2025Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
  29. NeurIPS 2025Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
  30. NeurIPS 2025Memory Mosaics at scale
  31. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
  32. NeurIPS 2025Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
  33. NeurIPS 2025Nested Learning: The Illusion of Deep Learning Architectures
  34. NeurIPS 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
  35. NeurIPS 2025Optimizing Retrieval for RAG via Reinforced Contrastive Learning
  36. NeurIPS 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
  37. NeurIPS 2025RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation
  38. NeurIPS 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
  39. NeurIPS 2025Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
  40. NeurIPS 2025Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance
  41. NeurIPS 2025REMI: Reconstructing Episodic Memory During Internally Driven Path Planning
  42. NeurIPS 2025RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  43. NeurIPS 2025SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
  44. NeurIPS 2025STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
  45. NeurIPS 2025Towards General Continuous Memory for Vision-Language Models
  46. NeurIPS 2025Understanding protein function with a multimodal retrieval-augmented foundation model
  47. NeurIPS 2025Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
  48. NeurIPS 2025VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
  49. NeurIPS 2024A Gradient Accumulation Method for Dense Retriever under Memory Constraint
  50. NeurIPS 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查检索记忆在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "retrieval-memory"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇检索记忆论文？
共 290 篇，按年份分别是 2023 年 23 篇、2024 年 44 篇、2025 年 72 篇、2026 年 151 篇。
NeurIPS 2026 有多少篇检索记忆论文？
NeurIPS 2026 有 64 篇检索记忆论文，上一届是 34 篇。
ICLR 2026 有多少篇检索记忆论文？
ICLR 2026 有 31 篇检索记忆论文，上一届是 19 篇。
ICML 2026 有多少篇检索记忆论文？
ICML 2026 有 38 篇检索记忆论文，上一届是 14 篇。
CVPR 2026 有多少篇检索记忆论文？
CVPR 2026 有 18 篇检索记忆论文，上一届是 5 篇。
哪个会议的检索记忆论文最多？
NeurIPS，2023–2026 年共 120 篇。

「长上下文与记忆」下的其他主题