低秩适配论文趋势 2023–2026

LoRA 与参数高效微调

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,273 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

低秩适配论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202378766563282
202419395124106518
2025241152136103632
2026269184240148841

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

全部低秩适配论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 193 篇，第 4 / 4 页

  1. NeurIPS 2024SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
  2. NeurIPS 2024Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
  3. NeurIPS 2024Sample-Efficient Private Learning of Mixtures of Gaussians
  4. NeurIPS 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
  5. NeurIPS 2024SGD vs GD: Rank Deficiency in Linear Networks
  6. NeurIPS 2024Shaping the distribution of neural responses with interneurons in a recurrent circuit model
  7. NeurIPS 2024Sharing Key Semantics in Transformer Makes Efficient Image Restoration
  8. NeurIPS 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
  9. NeurIPS 2024Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
  10. NeurIPS 2024Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
  11. NeurIPS 2024SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
  12. NeurIPS 2024SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
  13. NeurIPS 2024Sparse High Rank Adapters
  14. NeurIPS 2024Spectral Adapter: Fine-Tuning in Spectral Space
  15. NeurIPS 2024SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
  16. NeurIPS 2024Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks
  17. NeurIPS 2024SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
  18. NeurIPS 2024Stepping Forward on the Last Mile
  19. NeurIPS 2024Structured flexibility in recurrent neural networks via neuromodulation
  20. NeurIPS 2024Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
  21. NeurIPS 2024SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
  22. NeurIPS 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameters
  23. NeurIPS 2024Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
  24. NeurIPS 2024Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
  25. NeurIPS 2024The Impact of Initialization on LoRA Finetuning Dynamics
  26. NeurIPS 2024The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
  27. NeurIPS 2024The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
  28. NeurIPS 2024Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
  29. NeurIPS 2024Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
  30. NeurIPS 2024TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
  31. NeurIPS 2024Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
  32. NeurIPS 2024Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
  33. NeurIPS 2024Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
  34. NeurIPS 2024Unrolled denoising networks provably learn to perform optimal Bayesian inference
  35. NeurIPS 2024Unveiling LoRA Intrinsic Ranks via Salience Analysis
  36. NeurIPS 2024VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
  37. NeurIPS 2024VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
  38. NeurIPS 2024VFIMamba: Video Frame Interpolation with State Space Models
  39. NeurIPS 2024Visual Fourier Prompt Tuning
  40. NeurIPS 2024Weight decay induces low-rank attention layers
  41. NeurIPS 2024Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
  42. NeurIPS 2024You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
  43. NeurIPS 2024Zero-Shot Reinforcement Learning from Low Quality Data

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 查低秩适配在 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": "low-rank-adaptation"}

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低秩适配论文？
共 2,273 篇，按年份分别是 2023 年 282 篇、2024 年 518 篇、2025 年 632 篇、2026 年 841 篇。
NeurIPS 2026 有多少篇低秩适配论文？
NeurIPS 2026 有 269 篇低秩适配论文，上一届是 241 篇。
ICLR 2026 有多少篇低秩适配论文？
ICLR 2026 有 184 篇低秩适配论文，上一届是 152 篇。
ICML 2026 有多少篇低秩适配论文？
ICML 2026 有 240 篇低秩适配论文，上一届是 136 篇。
CVPR 2026 有多少篇低秩适配论文？
CVPR 2026 有 148 篇低秩适配论文，上一届是 103 篇。
哪个会议的低秩适配论文最多？
NeurIPS，2023–2026 年共 781 篇。

「优化与缩放」下的其他主题