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 2,272 篇，第 43 / 46 页

  1. ICLR 2023MECTA: Memory-Economic Continual Test-Time Model Adaptation
  2. ICLR 2023Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform
  3. ICLR 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
  4. ICLR 2023Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning
  5. ICLR 2023Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
  6. ICLR 2023Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
  7. ICLR 2023Online Low Rank Matrix Completion
  8. ICLR 2023Parameter-Efficient Fine-Tuning Design Spaces
  9. ICLR 2023Parametrizing Product Shape Manifolds by Composite Networks
  10. ICLR 2023Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
  11. ICLR 2023Provably Auditing Ordinary Least Squares in Low Dimensions
  12. ICLR 2023Quantifying Memorization Across Neural Language Models
  13. ICLR 2023Representation Learning for Low-rank General-sum Markov Games
  14. ICLR 2023Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks
  15. ICLR 2023Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
  16. ICLR 2023Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
  17. ICLR 2023SCoMoE: Efficient Mixtures of Experts with Structured Communication
  18. ICLR 2023Self-Distillation for Further Pre-training of Transformers
  19. ICLR 2023Sparse Random Networks for Communication-Efficient Federated Learning
  20. ICLR 2023Spatio-temporal point processes with deep non-stationary kernels
  21. ICLR 2023Spikformer: When Spiking Neural Network Meets Transformer
  22. ICLR 2023Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
  23. ICLR 2023Tensor-Based Sketching Method for the Low-Rank Approximation of Data Streams.
  24. ICLR 2023Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism
  25. ICLR 2023Towards Stable Test-time Adaptation in Dynamic Wild World
  26. ICLR 2023Treeformer: Dense Gradient Trees for Efficient Attention Computation
  27. ICLR 2023Tuning Frequency Bias in Neural Network Training with Nonuniform Data
  28. ICLR 2023UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual Pretraining
  29. ICLR 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labels
  30. ICML 2023A Three-regime Model of Network Pruning
  31. ICML 2023Adversarial Parameter Attack on Deep Neural Networks
  32. ICML 2023Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
  33. ICML 2023Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions
  34. ICML 2023Bootstrap in High Dimension with Low Computation
  35. ICML 2023Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models
  36. ICML 2023Curious Replay for Model-based Adaptation
  37. ICML 2023Data Efficient Neural Scaling Law via Model Reusing
  38. ICML 2023Diffusion Models are Minimax Optimal Distribution Estimators
  39. ICML 2023Discover-Then-Rank Unlabeled Support Vectors in the Dual Space for Multi-Class Active Learning
  40. ICML 2023DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
  41. ICML 2023Domain Adaptation for Time Series Under Feature and Label Shifts
  42. ICML 2023Double-Weighting for Covariate Shift Adaptation
  43. ICML 2023Efficient List-Decodable Regression using Batches
  44. ICML 2023Efficient Personalized Federated Learning via Sparse Model-Adaptation
  45. ICML 2023ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models
  46. ICML 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuning
  47. ICML 2023Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization
  48. ICML 2023Flash: Concept Drift Adaptation in Federated Learning
  49. ICML 2023Generalized Reductions: Making any Hierarchical Clustering Fair and Balanced with Low Cost
  50. ICML 2023Geometric Autoencoders - What You See is What You Decode

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