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 565 篇，第 6 / 12 页

  1. ICML 2025Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
  2. ICML 2025CLOVER: Cross-Layer Orthogonal Vectors Pruning
  3. ICML 2025Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
  4. ICML 2025Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
  5. ICML 2025Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
  6. ICML 2025Compute or Load KV Cache? Why Not Both?
  7. ICML 2025COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
  8. ICML 2025Customizing the Inductive Biases of Softmax Attention using Structured Matrices
  9. ICML 2025Disentangled Graph Spectral Domain Adaptation
  10. ICML 2025Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
  11. ICML 2025Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering
  12. ICML 2025DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
  13. ICML 2025Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
  14. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
  15. ICML 2025Efficient Network Automatic Relevance Determination
  16. ICML 2025Efficient Personalized Adaptation for Physiological Signal Foundation Model
  17. ICML 2025Ehrenfeucht-Haussler Rank and Chain of Thought
  18. ICML 2025ELoRA: Low-Rank Adaptation for Equivariant GNNs
  19. ICML 2025Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models
  20. ICML 2025ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
  21. ICML 2025Fast and Low-Cost Genomic Foundation Models via Outlier Removal
  22. ICML 2025Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation
  23. ICML 2025Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework
  24. ICML 2025Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
  25. ICML 2025Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
  26. ICML 2025From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
  27. ICML 2025From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
  28. ICML 2025FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
  29. ICML 2025Function-Space Learning Rates
  30. ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
  31. ICML 2025GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
  32. ICML 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
  33. ICML 2025Grokking Beyond the Euclidean Norm of Model Parameters
  34. ICML 2025GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
  35. ICML 2025Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
  36. ICML 2025H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models
  37. ICML 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
  38. ICML 2025Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots
  39. ICML 2025Hierarchical Refinement: Optimal Transport to Infinity and Beyond
  40. ICML 2025High-Dimensional Tensor Regression With Oracle Properties
  41. ICML 2025HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks
  42. ICML 2025Homophily Enhanced Graph Domain Adaptation
  43. ICML 2025Hyper-Transforming Latent Diffusion Models
  44. ICML 2025In-Context Adaptation to Concept Drift for Learned Database Operations
  45. ICML 2025InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
  46. ICML 2025IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
  47. ICML 2025Joint Localization and Activation Editing for Low-Resource Fine-Tuning
  48. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
  49. ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
  50. ICML 2025LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

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