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 44 / 46 页

  1. ICML 2023Hierarchical Imitation Learning with Vector Quantized Models
  2. ICML 2023Human-Timescale Adaptation in an Open-Ended Task Space
  3. ICML 2023HyperTuning: Toward Adapting Large Language Models without Back-propagation
  4. ICML 2023Improved Algorithms for White-Box Adversarial Streams
  5. ICML 2023In Search for a Generalizable Method for Source Free Domain Adaptation
  6. ICML 2023Last Switch Dependent Bandits with Monotone Payoff Functions
  7. ICML 2023Learning in POMDPs is Sample-Efficient with Hindsight Observability
  8. ICML 2023Learning-Rate-Free Learning by D-Adaptation
  9. ICML 2023LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation
  10. ICML 2023Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
  11. ICML 2023Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
  12. ICML 2023Mechanistic Mode Connectivity
  13. ICML 2023Multi-User Reinforcement Learning with Low Rank Rewards
  14. ICML 2023Naive imputation implicitly regularizes high-dimensional linear models
  15. ICML 2023NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning
  16. ICML 2023Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
  17. ICML 2023On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation
  18. ICML 2023On Pitfalls of Test-Time Adaptation
  19. ICML 2023On the Role of Attention in Prompt-tuning
  20. ICML 2023One-sided Matrix Completion from Two Observations Per Row
  21. ICML 2023Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points
  22. ICML 2023Provable Dynamic Fusion for Low-Quality Multimodal Data
  23. ICML 2023Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
  24. ICML 2023Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
  25. ICML 2023RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank
  26. ICML 2023Reinforcement Learning Can Be More Efficient with Multiple Rewards
  27. ICML 2023Reinforcement Learning in Low-rank MDPs with Density Features
  28. ICML 2023RLSbench: Domain Adaptation Under Relaxed Label Shift
  29. ICML 2023Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
  30. ICML 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
  31. ICML 2023Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
  32. ICML 2023Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
  33. ICML 2023Structural Re-weighting Improves Graph Domain Adaptation
  34. ICML 2023SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
  35. ICML 2023Taxonomy-Structured Domain Adaptation
  36. ICML 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
  37. ICML 2023The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
  38. ICML 2023Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming
  39. ICML 2023Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations
  40. ICML 2023Toward Efficient Gradient-Based Value Estimation
  41. ICML 2023Uncovering Adversarial Risks of Test-Time Adaptation
  42. ICML 2023Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
  43. ICML 2023What Can Be Learnt With Wide Convolutional Neural Networks?
  44. ICML 2023Which Tricks are Important for Learning to Rank?
  45. NeurIPS 2023(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
  46. NeurIPS 2023A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
  47. NeurIPS 2023A Unified Framework for Rank-based Loss Minimization
  48. NeurIPS 2023Adaptive whitening with fast gain modulation and slow synaptic plasticity
  49. NeurIPS 2023Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
  50. NeurIPS 2023Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

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