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 10 / 46 页

  1. ICML 2026Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
  2. ICML 2026Midtraining Bridges Pretraining and Posttraining Distributions
  3. ICML 2026Mining Useful General Data for Low-Resource Domain Adaptation
  4. ICML 2026Mitigating Error Propagation in Low-Rank Approximation of Large Models via Distribution-Aware Whitening
  5. ICML 2026ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
  6. ICML 2026MODEL SOUPS NEED ONLY ONE INGREDIENT
  7. ICML 2026Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
  8. ICML 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
  9. ICML 2026Multiple Choice Learning of Low-Rank Adapters for Language Modeling
  10. ICML 2026NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
  11. ICML 2026NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
  12. ICML 2026NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
  13. ICML 2026Neural Low-Discrepancy Sequences
  14. ICML 2026Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
  15. ICML 2026Noise-Guided Transport: Imitation Learning from Random Priors
  16. ICML 2026Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace Clustering
  17. ICML 2026Obliviate: Efficient Unlearning in Recommender Systems
  18. ICML 2026On the Convergence Rate of LoRA Gradient Descent
  19. ICML 2026On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models
  20. ICML 2026On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
  21. ICML 2026On the Theoretical Limitations of Embedding-based Link Prediction
  22. ICML 2026Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time Series
  23. ICML 2026Operationalising the Superficial Alignment Hypothesis via Task Complexity
  24. ICML 2026Optimizing Rank for High-Fidelity Implicit Neural Representations
  25. ICML 2026OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
  26. ICML 2026Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier Sum
  27. ICML 2026OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood Ratio
  28. ICML 2026Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing
  29. ICML 2026PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
  30. ICML 2026PLoRA: Efficient Concurrent LoRA Training for Large Language Models
  31. ICML 2026PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
  32. ICML 2026Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
  33. ICML 2026Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
  34. ICML 2026PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
  35. ICML 2026Private and Stable Test-time Adaptation with Differential Privacy
  36. ICML 2026Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
  37. ICML 2026Progressive Graph Structure Adjustment for Homophily Shift Adaptation
  38. ICML 2026ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
  39. ICML 2026Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
  40. ICML 2026Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
  41. ICML 2026RaBiT: Residual Aware Binarization Training for Accurate and Efficient LLMs
  42. ICML 2026Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
  43. ICML 2026Rank-Learner: Orthogonal Ranking of Treatment Effects
  44. ICML 2026Rational Neural Networks have Expressivity Advantages
  45. ICML 2026Reference-Free Meta-Learning for Generalized Implicit Neural Representation in Efficient MRI Reconstruction
  46. ICML 2026Refining Dual Spectral Sparsity in Transformed Tensor Singular Values
  47. ICML 2026Representation Drift Compensation: A Near-Zero Inference Cost Enhancement for LLM Decomposition
  48. ICML 2026Rethinking Low-Confidence Pseudo Labels: Influence-Aware Semi-Supervised Fine-Tuning for Hyperspectral Change Detection
  49. ICML 2026Rethinking Parameter Sharing as Graph Coloring for Structured Compression
  50. ICML 2026Rethinking the Flow-based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective

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