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 240 篇，第 3 / 5 页

  1. ICML 2026Learning to Rank by Directly Optimizing Full-Order Probabilities
  2. ICML 2026Learning to Rank from Incomplete Rankings
  3. ICML 2026LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
  4. ICML 2026LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution
  5. ICML 2026Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
  6. ICML 2026LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
  7. ICML 2026Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep Learning
  8. ICML 2026LoPhyDA: Low-Rank Tensor and Physics Gradient Guided Diffusion for Atmospheric Data Assimilation
  9. ICML 2026LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
  10. ICML 2026LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
  11. ICML 2026Low Kruskal-Rank Adaptation
  12. ICML 2026Low-Compute Watermark Removal via Dual-Domain Natural Projection
  13. ICML 2026Low-cost Full Fine-tuning: Learning What to Update for LLMs
  14. ICML 2026Low-dimensional topology of deep neural networks
  15. ICML 2026Low-Rank and Sparsity Are All You Need: Exploring Robust Hierarchical Latent Subspaces for Transferable Adversarial Attack
  16. ICML 2026LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
  17. ICML 2026MACKO: Sparse matrix-vector multiplication for low sparsity
  18. ICML 2026MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural Networks
  19. ICML 2026MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
  20. ICML 2026Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
  21. ICML 2026Midtraining Bridges Pretraining and Posttraining Distributions
  22. ICML 2026Mining Useful General Data for Low-Resource Domain Adaptation
  23. ICML 2026Mitigating Error Propagation in Low-Rank Approximation of Large Models via Distribution-Aware Whitening
  24. ICML 2026ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
  25. ICML 2026MODEL SOUPS NEED ONLY ONE INGREDIENT
  26. ICML 2026Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
  27. ICML 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
  28. ICML 2026Multiple Choice Learning of Low-Rank Adapters for Language Modeling
  29. ICML 2026NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
  30. ICML 2026NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
  31. ICML 2026NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
  32. ICML 2026Neural Low-Discrepancy Sequences
  33. ICML 2026Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
  34. ICML 2026Noise-Guided Transport: Imitation Learning from Random Priors
  35. ICML 2026Nonconvex Low-Rank Tensor Representation with Deep Priors for Multiview Subspace Clustering
  36. ICML 2026Obliviate: Efficient Unlearning in Recommender Systems
  37. ICML 2026On the Convergence Rate of LoRA Gradient Descent
  38. ICML 2026On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models
  39. ICML 2026On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
  40. ICML 2026On the Theoretical Limitations of Embedding-based Link Prediction
  41. ICML 2026Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time Series
  42. ICML 2026Operationalising the Superficial Alignment Hypothesis via Task Complexity
  43. ICML 2026Optimizing Rank for High-Fidelity Implicit Neural Representations
  44. ICML 2026OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
  45. ICML 2026Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier Sum
  46. ICML 2026OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood Ratio
  47. ICML 2026Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing
  48. ICML 2026PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
  49. ICML 2026PLoRA: Efficient Concurrent LoRA Training for Large Language Models
  50. ICML 2026PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training

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