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 8 / 12 页

  1. ICML 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
  2. ICML 2025Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
  3. ICML 2025Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models
  4. ICML 2025SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
  5. ICML 2025Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
  6. ICML 2025Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
  7. ICML 2025Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank
  8. ICML 2025Test-Time Learning for Large Language Models
  9. ICML 2025Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data
  10. ICML 2025Text-to-LoRA: Instant Transformer Adaption
  11. ICML 2025The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
  12. ICML 2025The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
  13. ICML 2025Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
  14. ICML 2025TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting
  15. ICML 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
  16. ICML 2025Tracking Most Significant Shifts in Infinite-Armed Bandits
  17. ICML 2025Transfer Q-Learning with Composite MDP Structures
  18. ICML 2025TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
  19. ICML 2025Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization
  20. ICML 2025Ultra-Resolution Adaptation with Ease
  21. ICML 2025Unified K-Means Clustering with Label-Guided Manifold Learning
  22. ICML 2025Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
  23. ICML 2025Vision Graph Prompting via Semantic Low-Rank Decomposition
  24. ICML 2025Vision-Language Model Selection and Reuse for Downstream Adaptation
  25. ICML 2025WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
  26. ICML 2025Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
  27. ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
  28. ICML 2024A Closer Look at the Limitations of Instruction Tuning
  29. ICML 2024A Tensor Decomposition Perspective on Second-order RNNs
  30. ICML 2024Adaptively Learning to Select-Rank in Online Platforms
  31. ICML 2024Allocation Requires Prediction Only if Inequality Is Low
  32. ICML 2024AMPA: Adaptive Mixed Precision Allocation for Low-Bit Integer Training
  33. ICML 2024Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
  34. ICML 2024APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
  35. ICML 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
  36. ICML 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  37. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
  38. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
  39. ICML 2024Bayesian Adaptation of Network Depth and Width for Continual Learning
  40. ICML 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
  41. ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
  42. ICML 2024Category-Aware Active Domain Adaptation
  43. ICML 2024CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
  44. ICML 2024Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model
  45. ICML 2024Collage: Light-Weight Low-Precision Strategy for LLM Training
  46. ICML 2024CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
  47. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
  48. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
  49. ICML 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatch
  50. ICML 2024Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes

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