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 34 / 46 页

  1. ICLR 2024ReLoRA: High-Rank Training Through Low-Rank Updates
  2. ICLR 2024Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
  3. ICLR 2024Sample-Efficient Quality-Diversity by Cooperative Coevolution
  4. ICLR 2024Set Learning for Accurate and Calibrated Models
  5. ICLR 2024SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
  6. ICLR 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
  7. ICLR 2024Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
  8. ICLR 2024TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
  9. ICLR 2024Test-time Adaptation against Multi-modal Reliability Bias
  10. ICLR 2024The Expressive Power of Low-Rank Adaptation
  11. ICLR 2024The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
  12. ICLR 2024The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
  13. ICLR 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
  14. ICLR 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
  15. ICLR 2024Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
  16. ICLR 2024True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
  17. ICLR 2024Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
  18. ICLR 2024UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
  19. ICLR 2024VeRA: Vector-based Random Matrix Adaptation
  20. ICLR 2024ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
  21. ICLR 2024When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
  22. ICLR 2024YaRN: Efficient Context Window Extension of Large Language Models
  23. ICLR 2024ZeRO++: Extremely Efficient Collective Communication for Large Model Training
  24. ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
  25. ICML 2024A Closer Look at the Limitations of Instruction Tuning
  26. ICML 2024A Tensor Decomposition Perspective on Second-order RNNs
  27. ICML 2024Adaptively Learning to Select-Rank in Online Platforms
  28. ICML 2024Allocation Requires Prediction Only if Inequality Is Low
  29. ICML 2024AMPA: Adaptive Mixed Precision Allocation for Low-Bit Integer Training
  30. ICML 2024Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
  31. ICML 2024APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
  32. ICML 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
  33. ICML 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  34. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
  35. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
  36. ICML 2024Bayesian Adaptation of Network Depth and Width for Continual Learning
  37. ICML 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
  38. ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
  39. ICML 2024Category-Aware Active Domain Adaptation
  40. ICML 2024CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
  41. ICML 2024Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model
  42. ICML 2024Collage: Light-Weight Low-Precision Strategy for LLM Training
  43. ICML 2024CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
  44. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
  45. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
  46. ICML 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatch
  47. ICML 2024Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
  48. ICML 2024Debiased Distribution Compression
  49. ICML 2024Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
  50. ICML 2024Differentiable Weightless Neural Networks

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