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 30 / 46 页

  1. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  2. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
  3. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  4. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  5. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
  6. NeurIPS 2025The Primacy of Magnitude in Low-Rank Adaptation
  7. NeurIPS 2025Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
  8. NeurIPS 2025Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
  9. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
  10. NeurIPS 2025Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
  11. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
  12. NeurIPS 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
  13. NeurIPS 2025Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
  14. NeurIPS 2025UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
  15. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  16. NeurIPS 2025Uni-LoRA: One Vector is All You Need
  17. NeurIPS 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
  18. NeurIPS 2025Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
  19. NeurIPS 2025VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
  20. NeurIPS 2025World Models as Reference Trajectories for Rapid Motor Adaptation
  21. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
  22. NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models
  23. CVPR 2024A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models
  24. CVPR 2024A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction
  25. CVPR 2024A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability
  26. CVPR 2024Active Domain Adaptation with False Negative Prediction for Object Detection
  27. CVPR 2024Adapters Strike Back
  28. CVPR 2024Adaptive Softassign via Hadamard-Equipped Sinkhorn
  29. CVPR 2024ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation
  30. CVPR 2024Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
  31. CVPR 2024Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
  32. CVPR 2024Binarized Low-light Raw Video Enhancement
  33. CVPR 2024Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
  34. CVPR 2024Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
  35. CVPR 2024Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis
  36. CVPR 2024Data-Free Quantization via Pseudo-label Filtering
  37. CVPR 2024DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting
  38. CVPR 2024DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
  39. CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
  40. CVPR 2024DePT: Decoupled Prompt Tuning
  41. CVPR 2024Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks
  42. CVPR 2024Differentiable Micro-Mesh Construction
  43. CVPR 2024Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation
  44. CVPR 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning
  45. CVPR 2024Driving Everywhere with Large Language Model Policy Adaptation
  46. CVPR 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
  47. CVPR 2024Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation
  48. CVPR 2024EasyDrag: Efficient Point-based Manipulation on Diffusion Models
  49. CVPR 2024Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
  50. CVPR 2024Efficient Model Stealing Defense with Noise Transition Matrix

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