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 632 篇，第 13 / 13 页

  1. NeurIPS 2025SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
  2. NeurIPS 2025Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
  3. NeurIPS 2025Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
  4. NeurIPS 2025Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks
  5. NeurIPS 2025SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography
  6. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
  7. NeurIPS 2025StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
  8. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
  9. NeurIPS 2025SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
  10. NeurIPS 2025Tensor Product Attention Is All You Need
  11. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  12. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
  13. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  14. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  15. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
  16. NeurIPS 2025The Primacy of Magnitude in Low-Rank Adaptation
  17. NeurIPS 2025Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
  18. NeurIPS 2025Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
  19. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
  20. NeurIPS 2025Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
  21. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
  22. NeurIPS 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
  23. NeurIPS 2025Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
  24. NeurIPS 2025UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
  25. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  26. NeurIPS 2025Uni-LoRA: One Vector is All You Need
  27. NeurIPS 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
  28. NeurIPS 2025Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
  29. NeurIPS 2025VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
  30. NeurIPS 2025World Models as Reference Trajectories for Rapid Motor Adaptation
  31. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
  32. NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models

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