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 241 篇，第 5 / 5 页

  1. NeurIPS 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
  2. NeurIPS 2025Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies
  3. NeurIPS 2025Self Iterative Label Refinement via Robust Unlabeled Learning
  4. NeurIPS 2025Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
  5. NeurIPS 2025Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning
  6. NeurIPS 2025Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models
  7. NeurIPS 2025Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
  8. NeurIPS 2025Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
  9. NeurIPS 2025Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks
  10. NeurIPS 2025SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
  11. NeurIPS 2025Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
  12. NeurIPS 2025Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
  13. NeurIPS 2025Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks
  14. NeurIPS 2025SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography
  15. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
  16. NeurIPS 2025StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
  17. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
  18. NeurIPS 2025SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
  19. NeurIPS 2025Tensor Product Attention Is All You Need
  20. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  21. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
  22. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  23. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  24. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
  25. NeurIPS 2025The Primacy of Magnitude in Low-Rank Adaptation
  26. NeurIPS 2025Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
  27. NeurIPS 2025Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
  28. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
  29. NeurIPS 2025Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
  30. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
  31. NeurIPS 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
  32. NeurIPS 2025Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
  33. NeurIPS 2025UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
  34. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  35. NeurIPS 2025Uni-LoRA: One Vector is All You Need
  36. NeurIPS 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
  37. NeurIPS 2025Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
  38. NeurIPS 2025VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
  39. NeurIPS 2025World Models as Reference Trajectories for Rapid Motor Adaptation
  40. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
  41. 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