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 240 篇，第 2 / 5 页

  1. ICML 2026Diving into Kronecker Adapters: Component Design Matters
  2. ICML 2026Doc-to-LoRA: Learning to Instantly Internalize Contexts
  3. ICML 2026Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization Bounds
  4. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
  5. ICML 2026Dynamic High-Dimensional Facility Location with Low Recourse
  6. ICML 2026Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
  7. ICML 2026Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
  8. ICML 2026Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
  9. ICML 2026Energy-Structured Low-Rank Adaptation for Continual Learning
  10. ICML 2026Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
  11. ICML 2026Equivalence of Context and Parameter Updates in Modern Transformer Blocks
  12. ICML 2026Escaping the Subspace Trap: The Role of Optimizer Geometry in Model Width Expansion
  13. ICML 2026Evaluating Parameter Efficient Methods for RLVR
  14. ICML 2026Exploring Data-Free LoRA Transferability for Video Diffusion Models
  15. ICML 2026Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
  16. ICML 2026Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent
  17. ICML 2026Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
  18. ICML 2026Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
  19. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources
  20. ICML 2026FedPAT: Federated Test-Time Adaptation via Prototype Affinity Topology
  21. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
  22. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
  23. ICML 2026FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
  24. ICML 2026Fine-Tuning of Transformer models with Frames
  25. ICML 2026FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
  26. ICML 2026From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
  27. ICML 2026From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
  28. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
  29. ICML 2026From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
  30. ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
  31. ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
  32. ICML 2026GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
  33. ICML 2026GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
  34. ICML 2026GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
  35. ICML 2026Grokking Finite-Dimensional Algebra
  36. ICML 2026Head-in-Head in Linear Attention
  37. ICML 2026HiCI: Hierarchical Construction–Integration for Long-Context Attention
  38. ICML 2026Identifying Common Hubs in Multiple Gaussian Graphical Models
  39. ICML 2026Identifying Connectivity Distributions from Neural Dynamics Using Flows
  40. ICML 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
  41. ICML 2026INDEXGUARD: Index-only Backdoor Vetting for Secure Federated PEFT of Large Language Models
  42. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
  43. ICML 2026Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
  44. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
  45. ICML 2026L-SR1: Learned Symmetric-Rank-One Preconditioning
  46. ICML 2026LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
  47. ICML 2026Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging
  48. ICML 2026Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
  49. ICML 2026Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
  50. ICML 2026Learning syntax without semantics: Disentangled tiny language 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