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 840 篇，第 9 / 17 页

  1. ICML 2026FedPAT: Federated Test-Time Adaptation via Prototype Affinity Topology
  2. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
  3. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
  4. ICML 2026FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
  5. ICML 2026Fine-Tuning of Transformer models with Frames
  6. ICML 2026FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
  7. ICML 2026From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
  8. ICML 2026From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
  9. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
  10. ICML 2026From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
  11. ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
  12. ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
  13. ICML 2026GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
  14. ICML 2026GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
  15. ICML 2026GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
  16. ICML 2026Grokking Finite-Dimensional Algebra
  17. ICML 2026Head-in-Head in Linear Attention
  18. ICML 2026HiCI: Hierarchical Construction–Integration for Long-Context Attention
  19. ICML 2026Identifying Common Hubs in Multiple Gaussian Graphical Models
  20. ICML 2026Identifying Connectivity Distributions from Neural Dynamics Using Flows
  21. ICML 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
  22. ICML 2026INDEXGUARD: Index-only Backdoor Vetting for Secure Federated PEFT of Large Language Models
  23. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
  24. ICML 2026Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
  25. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
  26. ICML 2026L-SR1: Learned Symmetric-Rank-One Preconditioning
  27. ICML 2026LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
  28. ICML 2026Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging
  29. ICML 2026Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
  30. ICML 2026Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
  31. ICML 2026Learning syntax without semantics: Disentangled tiny language models
  32. ICML 2026Learning to Rank by Directly Optimizing Full-Order Probabilities
  33. ICML 2026Learning to Rank from Incomplete Rankings
  34. ICML 2026LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
  35. ICML 2026LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution
  36. ICML 2026Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
  37. ICML 2026LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
  38. ICML 2026Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep Learning
  39. ICML 2026LoPhyDA: Low-Rank Tensor and Physics Gradient Guided Diffusion for Atmospheric Data Assimilation
  40. ICML 2026LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
  41. ICML 2026LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
  42. ICML 2026Low Kruskal-Rank Adaptation
  43. ICML 2026Low-Compute Watermark Removal via Dual-Domain Natural Projection
  44. ICML 2026Low-cost Full Fine-tuning: Learning What to Update for LLMs
  45. ICML 2026Low-dimensional topology of deep neural networks
  46. ICML 2026Low-Rank and Sparsity Are All You Need: Exploring Robust Hierarchical Latent Subspaces for Transferable Adversarial Attack
  47. ICML 2026LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
  48. ICML 2026MACKO: Sparse matrix-vector multiplication for low sparsity
  49. ICML 2026MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural Networks
  50. ICML 2026MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging

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