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 8 / 17 页

  1. ICML 2026Beyond Description: Federated Adaptation via Semantic-Visual Prototype Alignment
  2. ICML 2026Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision Transformers
  3. ICML 2026Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
  4. ICML 2026Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
  5. ICML 2026Biologically plausible heavy-tailed connectivity enhances generalizations on cognitive tasks in recurrent neural networks
  6. ICML 2026Blocking the Leakage: Manifold-Aware Gradient Projection for Long-Horizon Test-Time Adaptation
  7. ICML 2026Breaking the Computational Barrier: Provably Efficient Actor–Critic for Low-Rank MDPs
  8. ICML 2026Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
  9. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?
  10. ICML 2026Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
  11. ICML 2026Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL
  12. ICML 2026Clustering in Deep Stochastic Transformers
  13. ICML 2026COBRA: Contribution-Based Bayesian Rank Allocation for Parameter-Efficient Fine-Tuning
  14. ICML 2026CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
  15. ICML 2026Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
  16. ICML 2026Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
  17. ICML 2026Condition Number Based Low-Bit Quantization for Image Super-Resolution
  18. ICML 2026Connecting Independently Trained Modes via Layer-Wise Connectivity
  19. ICML 2026Convolutional Learnable-Group Weightless Neural Network
  20. ICML 2026CRAMER: Control via Request-Aware Masking for Editing Recommenders
  21. ICML 2026CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
  22. ICML 2026CSPLoRA: Confidence-Guided Structure Planning for Low-Rank Adaptation
  23. ICML 2026cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport
  24. ICML 2026Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
  25. ICML 2026Decoupled Low-Rank Adaptation for Robust Federated Fine-Tuning
  26. ICML 2026Diffract: Spectral View of LLM Domain Adaptation
  27. ICML 2026Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
  28. ICML 2026Discretized Density-Guided Source-Free Domain Adaptation for Regression
  29. ICML 2026Disentangling Geometry, Performance, and Training in Language Models
  30. ICML 2026Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation
  31. ICML 2026Diversity-aware Weight Perturbation Promotes Robust Adaptation
  32. ICML 2026Diving into Kronecker Adapters: Component Design Matters
  33. ICML 2026Doc-to-LoRA: Learning to Instantly Internalize Contexts
  34. ICML 2026Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization Bounds
  35. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
  36. ICML 2026Dynamic High-Dimensional Facility Location with Low Recourse
  37. ICML 2026Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
  38. ICML 2026Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
  39. ICML 2026Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
  40. ICML 2026Energy-Structured Low-Rank Adaptation for Continual Learning
  41. ICML 2026Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
  42. ICML 2026Equivalence of Context and Parameter Updates in Modern Transformer Blocks
  43. ICML 2026Escaping the Subspace Trap: The Role of Optimizer Geometry in Model Width Expansion
  44. ICML 2026Evaluating Parameter Efficient Methods for RLVR
  45. ICML 2026Exploring Data-Free LoRA Transferability for Video Diffusion Models
  46. ICML 2026Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
  47. ICML 2026Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent
  48. ICML 2026Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
  49. ICML 2026Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
  50. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources

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