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 565 篇，第 4 / 12 页

  1. ICML 2026Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
  2. ICML 2026Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
  3. ICML 2026PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
  4. ICML 2026Private and Stable Test-time Adaptation with Differential Privacy
  5. ICML 2026Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
  6. ICML 2026Progressive Graph Structure Adjustment for Homophily Shift Adaptation
  7. ICML 2026ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
  8. ICML 2026Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
  9. ICML 2026Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
  10. ICML 2026RaBiT: Residual Aware Binarization Training for Accurate and Efficient LLMs
  11. ICML 2026Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
  12. ICML 2026Rank-Learner: Orthogonal Ranking of Treatment Effects
  13. ICML 2026Rational Neural Networks have Expressivity Advantages
  14. ICML 2026Reference-Free Meta-Learning for Generalized Implicit Neural Representation in Efficient MRI Reconstruction
  15. ICML 2026Refining Dual Spectral Sparsity in Transformed Tensor Singular Values
  16. ICML 2026Representation Drift Compensation: A Near-Zero Inference Cost Enhancement for LLM Decomposition
  17. ICML 2026Rethinking Low-Confidence Pseudo Labels: Influence-Aware Semi-Supervised Fine-Tuning for Hyperspectral Change Detection
  18. ICML 2026Rethinking Parameter Sharing as Graph Coloring for Structured Compression
  19. ICML 2026Rethinking the Flow-based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
  20. ICML 2026Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners
  21. ICML 2026Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models
  22. ICML 2026Riemannian Networks over Full-Rank Correlation Matrices
  23. ICML 2026Robust Vision-Language Models via Manifold-Adversarial Adapters
  24. ICML 2026SABER: Continual Learning with Representation Conflict Management
  25. ICML 2026SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
  26. ICML 2026SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
  27. ICML 2026Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
  28. ICML 2026Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
  29. ICML 2026ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
  30. ICML 2026SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
  31. ICML 2026Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
  32. ICML 2026SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
  33. ICML 2026Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
  34. ICML 2026Singular Bayesian Neural Networks
  35. ICML 2026SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
  36. ICML 2026Sketch-Based Low-Rank Model Merging with Shared Circulant Transforms
  37. ICML 2026Skill Neologisms: Towards Skill-based Continual Learning
  38. ICML 2026Spectral Bridge Variational Inference: Dynamic LoRA via Bures-Wasserstein Gradient Flows
  39. ICML 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
  40. ICML 2026SPR-RAFT: Parameter-Efficient Regression-Aware Fine-Tuning for Biomedical LLM Regression
  41. ICML 2026SPR: A Structured Prompt Refinement Network for Modality Missing
  42. ICML 2026SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
  43. ICML 2026SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models
  44. ICML 2026Stabilizing Native Low-Rank LLM Pretraining
  45. ICML 2026STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
  46. ICML 2026Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
  47. ICML 2026Stochastic Sparse Attention for Memory-Bound Inference
  48. ICML 2026SubspacePath Pruner: Inference-time Pruning via Probe-based Representation–Parameter Coupling
  49. ICML 2026SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
  50. ICML 2026Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression

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