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 632 篇，第 7 / 13 页

  1. ICML 2025H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models
  2. ICML 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
  3. ICML 2025Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots
  4. ICML 2025Hierarchical Refinement: Optimal Transport to Infinity and Beyond
  5. ICML 2025High-Dimensional Tensor Regression With Oracle Properties
  6. ICML 2025HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks
  7. ICML 2025Homophily Enhanced Graph Domain Adaptation
  8. ICML 2025Hyper-Transforming Latent Diffusion Models
  9. ICML 2025In-Context Adaptation to Concept Drift for Learned Database Operations
  10. ICML 2025InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
  11. ICML 2025IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
  12. ICML 2025Joint Localization and Activation Editing for Low-Resource Fine-Tuning
  13. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
  14. ICML 2025Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
  15. ICML 2025LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation
  16. ICML 2025Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
  17. ICML 2025Learning to Reuse Policies in State Evolvable Environments
  18. ICML 2025LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
  19. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
  20. ICML 2025Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
  21. ICML 2025LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
  22. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
  23. ICML 2025Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
  24. ICML 2025Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
  25. ICML 2025Low-Rank Adapting Models for Sparse Autoencoders
  26. ICML 2025Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression
  27. ICML 2025Low-Rank Thinning
  28. ICML 2025LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
  29. ICML 2025LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers
  30. ICML 2025Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
  31. ICML 2025Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
  32. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
  33. ICML 2025Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers
  34. ICML 2025Mixture of Lookup Experts
  35. ICML 2025Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
  36. ICML 2025MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
  37. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
  38. ICML 2025MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
  39. ICML 2025Neutral residues: revisiting adapters for model extension
  40. ICML 2025Olica: Efficient Structured Pruning of Large Language Models without Retraining
  41. ICML 2025Optimizing Large Language Model Training Using FP4 Quantization
  42. ICML 2025Oscillation-Reduced MXFP4 Training for Vision Transformers
  43. ICML 2025Parameter-Efficient Fine-Tuning of State Space Models
  44. ICML 2025Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
  45. ICML 2025Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
  46. ICML 2025Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves
  47. ICML 2025Projection Pursuit Density Ratio Estimation
  48. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
  49. ICML 2025PTTA: Purifying Malicious Samples for Test-Time Model Adaptation
  50. ICML 2025Rank-One Modified Value Iteration

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