低秩适配论文趋势 2023–2026

主要结论

• 低秩适配论文从 2023 年的 282 篇增长到 2026 年的 841 篇，三年间扩大到约 3.0 倍。
• NeurIPS 是发低秩适配论文最多的会议，2023–2026 年共 781 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 61 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的缩放定律是 4.1 倍，低秩适配是 3.0 倍。

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

• NeurIPS 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
• ICML 2026A3: an Analytical Low-Rank Approximation Framework for Attention
• ICLR 2026A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
• CVPR 20262-Shots in the Dark Low-Light Denoising with Minimal Data Acquisition
• NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
• ICML 2025Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
• ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
• CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
• NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
• ICML 2024A Tensor Decomposition Perspective on Second-order RNNs
• ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
• CVPR 2024DePT: Decoupled Prompt Tuning
• NeurIPS 2023A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
• ICML 2023A Three-regime Model of Network Pruning
• ICLR 2023A General Rank Preserving Framework for Asymmetric Image Retrieval
• CVPR 20231% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
• NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
• ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
• ICLR 2026ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
• CVPR 2026Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation

全部低秩适配论文

共 124 篇，第 2 / 3 页

51. ICML 2024Feedback Efficient Online Fine-Tuning of Diffusion Models
52. ICML 2024Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
53. ICML 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
54. ICML 2024Flora: Low-Rank Adapters Are Secretly Gradient Compressors
55. ICML 2024FrameQuant: Flexible Low-Bit Quantization for Transformers
56. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
57. ICML 2024GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
58. ICML 2024Gated Linear Attention Transformers with Hardware-Efficient Training
59. ICML 2024Generalization Analysis of Deep Non-linear Matrix Completion
60. ICML 2024Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
61. ICML 2024Getting the most out of your tokenizer for pre-training and domain adaptation
62. ICML 2024GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
63. ICML 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
64. ICML 2024Harmonizing Generalization and Personalization in Federated Prompt Learning
65. ICML 2024Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexity
66. ICML 2024High-Dimensional Geometric Streaming for Nearly Low Rank Data
67. ICML 2024Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
68. ICML 2024IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
69. ICML 2024IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation
70. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
71. ICML 2024Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
72. ICML 2024Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
73. ICML 2024LESS: Selecting Influential Data for Targeted Instruction Tuning
74. ICML 2024Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
75. ICML 2024LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
76. ICML 2024LoRA Training in the NTK Regime has No Spurious Local Minima
77. ICML 2024LoRA+: Efficient Low Rank Adaptation of Large Models
78. ICML 2024Low-Cost High-Power Membership Inference Attacks
79. ICML 2024Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
80. ICML 2024Low-Rank Similarity Mining for Multimodal Dataset Distillation
81. ICML 2024LQER: Low-Rank Quantization Error Reconstruction for LLMs
82. ICML 2024Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
83. ICML 2024On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
84. ICML 2024On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors
85. ICML 2024Online Matrix Completion: A Collaborative Approach with Hott Items
86. ICML 2024Operator SVD with Neural Networks via Nested Low-Rank Approximation
87. ICML 2024Optimal Coresets for Low-Dimensional Geometric Median
88. ICML 2024Pairwise Alignment Improves Graph Domain Adaptation
89. ICML 2024Parallel Affine Transformation Tuning of Markov Chain Monte Carlo
90. ICML 2024Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
91. ICML 2024Parameter Estimation in DAGs from Incomplete Data via Optimal Transport
92. ICML 2024Parameter-Efficient Fine-Tuning with Controls
93. ICML 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
94. ICML 2024PcLast: Discovering Plannable Continuous Latent States
95. ICML 2024Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis
96. ICML 2024Prodigy: An Expeditiously Adaptive Parameter-Free Learner
97. ICML 2024Prompt-tuning Latent Diffusion Models for Inverse Problems
98. ICML 2024Provable Interactive Learning with Hindsight Instruction Feedback
99. ICML 2024Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation
100. ICML 2024Random features models: a way to study the success of naive imputation

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。