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 518 篇，第 2 / 11 页

51. CVPR 2024LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking
52. CVPR 2024Low-Latency Neural Stereo Streaming
53. CVPR 2024Low-power Continuous Remote Behavioral Localization with Event Cameras
54. CVPR 2024Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs
55. CVPR 2024Low-Rank Knowledge Decomposition for Medical Foundation Models
56. CVPR 2024Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
57. CVPR 2024Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
58. CVPR 2024LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction
59. CVPR 2024MedBN: Robust Test-Time Adaptation against Malicious Test Samples
60. CVPR 2024MoML: Online Meta Adaptation for 3D Human Motion Prediction
61. CVPR 2024MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning
62. CVPR 2024Multi-Task Dense Prediction via Mixture of Low-Rank Experts
63. CVPR 2024Multimodal Representation Learning by Alternating Unimodal Adaptation
64. CVPR 2024NightCC: Nighttime Color Constancy via Adaptive Channel Masking
65. CVPR 2024Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
66. CVPR 2024One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls
67. CVPR 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
68. CVPR 2024Orthogonal Adaptation for Modular Customization of Diffusion Models
69. CVPR 2024Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
70. CVPR 2024Parameter Efficient Self-Supervised Geospatial Domain Adaptation
71. CVPR 2024Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching
72. CVPR 2024PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
73. CVPR 2024PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
74. CVPR 2024PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
75. CVPR 2024PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
76. CVPR 2024Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
77. CVPR 2024Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
78. CVPR 2024Rapid Motor Adaptation for Robotic Manipulator Arms
79. CVPR 2024Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts
80. CVPR 2024Revisiting Adversarial Training at Scale
81. CVPR 2024Rewrite the Stars
82. CVPR 2024RobustSAM: Segment Anything Robustly on Degraded Images
83. CVPR 2024Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens
84. CVPR 2024Self-supervised Debiasing Using Low Rank Regularization
85. CVPR 2024Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
86. CVPR 2024Sheared Backpropagation for Fine-tuning Foundation Models
87. CVPR 2024Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
88. CVPR 2024Specularity Factorization for Low-Light Enhancement
89. CVPR 2024Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization
90. CVPR 2024Task-Conditioned Adaptation of Visual Features in Multi-Task Policy Learning
91. CVPR 2024TEA: Test-time Energy Adaptation
92. CVPR 2024The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
93. CVPR 2024Time- Memory- and Parameter-Efficient Visual Adaptation
94. CVPR 2024Towards 3D Vision with Low-Cost Single-Photon Cameras
95. CVPR 2024TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation
96. CVPR 2024Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning
97. CVPR 2024Uncertainty Visualization via Low-Dimensional Posterior Projections
98. CVPR 2024Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective
99. CVPR 2024Unified Language-driven Zero-shot Domain Adaptation
100. CVPR 2024UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory

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。