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 419 篇，第 3 / 9 页

101. CVPR 2026PointTPA Dynamic Network Parameter Adaptation for 3D Scene Understanding
102. CVPR 2026Preference-Aligned LoRA Merging Preserving Subspace Coverage and Addressing Directional Anisotropy
103. CVPR 2026Prime Once then Reprogram Locally An Efficient Alternative to Black-Box
104. CVPR 2026Protect to Adapt Orthogonal Subspace Control with Ranked Negative-Prompt Curriculum
105. CVPR 2026QD-PCQA Quality-Aware Domain Adaptation for Point Cloud Quality Assessment
106. CVPR 2026QuadSync Quadrifocal Tensor Synchronization via Tucker Decomposition
107. CVPR 2026RADAR VQ-VAE Decoder of VAR is a Good Student for
108. CVPR 2026Rank-Guided Pseudo-Bias Learning for Robust Black-Box Adaptation
109. CVPR 2026RAPID Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video
110. CVPR 2026RARE Learn to RAnk and REtrieve for Monocular 3D Object
111. CVPR 2026ReFTA Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning
112. CVPR 2026Render-to-Adapt Unsupervised Personal Adaptation for Gaze Estimation
113. CVPR 2026Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models
114. CVPR 2026Revisiting 3D Reconstruction Kernels as Low-Pass Filters
115. CVPR 2026Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning
116. CVPR 2026Reviving ConvNeXt for Efficient Convolutional Diffusion Models
117. CVPR 2026RNN as Linear Transformer A Closer Investigation into Representational Potentials
118. CVPR 2026S2FT Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
119. CVPR 2026SEATrack Simple Efficient and Adaptive Multimodal Tracker
120. CVPR 2026See Further Think Deeper Advancing VLMs Reasoning Ability with Low-level
121. CVPR 2026SG-LoRA Semantic-guided LoRA Parameters Generation
122. CVPR 2026SGI Structured 2D Gaussians for Efficient and Compact Large Image
123. CVPR 2026Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation
124. CVPR 2026Sparse Spectral LoRA Routed Experts for Medical VLMs
125. CVPR 2026SpatialTree How Spatial Intelligence Branches Out in MLLMs
126. CVPR 2026SPDMark Selective Parameter Displacement for Robust Video Watermarking
127. CVPR 2026SpiderCam Low-Power Snapshot Depth from Differential Defocus
128. CVPR 2026SpiralDiff Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras
129. CVPR 2026SplitFlux Learning to Decouple Content and Style from a Single
130. CVPR 2026SuP Sub-cloud Driven Point Cloud Registration
131. CVPR 2026SynMotion Semantic-Visual Adaptation for Motion Customized Video Generation
132. CVPR 2026TAS-LoRA Transformer Architecture Search with Mixture-of-LoRA Experts
133. CVPR 2026TaskIT Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transfer
134. CVPR 2026Tell2Adapt A Unified Framework for Source Free Unsupervised Domain Adaptation
135. CVPR 2026Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing
136. CVPR 2026The Blind Spot of Adaptation Quantifying and Mitigating Forgetting in
137. CVPR 2026Toward Low-Cost yet Effective Temporal Learning for UAV Tracking
138. CVPR 2026Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data
139. CVPR 2026Towards Generalized Representations for Low-Light Understanding When Signal Constancy Meets
140. CVPR 2026Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
141. CVPR 2026Training-free Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient
142. CVPR 2026UDAPose Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
143. CVPR 2026Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
144. CVPR 2026Uni-DAD Unified Distillation and Adaptation of Diffusion Models for Few-step
145. CVPR 2026VLA Models Are More Generalizable Than You Think Revisiting Physical
146. CVPR 2026Weight Space Representation Learning via Neural Field Adaptation
147. CVPR 2026When LoRA Betrays Backdooring Text-to-Image Models by Masquerading as Benign
148. CVPR 20253D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
149. CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
150. CVPR 2025Adaptive Parameter Selection for Tuning Vision-Language Models

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。