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 269 篇，第 3 / 6 页

101. NeurIPS 2026FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
102. NeurIPS 2026FELPS: Fair and Efficient Scheduling for Multi-LoRA Serving System
103. NeurIPS 2026FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
104. NeurIPS 2026Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting
105. NeurIPS 2026Flash-KMeans: Fast and Memory-Efficient Exact K-Means
106. NeurIPS 2026FLoRA-Chef: Making A Good LoRA Recipe in Federated Generalization
107. NeurIPS 2026Follow the Mean: Reference-Guided Flow Matching
108. NeurIPS 2026Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large Models
109. NeurIPS 2026From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs
110. NeurIPS 2026From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
111. NeurIPS 2026From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations
112. NeurIPS 2026From Weeks to Hours: Fast and Principled SFT Curation for LLM
113. NeurIPS 2026Full Fine-Tuning Is Not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP Adaptation
114. NeurIPS 2026FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
115. NeurIPS 2026Generalizing the Geometry of Model Merging Through Fréchet Averages
116. NeurIPS 2026Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
117. NeurIPS 2026GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
118. NeurIPS 2026Hadamard Representation: Scaffolding Performance Across Model-free RL
119. NeurIPS 2026HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
120. NeurIPS 2026Heavy-Tailed Flow Matching via Random Clocks
121. NeurIPS 2026HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
122. NeurIPS 2026HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
123. NeurIPS 2026Hint Tuning: Less Data Makes Better Reasoners
124. NeurIPS 2026How Finite-Rank Bottleneck Shape the Low-Rank Adaptation Landscape
125. NeurIPS 2026Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
126. NeurIPS 2026Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning
127. NeurIPS 2026Improving Quantized Zeroth-Order Optimization through Reconstructed Low-Rank Structures
128. NeurIPS 2026InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
129. NeurIPS 2026Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
130. NeurIPS 2026Knowing When Multivariate Forecasts Are Wrong
131. NeurIPS 2026LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
132. NeurIPS 2026Language-Induced Priors for Domain Adaptation
133. NeurIPS 2026LAPLEX: The FFT of Learnable Laplace Kernels
134. NeurIPS 2026LAtte: Hyperbolic Lorentz Attention for Joint-Subject EEG Classification
135. NeurIPS 2026LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning
136. NeurIPS 2026Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
137. NeurIPS 2026Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification
138. NeurIPS 2026Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
139. NeurIPS 2026Learning Process Rewards via Visitation Matching for Efficient RL
140. NeurIPS 2026Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
141. NeurIPS 2026Learning Reveals Invisible Structure in Low-Rank RNNs
142. NeurIPS 2026Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
143. NeurIPS 2026LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
144. NeurIPS 2026Locking Pretrained Weights via Deep Low-Rank Residual Distillation
145. NeurIPS 2026LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
146. NeurIPS 2026LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
147. NeurIPS 2026LoRAtorio: An intrinsic approach to LoRA Skill Composition
148. NeurIPS 2026Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
149. NeurIPS 2026Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
150. NeurIPS 2026LR-V2X: Loss Resilient Collaborative Perception under Low-Bandwidth Communication

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。