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 241 篇，第 4 / 5 页

151. NeurIPS 2025NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
152. NeurIPS 2025OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding
153. NeurIPS 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
154. NeurIPS 2025On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks
155. NeurIPS 2025On the Role of Hidden States of Modern Hopfield Network in Transformer
156. NeurIPS 2025Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics
157. NeurIPS 2025Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
158. NeurIPS 2025Optimization Inspired Few-Shot Adaptation for Large Language Models
159. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
160. NeurIPS 2025Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
161. NeurIPS 2025Parameter Dynamics of Online Machine Learning and Test-time Adaptation
162. NeurIPS 2025Parameter Efficient Fine-tuning via Explained Variance Adaptation
163. NeurIPS 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
164. NeurIPS 2025Pay Attention to Small Weights
165. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
166. NeurIPS 2025PoLAR: Polar-Decomposed Low-Rank Adapter Representation
167. NeurIPS 2025Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
168. NeurIPS 2025Principled Model Routing for Unknown Mixtures of Source Domains
169. NeurIPS 2025Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster
170. NeurIPS 2025Prompt Tuning Transformers for Data Memorization
171. NeurIPS 2025Provable Meta-Learning with Low-Rank Adaptations
172. NeurIPS 2025Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations
173. NeurIPS 2025PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
174. NeurIPS 2025PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
175. NeurIPS 2025Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
176. NeurIPS 2025QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution
177. NeurIPS 2025QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
178. NeurIPS 2025QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
179. NeurIPS 2025Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning
180. NeurIPS 2025Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
181. NeurIPS 2025RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
182. NeurIPS 2025Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning
183. NeurIPS 2025RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
184. NeurIPS 2025Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
185. NeurIPS 2025Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
186. NeurIPS 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
187. NeurIPS 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
188. NeurIPS 2025Restoring Pruned Large Language Models via Lost Component Compensation
189. NeurIPS 2025Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
190. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
191. NeurIPS 2025RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
192. NeurIPS 2025Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
193. NeurIPS 2025RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
194. NeurIPS 2025Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
195. NeurIPS 2025Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits
196. NeurIPS 2025RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
197. NeurIPS 2025S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
198. NeurIPS 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
199. NeurIPS 2025SALS: Sparse Attention in Latent Space for KV Cache Compression
200. NeurIPS 2025Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function

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。