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 565 篇，第 7 / 12 页

301. ICML 2025Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
302. ICML 2025Learning to Reuse Policies in State Evolvable Environments
303. ICML 2025LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
304. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
305. ICML 2025Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
306. ICML 2025LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
307. ICML 2025LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
308. ICML 2025Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
309. ICML 2025Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
310. ICML 2025Low-Rank Adapting Models for Sparse Autoencoders
311. ICML 2025Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression
312. ICML 2025Low-Rank Thinning
313. ICML 2025LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
314. ICML 2025LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers
315. ICML 2025Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
316. ICML 2025Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
317. ICML 2025MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
318. ICML 2025Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers
319. ICML 2025Mixture of Lookup Experts
320. ICML 2025Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
321. ICML 2025MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
322. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
323. ICML 2025MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
324. ICML 2025Neutral residues: revisiting adapters for model extension
325. ICML 2025Olica: Efficient Structured Pruning of Large Language Models without Retraining
326. ICML 2025Optimizing Large Language Model Training Using FP4 Quantization
327. ICML 2025Oscillation-Reduced MXFP4 Training for Vision Transformers
328. ICML 2025Parameter-Efficient Fine-Tuning of State Space Models
329. ICML 2025Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
330. ICML 2025Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
331. ICML 2025Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves
332. ICML 2025Projection Pursuit Density Ratio Estimation
333. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
334. ICML 2025PTTA: Purifying Malicious Samples for Test-Time Model Adaptation
335. ICML 2025Rank-One Modified Value Iteration
336. ICML 2025Ranked Entropy Minimization for Continual Test-Time Adaptation
337. ICML 2025Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
338. ICML 2025RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
339. ICML 2025ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
340. ICML 2025Robust Sparsification via Sensitivity
341. ICML 2025RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models
342. ICML 2025SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
343. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
344. ICML 2025Self-Bootstrapping for Versatile Test-Time Adaptation
345. ICML 2025Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
346. ICML 2025SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
347. ICML 2025SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
348. ICML 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
349. ICML 2025Sparse Autoencoders, Again?
350. ICML 2025Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

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。