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 95 篇，第 1 / 2 页

1. ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
2. ICLR 2024A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
3. ICLR 2024Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
4. ICLR 2024Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
5. ICLR 2024ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
6. ICLR 2024AlpaGasus: Training a Better Alpaca with Fewer Data
7. ICLR 2024Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
8. ICLR 2024AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
9. ICLR 2024AutoLoRa: An Automated Robust Fine-Tuning Framework
10. ICLR 2024AutoVP: An Automated Visual Prompting Framework and Benchmark
11. ICLR 2024BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
12. ICLR 2024Batched Low-Rank Adaptation of Foundation Models
13. ICLR 2024Bayesian Low-rank Adaptation for Large Language Models
14. ICLR 2024BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
15. ICLR 2024Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes
16. ICLR 2024Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
17. ICLR 2024Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
18. ICLR 2024CLAP: Collaborative Adaptation for Patchwork Learning
19. ICLR 2024Class Probability Matching with Calibrated Networks for Label Shift Adaption
20. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
21. ICLR 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
22. ICLR 2024Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
23. ICLR 2024DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
24. ICLR 2024Debiasing Algorithm through Model Adaptation
25. ICLR 2024DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
26. ICLR 2024Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
27. ICLR 2024Dissecting learning and forgetting in language model finetuning
28. ICLR 2024DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
29. ICLR 2024Dynamic Layer Tying for Parameter-Efficient Transformers
30. ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
31. ICLR 2024EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
32. ICLR 2024Enhancing Neural Training via a Correlated Dynamics Model
33. ICLR 2024Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
34. ICLR 2024FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
35. ICLR 2024Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
36. ICLR 2024First-order ANIL provably learns representations despite overparametrisation
37. ICLR 2024Gradual Domain Adaptation via Gradient Flow
38. ICLR 2024Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
39. ICLR 2024Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning
40. ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
41. ICLR 2024Improving Non-Transferable Representation Learning by Harnessing Content and Style
42. ICLR 2024Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
43. ICLR 2024Koopman-based generalization bound: New aspect for full-rank weights
44. ICLR 2024Learning Conditional Invariances through Non-Commutativity
45. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
46. ICLR 2024Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
47. ICLR 2024Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
48. ICLR 2024LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention
49. ICLR 2024LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
50. ICLR 2024LoftQ: LoRA-Fine-Tuning-aware Quantization for Large 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。