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 103 篇，第 1 / 3 页

1. CVPR 20253D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
2. CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
3. CVPR 2025Adaptive Parameter Selection for Tuning Vision-Language Models
4. CVPR 2025AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
5. CVPR 2025Bayesian Test-Time Adaptation for Vision-Language Models
6. CVPR 2025BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning
7. CVPR 2025Breaking the Low-Rank Dilemma of Linear Attention
8. CVPR 2025CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning
9. CVPR 2025CoA: Towards Real Image Dehazing via Compression-and-Adaptation
10. CVPR 2025COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
11. CVPR 2025COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
12. CVPR 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization
13. CVPR 2025DarkIR: Robust Low-Light Image Restoration
14. CVPR 2025DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
15. CVPR 2025DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
16. CVPR 2025Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment
17. CVPR 2025DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
18. CVPR 2025DocVLM: Make Your VLM an Efficient Reader
19. CVPR 2025Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics
20. CVPR 2025Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration
21. CVPR 2025Dynamic Updates for Language Adaptation in Visual-Language Tracking
22. CVPR 2025Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning
23. CVPR 2025Efficient Diffusion as Low Light Enhancer
24. CVPR 2025Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention
25. CVPR 2025Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
26. CVPR 2025Efficient Personalization of Quantized Diffusion Model without Backpropagation
27. CVPR 2025Effortless Active Labeling for Long-Term Test-Time Adaptation
28. CVPR 2025ERUPT: Efficient Rendering with Unposed Patch Transformer
29. CVPR 2025EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
30. CVPR 2025Faster Parameter-Efficient Tuning with Token Redundancy Reduction
31. CVPR 2025GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections
32. CVPR 2025Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
33. CVPR 2025Hazy Low-Quality Satellite Video Restoration Via Learning Optimal Joint Degradation Patterns and Continuous-Scale Super-Resolution Reconstruction
34. CVPR 2025Hiding Images in Diffusion Models by Editing Learned Score Functions
35. CVPR 2025Hierarchical Flow Diffusion for Efficient Frame Interpolation
36. CVPR 2025HOT: Hadamard-based Optimized Training
37. CVPR 2025HVI: A New Color Space for Low-light Image Enhancement
38. CVPR 2025HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
39. CVPR 2025Image Referenced Sketch Colorization Based on Animation Creation Workflow
40. CVPR 2025Improving Personalized Search with Regularized Low-Rank Parameter Updates
41. CVPR 2025IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
42. CVPR 2025IterIS: Iterative Inference-Solving Alignment for LoRA Merging
43. CVPR 2025Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation
44. CVPR 2025Label Shift Meets Online Learning: Ensuring Consistent Adaptation with Universal Dynamic Regret
45. CVPR 2025Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition
46. CVPR 2025Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
47. CVPR 2025Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation
48. CVPR 2025Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation
49. CVPR 2025LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models
50. CVPR 2025LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

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。