低秩适配论文趋势 2023–2026

LoRA 与参数高效微调

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,273 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

低秩适配论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202378766563282
202419395124106518
2025241152136103632
2026269184240148841

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

全部低秩适配论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,272 篇，第 4 / 46 页

  1. ICLR 2026ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
  2. ICLR 2026Achieving low-bit Muon through subspace preservation and grid quantization
  3. ICLR 2026Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
  4. ICLR 2026Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation
  5. ICLR 2026Adaptive Nonlinear Compression for Large Foundation Models
  6. ICLR 2026AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
  7. ICLR 2026ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
  8. ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
  9. ICLR 2026All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation
  10. ICLR 2026Arbitrary-Order Block SignSGD for Memory-Efficient LLM Fine-Tuning
  11. ICLR 2026Are we measuring oversmoothing in graph neural networks correctly?
  12. ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
  13. ICLR 2026Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image Compression
  14. ICLR 2026BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
  15. ICLR 2026Bayesian Evidence-Driven Prototype Evolution for Federated Domain Adaptation
  16. ICLR 2026Bayesian Test-Time Adaptation via Dirichlet feature projection and GMM-Driven Inference for Motor Imagery EEG Decoding
  17. ICLR 2026Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
  18. ICLR 2026Bilateral Information-aware Test-time Adaptation for Vision-Language Models
  19. ICLR 2026BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
  20. ICLR 2026Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training
  21. ICLR 2026Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
  22. ICLR 2026CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs
  23. ICLR 2026CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
  24. ICLR 2026CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detections
  25. ICLR 2026ChainGPT: Dual-Reasoning Model with Recurrent Depth and Multi-Rank State Updates
  26. ICLR 2026Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
  27. ICLR 2026CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
  28. ICLR 2026Consistent Low-Rank Approximation
  29. ICLR 2026Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
  30. ICLR 2026Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
  31. ICLR 2026CPQS-Tuning: A Model Self-Perception-Based Data Filtering Algorithm for Efficient Instruction Fine-Tuning
  32. ICLR 2026CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
  33. ICLR 2026DADA: Dual Averaging with Distance Adaptation
  34. ICLR 2026Deep Hierarchical Learning with Nested Subspace Networks
  35. ICLR 2026Deep Learning with Learnable Product-Structured Activations
  36. ICLR 2026Designing Rules to Pick a Rule: Aggregation by Consistency
  37. ICLR 2026Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM Adaptation
  38. ICLR 2026DiaBlo: Diagonal Blocks Are Sufficient For Finetuning
  39. ICLR 2026Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation
  40. ICLR 2026Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
  41. ICLR 2026Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity
  42. ICLR 2026Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks
  43. ICLR 2026DSSA: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
  44. ICLR 2026E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
  45. ICLR 2026Efficient Learning on Large Graphs using a Densifying Regularity Lemma
  46. ICLR 2026Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
  47. ICLR 2026Efficient Resource-Constrained Training of Transformers via Subspace Optimization
  48. ICLR 2026Efficient Spatially-Variant Convolution via Differentiable Sparse Kernel Complex
  49. ICLR 2026EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning
  50. ICLR 2026Enabling Fine-Tuning of Direct Feedback Alignment via Feedback-Weight Matching

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查低秩适配在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "low-rank-adaptation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「优化与缩放」下的其他主题