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 507 篇，第 4 / 11 页

  1. ICLR 2026Sequences of Logits Reveal the Low Rank Structure of Language Models
  2. ICLR 2026SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
  3. ICLR 2026SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
  4. ICLR 2026SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
  5. ICLR 2026SpareTrain: Fault-Tolerant LLM Training via Low-Cost Dual Modular Redundancy
  6. ICLR 2026Sparse Attention Adaptation for Long Reasoning
  7. ICLR 2026SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
  8. ICLR 2026Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaption
  9. ICLR 2026STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
  10. ICLR 2026Study of Training Dynamics for Memory-Constrained Fine-Tuning
  11. ICLR 2026SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis
  12. ICLR 2026Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
  13. ICLR 2026Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
  14. ICLR 2026The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor Recovery
  15. ICLR 2026The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
  16. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
  17. ICLR 2026Tina: Tiny Reasoning Models via LoRA
  18. ICLR 2026TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
  19. ICLR 2026Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
  20. ICLR 2026Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
  21. ICLR 2026TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-Tuning
  22. ICLR 2026Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks
  23. ICLR 2026ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted Inference
  24. ICLR 2026Unbalanced Soft-Matching Distance For Neural Representational Comparison With Partial Unit Correspondence
  25. ICLR 2026Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
  26. ICLR 2026UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
  27. ICLR 2026Video Unlearning via Low-Rank Refusal Vector
  28. ICLR 2026VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
  29. ICLR 2026What Layers When: Learning to Skip Compute in LLMs with Residual Gates
  30. ICLR 2026When and Where to Reset Matters for Long-Term Test-Time Adaptation
  31. ICLR 2026Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
  32. ICLR 2026Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
  33. ICLR 2026WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
  34. ICLR 2026ZeroSiam: An Efficient Siamese for Test-Time Entropy Optimization without Collapse
  35. ICLR 2025$InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
  36. ICLR 2025A Differentiable Rank-Based Objective for Better Feature Learning
  37. ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
  38. ICLR 2025Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization
  39. ICLR 2025Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
  40. ICLR 2025AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning
  41. ICLR 2025Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
  42. ICLR 2025ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
  43. ICLR 2025An Efficient Framework for Crediting Data Contributors of Diffusion Models
  44. ICLR 2025Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation
  45. ICLR 2025Binary Losses for Density Ratio Estimation
  46. ICLR 2025BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
  47. ICLR 2025Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition
  48. ICLR 2025Block-Attention for Efficient Prefilling
  49. ICLR 2025Cached Multi-Lora Composition for Multi-Concept Image Generation
  50. ICLR 2025Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

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