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 6 / 46 页

  1. ICLR 2026Merge before Forget: A Single LoRA Continual Learning via Continual Merging
  2. ICLR 2026MergeTune: Continued Fine-Tuning of Vision-Language Models
  3. ICLR 2026Meta-UCF: Unified Task-Conditioned LoRA Generation for Continual Learning in Large Language Models
  4. ICLR 2026MetaVLA: Unified Meta Co-Training for Efficient Embodied Adaptation
  5. ICLR 2026Metric $k$-clustering using only Weak Comparison Oracles
  6. ICLR 2026MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure
  7. ICLR 2026MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1K$ Parameters
  8. ICLR 2026MoM: Linear Sequence Modeling with Mixture-of-Memories
  9. ICLR 2026MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition
  10. ICLR 2026MoSA: Mosaic Shared Adaptation of Large Language Models
  11. ICLR 2026Multi-Head Low-Rank Attention
  12. ICLR 2026Multi-Task Low-Rank Model Adaptation
  13. ICLR 2026Not All Documents Are What You Need for Extracting Instruction Tuning Data
  14. ICLR 2026On Fairness of Task Arithmetic: The Role of Task Vectors
  15. ICLR 2026On Predictability of Reinforcement Learning Dynamics for Large Language Models
  16. ICLR 2026On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
  17. ICLR 2026Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
  18. ICLR 2026Oracle-efficient Hybrid Learning with Constrained Adversaries
  19. ICLR 2026PALC: Preference Alignment via Logit Calibration
  20. ICLR 2026Parameter-Efficient Reinforcement Learning using Prefix Optimization
  21. ICLR 2026PARD: Accelerating LLM Inference with Low‑Cost PARallel Draft Model Adaptation
  22. ICLR 2026PAS: Estimating the target accuracy before domain adaptation
  23. ICLR 2026PCLR: Progressively Compressed LoRA for Multimodal Continual Instruction Tuning
  24. ICLR 2026PerFit: Exploring Personalization Shifts in Representation Space of LLMs
  25. ICLR 2026Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
  26. ICLR 2026PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection
  27. ICLR 2026PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models
  28. ICLR 2026PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
  29. ICLR 2026Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters
  30. ICLR 2026PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
  31. ICLR 2026Quasi-Monte Carlo Methods Enable Extremely Low-Dimensional Deep Generative Models
  32. ICLR 2026QuRL: Low-Precision Reinforcement Learning for Efficient Reasoning
  33. ICLR 2026QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
  34. ICLR 2026Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification
  35. ICLR 2026RESA: Bringing Back What Sparse Attention Ignores with Residual Estimation
  36. ICLR 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
  37. ICLR 2026Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts
  38. ICLR 2026Revisiting Weight Regularization for Low-Rank Continual Learning
  39. ICLR 2026Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
  40. ICLR 2026Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis
  41. ICLR 2026Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
  42. ICLR 2026SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
  43. ICLR 2026Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
  44. ICLR 2026Scaling with Collapse: Efficient and Predictable Training of LLM Families
  45. ICLR 2026Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning
  46. ICLR 2026SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
  47. ICLR 2026Self-Destructive Language Models
  48. ICLR 2026Sequences of Logits Reveal the Low Rank Structure of Language Models
  49. ICLR 2026SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
  50. ICLR 2026SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA

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