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 840 篇，第 11 / 17 页

  1. ICML 2026Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners
  2. ICML 2026Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models
  3. ICML 2026Riemannian Networks over Full-Rank Correlation Matrices
  4. ICML 2026Robust Vision-Language Models via Manifold-Adversarial Adapters
  5. ICML 2026SABER: Continual Learning with Representation Conflict Management
  6. ICML 2026SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
  7. ICML 2026SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
  8. ICML 2026Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
  9. ICML 2026Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
  10. ICML 2026ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
  11. ICML 2026SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
  12. ICML 2026Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
  13. ICML 2026SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
  14. ICML 2026Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
  15. ICML 2026Singular Bayesian Neural Networks
  16. ICML 2026SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
  17. ICML 2026Sketch-Based Low-Rank Model Merging with Shared Circulant Transforms
  18. ICML 2026Skill Neologisms: Towards Skill-based Continual Learning
  19. ICML 2026Spectral Bridge Variational Inference: Dynamic LoRA via Bures-Wasserstein Gradient Flows
  20. ICML 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
  21. ICML 2026SPR-RAFT: Parameter-Efficient Regression-Aware Fine-Tuning for Biomedical LLM Regression
  22. ICML 2026SPR: A Structured Prompt Refinement Network for Modality Missing
  23. ICML 2026SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
  24. ICML 2026SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models
  25. ICML 2026Stabilizing Native Low-Rank LLM Pretraining
  26. ICML 2026STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
  27. ICML 2026Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
  28. ICML 2026Stochastic Sparse Attention for Memory-Bound Inference
  29. ICML 2026SubspacePath Pruner: Inference-time Pruning via Probe-based Representation–Parameter Coupling
  30. ICML 2026SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
  31. ICML 2026Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
  32. ICML 2026Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
  33. ICML 2026Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
  34. ICML 2026TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
  35. ICML 2026The Appeal and Reality of Recycling LoRAs with Adaptive Merging
  36. ICML 2026The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
  37. ICML 2026The Geometry of Narrow Fine-Tuning Degradation: Trajectory Lock-in and Spectral Bifurcation
  38. ICML 2026The Geometry of Updates: Fisher Alignment at Vocabulary Scale
  39. ICML 2026Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks
  40. ICML 2026TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling
  41. ICML 2026TokenDrop: Token-Level Importance-Aware Backward Propagation Skipping for Efficient LLM Fine-Tuning
  42. ICML 2026TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding
  43. ICML 2026Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
  44. ICML 2026Towards Understanding the Dynamics of Low-Rank Adaptation
  45. ICML 2026TPV: Parameter Perturbations Through the Lens of Test Prediction Variance
  46. ICML 2026Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
  47. ICML 2026Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment
  48. ICML 2026Transport Clustering: Solving Low-Rank Optimal Transport via Clustering
  49. ICML 2026Transport or Discard: Robust Unbalanced Optimal Transport for Cross-Domain Policy Adaptation
  50. ICML 2026Tucker Attention: A generalization of approximate attention mechanisms

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