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 7 / 17 页

  1. ICLR 2026SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
  2. ICLR 2026SpareTrain: Fault-Tolerant LLM Training via Low-Cost Dual Modular Redundancy
  3. ICLR 2026Sparse Attention Adaptation for Long Reasoning
  4. ICLR 2026SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
  5. ICLR 2026Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaption
  6. ICLR 2026STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
  7. ICLR 2026Study of Training Dynamics for Memory-Constrained Fine-Tuning
  8. ICLR 2026SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis
  9. ICLR 2026Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
  10. ICLR 2026Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
  11. ICLR 2026The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor Recovery
  12. ICLR 2026The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
  13. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
  14. ICLR 2026Tina: Tiny Reasoning Models via LoRA
  15. ICLR 2026TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
  16. ICLR 2026Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
  17. ICLR 2026Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
  18. ICLR 2026TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-Tuning
  19. ICLR 2026Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks
  20. ICLR 2026ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted Inference
  21. ICLR 2026Unbalanced Soft-Matching Distance For Neural Representational Comparison With Partial Unit Correspondence
  22. ICLR 2026Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
  23. ICLR 2026UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
  24. ICLR 2026Video Unlearning via Low-Rank Refusal Vector
  25. ICLR 2026VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
  26. ICLR 2026What Layers When: Learning to Skip Compute in LLMs with Residual Gates
  27. ICLR 2026When and Where to Reset Matters for Long-Term Test-Time Adaptation
  28. ICLR 2026Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
  29. ICLR 2026Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
  30. ICLR 2026WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
  31. ICLR 2026ZeroSiam: An Efficient Siamese for Test-Time Entropy Optimization without Collapse
  32. ICML 20261-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization
  33. ICML 2026A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity
  34. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
  35. ICML 2026A3: an Analytical Low-Rank Approximation Framework for Attention
  36. ICML 2026Accelerating Q-learning through Efficient Value-Sharing across Actions
  37. ICML 2026Active Learning with Low-Rank Structure for Data Selection
  38. ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
  39. ICML 2026AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM Agents
  40. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
  41. ICML 2026ANTiC: Adaptive Neural Temporal In Situ Compressor
  42. ICML 2026AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
  43. ICML 2026AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
  44. ICML 2026Approximating f -Divergences with Rank Statistics
  45. ICML 2026AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
  46. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
  47. ICML 2026BAS: Bridging Adam and SignSGD for Memory-Efficient LLM Training
  48. ICML 2026Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
  49. ICML 2026Bayesian Tensor Decomposition with Diffusion Model Prior
  50. ICML 2026Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models

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