学习排序论文趋势 2023–2026

主要结论

• 学习排序论文从 2023 年的 142 篇降到 2026 年的 55 篇，热度在回落。
• NeurIPS 是发学习排序论文最多的会议，2023–2026 年共 154 篇，占四个会议总量的 60%。
• 交叉方向里涨得最快的是低秩适配：同时属于两个主题的论文从 2023 年的 39 篇增至 2026 年的 43 篇。
• 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的交叉编码重排是 3.0 倍，学习排序是 0.4 倍。

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

• NeurIPS 2026Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
• ICML 2026From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
• ICLR 2026Designing Rules to Pick a Rule: Aggregation by Consistency
• CVPR 2026LRDUN A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive
• NeurIPS 2025From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
• ICML 2025Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
• ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
• CVPR 2025Breaking the Low-Rank Dilemma of Linear Attention
• NeurIPS 2024Efficient LLM Scheduling by Learning to Rank
• ICML 2024Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
• ICLR 2024LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
• CVPR 2024Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning
• NeurIPS 2023A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
• ICML 2023Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
• ICLR 2023Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
• CVPR 20231% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
• NeurIPS 2026Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors
• ICML 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
• ICLR 2026Revisiting Weight Regularization for Low-Rank Continual Learning
• CVPR 2026Low-Rank Residual Diffusion Models

全部学习排序论文

共 257 篇，第 2 / 6 页

51. NeurIPS 2026RECIPE: Learning to Rank Complete Precursor Sets for Inorganic Retrosynthesis
52. NeurIPS 2026SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
53. NeurIPS 2026Stabilizing the Dynamic Low-Rank Training
54. NeurIPS 2026Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
55. NeurIPS 2026VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V Inference
56. CVPR 2025Breaking the Low-Rank Dilemma of Linear Attention
57. ICLR 2025Efficient Learning with Sine-Activated Low-Rank Matrices
58. ICLR 2025Ensembles of Low-Rank Expert Adapters
59. ICLR 2025Lambda-Skip Connections: the architectural component that prevents Rank Collapse
60. ICLR 2025LoLCATs: On Low-Rank Linearizing of Large Language Models
61. ICLR 2025LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
62. ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
63. ICLR 2025SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
64. ICLR 2025SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
65. ICML 2025Approximation to Smooth Functions by Low-Rank Swish Networks
66. ICML 2025GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
67. ICML 2025Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
68. ICML 2025Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression
69. ICML 2025Low-Rank Thinning
70. ICML 2025Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
71. ICML 2025ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
72. ICML 2025Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
73. ICML 2025Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank
74. ICML 2025The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
75. NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
76. NeurIPS 2025AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
77. NeurIPS 2025Demystifying Language Model Forgetting with Low-rank Example Associations
78. NeurIPS 2025Efficient Low Rank Attention for Long-Context Inference in Large Language Models
79. NeurIPS 2025Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
80. NeurIPS 2025From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
81. NeurIPS 2025Generalization Bounds for Rank-sparse Neural Networks
82. NeurIPS 2025LittleBit: Ultra Low-Bit Quantization via Latent Factorization
83. NeurIPS 2025Low-Rank Graphon Learning for Networks
84. NeurIPS 2025Low-Rank Head Avatar Personalization with Registers
85. NeurIPS 2025On the Role of Hidden States of Modern Hopfield Network in Transformer
86. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
87. NeurIPS 2025Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
88. CVPR 2024LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking
89. CVPR 2024PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
90. CVPR 2024Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning
91. ICLR 2024LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
92. ICLR 2024Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
93. ICML 2024Efficient Pareto Manifold Learning with Low-Rank Structure
94. ICML 2024Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters
95. ICML 2024FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees
96. ICML 2024Flora: Low-Rank Adapters Are Secretly Gradient Compressors
97. ICML 2024GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
98. ICML 2024High-Dimensional Geometric Streaming for Nearly Low Rank Data
99. ICML 2024Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
100. ICML 2024Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery

常见问题

2023–2026 年四大会议一共有多少篇学习排序论文？

共 257 篇，按年份分别是 2023 年 142 篇、2024 年 28 篇、2025 年 32 篇、2026 年 55 篇。

NeurIPS 2026 有多少篇学习排序论文？

NeurIPS 2026 有 18 篇学习排序论文，上一届是 13 篇。

ICLR 2026 有多少篇学习排序论文？

ICLR 2026 有 9 篇学习排序论文，上一届是 8 篇。

ICML 2026 有多少篇学习排序论文？

ICML 2026 有 26 篇学习排序论文，上一届是 10 篇。

CVPR 2026 有多少篇学习排序论文？

CVPR 2026 有 2 篇学习排序论文，上一届是 1 篇。

哪个会议的学习排序论文最多？

NeurIPS，2023–2026 年共 154 篇。