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 1 / 6 页

1. CVPR 2026Low-Rank Residual Diffusion Models
2. CVPR 2026LRDUN A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive
3. ICLR 2026Consistent Low-Rank Approximation
4. ICLR 2026Designing Rules to Pick a Rule: Aggregation by Consistency
5. ICLR 2026GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
6. ICLR 2026Revisiting Weight Regularization for Low-Rank Continual Learning
7. ICLR 2026Sequences of Logits Reveal the Low Rank Structure of Language Models
8. ICLR 2026SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
9. ICLR 2026Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
10. ICLR 2026The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor Recovery
11. ICLR 2026Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
12. ICML 2026AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
13. ICML 2026Approximating f -Divergences with Rank Statistics
14. ICML 2026Breaking the Computational Barrier: Provably Efficient Actor–Critic for Low-Rank MDPs
15. ICML 2026Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
16. ICML 2026De-attribute to Forget for LLM Unlearning
17. ICML 2026Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
18. ICML 2026Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
19. ICML 2026From Drift to Coherence: Stabilizing Beliefs in LLMs
20. ICML 2026From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
21. ICML 2026Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Model
22. ICML 2026Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought
23. ICML 2026Learning to Evict from Key-Value Cache
24. ICML 2026Learning to Rank by Directly Optimizing Full-Order Probabilities
25. ICML 2026Learning to Rank from Incomplete Rankings
26. ICML 2026Learning to Route Languages for Multilingual Policy Optimization
27. ICML 2026Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
28. ICML 2026Mixtures Closest To A Given Measure: A Semidefinite Programming Approach
29. ICML 2026On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models
30. ICML 2026Refining Dual Spectral Sparsity in Transformed Tensor Singular Values
31. ICML 2026Rethinking Federated Prompt Learning for Medical Images: From Textual Tuning to Visual Manifold Anchoring
32. ICML 2026Riemannian Networks over Full-Rank Correlation Matrices
33. ICML 2026Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
34. ICML 2026Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
35. ICML 2026Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
36. ICML 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
37. ICML 2026Transport Clustering: Solving Low-Rank Optimal Transport via Clustering
38. NeurIPS 2026A Sparse Low-Rank Biclique Decomposition for Graphs
39. NeurIPS 2026Asymmetric Factorization for Low-Rank PSD Learning: When Is the Relaxation Exact ?
40. NeurIPS 2026BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode
41. NeurIPS 2026BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
42. NeurIPS 2026Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
43. NeurIPS 2026Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
44. NeurIPS 2026Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
45. NeurIPS 2026Learning Reveals Invisible Structure in Low-Rank RNNs
46. NeurIPS 2026Locking Pretrained Weights via Deep Low-Rank Residual Distillation
47. NeurIPS 2026Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors
48. NeurIPS 2026Overcoming Rank Collapse in Feedback Alignment
49. NeurIPS 2026Provably Efficient Representation Learning for Low-Rank CMDPs
50. NeurIPS 2026RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache Compression

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。