Learning to Rank papers, 2023–2026

Key findings

• Learning to Rank fell from 142 papers in 2023 to 55 in 2026, so interest is cooling.
• NeurIPS publishes the most Learning to Rank work: 154 papers from 2023 to 2026, 60% of the four-venue total.
• The fastest-growing overlap is with Low-Rank Adaptation: papers tagged with both rose from 39 in 2023 to 43 in 2026.
• Among the 5 topics under Information Retrieval, it ranks #4 by 2026 paper count; the fastest grower in the group, Cross-Encoder Reranking, is up 3.0x versus 0.4x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Learning to Rank papers

154 papers, page 1 of 4

1. NeurIPS 2026A Sparse Low-Rank Biclique Decomposition for Graphs
2. NeurIPS 2026Asymmetric Factorization for Low-Rank PSD Learning: When Is the Relaxation Exact ?
3. NeurIPS 2026BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode
4. NeurIPS 2026BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
5. NeurIPS 2026Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
6. NeurIPS 2026Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
7. NeurIPS 2026Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
8. NeurIPS 2026Learning Reveals Invisible Structure in Low-Rank RNNs
9. NeurIPS 2026Locking Pretrained Weights via Deep Low-Rank Residual Distillation
10. NeurIPS 2026Matrix Recovery Via Symmetric Rank-one Measurements With Random Unit-modulus Vectors
11. NeurIPS 2026Overcoming Rank Collapse in Feedback Alignment
12. NeurIPS 2026Provably Efficient Representation Learning for Low-Rank CMDPs
13. NeurIPS 2026RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache Compression
14. NeurIPS 2026RECIPE: Learning to Rank Complete Precursor Sets for Inorganic Retrosynthesis
15. NeurIPS 2026SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
16. NeurIPS 2026Stabilizing the Dynamic Low-Rank Training
17. NeurIPS 2026Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
18. NeurIPS 2026VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V Inference
19. NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
20. NeurIPS 2025AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
21. NeurIPS 2025Demystifying Language Model Forgetting with Low-rank Example Associations
22. NeurIPS 2025Efficient Low Rank Attention for Long-Context Inference in Large Language Models
23. NeurIPS 2025Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
24. NeurIPS 2025From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
25. NeurIPS 2025Generalization Bounds for Rank-sparse Neural Networks
26. NeurIPS 2025LittleBit: Ultra Low-Bit Quantization via Latent Factorization
27. NeurIPS 2025Low-Rank Graphon Learning for Networks
28. NeurIPS 2025Low-Rank Head Avatar Personalization with Registers
29. NeurIPS 2025On the Role of Hidden States of Modern Hopfield Network in Transformer
30. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
31. NeurIPS 2025Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
32. NeurIPS 2024Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models
33. NeurIPS 2024Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
34. NeurIPS 2024Efficient LLM Scheduling by Learning to Rank
35. NeurIPS 2024Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
36. NeurIPS 2024Entrywise error bounds for low-rank approximations of kernel matrices
37. NeurIPS 2024Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
38. NeurIPS 2024Loki: Low-rank Keys for Efficient Sparse Attention
39. NeurIPS 2024Neural Embeddings Rank: Aligning 3D latent dynamics with movements
40. NeurIPS 2024SGD vs GD: Rank Deficiency in Linear Networks
41. NeurIPS 2024Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
42. NeurIPS 2024Weight decay induces low-rank attention layers
43. NeurIPS 2023A Batch-to-Online Transformation under Random-Order Model
44. NeurIPS 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks
45. NeurIPS 2023A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
46. NeurIPS 2023A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment
47. NeurIPS 2023A Path to Simpler Models Starts With Noise
48. NeurIPS 2023A Randomized Approach to Tight Privacy Accounting
49. NeurIPS 2023A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
50. NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm

FAQ

How many Learning to Rank papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

257 in total: 142 in 2023, 28 in 2024, 32 in 2025, 55 in 2026.

How many Learning to Rank papers are at NeurIPS 2026?

NeurIPS 2026 has 18 Learning to Rank papers, versus 13 the year before.

How many Learning to Rank papers are at ICLR 2026?

ICLR 2026 has 9 Learning to Rank papers, versus 8 the year before.

How many Learning to Rank papers are at ICML 2026?

ICML 2026 has 26 Learning to Rank papers, versus 10 the year before.

How many Learning to Rank papers are at CVPR 2026?

CVPR 2026 has 2 Learning to Rank papers, versus 1 the year before.

Which conference publishes the most Learning to Rank papers?

NeurIPS, with 154 papers from 2023 to 2026.