Low-Rank Adaptation papers, 2023–2026

Key findings

• Low-Rank Adaptation went from 282 papers in 2023 to 841 in 2026, roughly 3.0x in three years.
• NeurIPS publishes the most Low-Rank Adaptation work: 781 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 4 in 2023 to 61 in 2026.
• Among the 5 topics under Optimization and Scaling, it ranks #1 by 2026 paper count; the fastest grower in the group, Scaling Laws, is up 4.1x versus 3.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
• ICML 2026A3: an Analytical Low-Rank Approximation Framework for Attention
• ICLR 2026A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
• CVPR 20262-Shots in the Dark Low-Light Denoising with Minimal Data Acquisition
• NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
• ICML 2025Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
• ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
• CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
• NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
• ICML 2024A Tensor Decomposition Perspective on Second-order RNNs
• ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
• CVPR 2024DePT: Decoupled Prompt Tuning
• NeurIPS 2023A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
• ICML 2023A Three-regime Model of Network Pruning
• ICLR 2023A General Rank Preserving Framework for Asymmetric Image Retrieval
• CVPR 20231% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
• NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
• ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
• ICLR 2026ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
• CVPR 2026Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation

All Low-Rank Adaptation papers

565 papers, page 2 of 12

51. ICML 2026Diving into Kronecker Adapters: Component Design Matters
52. ICML 2026Doc-to-LoRA: Learning to Instantly Internalize Contexts
53. ICML 2026Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization Bounds
54. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
55. ICML 2026Dynamic High-Dimensional Facility Location with Low Recourse
56. ICML 2026Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
57. ICML 2026Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
58. ICML 2026Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
59. ICML 2026Energy-Structured Low-Rank Adaptation for Continual Learning
60. ICML 2026Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
61. ICML 2026Equivalence of Context and Parameter Updates in Modern Transformer Blocks
62. ICML 2026Escaping the Subspace Trap: The Role of Optimizer Geometry in Model Width Expansion
63. ICML 2026Evaluating Parameter Efficient Methods for RLVR
64. ICML 2026Exploring Data-Free LoRA Transferability for Video Diffusion Models
65. ICML 2026Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
66. ICML 2026Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent
67. ICML 2026Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
68. ICML 2026Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
69. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources
70. ICML 2026FedPAT: Federated Test-Time Adaptation via Prototype Affinity Topology
71. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
72. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
73. ICML 2026FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
74. ICML 2026Fine-Tuning of Transformer models with Frames
75. ICML 2026FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
76. ICML 2026From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
77. ICML 2026From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
78. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
79. ICML 2026From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
80. ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
81. ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
82. ICML 2026GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
83. ICML 2026GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
84. ICML 2026GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
85. ICML 2026Grokking Finite-Dimensional Algebra
86. ICML 2026Head-in-Head in Linear Attention
87. ICML 2026HiCI: Hierarchical Construction–Integration for Long-Context Attention
88. ICML 2026Identifying Common Hubs in Multiple Gaussian Graphical Models
89. ICML 2026Identifying Connectivity Distributions from Neural Dynamics Using Flows
90. ICML 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
91. ICML 2026INDEXGUARD: Index-only Backdoor Vetting for Secure Federated PEFT of Large Language Models
92. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
93. ICML 2026Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
94. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
95. ICML 2026L-SR1: Learned Symmetric-Rank-One Preconditioning
96. ICML 2026LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
97. ICML 2026Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging
98. ICML 2026Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
99. ICML 2026Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
100. ICML 2026Learning syntax without semantics: Disentangled tiny language models

FAQ

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

2,273 in total: 282 in 2023, 518 in 2024, 632 in 2025, 841 in 2026.

How many Low-Rank Adaptation papers are at NeurIPS 2026?

NeurIPS 2026 has 269 Low-Rank Adaptation papers, versus 241 the year before.

How many Low-Rank Adaptation papers are at ICLR 2026?

ICLR 2026 has 184 Low-Rank Adaptation papers, versus 152 the year before.

How many Low-Rank Adaptation papers are at ICML 2026?

ICML 2026 has 240 Low-Rank Adaptation papers, versus 136 the year before.

How many Low-Rank Adaptation papers are at CVPR 2026?

CVPR 2026 has 148 Low-Rank Adaptation papers, versus 103 the year before.

Which conference publishes the most Low-Rank Adaptation papers?

NeurIPS, with 781 papers from 2023 to 2026.