{"total":103,"rows":[{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463,"area":null},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161,"area":null},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"area":null},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45,"area":null},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":20,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2509.11983","title":"Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training","created":"2025-09-15","cited_by_count":18,"area":null},{"id":"2502.01755","title":"Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2410.15352","title":"CompAct: Compressed Activations for Memory-Efficient LLM Training","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2407.05417","title":"See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition","created":"2024-07-07","cited_by_count":14,"area":null},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2408.10280","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2602.17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2507.02503","title":"Continual Gradient Low-Rank Projection Fine-Tuning for LLMs","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.18877","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2412.19820","title":"GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2605.06884","title":"Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2502.01378","title":"CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2409.16722","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2510.00444","title":"TokMem: One-Token Procedural Memory for Large Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2502.06820","title":"LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2601.17261","title":"AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning","created":"2026-01-24","cited_by_count":4,"area":null},{"id":"2409.17538","title":"LoRA Provides Differential Privacy by Design via Random Sketching","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2410.15858","title":"Towards Optimal Adapter Placement for Efficient Transfer Learning","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2505.14238","title":"ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2601.21929","title":"LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2608.20442","title":"Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2406.09041","title":"ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2506.02939","title":"QKV Projections Require a Fraction of Their Memory","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.15588","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2509.25214","title":"On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.03691","title":"REG: A Regularization Optimizer for Robust Training Dynamics","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2601.22708","title":"A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.01746","title":"Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.03019","title":"FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2502.13811","title":"On the Duality between Gradient Transformations and Adapters","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2503.19530","title":"VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2505.01744","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2505.12318","title":"Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.18777","title":"HD-PiSSA: High-Rank Distributed Orthogonal Adaptation","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2506.01897","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.00192","title":"Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.23818","title":"ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2510.26690","title":"LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.11396","title":"MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2609.00762","title":"Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2410.19694","title":"Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs","created":"2024-10-25","cited_by_count":0,"area":null},{"id":"2501.06332","title":"Aggregating Low Rank Adapters in Federated Fine-tuning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2505.18313","title":"PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.03402","title":"Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.01233","title":"Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.05204","title":"Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.14751","title":"Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.21901","title":"GiVA: Gradient-Informed Bases for Vector-Based Adaptation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.24103","title":"Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.07111","title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.12207","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13652","title":"Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.26290","title":"SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.15665","title":"SubZero+: Memory-Efficient Adaptive Zeroth-Order LLM Fine-Tuning in Random Subspaces","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2610.06621","title":"Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06647","title":"LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":"100"}