{"total":64,"rows":[{"id":"2411.19557","title":"Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning","created":"2024-11-29","cited_by_count":22,"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":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20,"area":null},{"id":"2505.23194","title":"Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2505.21289","title":"LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning","created":"2025-05-27","cited_by_count":14,"area":null},{"id":"2501.13669","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","created":"2025-01-23","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":"2502.14538","title":"LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization","created":"2025-02-20","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":"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":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2507.06558","title":"The Primacy of Magnitude in Low-Rank Adaptation","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2501.18475","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","created":"2025-01-30","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":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2602.09009","title":"ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2410.17222","title":"Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2510.24561","title":"LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","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":"2508.19564","title":"Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2502.08905","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","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":"2602.11171","title":"A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2501.06954","title":"A Hessian-informed hyperparameter optimization for differential learning rate","created":"2025-01-12","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":"2510.23818","title":"ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2510.25784","title":"zFLoRA: Zero-Latency Fused Low-Rank Adapters","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2512.17344","title":"Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.09689","title":"Model soups need only one ingredient","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.29824","title":"Curvature-Guided LoRA: Matching Full Fine-Tuning in Function Space","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.26388","title":"SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2606.16454","title":"SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.28932","title":"DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.02576","title":"CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2412.10362","title":"OP-LoRA: The Blessing of Dimensionality","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2507.18076","title":"Hybrid and Unitary PEFT for Resource-Efficient Large Language Models","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2601.21722","title":"Enhancing Language Models for Robust Greenwashing Detection","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.01267","title":"Diving into Kronecker Adapters: Component Design Matters","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.07479","title":"ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.16456","title":"Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.17051","title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","created":"2026-04-18","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":"2605.08174","title":"CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08734","title":"AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.29460","title":"FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.10196","title":"Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.14970","title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.31717","title":"Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.16252","title":"SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2609.02734","title":"LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.05885","title":"One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.34218","title":"Loop Dropout: Regularizing Shared Updates in Looped Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34449","title":"CORTEX: Learning to Share and Specialize in Dense Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04507","title":"LoRA's Second Descent Extends Beyond Parameter Parity","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07553","title":"Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.17730","title":"DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19700","title":"ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}