{"total":29,"rows":[{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"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":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2507.12142","title":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2510.10777","title":"Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","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":"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":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2505.05409","title":"Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2511.00051","title":"Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT","created":"2025-10-28","cited_by_count":4,"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":"2605.31484","title":"Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2507.05566","title":"SingLoRA: Low Rank Adaptation Using a Single Matrix","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2606.29176","title":"Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"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":"2606.16454","title":"SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2608.14492","title":"Approximate Muon with low-rank adapters","created":"2026-08-14","cited_by_count":1,"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":"2605.08734","title":"AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.00944","title":"PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.05136","title":"The Loss Does Not See the Basis, but Adam Does","created":"2026-08-05","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":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.34264","title":"Rotated Manifold Optimization for Low-Rank Adaptation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}