{"total":35,"rows":[{"id":"2512.18248","title":"On the Convergence Rate of LoRA Gradient Descent","created":"2025-12-20","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":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2510.21223","title":"Model Merging with Functional Dual Anchors","created":"2025-10-24","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":"2505.14238","title":"ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models","created":"2025-05-20","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":"2606.05899","title":"High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2510.21078","title":"Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data","created":"2025-10-24","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":"2602.02855","title":"When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.19018","title":"LoRA vs. Full Fine-Tuning: A Theoretical Perspective","created":"2026-05-18","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":"2511.19145","title":"Activation Boundary Matching: Task-Informed Initialization for Low-Rank Adaptation","created":"2025-11-24","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":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","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":"2607.21975","title":"On the Convergence of Stochastic Low-Rank Adaptation","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2509.04398","title":"IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation","created":"2025-09-04","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":"2604.08368","title":"SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization","created":"2026-04-09","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":"2605.08734","title":"AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.26247","title":"Between Gradient and Natural Gradient: A Continuum of LoRA Initializations","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.02639","title":"TaRA: Training-Aware Low-Rank Adaptation Initialization","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04715","title":"PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.34667","title":"Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37027","title":"Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition","created":"2026-09-29","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":"2610.19700","title":"ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}