{"total":20,"rows":[{"id":"2410.02724","title":"Large Language Models as Markov Chains","created":"2024-10-03","cited_by_count":35,"area":null},{"id":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"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":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2512.18248","title":"On the Convergence Rate of LoRA Gradient Descent","created":"2025-12-20","cited_by_count":10,"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":"2505.14808","title":"Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2410.21262","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2502.11152","title":"Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2508.20344","title":"Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization","created":"2025-08-28","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":"2605.06117","title":"BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification","created":"2026-05-07","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":"2508.10435","title":"Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.27739","title":"Worker Disagreement Reveals Sharp Directions in Local SGD","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.16637","title":"TopoTuner: Topological Finetuning of Large Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.26430","title":"Fine-Tuning of Transformer models with Frames","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}