{"total":18,"rows":[{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","cited_by_count":11,"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":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2506.14280","title":"Improving LoRA with Variational Learning","created":"2025-06-17","cited_by_count":5,"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":"2606.03723","title":"Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2604.04516","title":"GAIN: Multiplicative Modulation for Domain Adaptation","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2606.10488","title":"5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"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":"2602.07479","title":"ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2605.08177","title":"Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection","created":"2026-05-05","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":"2605.29580","title":"On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.36329","title":"Reducing the Adaptation Gap Through Reachable Fisher Geometry","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}