{"total":16,"rows":[{"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":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2602.20062","title":"A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.08239","title":"Linearization Explains Fine-Tuning in Large Language Models","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2606.06647","title":"The Identity Trap in EEG Foundation Models: A Diagnostic Audit","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2511.11293","title":"Toward Scalable Early Cancer Detection: Evaluating EHR-Based Predictive Models Against Traditional Screening Criteria","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2603.17859","title":"VISER: Visually-Informed System for Enhanced Robustness in Iris Presentation Attack Detection","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.10212","title":"Relational Probing: LM-to-Graph Adaptation for Financial Prediction","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.24350","title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.18298","title":"DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG","created":"2026-05-18","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":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}