Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimizationby Xinhao Yao, Hongjin Qian, Xiaolin Hu,…
Mitigating Memorization In Language Modelsby Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse,…
Universality in Transfer Learning for Linear Modelsby Reza Ghane, Danil Akhtiamov, Babak HassibiFirst submitted to…
Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Promptsby Minh Le, Chau Nguyen, Huy Nguyen, Quyen…
Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Imagesby Qingyuan Liu, Avideh ZakhorFirst…
TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysisby Ziyang Song, Qingcheng Lu, He Zhu,…
Plug-and-Play Controllable Generation for Discrete Masked Modelsby Wei Guo, Yuchen Zhu, Molei Tao, Yongxin ChenFirst…
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglementby Gaurav Patel, Christopher Sandino, Behrooz Mahasseni, Ellen…
TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Modelsby Zefang Liu, Yinzhu QuanFirst…
Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decompositionby Mariia Drozdova, Vitaliy Kinakh, Yury Belousov,…