Yejin Kim

Domain Switch-Aware Holistic Recurrent Neural Network for Modeling Multi-Domain User Behavior

2019

Understanding user behavior and predicting future behavior on the web is critical for providing seamless user experiences as well as increasing revenue of service providers. Recently, thanks to the remarkable success of recurrent neural networks …

Noise Improves Noise: Verification of Pre-Training Effect with Weakly Labeled Data on Social Media NER

2020

Recently, we are living in a flood of social media data. As the cost of data-annotating is too expensive, there is not much data annotated for natural language processing tasks. The purpose of our experiment …

Prompts have evil twins

2023 · arXiv (Cornell University)

We discover that many natural-language prompts can be replaced by corresponding prompts that are unintelligible to humans but that provably elicit similar behavior in language models. We call these prompts "evil twins" because they are …

Fast and Reliable Myelin Water Fraction Estimation Using Neural Network Informed Non-Linear Least Squares Fitting

2025 · Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition

Motivation: Non-Linear Least Squares (NLLS) is commonly used for fitting data in Myelin Water Fraction (MWF) imaging but suffers from slow fitting times and sensitivity to experimental factors. Goal(s): To accelerate and improve the performance …

Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective

2025 · arXiv (Cornell University)

In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, there has been growing interest in focusing on representation forgetting, the forgetting …

Convolutional Matrix Factorization for Document Context-Aware Recommendation

2016

Sparseness of user-to-item rating data is one of the major factors that deteriorate the quality of recommender system. To handle the sparsity problem, several recommendation techniques have been proposed that additionally consider auxiliary information to …

Collaborative Translational Metric Learning

2018

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue, existing approaches typically project each user …