Dae Yon Hwang
YOU?
Author Swipe
View article: Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval
Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval Open
Despite the recent advancements in information retrieval (IR), zero-shot IR remains a significant challenge, especially when dealing with new domains, languages, and newly-released use cases that lack historical query traffic from existing…
View article: Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrieval
Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrieval Open
Dense retrieval systems are commonly used for information retrieval (IR). They rely on learning text representations through an encoder and usually require supervised modeling via labelled data which can be costly to obtain or simply unava…
View article: EmbedTextNet: Dimension Reduction with Weighted Reconstruction and Correlation Losses for Efficient Text Embedding
EmbedTextNet: Dimension Reduction with Weighted Reconstruction and Correlation Losses for Efficient Text Embedding Open
The size of embeddings generated by large language models can negatively affect system latency and model size in certain downstream practical applications (e.g. KNN search). In this work, we propose EmbedTextNet, a light add-on network tha…
View article: GAN-LM: Generative Adversarial Network using Language Models for Downstream Applications
GAN-LM: Generative Adversarial Network using Language Models for Downstream Applications Open
In this work, we investigate Data Augmentation methods to improve the performance of state-of-the-art models for four different downstream tasks. Specifically, we propose Generative Adversarial Network using Language Models (GAN-LM) approa…
View article: Hierarchical Deep Learning Model with Inertial and Physiological Sensors Fusion for Wearable-Based Human Activity Recognition
Hierarchical Deep Learning Model with Inertial and Physiological Sensors Fusion for Wearable-Based Human Activity Recognition Open
This paper presents a human activity recognition (HAR) system with wearable devices. While various approaches have been suggested for HAR, most of them focus on either 1) the inertial sensors to capture the physical movement or 2) subject-…
View article: Hierarchical System Schedulability Analysis Framework Using UPPAAL
Hierarchical System Schedulability Analysis Framework Using UPPAAL Open
Analyzing the schedulability of hierarchical real-time systems is difficult because of the systems' complex behavior. It gets more complicated when shared resources or dependencies among tasks are included. This paper introduces a framewor…