Research Interest — P: preprint, J: journal, C: conference/workshop, A: abstract 

I am currently interested in neural network compression (e.g., pruning [C15, C14, C12, P3, C11, C10, C9], knowledge distillation [C15, C14, C13, C11, C10], quantization [C13, C10]).

My research interests are in the areas of machine learning to process:

Publication — IF: impact factor (JCR 2022 release)

2024

[C15] BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion [PAPER] [CODE] 

[P3] Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods [PAPER] [CODE]

[C14] LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights [PAPER]

[C13] EdgeFusion: On-Device Text-to-Image Generation [PAPER]

[C12] Shortened LLaMA: A Simple Depth Pruning for Large Language Models [PAPER] 

2023

[C11] BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation [PAPER] [DEMO] [POSTER]


[C10] A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation [PAPER] [DEMO] [SLIDE] [POSTER]

2022

[J8] Self-supervised RGB-NIR Fusion Video Vision Transformer Framework for rPPG Estimation [PAPER]

[C9] Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs [PAPER] [SLIDE] [POSTER] [VIDEO]

2021

[J7] Unsupervised Multi-Sense Language Models for Natural Language Processing Tasks [PAPER] [CODE]

2020

[P1] Semi-supervised Disentanglement with Independent Vector Variational Autoencoders [PAPER] [CODE]

2019

[Thesis] Learning-Based Image Synthesis with Disentangled Representations [THESIS] [SLIDE: PhD Defense] [SLIDE: Grad Research Portfolio]

[J6] Style-Controlled Synthesis of Clothing Segments for Fashion Image Manipulation [PAPER] [CODE]

[J5] Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition [PAPER] [CODE]

[A8] Feature Disentanglement and Top-Down Attention for Emotional Conversational Agents [LINK]

2017

[C8] Compositional Sentence Representation from Character within Large Context Text [PAPER] [CODE]

2016

[C7] Fusing Aligned and Non-Aligned Face Information for Automatic Affect Recognition in the Wild: A Deep Learning Approach [PAPER]

[J4] Hierarchical Committee of Deep Convolutional Neural Networks for Robust Facial Expression Recognition [PAPER] [CODE] [DEMO] [MEDIA]

[J3] EEG-based Classification of Implicit Intention during Self-relevant Sentence Reading [PAPER] [DEMO]

[J2] Implicit Agreeing/Disagreeing Intention while Reading Self-relevant Sentences: A Human fMRI Study [PAPER]

[A7] Hierarchical Committee and Top-Down Attention for Robust Classification: Cases for Emotional Facial Expression and Noisy Speech Recognition [LINK]

[A6] An EEG Study on Human Trust in Machine [LINK]

2015

[C6] Hierarchical Committee of Deep CNNs with Exponentially-Weighted Decision Fusion for Static Facial Expression Recognition [PAPER] [CODE]

[J1] Hierarchical Feature Extraction by Multi-layer Non-negative Matrix Factorization Network for Classification Task [PAPER]

[C5] A Preliminary Study on Human Trust Measurements by EEG for Human-Machine Interactions [PAPER]

[A5] Emergent Situation Classification with Environmental Sound [LINK]

[A4] Electrophysiological Correlates of Reasoning during a Theory-of-mind Game [LINK]

2014

[C4] Color Image Processing based on Nonnegative Matrix Factorization with Convolutional Neural Network [PAPER]

[A3] Understanding Shopper’s True Intention from Conversational Dialogue between Salesperson and Shopper [LINK]

2013

[C3] Spectral Feature Extraction Using dNMF for Emotion Recognition in Vowel Sounds [PAPER]

[C2] Decoding and Predicting Implicit Agreeing/Disagreeing Intention Based on Electroencephalography (EEG) [PAPER]

2012

[C1] Trust and Equity Theory in Prisoner's Dilemma [PAPER]

[A2] Social Interaction between Intelligent Individuals and Spontaneous Cooperation [LINK]

[A1] Discriminant Feature Extraction Based on Nonnegative Matrix Factorization for BCI System [LINK]