Hyoung-Kyu Song's picture

Hyoung-Kyu Song

deepkyu

·

https://linktr.ee/deepkyu

AI & ML interests

Efficient model for image/video generation

Recent Activity

upvoted a paper about 2 months ago

Latent Diffusion Model without Variational Autoencoder

upvoted a paper about 2 months ago

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

liked a dataset about 2 months ago

QingyanBai/Ditto-1M

View all activity

Organizations

authored a paper 6 months ago

Seeing Voices: Generating A-Roll Video from Audio with Mirage

Paper • 2506.08279 • Published Jun 9 • 27

authored 3 papers over 1 year ago

EdgeFusion: On-Device Text-to-Image Generation

Paper • 2404.11925 • Published Apr 18, 2024 • 23

LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights

Paper • 2404.11936 • Published Apr 18, 2024 • 1

LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping

Paper • 2402.18351 • Published Feb 28, 2024 • 2

authored a paper almost 2 years ago

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Paper • 2402.02834 • Published Feb 5, 2024 • 17

authored 3 papers over 2 years ago

On Architectural Compression of Text-to-Image Diffusion Models

Paper • 2305.15798 • Published May 25, 2023 • 4

A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation

Paper • 2304.00471 • Published Apr 2, 2023 • 1

Talking Face Generation with Multilingual TTS

Paper • 2205.06421 • Published May 13, 2022