Kyu Song

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

Introduces Mirage, a diffusion-based model that generates realistic talking-head video directly from audio input, enabling scalable A-roll video creation.

BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion

Distills compact Stable Diffusion variants that achieve 30–50% faster and smaller, more cost-efficient inference without sacrificing image quality, including deployment on NVIDIA Jetson devices.

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

Proposes a task-agnostic pruning method for latent diffusion models, achieving efficient compression without retraining on specific downstream tasks.

EdgeFusion: On-Device Text-to-Image Generation

Demonstrates subsecond text-to-image generation on smartphone by combining model compression techniques including knowledge distllation, step distillation, and quantization.

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Presents a straightforward depth pruning strategy for LLMs that removes entire transformer layers, yielding smaller models with minimal performance loss.

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

Unifies pruning, quantization, and knowledge distillation into a single framework to compress talking-face generation models for real-time inference.

Talking Face Generation with Multilingual TTS

Combines multilingual text-to-speech with lip-synced face generation, enabling talking-face videos in multiple languages from a single text input.

Deep User Identification Model with Multiple Biometric Data

Proposes a deep learning model that fuses multiple biometric signals for robust user identification, outperforming single-modality baselines.