52 citations · 73 across the 14 of their papers we have counts for
16 papers
Dynamic HBM Repartitioning for Multi-Turn MoE Serving
Jinpyo Kim, Mingi Kwon, Younghoon Min +2
Long-running multi-turn requests accumulate reusable key-value (KV) state. Once this state exceeds a fixed GPU KV-cache allocation, serving systems evict reusable prefixes, repeat…
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
Jibin Song, Mingi Kwon, Jaeseok Jeong +1
In this work, we show that the impact of model capacity varies across timesteps: it is crucial for the early and late stages but largely negligible during the intermediate stage. A…
Balanced conic rectified flow
Shin Seong Kim, Mingi Kwon, Jaeseok Jeong +1
Rectified flow is a generative model that learns smooth transport mappings between two distributions through an ordinary differential equation (ODE). Unlike diffusion-based generat…
Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers
Jibin Song, Mingi Kwon, Jaeseok Jeong +1
Text-to-video and image-to-video generation have made rapid progress in visual quality, but they remain limited in controlling the precise timing of motion. In contrast, audio prov…
TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNet
Jaeseok Jeong, Yuna Lee, Mingi Kwon +1
Recent advances in text-to-speech (TTS) have enabled natural speech synthesis, but fine-grained, time-varying emotion control remains challenging. Existing methods often allow only…
JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
Mingi Kwon, Joonghyuk Shin, Jaeseok Jung +2
The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as sep…
TCFG: Tangential Damping Classifier-free Guidance
Mingi Kwon, Shin seong Kim, Jaeseok Jeong. Yi Ting Hsiao +1
Diffusion models have achieved remarkable success in text-to-image synthesis, largely attributed to the use of classifier-free guidance (CFG), which enables high-quality, condition…
HARIVO: Harnessing Text-to-Image Models for Video Generation
Mingi Kwon, Seoung Wug Oh, Yang Zhou +6
We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training tem…
Plug-and-Play Diffusion Distillation
Yi-Ting Hsiao, Siavash Khodadadeh, Kevin Duarte +4
Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guidance, infe…
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
Yixuan Ren, Yang Zhou, Jimei Yang +5
Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V)…
Attribute Based Interpretable Evaluation Metrics for Generative Models
Dongkyun Kim, Mingi Kwon, Youngjung Uh
When the training dataset comprises a 1:1 proportion of dogs to cats, a generative model that produces 1:1 dogs and cats better resembles the training species distribution than ano…
Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry
Yong-Hyun Park, Mingi Kwon, Jaewoong Choi +2
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space. To understand the latent space , we analy…
Training-free Content Injection using h-space in Diffusion Models
Jaeseok Jeong, Mingi Kwon, Youngjung Uh
Diffusion models (DMs) synthesize high-quality images in various domains. However, controlling their generative process is still hazy because the intermediate variables in the proc…
Unsupervised Discovery of Semantic Latent Directions in Diffusion Models
Yong-Hyun Park, Mingi Kwon, Junghyo Jo +1
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space. While image editing with GANs builds upon latent space, DMs rely on edi…
Diffusion Models already have a Semantic Latent Space
Mingi Kwon, Jaeseok Jeong, Youngjung Uh
Diffusion models achieve outstanding generative performance in various domains. Despite their great success, they lack semantic latent space which is essential for controlling the…
FurryGAN: High Quality Foreground-aware Image Synthesis
Jeongmin Bae, Mingi Kwon, Youngjung Uh
Foreground-aware image synthesis aims to generate images as well as their foreground masks. A common approach is to formulate an image as an masked blending of a foreground image a…