Hyoung-Kyu Song's picture

Hyoung-Kyu Song PRO

deepkyu

·

https://linktr.ee/deepkyu

AI & ML interests

Efficient model for image/video generation

Organizations

deepkyu's activity

upvoted 2 papers 13 days ago

GPT-4o System Card

Paper • 2410.21276 • Published 18 days ago • 77

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Paper • 2410.20280 • Published 17 days ago • 21

upvoted a paper 25 days ago

Movie Gen: A Cast of Media Foundation Models

Paper • 2410.13720 • Published 26 days ago • 86

upvoted 2 papers 27 days ago

What Matters in Transformers? Not All Attention is Needed

Paper • 2406.15786 • Published Jun 22 • 28

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

Paper • 2410.11795 • Published 28 days ago • 16

upvoted a paper 28 days ago

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Paper • 2410.10306 • Published 30 days ago • 51

upvoted 2 papers 29 days ago

Progressive Autoregressive Video Diffusion Models

Paper • 2410.08151 • Published Oct 10 • 15

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published Oct 11 • 83

upvoted a paper about 1 month ago

Pyramidal Flow Matching for Efficient Video Generative Modeling

Paper • 2410.05954 • Published Oct 8 • 37

upvoted a paper 2 months ago

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Paper • 2409.02634 • Published Sep 4 • 89

upvoted a paper 3 months ago

Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields

Paper • 2408.03822 • Published Aug 7 • 9

upvoted 8 papers 4 months ago

Wolf: Captioning Everything with a World Summarization Framework

Paper • 2407.18908 • Published Jul 26 • 30

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation

Paper • 2407.17438 • Published Jul 24 • 23

SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

Paper • 2407.17470 • Published Jul 24 • 14

ViPer: Visual Personalization of Generative Models via Individual Preference Learning

Paper • 2407.17365 • Published Jul 24 • 11

VILA^2: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24 • 38

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

Paper • 2407.06938 • Published Jul 9 • 21

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Paper • 2406.06525 • Published Jun 10 • 64

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Paper • 2407.01392 • Published Jul 1 • 39

upvoted a paper 7 months ago

Pegasus-v1 Technical Report

Paper • 2404.14687 • Published Apr 23 • 30