Kyu Song PRO

deepkyu

·

https://deepkyu.me

AI & ML interests

Efficient model for image/video generation

Recent Activity

upvoted a paper about 16 hours ago

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

upvoted a paper about 16 hours ago

WorldReward: Reward Modeling for Camera-Conditioned World Models

upvoted a paper about 16 hours ago

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

View all activity

Organizations

deepkyu 's Spaces 3

compact-theme

compact-theme

Multilingual Font Style Transfer