Taesun Yeom
YOU?
Author Swipe
View article: Activation Quantization of Vision Encoders Needs Prefixing Registers
Activation Quantization of Vision Encoders Needs Prefixing Registers Open
Transformer-based vision encoders -- such as CLIP -- are central to multimodal intelligence, powering applications from autonomous web agents to robotic control. Since these applications often demand real-time processing of massive visual …
View article: Fast Training of Sinusoidal Neural Fields via Scaling Initialization
Fast Training of Sinusoidal Neural Fields via Scaling Initialization Open
Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high training cost, which prevents a broader adoption. In this paper, …
View article: DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion
DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion Open
Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output …
View article: DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion
DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion Open
Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output …
View article: SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains
SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains Open
Image-to-image translation with generative adversarial networks (GANs) has been extensively studied in recent years. Among the models, StarGAN has achieved image-to-image translation for multiple domains with a single generator, whereas co…