[Articles] PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask

Developed PromptDresser, a powerful virtual clothing tool with distinctive masking techniques.

[Articles] Reversible Instance Normalization for Accurate Time-Series Forecasting Against Distribution Shift

An overview of RevIN, a simple yet effective normalization method that tackles the distribution shift problem in time-series forecasting by reversibly removing and restoring instance-level statistics, significantly improving the accuracy of existing models.

[Articles] StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

An overview of StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.

[Articles] Improving Language-Understanding by Generative Pre-Training

Introducing Generative Pre-Training (GPT) model.

[Articles] Robust deep learning-based protein sequence design using ProteinMPNN

ProteinMPNN, a powerful deep learning tool for protein designing.