1 citations · 1 across the 4 of their papers we have counts for
4 papers
Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling
Sanghyeok Chu, Pyunghwan Ahn, Gwangmo Song +3
Sparse Upcycling provides an efficient way to initialize a Mixture-of-Experts (MoE) model from pretrained dense weights instead of training from scratch. However, since all experts…
Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
Youngtaek Oh, Pyunghwan Ahn, Jinhyung Kim +4
Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in l…
Story Visualization by Online Text Augmentation with Context Memory
Daechul Ahn, Daneul Kim, Gwangmo Song +4
Story visualization (SV) is a challenging text-to-image generation task for the difficulty of not only rendering visual details from the text descriptions but also encoding a long-…
L-Verse: Bidirectional Generation Between Image and Text
Taehoon Kim, Gwangmo Song, Sihaeng Lee +6
Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalability. Especially…