1 citations · 1 across the 12 of their papers we have counts for
7 papers · 1 filter
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
Dogyun Park, Taehoon Lee, Minseok Joo +1
Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the…
Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
Dogyun Park, Moayed Haji-Ali, Yanyu Li +5
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively exp…
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
Yujin Kim, Hyunsoo Kim, Hyunwoo J. Kim +1
Open-source pre-trained models hold great potential for diverse applications, but their utility declines when their training data is unavailable. Data-Free Image Synthesis (DFIS) a…
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao +14
Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge…
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
Sojin Lee, Dogyun Park, Inho Kong +1
Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using d…
Learning Equi-angular Representations for Online Continual Learning
Minhyuk Seo, Hyunseo Koh, Wonje Jeung +7
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e.g., single-epoch training). To address the challenge, we prop…
Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
Juyeon Ko, Inho Kong, Dogyun Park +1
Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user…