9 papers
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…
PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
Jaewon Chu, Seunghun Lee, Hyunwoo J. Kim
Large language models (LLMs) have achieved remarkable success across diverse domains, due to their strong instruction-following capabilities. This has led to increasing interest in…
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…
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
Dohoon Lee, Jaehyun Park, Hyunwoo J. Kim +1
Flow and diffusion models have demonstrated strong performance and training stability across various tasks but lack two critical properties of simulation-based methods: freedom of…
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…
Constant Acceleration Flow
Dogyun Park, Sojin Lee, Sihyeon Kim +3
Rectified flow and reflow procedures have significantly advanced fast generation by progressively straightening ordinary differential equation (ODE) flows. They operate under the a…