5 papers
Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
Inho Kong, Sojin Lee, Youngjoon Hong +1
Classifier-Free Guidance (CFG) has established the foundation for guidance mechanisms in diffusion models, showing that well-designed guidance proxies significantly improve conditi…
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…
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…
A Comprehensive Survey of Compression Algorithms for Language Models
Seungcheol Park, Jaehyeon Choi, Sojin Lee +1
How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable advances of…
DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
Dogyun Park, Sihyeon Kim, Sojin Lee +1
Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains…