102 citations · 118 across the 9 of their papers we have counts for
10 papers
Reward Sharpness-Aware Fine-Tuning for Diffusion Models
Kwanyoung Kim, Byeongsu Sim
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusi…
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Kwanyoung Kim, Byeongsu Sim
Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing me…
Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI
Won Jun Kim, Hyungjin Chung, Jaemin Kim +3
Gradient-based methods are a prototypical family of explainability techniques, especially for image-based models. Nonetheless, they have several shortcomings in that they (1) requi…
Magnitude and Angle Dynamics in Training Single ReLU Neurons
Sangmin Lee, Byeongsu Sim, Jong Chul Ye
To understand learning the dynamics of deep ReLU networks, we investigate the dynamic system of gradient flow by decomposing it to magnitude and angle $ϕ(t):= π- θ(t)…
Improving Diffusion Models for Inverse Problems using Manifold Constraints
Hyungjin Chung, Byeongsu Sim, Dohoon Ryu +1
Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process. However, the current s…
Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks
Sangmin Lee, Byeongsu Sim, Jong Chul Ye
Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, eve…