3 citations · 4 across the 8 of their papers we have counts for
8 papers
AttnMod: Attention-Based New Art Styles
Shih-Chieh Su
We introduce AttnMod, a training-free technique that modulates cross-attention in pre-trained diffusion models to generate novel, unpromptable art styles. The method is inspired by…
Latent Painter
Shih-Chieh Su
Latent diffusers revolutionized the generative AI and inspired creative art. When denoising the latent, the predicted original image at each step collectively animates the formatio…
Channel Decomposition into Painting Actions
Shih-Chieh Su
This work presents a method to decompose a convolutional layer of the deep neural network into painting actions. To behave like the human painter, these actions are driven by the c…
Topical Behavior Prediction from Massive Logs
Shih-Chieh Su
In this paper, we study the topical behavior in a large scale. We use the network logs where each entry contains the entity ID, the timestamp, and the meta data about the activity.…
Summarized Network Behavior Prediction
Shih-Chieh Su
This work studies the entity-wise topical behavior from massive network logs. Both the temporal and the spatial relationships of the behavior are explored with the learning archite…
Large Scale Behavioral Analytics via Topical Interaction
Shih-Chieh Su
We propose the split-diffuse (SD) algorithm that takes the output of an existing dimension reduction algorithm, and distributes the data points uniformly across the visualization s…