4 papers
Seeing What You Say: Expressive Image Generation from Speech
Jiyoung Lee, Song Park, Sanghyuk Chun +1
This paper proposes VoxStudio, the first unified and end-to-end speech-to-image model that generates expressive images directly from spoken descriptions by jointly aligning linguis…
Probabilistic Language-Image Pre-Training
Sanghyuk Chun, Wonjae Kim, Song Park +1
Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and…
DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias
Song Park, Sanghyuk Chun, Byeongho Heo +1
This paper argues that deep neural networks (DNNs) mostly determine their outputs during the early stages of inference, where biases inherent in the model play a crucial role in sh…
Rotary Position Embedding for Vision Transformer
Byeongho Heo, Song Park, Dongyoon Han +1
Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domain…