Author

Wonseok Shin

Standigm Inc.

h-index 3 Homepage View on Semantic Scholar

We have 1 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

The Visual Information-Guided Sampler (VIG-Sampler), which prioritizes tokens based on their attention to image tokens, and imposes a constraint that penalizes candidate tokens whose image-attention distributions are similar to those of previously selected tokens, thereby increasing the information gain of the decoded...

Insu Lee, Woo-Soon Park, Wonseok Shin et al. · 1 citation