Author

Hongyeob Kim

1 paper indexed here

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

Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs

This work proposes A-PACK, a two-stage framework that defers audio pruning until query-conditioned multimodal interactions emerge inside the LLM, and shows that audio exhibits higher task-relevant information density and representational diversity per token than video.

Kyeong-Jae Lee, Hongyeob Kim, Youngeun Kim et al. · 2 citations