Author

Kyeongbo Kong

h-index 1 View on Semantic Scholar

We have 3 of 11 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

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead...

Changwoo Baek, Kyeongbo Kong · 0 citations

Preprint Aug 2026

RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction

RestoreKV is introduced, which complements this selection-based formulation with learned restoration with learned restoration under the same total KV budget, and substantially reduces compression-induced degradation.

Changwoo Baek, Seung-Jun Shin, Kyeongbo Kong · 0 citations

Jul 2026

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs

This work proposes Single-Forward Pruner (SFPruner), a structural reformulation of visual token pruning that embeds redundancy control directly into the scoring space, bypassing the need for iterative combinatorial optimization and achieves redundancy-aware importance selection in a single forward pass.

J. Song, Woohyeong Kim, Kyeongbo Kong · arXiv.org · 0 citations