Seong Jae Hwang

7

Papers

121

Total Citations

Papers (7)

See What You Are Told: Visual Attention Sink in Large Multimodal Models

Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding

EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation

Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation

WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image

Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling