Min-Hung Chen

8

Papers

95

Total Citations

Papers (8)

Hymba: A Hybrid-head Architecture for Small Language Models

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

DoRA: Weight-Decomposed Low-Rank Adaptation

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting