Su Ho Han

ciplabhan

3

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

upvoted a paper 7 months ago

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

updated a dataset 8 months ago

CIPLab-Video/DecAF_output

View all activity

Organizations

upvoted a paper 10 days ago

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Paper • 2606.29513 • Published 14 days ago • 52

upvoted a paper 7 months ago

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Paper • 2510.19592 • Published Oct 22, 2025 • 13

updated a dataset 8 months ago

CIPLab-Video/DecAF_output

Updated Jun 10, 2025 • 7

upvoted a paper about 1 year ago

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Paper • 2507.07990 • Published Jul 10, 2025 • 45

updated a model over 1 year ago

ciplabhan/RVOSOriginal_ckpt

Updated Feb 17, 2025

published 2 models over 1 year ago

ciplabhan/RVOSOriginal_ckpt

Updated Feb 17, 2025

ciplabhan/RVOSBaseline_ckpt

Updated Feb 14, 2025

updated a model over 1 year ago

ciplabhan/RVOSBaseline_ckpt

Updated Feb 14, 2025