Byung-Kwan Lee's picture

Byung-Kwan Lee

BK-Lee

·

https://sites.google.com/view/byungkwanlee

AI & ML interests

Vision Language Models

Recent Activity

upvoted a paper 3 days ago

OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding

upvoted a paper 3 days ago

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

upvoted a paper 9 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

View all activity

Organizations

BK-Lee 's Spaces 3

Meteor

Generate text and answer questions using images and text

Phantom

Generate text from images and questions

TroL

Generate text descriptions from images and questions