JoonHo (Brian) Lee

Blogs

Note: Unless specified under publications, the papers covered by these blogs are not my own work

Unsupervised Domain Adaptation for LiDAR Semantic Segmentation

Semantics and NeRF: Towards 3D Semantic Scene Understanding from images

Vision Langauge Models

MultiModal Generalist Modeling (and embodiment)

Simulators for Autonomous Driving

Pre-training for Robotics

Transformer (attention) architectures in Computer Vision

Random notes

Random Daily Notes

For something less comprehensive than blogs, written faster with less quality.

From LLMs to Data Agents