Sang Min Kim

I am a Ph.D. student in Electrical and Computer Engineering at Seoul National University, advised by Prof. Young Min Kim, and I am currently a visiting student at the MIT Biomimetic Robotics Lab, hosted by Prof. Sangbae Kim.

My research goal is generalizable manipulation. I believe each stage—from perception to control—offers problems that are easier to solve on its own terms, and generalization comes from weaving these solutions together across the full pipeline. Rather than specializing in a single stage, I want to be a generalist who spans the whole pipeline to build robots that manipulate reliably across novel objects, tasks, and environments.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo

News

  • [June 2026] One paper accepted to RSS 2026 @ SemRob workshop!
  • [June 2026] One paper accepted to IROS 2026!
  • [Apr 2026] Started as a visiting student at MIT Biomimetic Robotics Lab, hosted by Prof. Sangbae Kim!
  • [Jan 2026] One paper accepted to ICRA 2026!
  • [Sep 2025] One paper accepted to NeurIPS 2025!
  • [Jul 2024] One paper accepted to ECCV 2024!
  • [Nov 2023] One paper accepted to RA-L!
  • [Jul 2023] One paper accepted to Pacific Graphics 2023!
  • [Feb 2023] One paper accepted to CVPR 2023!

Research
INGRID: interactive geometry and instance identification for occluded scenes

INGRID: Interactive Geometry and Instance Identification for Occluded Scenes


Junho Lee, Sang Min Kim, Yonghyeon Lee, Young Min Kim
Robotics: Science and Systems (RSS) @ SemRob Workshop, 2026
project page / paper

AnyCamVLA: zero-shot camera adaptation for viewpoint-robust vision-language-action models

AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models


Hyeongjun Heo, Seungyeon Woo, Sang Min Kim, Junho Kim, Junho Lee, Yonghyeon Lee, Young Min Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
project page / paper

Point2Act: robot grasping guided by 3D relevancy fields distilled from multimodal LLMs

Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Grasping


Sang Min Kim, Hyeongjun Heo, Junho Kim, Yonghyeon Lee, Young Min Kim
ICRA, 2026
project page / paper / code

EUGens: efficient, unified and general dense layers

EUGens: Efficient, Unified and General Dense Layers


Sang Min Kim*, Byeongchan Kim*, Arijit Sehanobish*, Somnath Basu Roy Chowdhury*, Rahul Kidambi*, Dongseok Shim, Avinava Dubey*, Snigdha Chaturvedi, Min-hwan Oh, Krzysztof Choromanski*
(*Equal contribution)
NeurIPS, 2025
paper / code

I2-SLAM: photorealistic dense SLAM by inverting the imaging process

I2-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM


Gwangtak Bae*, Changwoon Choi*, Hyeongjun Heo, Sang Min Kim, Young Min Kim
(*Equal contribution)
ECCV, 2024
project page / paper

NFL: normal field learning for 6-DoF grasping of transparent objects

NFL: Normal Field Learning for 6-DoF Grasping of Transparent Objects


Junho Lee, Sang Min Kim, Yonghyeon Lee, Young Min Kim
RA-L, 2023
project page / paper / video

Robust novel view synthesis with color transform module

Robust Novel View Synthesis with Color Transform Module


Sang Min Kim, Changwoon Choi, Hyeongjun Heo, Young Min Kim
Computer Graphics Forum (Proceedings of Pacific Graphics), 2023
project page / paper / code

EgoNeRF: balanced spherical grid for egocentric view synthesis

Balanced Spherical Grid for Egocentric View Synthesis


Changwoon Choi, Sang Min Kim, Young Min Kim
CVPR, 2023
project page / code / arXiv

Misc
Minicraft: ray-traced Minecraft clone

Minicraft: ray-tracing version of minecraft


Graphics Programming, SNU, Fall 2022
video

Clone the minecraft with OpenGL. Implement the ray-tracing acceleration algorithm(3D DDA).
🧩

Nonogram Puzzle


Mini game
play

A browser-based nonogram (picross) puzzle game with 15 puzzles ranging from Beginner to Expert difficulty. Fill in the grid guided by row and column clues to reveal the hidden picture.

This template is a modification to Jon Barron's website. Find the source code to my version here. Feel free to clone it for your own use while attributing the original author Jon Barron.