Jinyoon Kim

University of Virginia · Computer Science

Jinyoon Kim

Learning how robots perceive, act, and interact.

I am a master's student in Computer Science at the University of Virginia, advised by Professor Yen-Ling Kuo. My research connects embodied AI, computer vision, and language, with a focus on part-guided manipulation and long-horizon interactive robotics.

Previously, I studied Computer Science at Penn State University, graduating in 2024. My earlier work explored medical image analysis, self-supervised learning, and uncertainty-aware segmentation.

Curriculum vitae ↗ GitHub ↗ LinkedIn ↗
Jinyoon Kim
Computer Science · M.S. student

Education

University of Virginia

M.S. in Computer Science Current GPA: 3.963 / 4.0

Penn State University

B.S. in Computer Science 2024

University of Virginia

Current research

Ongoing · Simulation research
Part2Action simulation of a Franka Panda robot manipulating a bottle at its neck
Part-guided bottle manipulation.

Part2Action

Part-guided robotic manipulation

  • Enable robots to follow instructions about specific object parts, such as “grasp the bottle at its neck.”
  • Explore how understanding where to interact with an object can guide robot manipulation.
  • Aim to extend part-guided manipulation to human–robot interaction and assistance.

Master's research · Advised by Professor Yen-Ling Kuo

[ code ]

Long-horizon robotics simulation showing RB-Y1 navigation and door interaction
Connecting navigation with door interaction.

Long-horizon interactive robotics

From navigation to physical interaction

  • Study how robots connect navigation with physical interaction in continuous tasks, such as reaching and opening a door.
  • Investigate how robot foundation models can support reliable interaction over longer task sequences.

Ongoing contribution to Link Lab research at the University of Virginia

[ code ]

Selected UVA projects

GPU systems
Spring 2026

Multi-GPU Training for 3D Gaussian Splatting (2026)

Jinyoon Kim · Built on Binh's multi-GPU CLM-GS framework
[ code | original framework ]
  • Explore scalable training of large 3D scenes across multiple GPUs.
  • Combine peer-to-peer sharing, asynchronous gradient reduction, and transfer overlap in a configurable training pipeline.
3D Gaussian Splatting Project

Text-Guided 3D Scene Editing: Volumetric Removal & Generative Addition (2025)

Jinyoon Kim, Sansshita Baskaran, Manvitha Sunireddy [ presentation | code ]
  • Developed an end-to-end pipeline for editing unbounded Mip-NeRF 360 scenes using 3D Gaussian Splatting.
  • Engineered a custom "Occlusion-Aware Lifting" algorithm to bridge 2D semantics (GroundingDINO + SAM 2) with 3D geometry, enabling precise zero-shot object selection.
  • Integrated LaMa for multi-view consistent inpainting (removal) and GaussianDreamer for inserting generative 3D assets (addition), solving the "Artichoke Problem" in volumetric editing.
RL LLM Project

A Reinforcement Learning Pipeline for Financial Reasoning (2025)

Jinyoon Kim, Scarlett Yu, Donggen Li [ report | presentation | code ]
  • Developed a comprehensive ablation study comparing Deep Contextual RL (PPO, GRPO, RLOO, DPO) against Heuristic Bandits for the FinQA task.
  • Engineered a "Discriminative Reranking" pipeline to bypass generation failures, successfully training Llama-3.2-3B and TinyLlama-1.1B models.
  • Demonstrated that RL provides massive gains for weak learners (+35% accuracy on 1B models) while establishing the "SFT Ceiling" effect on capable 3B models.

Prior research · Penn State University

Publications

Penn State University

Earlier projects

Skin Cancer Detection Project

Capstone Project: Skin Cancer Detection Web Application (2024)

Jinyoon Kim, Tianjie Chen, Hien Nguyen, and Md Faisal Kabir [ slides | project code | web app code ]
  • Created an accessible and user-friendly web application for skin cancer detection using YOLOv8.
  • Utilized combined ISIC datasets, implemented confounding factors removal, and incorporated interpretability techniques.
  • Developed a PWA-based web application ensuring wide accessibility and transparent diagnostics through visual interpretability.
Face Recognition Project

Machine Learning Project: Face Recognition Program (2023)

Jinyoon Kim, Aditya Kendre, et al. [ slides | code ]
  • Built a face recognition system focused on high accuracy and effective feature extraction.
  • Developed using a fine-tuned ResNet model and implemented a Top-k features algorithm.
  • Successfully created a model capable of accurately classifying team members via face recognition.
Plant Village Demo Project

Plant Village Demo: ML Classification on Mobile Application (2023)

Jinyoon Kim [ code | video ]
  • Created a mobile application for detecting plant diseases using neural networks.
  • Developed and fine-tuned MobileNet specifically for plant disease detection on mobile devices.
  • The resulting application runs efficiently and accurately classifies plant disease images in a mobile environment.

Awards & honors

Conference highlights

PSU Capstone Conference
Pennsylvania State University Capstone Project Conference 2024. May 1, 2024. I attended the Penn State Capstone Project Conference 2024 as a member of the Capstone Project Team. Thanks to Professor Nguyen, Professor Kabir, and my colleague Tianjie Chen.
ICMLA Conference 2023
IEEE International Conference on Machine Learning and Applications (IEEE ICMLA 2023). December 15, 2023. I attended ICMLA 2023 with the poster of my paper for the presentation. Thanks for Dr. Kabir and everyone I met at the conference. [ieee website]