Skip to content

A0 - Seonghee Lee (shl1027) #172

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shljessie wants to merge 4 commits into
base: main
Choose a base branch
from
Open

A0 - Seonghee Lee (shl1027) #172

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6918822
A0-Adding Seonghee Lee (shl1027) ReadMe File
shljessie Jan 8, 2025
bb79285
update changes to readme
shljessie Jan 8, 2025
085351f
publication fix
shljessie Jan 8, 2025
ffca912
project description add
shljessie Jan 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 56 additions & 0 deletions README-shl1027.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
# Seonghee Lee

## Education
- **Stanford University**
- Master of Science in Computer Science (Focus: AI and HCI), Expected June 2025

## Technical Skills
- **Programming Languages:** Python, JavaScript(React, Typescript, NodeJS), C, C#, C++, HTML/CSS
- **Frameworks and Tools:** PyTorch, TensorFlow, React, Node.js, Docker, Git, OpenCV, Hugging Face Transformers
- **Domains:** Machine Learning, Deep Learning, NLP, Vision, Full-Stack Development

## Professional Experience

### Incoming AI Engineer @NVIDIA
### Microsoft Research | AI Research Intern | HCAIX Group
- Led development of multimodal conversational agents situated in an open space - Published Paper

### Stanford NLP Group | AI Research Assistant
- Fine-tuned large language models for task-specific applications.
- Developed interactive AI prototypes focused on accessibility.

### Cochl.AI | AI Software Engineer Intern
- Designed and deployed audio-based AI prototypes for real-time analysis and enhancement.

## Research Projects
### AltCanvas - Web Based Image Editor for Blind and Visually Impaired Users
- Designed a tile-based image editor integrating Stable Diffusion for generating accessible tactile graphics.
- Conducted three-stage user studies to refine usability and effectiveness for Blind or Visually Impaired (BVI) users.

### Microsoft Research- Multimodal Agents
- Created AI agents for open office spaces using computer vision, speech processing, and generative conversational models.
- Implemented proxemic interaction logic for real-time engagement.

### StyleAligned
- Controlled Image Generation (stable diffusion) and Image Evaluation (segmentation)
- Researched AI-driven tactile pattern evaluation ensuring controlled placement for accessibility.
- Developed algorithms balancing usability and aesthetic constraints in tactile graphics.
## Publications
- "AltCanvas: Enhancing Visual Accessibility through Generative AI," ACM ASSETS 2024.
- "Integrating Multimodal Agents in Shared Spaces: Challenges and Solutions," under review for ACM CHI 2025.
- "StyleAligned: AI-Driven Generation of Tactile Graphics for Accessibility,"
- "IRL Dittos: Embodied Multimodal Agents in Open Spaces"
- **ACM/IEEE CHI 2024 Honorable Mention**
- 'Teach AI How to Code' project recognized for its impact in education and generative AI.
- **ASSETS 2024**
- "AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired People."
## Hobbies
- Cooking! : @shl_eats

## Links
- **GitHub:** [github.com/shljessie](https://github.com/shljessie)
- **Portfolio:** [shljessie.github.io](https://shljessie.github.io/)
- **LinkedIn:** [linkedin.com/in/seonghee-lee/](https://www.linkedin.com/in/seonghee-lee/)

## Contact
- **Email:** shlee@cs.stanford.edu