Seongmin Lee

Orcid: 0000-0002-1950-5004

Affiliations:
  • Georgia Institute of Technology, Atlanta, GA, USA


According to our database1, Seongmin Lee authored at least 24 papers between 2022 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety.
CoRR, June, 2025

Shape it Up! Restoring LLM Safety during Finetuning.
CoRR, May, 2025

TRANSFORMER EXPLAINER: Interactive Learning of Text-Generative Models.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

LLM Attributor: Interactive Visual Attribution for LLM Generation.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
VG: Automatic Grading of D3 Visualizations.
IEEE Trans. Vis. Comput. Graph., January, 2024

LLM Hallucination Reasoning with Zero-shot Knowledge Test.
CoRR, 2024

ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing.
CoRR, 2024

UniTable: Towards a Unified Framework for Table Structure Recognition via Self-Supervised Pretraining.
CoRR, 2024

Self-Supervised Pre-Training for Table Structure Recognition Transformer.
CoRR, 2024

Point and Instruct: Enabling Precise Image Editing by Unifying Direct Manipulation and Text Instructions.
CoRR, 2024

Mobile Fitting Room: On-device Virtual Try-on via Diffusion Models.
CoRR, 2024

Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion.
Proceedings of the IEEE Visualization and Visual Analytics, 2024

Interactive Visual Learning for Stable Diffusion.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks.
Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 2024

Effective Guidance for Model Attention with Simple Yes-no Annotations.
Proceedings of the IEEE International Conference on Big Data, 2024

2023
High-Performance Transformers for Table Structure Recognition Need Early Convolutions.
CoRR, 2023

VisGrader: Automatic Grading of D3 Visualizations.
CoRR, 2023

Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

2022
Explaining Website Reliability by Visualizing Hyperlink Connectivity.
CoRR, 2022

NOVA: A Practical Method for Creating Notebook-Ready Visual Analytics.
CoRR, 2022

ConceptEvo: Interpreting Concept Evolution in Deep Learning Training.
CoRR, 2022

Explaining Website Reliability by Visualizing Hyperlink Connectivity.
Proceedings of the 2022 IEEE Visualization and Visual Analytics (VIS), 2022

VIsCUIT: Visual Auditor for Bias in CNN Image Classifier.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

MisVis: Explaining Web Misinformation Connections via Visual Summary.
Proceedings of the CHI '22: CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA, 29 April 2022, 2022


  Loading...