Minki Hong

Minki Hong

AI Researcher at SK Telecom, working on sovereign AI model development with interests in generative AI, multimodal reasoning, and socially aware AI.

Posts by Tags

CMU

Conference

EACL 2026 (Findings) paper accepted! 🎉

1 minute read

Published:

Excited to share that our paper, “VisDoT: Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought,” has been accepted to EACL 2026 (Findings)! 🎉

IASEAI 2026 paper accepted! 🎉

1 minute read

Published:

Excited to share that our paper, “Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models,” has been accepted to IASEAI 2026! 🎉

🎉 SAC Highlights at EMNLP 2025 🎉

1 minute read

Published:

I’m honored to share that I presented my first paper at EMNLP2025, the very conference where I first read the paper that sparked my journey into AI research: “SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization.” Starting from the concepts introduced in SODA, I eventually delved into the research area of social norm dialogue, which became the foundation of my current work. It was truly meaningful to come full circle and present at the same conference that first inspired me.

EMNLP 2025 paper accepted! 🎉

less than 1 minute read

Published:

Excited to share that our paper, “NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recovery,” has been accepted to the Main Conference of EMNLP 2025! 🎉 This work addresses a key limitation of large language models (LLMs): their inability to adequately reflect social norms and generate high-quality dialogues in low-resource languages.

EACL 2026

EACL 2026 (Findings) paper accepted! 🎉

1 minute read

Published:

Excited to share that our paper, “VisDoT: Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought,” has been accepted to EACL 2026 (Findings)! 🎉

EMNLP 2025

🎉 SAC Highlights at EMNLP 2025 🎉

1 minute read

Published:

I’m honored to share that I presented my first paper at EMNLP2025, the very conference where I first read the paper that sparked my journey into AI research: “SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization.” Starting from the concepts introduced in SODA, I eventually delved into the research area of social norm dialogue, which became the foundation of my current work. It was truly meaningful to come full circle and present at the same conference that first inspired me.

EMNLP 2025 paper accepted! 🎉

less than 1 minute read

Published:

Excited to share that our paper, “NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recovery,” has been accepted to the Main Conference of EMNLP 2025! 🎉 This work addresses a key limitation of large language models (LLMs): their inability to adequately reflect social norms and generate high-quality dialogues in low-resource languages.

Education

Evaluation Metrics

PEEM paper published in IEEE Access!

1 minute read

Published:

I am thrilled to announce that our paper, “PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses,” has been officially published in IEEE Access! 📄

Fairness

New preprint on arXiv! 📄

1 minute read

Published:

Excited to share our new preprint, “Evaluating Demographic Misrepresentation in Image-to-Image Portrait Editing,” now available on arXiv! 📄

Findings

EACL 2026 (Findings) paper accepted! 🎉

1 minute read

Published:

Excited to share that our paper, “VisDoT: Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought,” has been accepted to EACL 2026 (Findings)! 🎉

Foundation Model

Starting Internship at SKT 🚀

less than 1 minute read

Published:

I will be joining SK Telecom (SKT) as an intern from March 16 to June 30, 2026, working on their proprietary foundation model. Excited to contribute to the development of SKT’s in-house foundation model and gain hands-on industry experience! 🎉

IASEAI 2026

IASEAI 2026 paper accepted! 🎉

1 minute read

Published:

Excited to share that our paper, “Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models,” has been accepted to IASEAI 2026! 🎉

IEEE Access

PEEM paper published in IEEE Access!

1 minute read

Published:

I am thrilled to announce that our paper, “PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses,” has been officially published in IEEE Access! 📄

Internship

Starting Internship at SKT 🚀

less than 1 minute read

Published:

I will be joining SK Telecom (SKT) as an intern from March 16 to June 30, 2026, working on their proprietary foundation model. Excited to contribute to the development of SKT’s in-house foundation model and gain hands-on industry experience! 🎉

Preprint

New preprint on arXiv! 📄

1 minute read

Published:

Excited to share our new preprint, “Evaluating Demographic Misrepresentation in Image-to-Image Portrait Editing,” now available on arXiv! 📄

Prompt Engineering

PEEM paper published in IEEE Access!

1 minute read

Published:

I am thrilled to announce that our paper, “PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses,” has been officially published in IEEE Access! 📄

Publication

PEEM paper published in IEEE Access!

1 minute read

Published:

I am thrilled to announce that our paper, “PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses,” has been officially published in IEEE Access! 📄

Robotics

SKT

Starting Internship at SKT 🚀

less than 1 minute read

Published:

I will be joining SK Telecom (SKT) as an intern from March 16 to June 30, 2026, working on their proprietary foundation model. Excited to contribute to the development of SKT’s in-house foundation model and gain hands-on industry experience! 🎉

arXiv

New preprint on arXiv! 📄

1 minute read

Published:

Excited to share our new preprint, “Evaluating Demographic Misrepresentation in Image-to-Image Portrait Editing,” now available on arXiv! 📄