Skip to content
View taegyeong-lee's full-sized avatar
86 followers · 71 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Starstruck

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Starstruck

Block or report taegyeong-lee

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
taegyeong-lee/README.md

Taegyeong Lee

Hi, I'm Taegyeong Lee. I'm passionate about novel research on AI Agents and LLM post-training, with a particular focus on building agents that work reliably in real-world systems. I enjoy exploring research that is simple yet effective, leveraging LLMs and generative models to make a strong impact in the real world.

I'm also broadly interested in multimodal generation—especially generating images or videos from audio and text—and in quantitative trading, where I see strong potential for applying multimodal large language models and generative models to quant finance.

I am currently working as a ML Engineer at Miridih, focusing on AI Agents and LLM post-training. Previously, I worked as an AI Researcher at FnGuide, focusing on LLMs and RAG (Retrieval-Augmented Generation). I earned my Master's degree from the UNIST AIGS. I interned at ETRI and completed the Software Maestro 8th. I also served as a software developer in the Promotion Data Management Division at the Republic of Korea Army Headquarters. I hold a Bachelor of Computer Engineering from Pukyong National University.

LinkedIn

[NEWS] Our paper on Negation-aware Retrieval has been accepted to an ACL 2026 Workshop (RAG4REPORT).
[NEWS] I have started working as a ML Engineer at Miri.DIH.
[NEWS] Our paper on prompt guard for safety LLM has been accepted to an ACL 2025 Workshop (Selected as a lightning talk presentation).
[NEWS] I have started working as an AI Researcher at FnGuide.
[NEWS] Our paper on knowledge distillation has been accepted to a CVPR 2025 Workshop.
[NEWS] Our paper on sound-to-image generation has been accepted to ICCV 2023.

Pinned Loading

  1. Generating-Realistic-Images-from-In-the-wild-Sounds Generating-Realistic-Images-from-In-the-wild-Sounds Public

    Official Code Repository for the paper "Generating Realistic Images from In-the-wild Sounds", ICCV 2023

    Jupyter Notebook 12 1

  2. MaKD-Multi-aspect-knowledge-distillation-with-Large-Language-Model MaKD-Multi-aspect-knowledge-distillation-with-Large-Language-Model Public

    Official Code Repository for the paper, Multi-aspect knowledge distillation with Large Language Model, CVPRW 2025

    Python 4

  3. QGuard-Question-based-Zero-shot-Guard-for-Multi-modal-LLM-Safety QGuard-Question-based-Zero-shot-Guard-for-Multi-modal-LLM-Safety Public

    QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety, ACL 2025 Workshop

    Python 7 1

  4. DEO-negation-aware-retrieval DEO-negation-aware-retrieval Public

    DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval, ACL 2026 Workshop RAG4REPORT

    Python 6