activity
20242026
most citedDS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries

2 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV2026

SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders

Seunghyun Lee, Byoungkwon Kim, Jaehyun Nam +2

The rapid advancement of generative models has blurred the boundary between synthetic and real imagery, creating an urgent need for reliable deepfake detection. Yet most existing a…

cs.AI2026

DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen +3

While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring…

cs.CL2025

Training Text-to-Molecule Models with Context-Aware Tokenization

Seojin Kim, Hyeontae Song, Jaehyun Nam +1

Recently, text-to-molecule models have shown great potential across various chemical applications, e.g., drug-discovery. These models adapt language models to molecular data by rep…

cs.LG2025

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen +3

Agents based on large language models (LLMs) for machine learning engineering (MLE) can automatically implement ML models via code generation. However, existing approaches to build…

cs.CV2025

FontAdapter: Instant Font Adaptation in Visual Text Generation

Myungkyu Koo, Subin Kim, Sangkyung Kwak +3

Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font…

cs.LG2024

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning

Jaehyun Nam, Kyuyoung Kim, Seunghyuk Oh +3

In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. W…