CODE:751 Research 4 papers Nominal
Research

Publications

Four papers, one question: how do you train well when the data is too little or the labels are wrong? Each pulls a different lever — which samples to label, how to adapt when there are few, how to synthesize what's missing, and how to keep the optimization stable when the signal is noisy. First or co-first author on all four; two published at ICML 2023 and AAAI 2024, two preprints.

Ref 01/04 arXiv 2026 Preprint ★ First author

GAPO — Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment

Youngjae Cho, Jongsuk Kim, Ji-Hoon Kim

Stability · noisy preferences

Reads preference optimization as learning dynamics, and puts the stability problem in the reference: DPO's frozen anchor becomes a geometrically perturbed one — a worst-case local perturbation of the current policy — with each pair reweighted by its geometric brittleness. A steadier objective, which is what holds up under noisy labels and on less data.

AlpacaEval 2.0 LC +3.6pp vs SimPObeats DPO · SimPO · KTO · ORPO
Read the paper
Ref 02/04 arXiv 2024 Preprint ★ First author

Background-Aware Defect Generation for Robust Industrial Anomaly Detection

Youngjae Cho, Gwangyeol Kim, Sirojbek Safarov, Seongdeok Bang, Jaewoo Park

Synthesis · scarce anomalies

When real defects are too rare to train on, generate them — diffusion synthesis that models the relationship between foreground defect and background surface explicitly, and argues the disentanglement theoretically rather than only showing it. The method behind the production system on the product page.

Read the paper
Ref 03/04 AAAI 2024 Published ★ First author

APP — Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

Youngjae Cho, HeeSun Bae, Seungjae Shin, YeoDong Youn, Weonyoung Joo, Il-Chul Moon

Adaptation · scarce data

Bayesian, data-dependent priors that let vision-language prompts adapt per input instead of staying fixed — so a VLM holds up when there is little data to tune on, and stays calibrated when the input shifts.

Read the paper
Ref 04/04 ICML 2023 Published ★ Co-first author

SAAL — Sharpness-Aware Active Learning

Yoon-Yeong Kim*, Youngjae Cho*, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

Acquisition · scarce labels

An acquisition function that bridges sharpness-aware minimization and active learning — select the samples that flatten the loss landscape, and a fixed labeling budget buys more generalization per label.

Read the paper
In progress

Two lines still open.

Neither is public and neither has a result to report. They're here because they're where the work is going, and because both extend threads already on this site — the temporal localization behind the hackathon entry, and the safety side of the moderation stack.

Unpublished No result yet

Video temporal grounding

Locating the moment inside a long video that a description actually refers to.

Findings withheld
Unpublished No result yet

Safe diffusion

Keeping a diffusion model from generating what it shouldn't.

Findings withheld