3 citations · 6 across the 7 of their papers we have counts for
10 papers
Reader--Writer Coupling in Transformer MLPs
Giyeong Oh, Sunghee Ahn, Youngjae Yu
A transformer MLP gives each hidden channel two roles: a reader that decides when the channel responds, and a writer that decides what it adds back to the residual stream. Read as…
A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
Giyeong Oh, Junghun Park, Yuhan Bae +1
Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with vision--language model (VLM) captioners replacing sparse alt-text by dense descriptions. A re…
Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs
Giyeong Oh, Junghyun Lee, Jaehyun Park +3
Modern LLMs inherit strong priors from web-scale pretraining, which can limit the headroom of post-training data-selection strategies. While Active Preference Learning (APL) seeks…
Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
Jeongin Kim, Wonho Bae, YouLee Han +4
Semantic segmentation demands dense pixel-level annotations, which can be prohibitively expensive - especially under extremely constrained labeling budgets. In this paper, we addre…
SlumpGuard: An AI-Powered Real-Time System for Automated Concrete Slump Prediction via Video Analysis
Youngmin Kim, Giyeong Oh, Kwangsoo Youm +1
Concrete workability is essential for construction quality, with the slump test being the most widely used on-site method for its assessment. However, traditional slump testing is…
Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
Giyeong Oh, Woohyun Cho, Siyeol Kim +2
Residual connections are pivotal for deep neural networks, enabling greater depth by mitigating vanishing gradients. However, in standard residual updates, the module's output is d…
SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
Giyeong Oh, Saejin Kim, Woohyun Cho +4
Recently, LoRA and its variants have become the de facto strategy for training and sharing task-specific versions of large pretrained models, thanks to their efficiency and simplic…
TIPO: Text to Image with Text Presampling for Prompt Optimization
Shih-Ying Yeh, Yi Li, Sang-Hyun Park +5
TIPO (Text-to-Image Prompt Optimization) introduces an efficient approach for automatic prompt refinement in text-to-image (T2I) generation. Starting from simple user prompts, TIPO…
Towards Visual Text Design Transfer Across Languages
Yejin Choi, Jiwan Chung, Sumin Shim +2
Visual text design plays a critical role in conveying themes, emotions, and atmospheres in multimodal formats such as film posters and album covers. Translating these visual and te…
Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
Seungbeen Lee, Seungwon Lim, Seungju Han +9
Recent advancements in Large Language Models (LLMs) have led to their adaptation in various domains as conversational agents. We wonder: can personality tests be applied to these a…