6 papers
LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
Beomsik Cho, Jinhyeong Kim, Dongseok Lee +1
Large Vision-Language Models (LVLMs) integrate visual perception with language generation, enabling responses that span image understanding and complex reasoning. However, LVLMs do…
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Minju Gwak, Minseo Kwak, Dongseok Lee +3
Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamin…
Toward a Robust and Generalizable Metamaterial Foundation Model
Namjung Kim, Dongseok Lee, Jongbin Yu +4
Advances in material functionalities drive innovations across various fields, where metamaterials-defined by structure rather than composition-are leading the way. Despite the rise…
MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data
Mingu Kang, Dongseok Lee, Woojin Cho +5
Large language models (LLMs), like ChatGPT, have shown that even trained with noisy prior data, they can generalize effectively to new tasks through in-context learning (ICL) and p…
Simple arithmetic operation in latent space can generate a novel three dimensional graph metamaterials
Namjung Kim, Dongseok Lee, Chanyoung Kim +2
Recent advancements in artificial intelligence (AI)-based design strategies for metamaterials have revolutionized the creation of customizable architectures spanning nano- to macro…
Singular Layer Physics-Informed Neural Network Method for Convection-Dominated Boundary Layer Problems in Two Dimensions
Gung-Min Gie, Youngjoon Hong, Chang-Yeol Jung +1
This research explores neural network-based numerical approximation of two-dimensional convection-dominated singularly perturbed problems on square, circular, and elliptic domains.…