3 papers
cs.LG2026
Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
Subeen Park, Joowang Kim, Hakyung Lee +2
Deep learning models achieve strong performance across various domains but often rely on spurious correlations, making them vulnerable to distribution shifts. This issue is particu…
cs.LG2025
Adaptive Task Vectors for Large Language Models
Joonseong Kang, Soojeong Lee, Subeen Park +5
In-Context Learning (ICL) enables Large Language Models (LLMs) to perform tasks without parameter updates by conditioning on a few demonstrations provided in the prompt. Despite it…
cs.AI2024
Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation
Suho Kang, Jungyang Park, Joonseo Ha +4
Foundation models (FMs) have achieved significant success across various tasks, leading to research on benchmarks for reasoning abilities. However, there is a lack of studies on FM…