Siwon Kim

Siwon Kim is an experienced Applied Scientist with a strong focus on AI research, particularly in explainable AI and safe dialogue systems. Notable positions include work at Amazon Alexa AI, where a paper titled "Grounding explanation of image classifiers to textual concept space" was accepted at CVPR 2023, and a recent role at Stability AI as a research collaborator. Siwon also interned at ParameterLab, contributing to a paper on privacy leakage in large language models that received a spotlight at NeurIPS 2023. Education includes a Bachelor's degree and ongoing PhD candidacy in Electrical and Computer Engineering from Seoul National University. Current involvement includes a position at Amazon developing AGI audio foundation models.