Profile

Jae Myung Kim is a PhD student at the University of Tübingen and a member of ELLIS & IMPRS-IS programs advised by Zeynep Akata (TU Munich, Helmholtz Munich) and Cordelia Schmid (Google, Inria). Previously, he completed his B.S. and M.S. degrees at the Seoul National University. During the winter of 2020, he worked as a research intern at NAVER AI Lab. He is broadly interested in efficient data-centric approaches, including synthetic data as training data, data weak alignment, and zero-shot/few-shot learning. He has previously worked on building reliable models, topics such as XAI, bias, and uncertainty.

Publications

"DataDream: Few-shot Guided Dataset Generation"
Jae Myung Kim*, Jessica Bader*, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
ECCV 2024

"Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models"
Nishad Singhi, Jae Myung Kim, Karsten Roth, Zeynep Akata
ECCV 2024

"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts"
Karsten Roth*, Jae Myung Kim*, A. Sophia Koepke, Oriol Vinyals, Cordelia Schmid, Zeynep Akata
ICCV 2023

"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval"
Jae Myung Kim, A. Sophia Koepke, Cordelia Schmid, Zeynep Akata
CVPR Workshop 2023

"Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification"
Youngwook Kim, Jae Myung Kim, Jieun Jeong, Cordelia Schmid, Zeynep Akata, Jungwoo Lee
CVPR 2023

"Large Loss Matters in Weakly Supervised Multi-Label Classification"
Youngwook Kim*, Jae Myung Kim*, Zeynep Akata, Jungwoo Lee
CVPR 2022

"Keep CALM and Improve Visual Feature Attribution"
Jae Myung Kim*, Junsuk Choe*, Zeynep Akata, Seong Joon Oh
ICCV 2021