Publications

Yunqi Hong, Sohyun An, Andrew Bai, Neil Y.C. Lin, Cho-Jui Hsieh (2025). Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs. Under Review.

Yu Zhou*, Sohyun An*, Haikang Deng*, Da Yin, Clark Peng, Cho-Jui Hsieh, Kai-Wei Chang, Nanyun Peng (2025). DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation. Under Review.

Sohyun An, Ruochen Wang, Tianyi Zhou, Cho-Jui Hsieh (2025). Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models. Under Review.

Sohyun An (2024). Optimal Neural Architecture Generation with Diffusion Models. KAIST M.S. Thesis 2024.

Ruochen Wang*, Sohyun An*, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang, Cho-Jui Hsieh (2024). One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts. ICML 2024.

Sohyun An*, Hayeon Lee*, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang (2024). DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models. ICLR 2024.

Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang (2023). Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets. ICLR 2023, Spotlight (notable-top-25%).

Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang (2022). Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation. AutoML 2022 Workshop.

Sohyun An, Robert Ford (2013). An example conference paper. In ICW.

PDF Cite Code Dataset Project Slides Video Source Document