Manuscript

DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation
Contact languages like English exhibit rich regional variations in the form of dialects, which are often used by dialect speakers …
Yu Zhou*, Sohyun An*, Haikang Deng*, Da Yin, Clark Peng, Cho-Jui Hsieh, Kai-Wei Chang, Nanyun Peng
Cite PDF
Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, …
Yunqi Hong, Sohyun An, Andrew Bai, Neil Y.C. Lin, Cho-Jui Hsieh
Cite PDF Code
Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
While recent success of large reasoning models (LRMs) significantly advanced LLMs’ reasoning capability by optimizing the final …
Sohyun An, Ruochen Wang, Tianyi Zhou, Cho-Jui Hsieh
Cite PDF
Optimal Neural Architecture Generation with Diffusion Models
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant …
Sohyun An
Cite PDF
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and …
Ruochen Wang*, Sohyun An*, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang, Cho-Jui Hsieh
Cite PDF
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant …
Sohyun An*, Hayeon Lee*, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
Cite PDF Code
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best …
Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang
Cite PDF Code
Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation
Designing diverse neural architectures taking into account resource constraints or datasets is one of the main challenges in Neural …
Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang
Cite PDF