Min-Hung Chen

Min-Hung (Steve) Chen is a senior research scientist at NVIDIA Research Taiwan, working on vision+X multi-modal AI. He received his PhD from Georgia Tech in 2020. Min-Hung's primary research interest is multi-modal AI, including vision-language, video understanding, cross-modal learning, efficient tuning, and transformers. He is also interested in learning beyond full supervision, including domain adaptation, transfer learning, X-supervised learning, and more.
Min-Hung Chen

Posts by Min-Hung Chen

Generative AI Jun 09, 2025

A Fine-tuning–Free Approach for Rapidly Recovering LLM Compression Errors with EoRA

Model compression techniques have been extensively explored to reduce the computational resource demands of serving large language models (LLMs) or other... 9 MIN READ
Generative AI Jun 28, 2024

Introducing DoRA, a High-Performing Alternative to LoRA for Fine-Tuning

Full fine-tuning (FT) is commonly employed to tailor general pretrained models for specific downstream tasks. To reduce the training cost, parameter-efficient... 6 MIN READ