← Search

Yu-Ang Lee

2 accepted papers

2025

Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions

EMNLP 2025

Recent advancements in large language models (LLMs) and AI systems have led to a paradigm shift in the design and optimization of complex AI workflows. By integrating multiple components, compound AI systems have become increasingly adept at performing sophisticated tasks. However, as these systems

2025

STAR: Spectral Truncation and Rescale for Model Merging

NAACL 2025short

Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the efficiency, a key challenge in model merging is the seemingly inevita…