Sin-Han Yang

Contact

prof_pic.png

Pursuing curiosity-driven research on AI systems, seeking deeper understanding and actionable insights. So far, I have explored algorithms, calibration, and phenomena in AI systems.

Currently, I am a research scientist at Appier AI Research, working with Prof. Shao-Hua Sun, Prof. Hung-yi Lee, and Prof. Yun-Nung (Vivian) Chen. Previously, I was a research assistant at RIKEN Center for Advanced Intelligence Project, working with Prof. Emtiyaz Khan. I earned my B.Sc. in Computer Science and Physics from National Taiwan University, where I worked with Prof. Hsin-Hsi Chen.

Favorite Research Quotes

“To myself I seem to have been only like a boy playing on the sea-shore, and diverting myself in now and then finding a smoother pebble or a prettier shell than ordinary, whilst the great ocean of truth lay all undiscovered before me.” - Isaac Newton

“Everything should be made as simple as possible, but not simpler.” - Albert Einstein

Selected Papers

  1. A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic
    Sin-Han Yang*, Shih-Cheng Huang*, Chieh-Yen Lin, Yun-Nung Chen†, Shao-Hua Sun†, and Hung-yi Lee†
    arXiv preprint arXiv:2610.07990 , 2026
  2. On Calibration of Large Language Models: From Response To Capability
    Sin-Han Yang*, Cheng-Kuang Wu*, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee, and Shao-Hua Sun
    arXiv preprint arXiv:2602.13540 , 2026
  3. Variational Learning Induces Adaptive Label Smoothing
    Sin-Han Yang, Zhedong Liu, Gian Maria Marconi, and Mohammad Emtiyaz Khan
    arXiv preprint arXiv:2502.07273 , 2025