Yaoqing Yang
Scholar

Yaoqing Yang

Google Scholar ID: LYvugWgAAAAJ
Assistant Professor@Dartmouth CS
machine learning model diagnosticsstructured datainformation theory
Citations & Impact
All-time
Citations
3,736
 
H-index
19
 
i10-index
24
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • Multiple papers accepted at top-tier conferences, including ICML 2024, NeurIPS 2024, ICLR 2024, etc.; received several awards, including the Burke Research Initiation Award; research projects funded by DOE and DARPA.
Research Experience
  • Served as Area Chair for multiple international conferences (e.g., ICLR 2025, NeurIPS 2024); gave talks at places like Google Research; involved in organizing a workshop on AI for Science at ICLR 2025.
Education
  • PhD, Electrical and Computer Engineering, Carnegie Mellon University; BS, Electrical Engineering, Tsinghua University; Postdoc, RISE Lab, EECS, UC Berkeley.
Background
  • Currently an Assistant Professor in the Department of Computer Science at Dartmouth. His research focuses on diagnosing and mitigating failures in machine learning models, such as analyzing shape and geometric features in high-dimensional spaces (e.g., loss landscapes, weight matrix spectral densities, and decision boundaries) to provide actionable insights for addressing common failure modes in these models. He also applies these techniques to applications such as 3D point clouds and graphs. His research draws inspiration from statistical learning and information theory.
Miscellany
  • Hobbies and interests not mentioned