معرفی
Yaniv Yacoby is an Assistant Professor of Computer Science at Wellesley College, where he leads the Model-Guided Uncertainty (MOGU) Lab. His research integrates machine learning with mental health, focusing on suicide prevention and clinician-AI collaboration. He holds a B.A. in Computer Science (Harvard), M.M. in Contemporary Improvisation (New England Conservatory), and Ph.D. in Machine Learning (Harvard). Prior roles include a postdoctoral fellowship at Harvard's Nock Lab.
His research emphasizes safety-critical applications of deep learning, developing methods to quantify uncertainty and improve human-AI partnerships in healthcare. Key themes include:
- Model-agnostic posterior approximation for variational autoencoders
- Bayesian neural networks with latent variables
- Socio-technical frameworks for clinical AI integration
Publications reflect dual expertise in ML methodology (e.g., JMLR papers on variational inference) and applied mental health research (e.g., SIGCSE work on academic well-being). The MOGU Lab collaborates with clinicians at Mass General Hospital and Harvard Medical School.
