Scholar
Shervin Khalafi
Google Scholar ID: rdfxlq8AAAAJ
PhD Student, University of Pennsylvania
Citations & Impact
Citations
8
H-index
1
i10-index
0
Publications
3
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Paper 'Composition and Alignment of Diffusion Models using Constrained Learning' accepted in NeurIPS 2025.
- - Paper 'Constrained Diffusion Models via Dual Training' accepted in NeurIPS 2024.
- - Paper 'Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks' accepted in ICML 2024.
Research Experience
- Currently developing constrained optimization frameworks for training generative models (diffusion models in particular) under requirements. Also studying generative diffusion models for Graphs.
Education
- PhD student in Electrical & Systems Engineering at the University of Pennsylvania, advised by Prof. Alejandro Ribeiro.
Background
- PhD student in Electrical & Systems Engineering at the University of Pennsylvania, advised by Prof. Alejandro Ribeiro. Research interests include Generative Models, Optimization Theory, and graph-based Machine Learning.
Co-authors