Michael Cardei

Profile

Computer Science Ph.D. Student at the University of Virginia - RAISE Lab researching Generative AI for Scientific Application and Responsible Generative AI.

Publications

Speculative Diffusion Decoding for Accelerated Language Generation

Speculative Diffusion Decoding for Accelerated Language Generation

Jacob K Christopher, Brian R Bartoldson, Tal Ben-Nun, Michael Cardei, Bhavya Kailkhura, Ferdinando Fioretto

Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)

ABSPDF
Improving Equity in Deep Learning Medical Applications with the Gerchberg-Saxton Algorithm

Improving Equity in Deep Learning Medical Applications with the Gerchberg-Saxton Algorithm

Seha Ay, Michael Cardei, Anne-Marie Meyer, Wei Zhang, Umit Topaloglu

Journal of Healthcare Informatics Research

ABSPDF
ROADWork Dataset: Learning to Recognize, Observe, Analyze and Drive Through Work Zones

ROADWork Dataset: Learning to Recognize, Observe, Analyze and Drive Through Work Zones

Anurag Ghosh, Robert Tamburo, Shen Zheng, Juan R Alvarez-Padilla, Hailiang Zhu, Michael Cardei, Nicholas Dunn, Christoph Mertz, Srinivasa G Narasimhan

International Conference on Computer Vision (ICCV)

ABSPDF
Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation

Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation

Jacob K Christopher, Michael Cardei, Jinhao Liang, Ferdinando Fioretto

International Conference on Neuro-symbolic Systems (NeuS 2025)

ABS
Constrained Discrete Diffusion

Constrained Discrete Diffusion

Michael Cardei, Jacob K Christopher, Thomas Hartvigsen, Brian R Bartoldson, Bhavya Kailkhura, Ferdinando Fioretto

arXiv preprint arXiv:2503.09790

ABS