Muhammad Ashiq

About Me

Portrait of Muhammad Ashiq

🔗 LinkedIn
💻 GitHub
📚 Google Scholar
📧 ashiq [at] wisc [dot] edu

I am a senior undergraduate at the University of Wisconsin-Madison studying mathematics and computer science, working with Prof. Grigorios Chrysos. Starting in Summer 2026, I will join the University of Michigan as a Ph.D. student in EECS at the DeepThink Lab, advised by Prof. Qing Qu and working closely with Dr. Ismail Alkhouri at Los Alamos National Laboratory.

My research interests are in flow-based generative models (e.g. diffusion, flow matching, etc.). In particular, I work on:

  • Trustworthiness: Attacks and defenses on the reliability, privacy, and security of these models.
  • Scientific Applications: Extending these models to solve problems across science and engineering: PDEs, data assimilation, inverse problems, and more.

Previously, I worked with Yeyu Wang and the Epistemic Analytics lab on learning analytics.

Selected Publications

Thumbnail for DDIM vs DDPM paper

Why DDIM Hallucinates More than DDPM: A Theoretical Analysis of Reverse Dynamics

M. H. Ashiq, S. Arora, A. N. Harish, I. Kharbanda, H. Y. Tseng, G. G. Chrysos

In Submission, ICML'26

Thumbnail for test-time privacy paper

Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition

M. H. Ashiq, P. Triantafillou, H. Y. Tseng, G. G. Chrysos

NeurIPS Workshop on Regulatable ML, 2025. In Submission, ICML'26

ArXiv / PDF / Code

Thumbnail for arithmetic length generalization paper

Data Augmentations for Arithmetic Length Generalization in Transformers

L. Zhou, M. H. Ashiq, G. G. Chrysos

NeurIPS Workshop on What Can't Transformers Do, 2025. In Submission, ICML'26

Other publications, including all those in learning analytics, can be found at my Google Scholar.

Miscellaneous