👋 About Me

I am a Ph.D. student in the School of Computing and Information Systems at The University of Melbourne, supervised by Dr. Basim Azam and Prof. Naveed Akhtar.

My thesis investigates approaches to enhance the robustness of AI models, with a particular focus on multimodal large language models and diffusion-based generative models. My broader research interests include trustworthy machine learning, dataset design, and the development of reliable deep generative systems.

📰 News & Updates

• Sep 2025 – 🎉 GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs released as an arXiv Preprint
  Authors: A. Yazdan Parast*, P. Hosseini*, H. Asadollahzadeh, A. Soltani Moakhar, B. Azam, S. Feizi, N. Akhtar

• Jun 2025 – 🎉 DDB: Diffusion Driven Balancing to Address Spurious Correlations accepted at ICCV 2025. Project Page
  Authors: A. Yazdan Parast, B. Azam, N. Akhtar

• Oct 2024 – 🎓 Began Ph.D. in the School of Computing and Information Systems at The University of Melbourne

• Jun 2024 – 🎉 Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation presented at CVPR 2024. Project Page
  Authors: F. Hosseini Noohdani, P. Hosseini*, A. Yazdan Parast*, H. Yaghoubi Araghi, M. Soleymani Baghshah

• Feb 2024 – 🎓 Completed B.Sc. in Computer Engineering at Sharif University of Technology