About me

I’m a final-year Computer Science Ph.D. candidate at the University of Pittsburgh, advised by Prof. Adriana Kovashka.

My research interests are computer vision, multimodal learning, and foundational models (Vision-Language Models, Multimodal LLMs, and Text-to-Image Diffusion Models), aiming to build robust and generalizable systems that can understand and reason about complex visual data. During my Ph.D., I have interned at Apple, eBay, and Amazon. Prior to that, I received my B.S. in Software Engineering from Amirkabir University of Technology, specializing in Artificial Intelligence, where I received an outstanding student award and visited Johannes Gutenberg University in Mainz as a research intern.

I’m currently working on the following problems, with research appearing in ICLR’26, NeurIPS’25, CVPR’24, WACV’25, and BMVC’23:

• Robustness & Domain Generalization
  How to leverage multimodal data to learn semantically rich robust representation that generalize beyond their training distribution, including robustness to domain shift, geographic variation, and real-world data diversity [Language-Guided Feature Alignment, GeoKnowledgePrompting, MuST]

• Compositionality
  How models can generalize to novel and rare (e.g. creative) combinations of concepts (e.g., new objects, relations, attributes) and compositional reasoning [ReBind, PersuasiveAdVLMBenchmark]

• Cultural Understanding
  How Vision-Language and Text-to-Image generative models understand and represent cultural concepts (e.g., objects, social activities and human interactions) across diverse cultures and especially low-resource countries [AHEaD,GeoKnowledgePrompting]

Feel free to reach me at sem238 [AT] pitt [DOT] edu or siinamalakouti [AT] gmail [DOT] com

Good News!

• [01.2026] Paper accepted to ICLR’26

• [10.2025] Received NeurIPS’25 Scholar Award

• [09.2025] Paper accepted to NeurIPS’25

• [09.2025] Presenting Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition as an oral at CDEL Workshop, ICCV 2025

• [05.2025] Passed Ph.D. Proposal Exam on Compositional and Cultural Generalization in Discriminative and Generative Vision Foundational Models. Thanks to my amazing advisor, Dr. Adriana Kovashka, and my committee: Dr. Milos Hausckrecht, Dr. Xiang Lorraine Li, and Dr. Boqing Gong

• [02.2025] Co-organizing Demographic Diversity in Computer Vision workshop at CVPR 2025

• [01.2025] I’ll be participating in WACV 2025 Doctoral Consortium
• [10.2024] A paper accepted to WACV’25 in Tucson,AZ.
• [09.2024] Received Outstanding Reviewer award from ECCV’24
• [Summer’24] Joined Prime Video at Amazon as an Applied Scientist Intern in New York, NY.
• [04.2024] A Paper accepted to CVPR’24
• [04.2024] I passed my Oral Ph.D. Comprehensive Exam!
• [08.2023] A paper accepted to BMVC’23
• [Summer’23] Joined eBay as an Applied Research Intern in San Jose, CA.
• [Summer’22] Joined Apple as a Computer Vision Intern in Cupertino, CA.