About Me
I am currently pursuing a Master’s degree in Artificial Intelligence and Robotics at Sapienza University of Rome, having completed my Bachelor’s in Computer Engineering at Sharif University of Technology.
My technical skills include proficiency in Python and its relevant academic libraries such as PyTorch, PyTorch Lightning, Pandas, and NumPy. I also have experience with C++ and C through projects in robotics, and my background in front-end development has provided me with valuable experience working in agile team environments.
I am driven by the desire to push the boundaries of research and innovation in AI, aspiring not just to enter the job market but to contribute meaningful advancements in the field. I am a determined problem solver, dedicated team player, and consistent in delivering high-quality work, regardless of the challenges.
Education
Sapienza University of Rome
MSc AI & Robotics
2023 - Current
Currently pursuing a Master’s degree in Artificial Intelligence and Robotics, with a strong academic record (GPA: 29.2/30). My coursework has covered advanced topics such as Multilingual NLP, Machine Learning, Reinforcement Learning, Deep Learning, and Computer Vision. I am particularly interested in generative AI and vision-based AI models. I am working on my thesis under the supervision of Professor Fabrizio Silvestri, focusing on Graph OOD Generalization.
Sharif University of Technology
BSc Computer Engineering
2018 - 2023
Completed my undergraduate studies in Computer Engineering at Sharif University of Technology, one of the most prestigious institutions in Iran. My coursework provided a strong foundation in algorithms, systems, and AI. For my thesis, I developed a Paraphrasing Model for Persian Sentences, which introduced me to natural language processing and deep learning techniques. During my studies, I consistently improved my problem-solving skills and adaptability, preparing me for advanced research in AI.
Publications
[1] Emanuele Mule*, Matteo Pannacci*, Ali Ghasemi Goudarzi*, Francesco Pro, Lorenzo Papa, Luca Maiano, and Irene Amerini. Enhancing ground-to-aerial image matching for visual misinformation detection using semantic segmentation, 2025. 📄
*: Equal contribution
Projects
This project introduces a pipeline for facial animation retargeting that combines unsupervised expression transfer with 3D blendshape prediction, enabling the geometric reconstruction of facial expressions from 2D images. By bridging 2D reenactment with 3D parametric models, this work offers a modular framework for animation workflows, eliminating the need for paired training data or manual blendshape annotation. The results highlight its potential for applications in virtual avatars, AR/VR, and automated animation pipelines.
DiffiT introduces a novel approach to image generation by combining Vision Transformers (ViTs) with diffusion-based models, leveraging a Time-dependent Multihead Self Attention (TMSA) mechanism to achieve high-fidelity image synthesis. The project explores the image space model, outperforming other Transformer-based diffusion models while maintaining parameter efficiency. The implementation includes a detailed diffusion process with a linear noise schedule, efficient noisification techniques, and a learned reverse process. The model is preconfigured for datasets like CIFAR-10 and Tiny ImageNet, with flexible hyperparameters for customization. Key features include the TMSA mechanism, parameter efficiency, and dual support for latent and pixel space implementations. The project provides training and evaluation code, along with pretrained models, making it a comprehensive resource for researchers and practitioners in generative AI.
This project explores the Natural Language Inference (NLI) task, focusing on enhancing dataset performance against adversarial test sets. It incorporates word sense disambiguation and semantic role labeling to improve robustness. The primary goal is to develop an effective data augmentation strategy that strengthens the model’s ability to handle adversarial examples.
This project explores curiosity-driven exploration as an intrinsic reward mechanism for agents in environments with sparse or no extrinsic rewards. By formulating curiosity as the error in predicting action consequences within a self-supervised visual feature space, the approach enables efficient exploration and generalization. It allows agents to reach goals with fewer interactions, explore more effectively in the absence of rewards, and adapt to new scenarios by leveraging prior experience.
This project explores the use of projective geometric algebra (PGA) in deep learning models for classifying 3D vascular geometries. By integrating PGA representations with various architectures, including SVM, Logistic Regression, and the Geometric Algebra Transformer (GATr), the study demonstrates the effectiveness of equivariant operations in geometric processing. Additionally, novel EquiLSTM and BiEquiLSTM architectures are introduced, achieving optimal performance and highlighting the potential of PGA-based models in deep learning.
Experience
Marketmap
Front-End Developer
March 2020 - September 2022
- Led the front-end team, overseeing the development of the website’s homepage, comparison page, and product profile page, among others.
- Collaborated closely with the UI designer and back-end team to ensure seamless integration of front-end design and user experience with back-end functionality.
- Participated in sprint meetings to ensure that project timelines were on track and to identify and troubleshoot any potential roadblocks or issues.
- Mentored a team member, providing guidance and training to help him develop the skills needed to become a successful front-end developer.
- Conducted user testing and analysis to identify areas for improvement and worked with the team to implement changes and optimize the user experience.
- Worked as part of the front-end team to help accelerate the website development process, contributing to the timely launch of the website.
- Developed and integrated the sign-up feature into the website’s front end, ensuring a smooth and user-friendly experience for users.
- Implemented the ”house for rent by users” feature, allowing users to easily list their properties for rent on the website.
- Designed and developed the filtering and searching functionality, allowing users to easily find relevant properties based on their preferences.
- Collaborated with other members of the front-end and back-end teams to ensure seamless integration of new features and functionality and to troubleshoot any potential issues.
Language Skills
English
Fluent (TOEFL iBT: 111/120)
Persian
Native
A Little More About Me
Alongside my interests in AI and Software Development some of my other interests and hobbies are:
- Gaming
- Watching Movies