Machine Learning Lab

MLL

Sharif University of Technology



What is MLL Lab?

The Machine Learning Lab (MLL), under the supervision of Dr. Soleymani, is a cutting-edge research center based in Sharif University of Technology, Tehran, Iran. MLL is dedicated to exploring a wide range of critical topics in the field of machine learning, from generalization to compositionality.

Research Area

  • Generalization
  • Compositional Learning
  • Reinforcement Learning
  • Generative Models
  • Vision-language Models

Contact Info

People

Dr. Mahdieh Soleymani

Associate Professor

Email: soleymani@sharif.edu

Google Scholar: link

GitHub: -

LinkedIn: -

Hosein Hasani

PhD Student

Email: hosein.hasani.ce@gmail.com

Google Scholar: –

GitHub: link

LinkedIn: link

Mohammad Mahdi Samiei

PhD Student

Email: mohmahsamiei@gmail.com

Google Scholar: link

GitHub: link

LinkedIn: link

Negin Hashemi Dijujin

PhD Student

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Ali Rahimiakbar

MSc Student

Email: alirahimyakbar@gmail.com

Google Scholar: –

GitHub: link

LinkedIn: link

Ali Abbasi

MSc Student

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Ali Bababeig

MSc Student

Email: mr.bababeig@gmail.com

Google Scholar: –

GitHub: –

LinkedIn: –

Arash Marioriyad

MSc Student

Email: arashmarioriyad@gmail.com

Google Scholar: –

GitHub: link

LinkedIn: link

Fatemeh Askari

MSc Student

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Mohammad Mahdi Vahedi

MSc Student

Email: m.m.vahedi13800@gmail.com

Google Scholar: –

GitHub: link

LinkedIn: link

Seyed Mohammad Hadi Hosseini

MSc Student

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Soroush Vafaie Tabar

MSc Student

Email: svafaie@gmail.com

Google Scholar: link

GitHub: link

LinkedIn: link

Adeleh Bitarafan

PhD Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Faezeh Faez

PhD Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Mahsa Ghorbani

PhD Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyedeh Fatemeh Seyed Salehi

PhD Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Adeleh Bitarafan

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Ali Abdollahi

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Alireza Roshanzamir

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Alireza Sahaf

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

AmirHossein Ameli Kalkhoran

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

AmirShayan Haghipour

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Amirali Moinfar

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Amirhossein Akbarnejad

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Danial Alihosseini

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Ehsan Montahaei

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Fahimeh HosseiniNoohdani

MSc Graduate

Email: –

Google Scholar: link

GitHub: –

LinkedIn: link

Faridoun Mehri

MSc Graduate

Email: feraidoonmehri@gmail.com

Google Scholar: link

GitHub: link

LinkedIn: link

Fatemeh Farahnak

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Hossein Khalili

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Mahdi Ghaznavi

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Majid Aminzadeh

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Marzieh Gheisari

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Melika Bahjati

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Mohammad Amin Banayeeanzade

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Mohammad Mozafari

MSc Graduate

Email: mozafari.mmd@gmail.com

Google Scholar: link

GitHub: –

LinkedIn: link

Mohammadreza Fereydooni

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Omid Abbasi

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Parishad Behnam Ghader

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Rasool Mirzaiezadeh

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Sara Rastegar

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyed Alireza Mirmohammad Sadeghi

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyed Mahdi Roostaiyan

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyed Mohammad Chavoshian

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyed Mohsen Shojaee

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Seyed Roozbeh Razavi Rohani

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Sina Hajimiri

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Zeinab Golgooni

MSc Graduate

Email: –

Google Scholar: –

GitHub: –

LinkedIn: –

Courses

Artificial intelligence

Fall 2023

Website: ...

Large Language Models

Fall 2023

Website: ...

Moder Information Retrieval

Spring 2024

Website: ...

Deep Learning

Spring 2024

Website: ...

Projects

Compositional Generation

In recent years, text-to-image (T2I) diffusion models such as Stable Diffusion and DALL-E have shown promising performance in generating realistic, creative, diverse, and high-quality images from textual descriptions. These models leverage the iterative denoising process and text embeddings through the cross-attention mechanism to generate images used in many applications across various domains. However, despite their impressive capabilities, these models often struggle to faithfully capture all the entities, attributes, and relationships described in the input prompt, leading to various compositional misalignments such as entity missing, improper attribute binding, wrong spatial relationships, and counting problems. We aim to add compositional generation capability into T2I models to overcome the mentioned compositional generation failure modes.

Spurious Correlation

Description

Open Positions

Spurious Correlation

Requirements: ...

Publications

Divide and Conquer: Two-Level Problem Remodeling for Large-Scale Few-Shot Learning

R0-FoMo - 2023

Autors

Description

Link

Send a message