Mohammadmostafa Rostamkhani

My research interests sit at the intersection of language, vision, and reasoning. I have worked on benchmarks for multimodal perception, multilingual claim retrieval, puzzle reasoning, and hate speech detection.

• M.Sc. in Artificial Intelligence

  Iran University of Science and Technology

  Department of Computer Engineering · GPA: 19.52/20 · First in graduating cohort

  Thesis: Enhancing Reasoning of Multimodal Models Using Text-to-Image and Large Language Models
  Supervisor: Dr. Sauleh Eetemadi

  Sep. 2022 – Nov. 2024

• B.Sc. in Computer Science

  Iran University of Science and Technology

  GPA: 19.13/20 · First in graduating cohort

  Sep. 2018 – Jul. 2022

• Multimodal learning and reasoning. Vision-language models, visual question answering, and perceptual challenges such as visual illusions.
• Natural language processing. Multilingual learning, claim retrieval, text classification, question answering, and token classification.
• Model evaluation. Studying language and multimodal models on tasks that test reasoning and robustness.

Research resources

• Illusory VQA

  Experiment notebooks and released results accompanying our work on visual illusions. Benchmark datasets are available through the VQA-Illusion organization on Hugging Face.

• HASOC2023

  Experiment notebooks for hate speech and offensive content detection in English and Indo-Aryan languages. Working-notes paper.

1. Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions

   Mohammadmostafa Rostamkhani, Baktash Ansari, Hoorieh Sabzevari, Farzan Rahmani, and Sauleh Eetemadi.

   IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), MAR Workshop, 2025.

   Spotlight at MAR, CVPR 2025; also presented as a spotlight at MAR, NeurIPS 2024.

   arXivCodeDatasets

2. Word2winners at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval

   Amirmohammad Azadi, Sina Zamani, Mohammadmostafa Rostamkhani, and Sauleh Eetemadi.

   Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval), 2025.

3. ROSHA at SemEval-2024 Task 9: BRAINTEASER A Novel Task Defying Common Sense

   Mohammadmostafa Rostamkhani, Shayan Mousavinia, and Sauleh Eetemadi.

   Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval), 2024.

4. BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense

   Baktash Ansari, Mohammadmostafa Rostamkhani, and Sauleh Eetemadi.

   Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval), 2024.

5. eagerlearners at SemEval2024 Task 5: The Legal Argument Reasoning Task in Civil Procedure

   Hoorieh Sabzevari, Mohammadmostafa Rostamkhani, and Sauleh Eetemadi.

   Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval), 2024.

6. Detecting Hate Speech and Offensive Content in English and Indo-Aryan Texts

   Mohammadmostafa Rostamkhani and Sauleh Eetemadi.

   FIRE 2023 Working Notes, CEUR Workshop Proceedings, Vol. 3681, 2023.

7. ROZAM at SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis

   Mohammadmostafa Rostamkhani, Ghazal Zamaninejad, and Sauleh Eetemadi.

   Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval), 2023.

Instructor

• Gold Medal Training Course

  Young Scholars Club

  Fall 2025

• Top-40 Training Course

  Young Scholars Club

  Summer 2025

Teaching Assistant

• System 2

  Sharif University of Technology · Graduate

  Spring 2026

• Multimodal Models

  IUST · Graduate

  Fall 2025

• Deep Learning

  IUST · Graduate

  Spring 2025

• Computational Intelligence

  IUST · Undergraduate

  Spring 2025

• Embedded Systems

  IUST · Undergraduate

  Fall 2024

• Natural Language Processing

  IUST · Graduate

  Fall 2024

• Natural Language Processing

  IUST · Undergraduate

  Spring 2024

• Deep Learning

  IUST · Graduate

  Spring 2024

• Multi-Agent Systems

  IUST · Graduate

  Spring 2024

• Natural Language Processing

  IUST · Undergraduate

  Spring 2023

• Operating Systems

  IUST · Undergraduate · Head Teaching Assistant

  Spring 2022

• Operating Systems

  IUST · Undergraduate

  Fall 2021

• Artificial Intelligence

  IUST · Undergraduate

  Fall 2021

• Algorithm Design

  IUST · Undergraduate

  Fall 2020

• Data Structures

  IUST · Undergraduate

  Spring 2020

• Advanced Programming

  IUST · Undergraduate

  Fall 2019

• NLP Researcher

  ZharfaTech

  Aug. 2025 – Present

• NLP Engineer

  Dadmatech

  Nov. 2024 – Apr. 2025

• Data Scientist, Business Intelligence

  Middle East Bank

  Sep. 2022 – Nov. 2023

• Developer

  Trading Algorithm Lab, IUST

  Feb. 2022 – Sep. 2022

Technical skills

Programming

Python, C, C++, C#, JavaScript, VHDL, Verilog

Machine learning and NLP

PyTorch, TensorFlow, Keras, scikit-learn, XGBoost, Hugging Face Transformers, Sentence Transformers, Gensim, NLTK

Data and vision

NumPy, pandas, OpenCV

Inference and tooling

vLLM, Ollama, TensorBoard; Linux shell and Bash

Visualization

Matplotlib, Seaborn, Plotly Dash, Bokeh

Second place, Rayan AI 2025 World Finals

Member of AI Guardians of Trust, the team ranked second in the world finals.

Official team results

mohammadmostafarostamkhani@gmail.com