About me

I am a Ph.D. student in Computer Science at York University supervised by Prof. Enamul Hoque. My research focuses on developing multimodal vision-language models and benchmarks for chart, table, and document comprehension. I earned my Master of Science in Computer Science from York University in 2022 and a Bachelor of Science in Computer Engineering from Koc University in 2020, supported by the fully-funded Al Ghurair Foundation (AGFE) STEM scholarship.

My research, published in top-tier conferences such as ACL 2022, EuroVis 2022, EMNLP 2023, ACL 2024, EMNLP 2024, COLING 2025, and ICLR 2025, as well as workshops at Neurips 2024, ICLR 2025, AAAI 2024 and CVPR 2021 (where I received the Best Paper Award), focuses on advancing chart understanding benchmarks (e.g., ChartQA, Chart2Text) and models (e.g., UniChart, ChartInstruct, ChartGemma). These contributions have been widely adopted, accumulating over 100,000 downloads on open-source platforms like Hugging Face. Notably, our ChartQA benchmark has been featured as a key multimodal evaluation benchmark by OpenAI’s GPT-4 official blog post and Google’s Gemini paper in evaluating their models visual reasoning capabilities. As of March 7th, 2025, my publications have received 946 citations, and I have an h-index of 9 on Google Scholar. My research is also supported by funding awards such as the Google PaliGemma Academic Award.

Professionally, I have worked as a Senior Data Scientist at Arteria AI, leading multimodal document understanding projects for clients in the finance and legal industries in Canada between 2022 and 2024. Currently, I am a visiting researcher at ServiceNow Research, where I focus on designing novel vision-language large model (VLMs) architectures for multimodal document understanding and training cutting-edge VLLMs (e.g., LLama 3.2, Phi3.5, Idefics-3) on large compute clusters with multi-node H100 GPUs.

Research Interests

Multimodal Large Language Modeling
Multimodal Chart Understnding
Multimodal Document Understanding
Natural Language Processing
Large Language Models
Vision - Language

Education

York University
PhD in Computer Science, Sep 2024 - Present
York University
M.Sc. in Computer Science, Sep 2020 - June 2022
GPA: 9/9, Exceptional A+
Koc University
B.Sc. in Computer Engineering, Sep 2017 - June 2020
GPA: 3.9/4.0

Work Experience

ServiceNow Research
Visiting Researcher, September 2024 - Present
Arteria AI
Senior Data Scientist, January 2024 - September 2024
Arteria AI
Data Scientist, May 2022 - December 2023
York University
Research Assistant, Sep 2020 - June 2022
York University
Teaching Assistant, Jan 2021 - Apr 2022
ShallowAI
Data Scientist Intern, July 2020 - Sep 2020
Koc University
Undergraduate Research Assistant, June 2019 - Jan 2020

Conference Publications

BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks.
Juan A. Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, Francois Savard, Amirhossein Abaskohi, Ahmed Masry, Perampalli Shravan Nayak, Mahsa Massoud, Rabiul Awal, Pierre-André Noël, Mats L. Richter, Saverio Vadacchino, Shubham Agarwal, Sanket Biswas, Ying Zhang, Sathwik Tejaswi Madhusudhan, João Monteiro, Krishnamurthy (Dj) Dvijotham, Torsten Scholak, Nicolas Chapados, Sean Hughes, Tamer Özsu, Aishwarya Agrawal, Marco Pedersoli, Christopher Pal, Perouz Taslakian, David Vazquez, Issam H. Laradji, Spandana Gella, Sai Rajeswar Mudumba. Published at ICLR 2025
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
Ahmed Masry*, Megh Thakkar*, Aayush Bajaj, Aaryaman Kartha, Enamul Hoque, Shafiq Joty
Published at COLING 2025
Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs
Mohammed Saidul Islam, Raian Rahman, Ahmed Masry, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Enamul Hoque
Published at EMNLP 2024
ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
Ahmed Masry*, Mehrad Shahmohammadi*, Md Rizwan Parvez, Enamul Hoque, Shafiq Joty [*Equal Contribution]
Published at ACL 2024
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
Ahmed Masry*, Parsa Kavehzadeh*, Xuan Long Do, Shafiq Joty, and Enamul Hoque [*Equal Contribution]
Published at EMNLP 2023
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Shankar Kantharaj*, Rixie Tiffany Leong*, Xiang Lin*, Ahmed Masry*, Megh Thakkar*, Enamul Hoque, Shafiq Joty [*Equal Contribution]
Published at ACL 2022
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
Ahmed Masry, Do Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque.
Published at ACL 2022
Chain FL: Decentralized Federated Machine Learning via Blockchain
C. Korkmaz, H. E. Kocas, A. Uysal, A. Masry, O. Ozkasap and B. Akgun
Published at BCCA 2020

Journal Publications

Chart Question Answering: State of the Art and Future Directions
Enamul Hoque, Parsa Kavehzadeh, Ahmed Masry
Published at EuroVis 2022

Workshop Papers

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Ahmed Masry, Juan A. Rodriguez, Tianyu Zhang, Suyuchen Wang, Chao Wang, Aarash Feizi, Akshay Kalkunte Suresh, Abhay Puri, Xiangru Jian, Pierre-André Noël, Sathwik Tejaswi Madhusudhan, Marco Pedersoli, Bang Liu, Nicolas Chapados, Yoshua Bengio, Enamul Hoque, Christopher Pal, Issam H. Laradji, David Vazquez, Perouz Taslakian, Spandana Gella, Sai Rajeswar.
Presented at Re-Align @ ICLR 2025
BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks.
Juan A. Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, Francois Savard, Amirhossein Abaskohi, Ahmed Masry, Perampalli Shravan Nayak, Mahsa Massoud, Rabiul Awal, Pierre-André Noël, Mats L. Richter, Saverio Vadacchino, Shubham Agarwal, Sanket Biswas, Ying Zhang, Sathwik Tejaswi Madhusudhan, João Monteiro, Krishnamurthy (Dj) Dvijotham, Torsten Scholak, Nicolas Chapados, Sean Hughes, Tamer Özsu, Aishwarya Agrawal, Marco Pedersoli, Christopher Pal, Perouz Taslakian, David Vazquez, Issam H. Laradji, Spandana Gella, Sai Rajeswar Mudumba.
Presented at RBFM @ NeurIPS 2024
LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents
Ahmed Masry and Amir Hajian.
Presented at AIFinSI @ AAAI 2024
Integrating Image Data Extraction and Table Parsing Methods for Chart Question Answering
Ahmed Masry, Enamul Hoque Prince
Presented at ChartQA @ CVPR 2021 [Best Paper Award]

Preprints

Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization
Xuan Long Do, Mohammad Hassanpour, Ahmed Masry, Parsa Kavehzadeh, Enamul Hoque, Shafiq Joty

Academic Awards

Mitacs Accelerate Award
15K CAD to support my multimodal research at ServiceNow Research.
Google PaliGemma Academic Award
5K USD in GCP Credits to support my multimodal research.
Al Ghurair Foundation for Education STEM Scholarship Program (AGFE)
A merit-based full-ride scholarship for highly achieving Arab students to pursue a STEM degree.
Vehbi Koc Scholar And Dean’s Honor Roll
Merit-based Awards for Academic Excellence
CVPR 2021 Chart Question Answering Workshop
Achieved Best Paper Award.

Extracurricular Activities

Arabic NLP Winter School
Attended 2025 winter school at MBZUAI campus in Abu Dhabi, UAE (January 2025)
Multimodal AI Winter School
Attended winter school at Saudi Data & AI Authority (SDAIA) in Riyadh, Saudi Arabia (December 2024)
Al-Ghurair Foundation (AGFE)
Student Ambassador (2018-2019)
Robotics Craftsmanship International Academy (University of Coimbra)
Attended 2018 summer robotics school and Ranked 1st in the sumo robots competition, and in the top 10 out of 84 participants.

Academic Services

ACL 2025 Reviewer
NAACL 2025 Reviewer
ACL 2024 Reviewer
EMNLP 2024 Reviewer

Ahmed Masry