Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Chain FL: Decentralized Federated Machine Learning via Blockchain
Published in BCCA 2020, 2020
Chain FL: Decentralized federated machine learning via blockchain.
Download here
Integrating Image Data Extraction and Table Parsing Methods for Chart Question Answering
Published in ChartQA @ CVPR 2021, 2021
Integrating image data extraction and table parsing methods for chart question answering.
Download here
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Published in ACL 2022, 2022
Chart-to-Text: A large-scale benchmark for chart summarization.
Download here
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
Published in ACL 2022 Findings, 2022
ChartQA: A benchmark for question answering about charts with visual and logical reasoning.
Download here
Chart Question Answering: State of the Art and Future Directions
Published in EuroVis 2022, 2022
Chart Question Answering: State of the art and future directions.
Download here
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
Published in EMNLP 2023, 2023
UniChart: A universal vision-language pretrained model for chart comprehension and reasoning.
Download here
Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization
Published in arXiv Preprint, 2023
Do LLMs Work on Charts? Designing few-shot prompts for chart question answering and summarization.
Download here
LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents
Published in AIFinSI @ AAAI 2024, 2024
LongFin: A multimodal document understanding model for long financial domain documents.
Download here
ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
Published in ACL 2024, 2024
ChartInstruct: Instruction tuning for chart comprehension and reasoning.
Download here
Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs
Published in EMNLP 2024, 2024
An extensive investigation into the capabilities and limitations of Large Vision Language Models for chart comprehension and reasoning.
Download here
BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks
Published in RBFM @ NeurIPS 2024, 2024
BigDocs is a permissively-licensed dataset for training vision-language models on document and code tasks.
Download here
Apriel-1.5-15b-Thinker
Published in arXiv Preprint, 2025
Apriel-1.5-15b-Thinker.
Download here
LLM-based data science agents: A survey of capabilities, challenges, and future directions
Published in arXiv Preprint, 2025
LLM-based data science agents: A survey of capabilities, challenges, and future directions.
Download here
Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
Published in arXiv Preprint, 2025
Improving GUI Grounding with Explicit Position-to-Coordinate Mapping.
Download here
Scope: Selective Cross-modal Orchestration of Visual Perception Experts
Published in arXiv Preprint, 2025
Scope: Selective Cross-modal Orchestration of Visual Perception Experts.
Download here
Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
Published in ACL Industry Track 2025, 2025
Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
Download here
Learning or Cheating? Assessing Data Contamination in Large Vision-Language Models
Published in IEEE MLSP 2025, 2025
Learning or Cheating? Assessing Data Contamination in Large Vision-Language Models.
Download here
Colflor: Towards Bert-Size Vision-Language Document Retrieval Models
Published in IEEE MLSP 2025, 2025
Colflor: Towards Bert-Size Vision-Language Document Retrieval Models.
Download here
BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks
Published in ICLR 2025, 2025
BigDocs is a permissively-licensed dataset for training vision-language models on document and code tasks.
Download here
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
Published in COLING 2025 Industry Track, 2025
ChartGemma is a visual instruction-tuned model for chart reasoning.
Recommended citation: Masry, A., Thakkar, M., Bajaj, A., Kartha, A., Hoque, E., & Joty, S. (2025). ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild. COLING 2025. https://arxiv.org/abs/2407.04172v1
COLMATE: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Published in EMNLP 2025 Industry Track, 2025
COLMATE: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval.
Download here
ChartQAPro: A more diverse and challenging benchmark for chart question answering
Published in ACL 2025 Findings, 2025
ChartQAPro: A more diverse and challenging benchmark for chart question answering.
Download here
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Published in COLM 2025, 2025
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning.
Download here
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
Published in NeurIPS 2025, 2025
AlignVLM: Bridging vision and language latent spaces for multimodal understanding.
Download here
DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards
Published in EACL 2026, 2026
DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards.
Download here
talks
teaching
Undergraduate Teaching Assistant
Undergraduate course, Office of Learning and Teaching (KOLT), Koç University, 2019
Role: Undergraduate Teaching Assistant
Period: Spring Semester, 2019
Location: Istanbul, Turkey
Teaching Assistant
Graduate and Undergraduate courses, York University, 2021
Role: Teaching Assistant
Period: January 2021 – April 2022 & September 2024 – Present
Location: Toronto, Ontario