Research Output

Publications & Manuscripts

Peer-reviewed work and manuscripts in preparation. Please see my CV for the most current list.

PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark

M. J. Ranjbar, M. Amini, P. Bathayan, H. Faili, A. Shakery

In preparation for submission to EACL 2027

Preprint Persian · Audio-Language Models · Benchmarking arXiv:2603.14456 ↗
  • A comprehensive benchmark for evaluating large audio-language models on Persian speech and language tasks.
  • Assesses model performance across diverse tasks to characterize capabilities and gaps for Persian.

Thesis Research

Leveraging EEG Signals from Persian and English Speakers to Enhance Multimodal Sentiment Analysis

M.Sc. Thesis · University of Tehran

Supervisors: Dr. Azadeh Shakery & Dr. Mohammad-Reza A. Dehaqani

In progress EEG · Multimodal · Cross-lingual NLP
  • Studies cross-cultural neural correlates of language and sentiment processing using EEG from Persian and English speakers.
  • Develops multimodal models that integrate EEG signals with textual representations for sentiment analysis.