Ehsan Aghazadeh

PhD Student in Computer Science · UMass Amherst

prof_pic.jpg

Amherst, MA

Hi! I’m a PhD student at UMass Amherst in Computer Science. I’m working under the supervision of Hossein Pishro-Nik and Hedyeh Beyhaghi.

My research focuses on Large Language Models (LLMs) from both practical and theoretical perspectives. More specifically, I work on:

  • Test-time scaling and mixture of agents/experts

Previously, I worked on explainability of Language Models and efficient fine-tuning.

news

Jul 01, 2025 Paper accepted at KnowledgeFM @ ACL 2025: A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models.
Dec 01, 2024 Paper accepted at BlackboxNLP @ EMNLP 2024: From RAGs to Rich Parameters.

selected publications

  1. NeurIPS
    CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency
    Ehsan Aghazadeh, Ahmad Ghasemi, Hedyeh Beyhaghi, and 1 more author
    In Efficient Reasoning Workshop (Efficient Reasoning @ NeurIPS), 2025