publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Preprint
    On the Reliability of Networks of AI Agents: Density Evolution, Stopping Sets, and Architecture Optimization
    Ehsan Aghazadeh and Hossein Pishro-Nik
    2026
    Ongoing
  2. NeurIPS
    Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
    Ehsan Aghazadeh, Mohammad Malekzadeh, Alireza Ghasemi, and 1 more author
    2026
    In Submission @ NeurIPS 2026
  3. EMNLP
    A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
    Lingyu Jing, Hao Chen, Ehsan Aghazadeh, and 2 more authors
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026

2025

  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

2024

  1. BlackboxNLP
    From RAGs to Rich Parameters: Probing How Language Models Utilize External Knowledge over Parametric Information for Factual Queries
    Harsh Wadhwa, Rahul Seetharaman, Shubham Aggarwal, and 6 more authors
    In Proceedings of the 7th BlackboxNLP Workshop (BlackboxNLP @ EMNLP), 2024

2023

  1. ACL
    DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
    Ali Modaressi, Mohsen Fayyaz, Ehsan Aghazadeh, and 2 more authors
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023

2022

  1. ACL
    Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
    Ehsan Aghazadeh, Mohsen Fayyaz, and Yadollah Yaghoobzadeh
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), 2022
    *Equal contribution
  2. ENLSP
    BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
    Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modaressi, and 3 more authors
    In Efficient Natural Language and Speech Processing Workshop (ENLSP @ NeurIPS), 2022
    *Equal contribution

2021

  1. BlackboxNLP
    Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
    Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modaressi, and 2 more authors
    In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP @ EMNLP), 2021
    *Equal contribution