publications

Publications in reverse chronological order.

2026

  1. ICLR
    The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
    Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar, Alessandro Sordoni, Aaron Courville, and Siva Reddy
    International Conference on Learning Representations (ICLR), 2026
    arXiv ICLR code

2025

  1. GenBio
    NovoMolGen: Rethinking Molecular Language Model Pretraining
    Kamran Chitsaz, Roshan Balaji, Quentin Fournier, Nirav Pravinbhai Bhatt, and Sarath Chandar
    ICML 2nd Generative AI for Biology Workshop, 2025
    project arXiv code

2024

  1. EMNLP
    Exploring Quantization for Efficient Pre-Training of Transformer Language Models
    Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, and Sarath Chandar
    Findings of the Association for Computational Linguistics: EMNLP, 2024
    paper arXiv code

2023

  1. TMLR
    Training DNNs Resilient to Adversarial and Random Bit-Flips by Learning Quantization Ranges
    Kamran Chitsaz, Gonçalo Mordido, Jean-Pierre David, and François Leduc-Primeau
    Transactions on Machine Learning Research, 2023
    paper code

2021

  1. Use of frequency domain for complexity reduction of convolutional neural networks
    Kamran Chitsaz, Mohsen Hajabdollahi, Pejman Khadivi, Shadrokh Samavi, Nader Karimi, and Shahram Shirani
    Pattern Recognition, ICPR International Workshops and Challenges, 2021
    arXiv
  2. Degree-based Feature Is All You Need: Science4Cast Report
    Milad Aghajohari, Mohammad Sadegh Akhondzadeh, Saleh Ashkboos, and Kamran Chitsaz
    IEEE International Conference on Big Data, 2021
    paper

2020

  1. arXiv
    Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions
    Kamran Chitsaz, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi, and Shahram Shirani
    arXiv preprint arXiv:2003.12621, 2020
    arXiv