Kamran Chitsaz

me.jpg

Hey! I’m Kamran :wave:. I’m currently a research assistant at Mila – Quebec AI Institute, where I am advised by Prof. Sarath Chandar.

My research focuses on reasoning in large language models and reinforcement learning for post-training. Previously, I worked on efficient machine learning, including quantization and hardware acceleration.

Before joining Mila, I completed an M.Sc. in Electrical Engineering at Polytechnique Montréal in 2023, under the supervision of Prof. François Leduc-Primeau. I earned my B.Sc. in Computer Engineering from Isfahan University of Technology in 2020.

news

Jan 26, 2026 🧠 The Markovian Thinker was accepted to ICLR 2026.
Jul 18, 2025 🧬 We presented NovoMolGen at the ICML 2025 Generative AI for Biology Workshop.
Nov 12, 2024 📄 Our work on efficient pre-training through quantization was published in Findings of EMNLP 2024.
Aug 21, 2023 🚴 I joined Chandar Research Lab as a research assistant.

See all news here.

selected publications

  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
    paper code
  2. GenBio
    NovoMolGen: Rethinking Molecular Language Model Pretraining
    Kamran Chitsaz, Roshan Balaji, Quentin Fournier, Nirav Pravinbhai Bhatt, and Sarath Chandar
    ICML Generative AI for Biology Workshop, 2025
    project code
  3. EMNLP
    Exploring Quantization for Efficient Pre-Training of Transformer Language Models
    Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, and Sarath Chandar
    Findings of EMNLP, 2024
    paper code