Publications by Maryam Hashemzadeh

• 

  Maryam Hashemzadeh

  Research Areas: Reinforcement Learning, Continual and Lifelong learning, Natural Language Processing

Activity

• PhD Student: Jan 2024 - now
• Intern: Sep 2022 - Dec 2023

Preprints

• Probabilistic Calibration Is a Trainable Capability in Language Models
  Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh, Amal Zouaq, and Sarath Chandar
  In ArXiv, 2026.
  #NLP
  [arXiv]

• REAM: Merging Improves Pruning of Experts in LLMs
  Saurav Jha*, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, and Boris Knyazev*
  In ArXiv, 2026.
  #DL, #NLP
  [arXiv]

Conference and Journal Papers

2026

2. Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
   Maryam Hashemzadeh*, Jerry Huang*, Minseon Kim, Marc-Alexandre Côté, and Sarath Chandar
   Conference on Neural Information Processing Systems (NeurIPS), 2026.
   #DL, #NLP
   [arXiv]

2024

1. Sub-goal Distillation: A Method to Improve Small Language Agents
   Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar, and Marc-Alexandre Cote
   Conference on Lifelong Learning Agents (CoLLAs), 2024. [Oral presentation.]
   #RL, #NLP
   [arXiv], [code]