Publications d'Maryam Hashemzadeh

• 

  Maryam Hashemzadeh

  Domaines de recherche: Apprentissage par renforcement, Apprentissage continu et permanent, Traitement du langage naturel

Activité

• Étudiant au doctorat: fév. 2024 - maintenant
• Stagiaire: oct. 2022 - 2023

Prépublications

• Probabilistic Calibration Is a Trainable Capability in Language Models
  Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh, Amal Zouaq et 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 et Boris Knyazev*
  In ArXiv, 2026.
  #DL, #NLP
  [arXiv]

Articles de conférence et de revue

2024

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