Publications d'Saurav Jha

• 

  Saurav Jha

  Domaines de recherche: Modèles de Fondation, Apprentissage continu et permanent

Activité

• Chercheur postdoctoral: oct. 2025 - maintenant

Prépublications

• 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]

• Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
  Saurav Jha, M. Jehanzeb Mirza, Wei Lin, Shiqi Yang et Sarath Chandar
  In ArXiv, 2025.
  #DL
  [arXiv]

Articles de conférence et de revue

2026

1. Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
   Nilaksh*, Saurav Jha*, Artem Zholus* et Sarath Chandar
   Conference on Neural Information Processing Systems (NeurIPS) Evaluations & Datasets Track, 2026.
   #DL, #RL
   [openreview], [arXiv], [code]