About Me

I am a PhD student in the Electrical and Computer Engineering Department at the University of California, Santa Barbara (UCSB). Prior to joining UCSB, I earned my B.Sc. degree in Electrical Engineering with a minor in Mathematics from Sharif University of Technology in 2023. I am currently an intern at Handshake AI, where I focus on improving and evaluating LLM-generated code experiments.

My research interests span both text-based and multimodal large language models (LLMs), with particular emphasis on:

• Personalization of LLMs and VLMs
• Efficient fine-tuning of LLMs and VLMs
• Federated and decentralized learning
• Robust machine learning

News

• 03/01/2026: Our paper "Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models" is accepted to Trustworthy AI Workshop at ICLR 2026!
• 01/26/2026: Our paper "pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models" is accepted to ICLR 2026!
• 08/21/2025: I started an internship at Handshake AI!
• 05/15/2025: Our paper "Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models" is accepted to ACL Findings 2025!
• 05/13/2025: Our paper "Decentralized Low-Rank Fine-Tuning of Large Language Models" is accepted to REALM Workshop at ACL 2025!
• 04/09/2025: Our paper "Robust Decentralized Learning with Local Updates and Gradient Tracking" is accepted to IEEE Transactions on Networking!

Publications

• MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
  S. Ghiasvand, H. E. Oskouie, M. Alizadeh, R. Pedarsani
  Arxiv Preprint, 2026. [Link]
• pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
  S. Ghiasvand, M. Alizadeh, R. Pedarsani
  ICLR, 2026. [Link]
• Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models
  S. Ghiasvand, H. E. Oskouie, M. Alizadeh, R. Pedarsani
  Trustworthy AI @ ICLR, 2026. [Link]
• Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models
  S. Ghiasvand, Y. Yang, Z. Xue, M. Alizadeh, Z. Zhang, R. Pedarsani
  ACL Findings, 2025. [Link]
• Decentralized Low-Rank Fine-Tuning of Large Language Models
  S. Ghiasvand, M. Alizadeh, R. Pedarsani
  REALM Workshop @ ACL, 2025. [Link]
• Robust Decentralized Learning with Local Updates and Gradient Tracking
  S. Ghiasvand, A. Reisizadeh, M. Alizadeh, R. Pedarsani
  IEEE/ACM Transactions on Networking, 2025. [Link]
• Communication-efficient and Decentralized Federated Minimax Optimization
  S. Ghiasvand, A. Reisizadeh, M. Alizadeh, R. Pedarsani
  Allerton Conference on Communication, Control, and Computing, 2024. [Link]