activity
20122026
most citedRobust Federated Learning: The Case of Affine Distribution Shifts

64 citations · 113 across the 31 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Low-Rank Prompt Learning for Vision-Language Models with Fixed-Token Bases

Tanvir Muntakim Tonoy, Sajjad Ghiasvand, Mahnoosh Alizadeh +1

Prompt learning adapts CLIP to downstream recognition by replacing hand-written templates with learned continuous context vectors, which in Context Optimization (CoOp) form a dense…

cs.CV2026

ZOMP: Zeroth-Order Multi-Modal Prompt Tuning for Vision-Language Models

Sajjad Ghiasvand, Yifan Yang, Mahnoosh Alizadeh +1

Fine-tuning vision-language models such as CLIP typically requires backpropagation (BP) through the full model, which is infeasible when only forward-pass access is available, as i…

cs.CV2026

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh +1

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending pro…

cs.CV2025

INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models

Parsa Madinei, Ryan Solgi, Ziqi Wen +3

We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lea…

cs.CV2025

pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models

Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani

Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous da…

cs.CV2025

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations

Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani

Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including visi…