Parsa Nooralinejad — accepted AI-conference papers

2025

MCNC: Manifold-Constrained Reparameterization for Neural Compression

Chayne Thrash, Reed Andreas, Ali Abbasi, Parsa Nooralinejad, Soroush Abbasi Koohpayegani, Hamed Pirsiavash +1

ICLR 2025poster

The outstanding performance of large foundational models across diverse tasks, from computer vision to speech and natural language processing, has significantly increased their demand. However, storing and transmitting these models poses significant challenges due to their massive size (e.g., 750GB…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

BrainWash: A Poisoning Attack to Forget in Continual Learning

Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash, Soheil Kolouri

CVPR 2024poster

Continual learning has gained substantial attention within the deep learning community offering promising solutions to the challenging problem of sequential learning. Yet a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks especially with the aim of inducing forg…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

NOLA: Compressing LoRA using Linear Combination of Random Basis

Soroush Abbasi Koohpayegani, Navaneet K L, Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash

ICLR 2024poster

Fine-tuning Large Language Models (LLMs) and storing them for each downstream task or domain is impractical because of the massive model size (e.g., 350GB in GPT-3). Current literature, such as LoRA, showcases the potential of low-rank modifications to the original weights of an LLM, enabling effici…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2023

PRANC: Pseudo RAndom Networks for Compacting Deep Models

Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani, Kossar Pourahmadi Meibodi, Rana Muhammad Shahroz Khan, Soheil Kolouri +1

ICCV 2023poster

We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek local minima that reside within the subspace spanned by these random models (i.e., `basis' networks). Our framework, PRA…

Cited by 12 PDF ↗code ↗Scholar ↗