Follow
Marzieh S. Tahaei
Marzieh S. Tahaei
Research Scientist
No verified email
Title
Cited by
Cited by
Year
Krona: Parameter efficient tuning with kronecker adapter
A Edalati, M Tahaei, I Kobyzev, VP Nia, JJ Clark, M Rezagholizadeh
arXiv preprint arXiv:2212.10650, 2022
1112022
Synchronizability of EEG-based functional networks in early Alzheimer's disease
MS Tahaei, M Jalili, MG Knyazeva
IEEE Transactions on Neural Systems and Rehabilitation Engineering 20 (5 …, 2012
632012
KroneckerBERT: Significant compression of pre-trained language models through kronecker decomposition and knowledge distillation
M Tahaei, E Charlaix, V Nia, A Ghodsi, M Rezagholizadeh
Proceedings of the 2022 Conference of the North American Chapter of the …, 2022
39*2022
Kronecker decomposition for gpt compression
A Edalati, M Tahaei, A Rashid, VP Nia, JJ Clark, M Rezagholizadeh
arXiv preprint arXiv:2110.08152, 2021
372021
Patch-based image reconstruction for PET using prior-image derived dictionaries
MS Tahaei, AJ Reader
Physics in Medicine & Biology 61 (18), 6833, 2016
272016
Convolutional neural network compression through generalized Kronecker product decomposition
MGA Hameed, MS Tahaei, A Mosleh, VP Nia
Proceedings of the AAAI Conference on Artificial Intelligence 36 (1), 771-779, 2022
242022
Compressing pre-trained language models using progressive low rank decomposition
H Hajimolahoseini, M Rezagholizadeh, V Partovinia, M Tahaei, OM Awad, ...
Advances in Neural Information Processing Systems, 2021
162021
Is integer arithmetic enough for deep learning training?
A Ghaffari, MS Tahaei, M Tayaranian, M Asgharian, V Partovi Nia
Advances in Neural Information Processing Systems 35, 27402-27413, 2022
152022
FoCL: Feature-oriented continual learning for generative models
Q Lao, M Mortazavi, M Tahaei, F Dutil, T Fevens, M Havaei
Pattern Recognition 120, 108127, 2021
152021
Sortednet, a place for every network and every network in its place: Towards a generalized solution for training many-in-one neural networks
M Valipour, M Rezagholizadeh, H Rajabzadeh, MS Tahaei, B Chen, ...
CoRR, 2023
102023
Qdylora: Quantized dynamic low-rank adaptation for efficient large language model tuning
H Rajabzadeh, M Valipour, T Zhu, M Tahaei, HJ Kwon, A Ghodsi, B Chen, ...
arXiv preprint arXiv:2402.10462, 2024
82024
MR-guided PET image denoising
MS Tahaei, AJ Reader, DL Collins
2016 IEEE Nuclear Science Symposium, Medical Imaging Conference and Room …, 2016
72016
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
P Kavehzadeh, M Valipour, M Tahaei, A Ghodsi, B Chen, ...
Findings of the Association for Computational Linguistics: EACL 2024, 2129-2145, 2024
62024
Two novel PET image restoration methods guided by PET‐MR kernels: Application to brain imaging
MS Tahaei, AJ Reader, DL Collins
Medical Physics 46 (5), 2085-2102, 2019
62019
Towards fine-tuning pre-trained language models with integer forward and backward propagation
M Tayaranian, A Ghaffari, MS Tahaei, M Rezagholizadeh, M Asgharian, ...
arXiv preprint arXiv:2209.09815, 2022
52022
On the Transferability of Whisper-based Representations for" In-the-Wild" Cross-Task Downstream Speech Applications
V Chemudupati, M Tahaei, H Guimaraes, A Pimentel, A Avila, ...
arXiv preprint arXiv:2305.14546, 2023
42023
Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
M Tahaei, A Jafari, A Rashid, D Alfonso-Hermelo, K Bibi, Y Wu, A Ghodsi, ...
Findings of the Association for Computational Linguistics: NAACL 2024, 4443-4450, 2024
32024
Combining different variance reduction approaches for PET image reconstruction
MS Tahaei, AJ Reader
2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC …, 2014
22014
Multi-Centre Assessment of HRRT Image Uniformity via 68 Ge and 18 F Cylindrical and Anthropomorphic Phantoms
AJ Reader, MS Tahaei, A Rahmim, SH Keller, S Blinder, M Sibomana, ...
Medical Imaging Conference, 2013
22013
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
P Kavehzadeh, M Valipour, M Tahaei, A Ghodsi, B Chen, ...
arXiv preprint arXiv:2309.08968, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20