Marzieh S. Tahaei

26 papers A* 3Journal 15Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models. EMNLP Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei
2025	J	`jnl`	Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models. CoRR Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei
2025	J	`jnl`	DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers. CoRR Aman Sharma, Saeed Najafi, Parsa Farinneya, Benyamin Jamialahmadi, Marzieh S. Tahaei, Yuhe Fan, Mehdi Rezagholizadeh, Boxing Chen, Aref Jafari
2025	J	`jnl`	InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation. CoRR Faezeh Faez, Marzieh S. Tahaei, Yaochen Hu, Ali Pourranjbar, Mahdi Biparva, Mark Coates, Yingxue Zhang
2025	J	`jnl`	SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers. CoRR Aref Jafari, Yuhe Fan, Benyamin Jamialahmadi, Parsa Farinneya, Boxing Chen, Marzieh S. Tahaei
2024	—	`conf`	Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification. NAACL-HLT (Findings) Marzieh S. Tahaei, Aref Jafari, Ahmad Rashid, David Alfonso-Hermelo, Khalil Bibi, Yimeng Wu, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`conf`	QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning. EMNLP (Industry Track) Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh S. Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	J	`jnl`	QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning. CoRR Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh S. Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2024	—	`conf`	Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference. EACL (Findings) Parsa Kavehzadeh, Mojtaba Valipour, Marzieh S. Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2023	J	`jnl`	On the Transferability of Whisper-based Representations for "In-the-Wild" Cross-Task Downstream Speech Applications. CoRR Vamsikrishna Chemudupati, Marzieh S. Tahaei, Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk
2023	J	`jnl`	Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT). CoRR Parsa Kavehzadeh, Mojtaba Valipour, Marzieh S. Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
2023	J	`jnl`	SortedNet, a Place for Every Network and Every Network in its Place: Towards a Generalized Solution for Training Many-in-One Neural Networks. CoRR Mojtaba Valipour, Mehdi Rezagholizadeh, Hossein Rajabzadeh, Marzieh S. Tahaei, Boxing Chen, Ali Ghodsi
2023	—	`conf`	Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation. EACL (Findings) Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia
2023	—	`conf`	Towards Low-Cost Learning-based Camera ISP via Unrolled Optimization. CRV Ali Mosleh, Marzieh S. Tahaei, James J. Clark, Vahid Partovi Nia
2022	A*	`conf`	Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition. AAAI Marawan Gamal Abdel Hameed, Marzieh S. Tahaei, Ali Mosleh, Vahid Partovi Nia
2022	J	`jnl`	Integer Fine-tuning of Transformer-based Models. CoRR Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia
2022	A*	`conf`	Is Integer Arithmetic Enough for Deep Learning Training? NeurIPS Alireza Ghaffari, Marzieh S. Tahaei, Mohammadreza Tayaranian, Masoud Asgharian, Vahid Partovi Nia
2022	J	`jnl`	Is Integer Arithmetic Enough for Deep Learning Training? CoRR Alireza Ghaffari, Marzieh S. Tahaei, Mohammadreza Tayaranian, Masoud Asgharian, Vahid Partovi Nia
2022	J	`jnl`	KronA: Parameter Efficient Tuning with Kronecker Adapter. CoRR Ali Edalati, Marzieh S. Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2022	—	`conf`	Kronecker Decomposition for GPT Compression. ACL (2) Ali Edalati, Marzieh S. Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2022	—	`conf`	KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation. NAACL-HLT Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi, Mehdi Rezagholizadeh
2022	J	`jnl`	SeKron: A Decomposition Method Supporting Many Factorization Structures. CoRR Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei, Vahid Partovi Nia
2021	J	`jnl`	Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition. CoRR Marawan Gamal Abdel Hameed, Marzieh S. Tahaei, Ali Mosleh, Vahid Partovi Nia
2021	J	`jnl`	Kronecker Decomposition for GPT Compression. CoRR Ali Edalati, Marzieh S. Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
2021	J	`jnl`	KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation. CoRR Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi, Mehdi Rezagholizadeh
2012	—	`conf`	Nonlinear Unsupervised Feature Learning: How Local Similarities Lead to Global Coding. ICDM Workshops Amirreza Shaban, Hamid R. Rabiee, Marzieh S. Tahaei, Erfan Salavati