11 citations · 32 across the 15 of their papers we have counts for
15 papers
SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers
Aref Jafari, Yuhe Fan, Benyamin Jamialahmadi +3
Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Lin…
DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
Aman Sharma, Saeed Najafi, Parsa Farinneya +6
Transformers achieve state-of-the-art results across many tasks, but their uniform application of quadratic self-attention to every token at every layer makes them computationally…
Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models
Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh +5
Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility…
QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning
Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu +5
Finetuning large language models requires huge GPU memory, restricting the choice to acquire Larger models. While the quantized version of the Low-Rank Adaptation technique, named…
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Parsa Kavehzadeh, Mojtaba Valipour, Marzieh Tahaei +3
Large language models (LLMs) have revolutionized natural language processing (NLP) by excelling at understanding and generating human-like text. However, their widespread deploymen…
SortedNet: A Scalable and Generalized Framework for Training Modular Deep Neural Networks
Mojtaba Valipour, Mehdi Rezagholizadeh, Hossein Rajabzadeh +4
Deep neural networks (DNNs) must cater to a variety of users with different performance needs and budgets, leading to the costly practice of training, storing, and maintaining nume…
On the Transferability of Whisper-based Representations for "In-the-Wild" Cross-Task Downstream Speech Applications
Vamsikrishna Chemudupati, Marzieh Tahaei, Heitor Guimaraes +5
Large self-supervised pre-trained speech models have achieved remarkable success across various speech-processing tasks. The self-supervised training of these models leads to unive…
KronA: Parameter Efficient Tuning with Kronecker Adapter
Ali Edalati, Marzieh Tahaei, Ivan Kobyzev +3
Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of P…
SeKron: A Decomposition Method Supporting Many Factorization Structures
Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei +1
While convolutional neural networks (CNNs) have become the de facto standard for most image processing and computer vision applications, their deployment on edge devices remains ch…
Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation
Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei +3
The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously…
Is Integer Arithmetic Enough for Deep Learning Training?
Alireza Ghaffari, Marzieh S. Tahaei, Mohammadreza Tayaranian +2
The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point ari…
Kronecker Decomposition for GPT Compression
Ali Edalati, Marzieh Tahaei, Ahmad Rashid +3
GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain due to its state-of-th…
KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation
Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia +2
The development of over-parameterized pre-trained language models has made a significant contribution toward the success of natural language processing. While over-parameterization…
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition
Marawan Gamal Abdel Hameed, Marzieh S. Tahaei, Ali Mosleh +1
Modern Convolutional Neural Network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge…
FoCL: Feature-Oriented Continual Learning for Generative Models
Qicheng Lao, Mehrzad Mortazavi, Marzieh Tahaei +3
In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the c…