3 citations · 8 across the 13 of their papers we have counts for
14 papers
Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh +2
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model de…
KV-Pipe: On the Relation Between KV Sharing and Pipeline Parallel Efficiency in LLMs
Maryam Dialameh, Hossein Rajabzadeh, Harish Krishnamoorthy Murali +3
Pipeline parallelism (PP) is widely used to scale large language model (LLM) training, but its efficiency is often limited by stage imbalance and pipeline bubbles. Meanwhile, cross…
LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference
Hossein Rajabzadeh, Maryam Dialameh, Chul B. Park +2
Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-dept…
FLOP-Efficient Training: Early Stopping Based on Test-Time Compute Awareness
Hossam Amer, Maryam Dialameh, Hossein Rajabzadeh +3
Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that in…
Bayesian Mixture of Experts For Large Language Models
Maryam Dialameh, Hossein Rajabzadeh, Weiwei Zhang +2
We present Bayesian Mixture of Experts (Bayesian-MoE), a post-hoc uncertainty estimation framework for fine-tuned large language models (LLMs) based on Mixture-of-Experts architect…
EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation
Maryam Dialameh, Hossein Rajabzadeh, Jung Suk Sim +1
Papillary thyroid microcarcinoma (PTMC) is increasingly managed with radio-frequency ablation (RFA), yet accurate lesion segmentation in ultrasound videos remains difficult due to…
ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training
Maryam Dialameh, Rezaul Karim, Hossein Rajabzadeh +5
This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its…
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…
DualSwinUnet++: An Enhanced Swin-Unet Architecture With Dual Decoders For PTMC Segmentation
Maryam Dialameh, Hossein Rajabzadeh, Moslem Sadeghi-Goughari +2
Precise segmentation of papillary thyroid microcarcinoma (PTMC) during ultrasound-guided radiofrequency ablation (RFA) is critical for effective treatment but remains challenging d…
EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models
Hossein Rajabzadeh, Aref Jafari, Aman Sharma +5
Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks.…
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…
Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models
Hossein Rajabzadeh, Suyuchen Wang, Hyock Ju Kwon +1
We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. In particular, we harness the power…
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…
Local Distance Metric Learning for Nearest Neighbor Algorithm
Hossein Rajabzadeh, Mansoor Zolghadri Jahromi, Mohammad Sadegh Zare +1
Distance metric learning is a successful way to enhance the performance of the nearest neighbor classifier. In most cases, however, the distribution of data does not obey a regular…