1 citations · 1 across the 7 of their papers we have counts for
7 papers
The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Yuanxin Wang, Pawel Filipczuk, Anisha Garg +4
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as…
Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model
Habib Hajimolahoseini, Mohammad Hassanpour, Foozhan Ataiefard +2
This paper introduces a novel method of Progressive Low Rank Decomposition (PLRD) tailored for the compression of large language models. Our approach leverages a pre-trained model,…
SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection
Foozhan Ataiefard, Walid Ahmed, Habib Hajimolahoseini +7
Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the r…
Test-Time Personalization with Meta Prompt for Gaze Estimation
Huan Liu, Julia Qi, Zhenhao Li +4
Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on…
Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization
Xuan Long Do, Mohammad Hassanpour, Ahmed Masry +3
A number of tasks have been proposed recently to facilitate easy access to charts such as chart QA and summarization. The dominant paradigm to solve these tasks has been to fine-tu…
GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values
Farnoosh Javadi, Walid Ahmed, Habib Hajimolahoseini +7
Massive transformer-based models face several challenges, including slow and computationally intensive pre-training and over-parametrization. This paper addresses these challenges…
SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling
Habib Hajimolahoseini, Omar Mohamed Awad, Walid Ahmed +8
In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of…