SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

1 code implementation • 16 Mar 2025 • Xin Wang, Samiul Alam, Zhongwei Wan, Hui Shen, Mi Zhang

In this work, we introduce SVD-LLM V2, a SVD-based LLM compression method that optimizes singular value truncation in SVD compression with two techniques.

Language Modeling Language Modelling +2

Artificial Intelligence of Things: A Survey

1 code implementation • 25 Oct 2024 • Shakhrul Iman Siam, Hyunho Ahn, Li Liu, Samiul Alam, Hui Shen, Zhichao Cao, Ness Shroff, Bhaskar Krishnamachari, Mani Srivastava, Mi Zhang

We hope this survey will serve as a valuable resource for those engaged in AIoT research and act as a catalyst for future explorations to bridge gaps and drive advancements in this exciting field.

Survey

The Internet of Things in the Era of Generative AI: Vision and Challenges

no code implementations • 3 Jan 2024 • Xin Wang, Zhongwei Wan, Arvin Hekmati, Mingyu Zong, Samiul Alam, Mi Zhang, Bhaskar Krishnamachari

Advancements in Generative AI hold immense promise to push Internet of Things (IoT) to the next level.

Federated Learning Prompt Engineering

Efficient Large Language Models: A Survey

3 code implementations • 6 Dec 2023 • Zhongwei Wan, Xin Wang, Che Liu, Samiul Alam, Yu Zheng, Jiachen Liu, Zhongnan Qu, Shen Yan, Yi Zhu, Quanlu Zhang, Mosharaf Chowdhury, Mi Zhang

We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of efficient LLMs research and inspire them to contribute to this important and exciting field.

Natural Language Understanding Survey +1

FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things

1 code implementation • 29 Sep 2023 • Samiul Alam, Tuo Zhang, Tiantian Feng, Hui Shen, Zhichao Cao, Dong Zhao, JeongGil Ko, Kiran Somasundaram, Shrikanth S. Narayanan, Salman Avestimehr, Mi Zhang

However, most existing FL works do not use datasets collected from authentic IoT devices and thus do not capture unique modalities and inherent challenges of IoT data.

Benchmarking Federated Learning

GPT-FL: Generative Pre-trained Model-Assisted Federated Learning

1 code implementation • 3 Jun 2023 • Tuo Zhang, Tiantian Feng, Samiul Alam, Dimitrios Dimitriadis, Sunwoo Lee, Mi Zhang, Shrikanth S. Narayanan, Salman Avestimehr

Through comprehensive ablation analysis across various data modalities, we discover that the downstream model generated by synthetic data plays a crucial role in controlling the direction of gradient diversity during FL training, which enhances convergence speed and contributes to the notable accuracy boost observed with GPT-FL.

Diversity Federated Learning

OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking

no code implementations • 15 May 2023 • Fazle Rabbi Rakib, Souhardya Saha Dip, Samiul Alam, Nazia Tasnim, Md. Istiak Hossain Shihab, MD. Nazmuddoha Ansary, Syed Mobassir Hossen, Marsia Haque Meghla, Mamunur Mamun, Farig Sadeque, Sayma Sultana Chowdhury, Tahsin Reasat, Asif Sushmit, Ahmed Imtiaz Humayun

Our test dataset comprises 23. 03 hours of speech collected and manually annotated from 17 different sources, e. g., Bengali TV drama, Audiobook, Talk show, Online class, and Islamic sermons to name a few.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

3 code implementations • 3 Dec 2022 • Samiul Alam, Luyang Liu, Ming Yan, Mi Zhang

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical.

Federated Learning model +1

Bengali Common Voice Speech Dataset for Automatic Speech Recognition

no code implementations • 28 Jun 2022 • Samiul Alam, Asif Sushmit, Zaowad Abdullah, Shahrin Nakkhatra, MD. Nazmuddoha Ansary, Syed Mobassir Hossen, Sazia Morshed Mehnaz, Tahsin Reasat, Ahmed Imtiaz Humayun

Bengali is one of the most spoken languages in the world with over 300 million speakers globally.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes

2 code implementations • 1 Oct 2020 • Samiul Alam, Tahsin Reasat, Asif Shahriyar Sushmit, Sadi Mohammad Siddiquee, Fuad Rahman, Mahady Hasan, Ahmed Imtiaz Humayun

We propose a labeling scheme based on graphemes (linguistic segments of word formation) that makes segmentation in-side alpha-syllabary words linear and present the first dataset of Bengali handwritten graphemes that are commonly used in an everyday context.

Multi-Label Classification Optical Character Recognition +1

AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018

no code implementations • 10 Oct 2018 • Sharif Amit Kamran, Ahmed Imtiaz Humayun, Samiul Alam, Rashed Mohammad Doha, Manash Kumar Mandal, Tahsin Reasat, Fuad Rahman

Solving problems with Artificial intelligence in a competitive manner has long been absent in Bangladesh and Bengali-speaking community.

BIG-bench Machine Learning

NumtaDB - Assembled Bengali Handwritten Digits

2 code implementations • 6 Jun 2018 • Samiul Alam, Tahsin Reasat, Rashed Mohammad Doha, Ahmed Imtiaz Humayun

To benchmark Bengali digit recognition algorithms, a large publicly available dataset is required which is free from biases originating from geographical location, gender, and age.