Samiul Alam

PhD Student, Ohio State University.


Hi there! I am an incoming PhD. student at Ohio State University. I work on improving privacy and fairness in deep learning. I used to work at Samsung Research and Development Institute in Bangladesh as a Software Engineer till 2021. I graduated from Bangladesh University of Engineering and Technology in 2017.

I am one of the co-founders of I lead the collection and standardisation efforts behind popular open source Bengali Natural Language and OCR Datasets like NumtaDB, Bengali Graphemes and Common Voice Bengali Speech Dataset.

I am deeply passionate about my work and regularly try and find novel applications. As such, I have worked in a wide range of applications. If you have any questions about my research or have any relevant ideas in mind, feel free to e-mail me.


Dec 17, 2023 We just released our survey paper on Efficient LLMs. Check it out!
Dec 14, 2023 My research on Multi-channel Skin Conductance deconvolution was published at IEEE Journal of Open Engineering, Medicine and Biology
Aug 15, 2023 Finished my MS degree at MSU and joined OSU as a Graduate Fellow.
Jan 1, 2023 Humbled to be awarded the highly competitive OSU Graduate School University Fellowship!
Nov 11, 2022 Invited to present my research on model heterogeneous federated learning at Google’s Workshop on Federated Learning and Analyics

selected publications

  1. Efficient Large Language Models: A Survey
    Wan, Zhongwei, Wang, Xin, Liu, Che,  Alam, Samiul, Zheng, Yu, Qu, Zhongnan, Yan, Shen, Zhu, Yi, Zhang, Quanlu, Chowdhury, Mosharaf, and others,
  2. Sparse Multichannel Decomposition of Electrodermal Activity With Physiological Priors
    Alam, Samiul, Amin, Md. Rafiul, and Faghih, Rose T.
    IEEE Open Journal of Engineering in Medicine and Biology 2023
  3. OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
    Rakib, Fazle Rabbi, Dip, Souhardya Saha,  Alam, Samiul, Tasnim, Nazia, Shihab, Md. Istiak Hossain, Ansary, Md. Nazmuddoha, Hossen, Syed Mobassir, Meghla, Marsia Haque, Mamun, Mamunur, Sadeque, Farig, Chowdhury, Sayma Sultana, Reasat, Tahsin, Sushmit, Asif, and Humayun, Ahmed Imtiaz
    In Proc. INTERSPEECH 2023 2023
  4. FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
    Alam, Samiul, Liu, Luyang, Yan, Ming, and Zhang, Mi
    In Advances in Neural Information Processing Systems 2022
  5. Bengali Common Voice Speech Dataset for Automatic Speech Recognition
    Alam, Samiul, Sushmit, Asif, Abdullah, Zaowad, Nakkhatra, Shahrin, Ansary, MD, Hossen, Syed Mobassir, Mehnaz, Sazia Morshed, Reasat, Tahsin, and Humayun, Ahmed Imtiaz
    arXiv preprint arXiv:2206.14053 2022
  6. A large multi-target dataset of common bengali handwritten graphemes
    Alam, Samiul, Reasat, Tahsin, Sushmit, Asif Shahriyar, Siddique, Sadi Mohammad, Rahman, Fuad, Hasan, Mahady, and Humayun, Ahmed Imtiaz
  7. Numtadb-assembled bengali handwritten digits
    Alam, Samiul, Reasat, Tahsin, Doha, Rashed Mohammad, and Humayun, Ahmed Imtiaz
    arXiv preprint arXiv:1806.02452 2018