publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2024

  1. When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
    Norah Alzahrani, Hisham Abdullah Alyahya, Yazeed Alnumay, and 8 more authors
    arXiv preprint arXiv:2402.01781, 2024
    arXiv
  2. A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
    Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari, and 8 more authors
    arXiv preprint arXiv:2407.04069, 2024
    arXiv
  3. ALLaM: Large Language Models for Arabic and English
    M Saiful Bari, Yazeed Alnumay, Norah A Alzahrani, and 8 more authors
    arXiv preprint arXiv:2407.15390, 2024
    arXiv

2023

  1. Mixture of domain experts for language understanding: An analysis of modularity, task performance, and memory tradeoffs
    Benjamin Kleiner, Jack GM Fitzgerald, Haidar Khan, and 1 more author
    In 2022 IEEE Spoken Language Technology Workshop (SLT), 2023
    Website
  2. Low-Resource Compositional Semantic Parsing with Concept Pretraining
    Subendhu Rongali, Mukund Sridhar, Haidar Khan, and 3 more authors
    arXiv preprint arXiv:2301.09809, 2023
    arXiv
  3. Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning
    Mustafa Safa Ozdayi, Charith Peris, Jack Fitzgerald, and 5 more authors
    arXiv preprint arXiv:2305.11759, 2023
    arXiv

2022

  1. RescoreBERT: Discriminative Speech Recognition Rescoring With Bert
    Liyan Xu, Yile Gu, Jari Kolehmainen, and 5 more authors
    In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
    arXiv
  2. Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models
    Weiqi Sun, Haidar Khan, Nicolas Mesnards, and 2 more authors
    In Proceedings of the ACM Web Conference 2022, 2022
    arXiv
  3. Controlled Data Generation via Insertion Operations for NLU
    Manoj Kumar, Yuval Merhav, Haidar Khan, and 3 more authors
    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, 2022
    Website
  4. Alexa teacher model: Pretraining and distilling multi-billion-parameter encoders for natural language understanding systems
    Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, and 8 more authors
    In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022
    arXiv
  5. AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model
    Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, and 8 more authors
    arXiv preprint arXiv:2208.01448, 2022
    arXiv
  6. Squashed weight distribution for low bit quantization of deep models
    Nikko Ström, Haidar Khan, and Wael Hamza
    2022
    Website

2021

  1. ASR N-Best Fusion Nets
    Xinyue Liu, Mingda Li, Luoxin Chen, and 5 more authors
    In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
    Website
  2. Output Randomization: A Novel Defense for both White-box and Black-box Adversarial Models
    Daniel Park, Haidar Khan, Azer Khan, and 2 more authors
    arXiv preprint arXiv:2107.03806, 2021
    arXiv
  3. Limitations of Knowledge Distillation for Zero-shot Transfer Learning
    Saleh Soltan, Haidar Khan, and Wael Hamza
    In Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, 2021
    Website

2020

  1. Don’t Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
    Qile Zhu, Haidar Khan, Saleh Soltan, and 2 more authors
    arXiv preprint arXiv:2010.03714, 2020
    arXiv
  2. Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings
    Prafull Prakash, Saurabh Kumar Shashidhar, Wenlong Zhao, and 3 more authors
    arXiv preprint arXiv:2010.05002, 2020
    arXiv
  3. Using multiple ASR hypotheses to boost i18n NLU performance
    Charith Peris, Gokmen Oz, Khadige Abboud, and 3 more authors
    arXiv preprint arXiv:2012.04099, 2020
    arXiv

2019

  1. Short paper: creating adversarial malware examples using code insertion
    Daniel Park, Haidar Khan, and Bülent Yener
    Arxiv preprint, 2019
    arXiv
  2. Deep density ratio estimation for change point detection
    Haidar Khan, Lara Marcuse, and Bülent Yener
    arXiv preprint arXiv:1905.09876, 2019
    arXiv
  3. Thwarting finite difference adversarial attacks with output randomization
    Haidar Khan, Daniel Park, Azer Khan, and 1 more author
    arXiv preprint arXiv:1905.09871, 2019
    arXiv
  4. Predicting Change Points in Multivariate Time Series Data
    Haidar Khan
    Rensselaer Polytechnic Institute, 2019
    Website
  5. Optimal Mini-Batch Size Selection for Fast Gradient Descent
    Michael P Perrone, Haidar Khan, Changhoan Kim, and 3 more authors
    arXiv preprint arXiv:1911.06459, 2019
    arXiv
  6. Generation & Evaluation of Adversarial Examples for Malware Obfuscation
    Daniel Park, Haidar Khan, and Bülent Yener
    In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), 2019
    arXiv

2018

  1. Learning filter widths of spectral decompositions with wavelets
    Haidar Khan, and Bulent Yener
    Advances in Neural Information Processing Systems, 2018
    Website

2017

  1. Focal onset seizure prediction using convolutional networks
    Haidar Khan, Lara Marcuse, Madeline Fields, and 2 more authors
    IEEE Transactions on Biomedical Engineering, 2017
    arXiv

2014

  1. Interaction Recognition Using Sparse Portraits
    Ivan Bogun, Haidar Khan, Jacob Chen, and 1 more author
    In 2014 22nd International Conference on Pattern Recognition, 2014
    Website