Mohammad-Javad Darvishi-Bayazi

prof_pic.jpg

Montreal, Qc, Canada

Javad Bayazi is an Artificial Intelligence (AI) Research Scientist at Hydro-Québec Research Institute (IREQ) where he focuses on developing innovative AI solutions for the renewable energy sector, with particular emphasis on foundation models and time series forecasting. Prior to this role, he was a PhD student at Mila - Quebec Artificial Intelligence Institute (Mila) and the Université de Montréal (UdeM), working under the supervision of Jocelyn Faubert and Irina Rish. Javad’s research focuses on robustness and transfer learning in artificial neural networks, with recent work evaluating and developing foundation models and time series forecasting (Google Scholar, Web of Science). He has dedicated his academic career to exploring the frontiers of AI, aiming to develop models that are not only accurate but also reliable and adaptable. Javad’s contributions to the field are poised to make significant impacts on both theoretical research and practical applications in AI and cognitive science.

news

Jul 26, 2024 Presented our paper 'VFA' at ICML 2024 FM-Wild Workshop
Jun 07, 2024 Generative AI with Large Language Models
Apr 15, 2024 New Paper: Pathological Detection in EEG with Transfer Learning
Mar 01, 2024 Diving Deep into AI: My Experience at AAAI 2024

latest posts

Sep 27, 2024 Time Series Forecasting demo
Apr 08, 2024 Psycho-LLaVA: Psychology of Large Language and Vision Assistant

selected publications

  1. vision-frequency-analysis-foundation-models-human.png
    VFA: Vision Frequency Analysis of Foundation Models and Human
    Mohammad-Javad Darvishi-Bayazi, Md Rifat Arefin, Jocelyn Faubert, and 1 more author
    In ICML 2024 Workshop on Foundation Models in the Wild, 2024
    arXiv PDF Code
  2. generalizing-unseen-domains-distribution-matching.png
    Generalizing to unseen domains via distribution matching
    Isabela Albuquerque, João Monteiro, Mohammad-Javad Darvishi-Bayazi, and 2 more authors
    arXiv preprint arXiv:1911.00804, 2019
    arXiv Code
  3. lag-llama-foundation-models-time-series-forecasting.png
    Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
    Kashif Rasul, Arjun Ashok, Andrew Robert Williams, and 15 more authors
    2023
    arXiv Code
  4. beyond-performance-task-demand-effort-individual-differences-pilots.png
    Beyond performance: the role of task demand, effort, and individual differences in ab initio pilots
    Mohammad-Javad Darvishi-Bayazi, Andrew Law, Sergio Mejia Romero, and 3 more authors
    Scientific Reports, 2023
    DOI HTML
  5. amplifying-pathological-detection-eeg-transfer-learning.png
    Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning
    Mohammad-Javad Darvishi-Bayazi, Mohammad Sajjad Ghaemi, Timothee Lesort, and 3 more authors
    Computers in Biology and Medicine, 2024
    HTML Code
  6. woods-benchmarks-out-distribution-generalization-time-series.png
    WOODS: Benchmarks for out-of-distribution generalization in time series
    Jean-Christophe Gagnon-Audet, Kartik Ahuja, Mohammad-Javad Darvishi-Bayazi, and 3 more authors
    arXiv preprint arXiv:2203.09978, 2022
    HTML Code
  7. general-purpose-brain-foundation-models-time-series-neuroimaging.png
    General-Purpose Brain Foundation Models for Time-Series Neuroimaging Data
    Mohammad-Javad Darvishi-Bayazi, Hena Ghonia, Roland Riachi, and 6 more authors
    In NeurIPS Workshop on Time Series in the Age of Large Models, 2024
    HTML