Skip to content
View igor17400's full-sized avatar
Seeking knowledge
Seeking knowledge

Block or report igor17400

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
igor17400/README.md

Hi there, I'm Igor Lima Rocha Azevedo 👋

Website LinkedIn Google Scholar GitHub Twitter(X) Email


📖 A Bit About Me

My research journey spans three continents: I began in Brazil, earning a first-class Electrical Engineering degree from the University of Brasilia and winning the Brazilian Government Scientific Initiation Scholarship Award for FPGA research with Professor Alexandre Nery. After that I worked in partnership with Cellcrypt supervised by Professor Edson Mintsu Hung researching machine learning pipelines to improve call quality by optimizing PJSIP codec parameters.

My next step was in Japan, where I received the prestigious Japanese Government (MEXT) Scholarship to work at The University of Tokyo under Prof. Toyotaro Suzumura, former MIT-IBM Watson AI Lab Research principal scientist. There, I collaborated with Nikkei Inc. (Japan's second-largest media company) under supervision of Dr. Yuichiro Yasui, researching news recommender systems and foundational LLMs. This resulted in a SIAM SDM'25 paper publication work on news recommenders achieving superior multilingual performance and earning the SIAM Travel Award, which recognizes promising early-career researchers in data mining.

Now at United Kingdom studying at Imperial College London, I'm pursuing an MRes in AI/ML, supervised by Prof. Pedro Mediano on generative and contrastive deep learning for predicting rare events in large-scale clinical data in partnership with the NHS.

Pinned Loading

  1. awrs_recsys awrs_recsys Public

    Forked from toyolabo/awrs_recsys

    AWRS: An Avoidance-Aware Recommender System. Our research indicates that recommender systems should consider avoidance as a fundamental factor.

    Jupyter Notebook

  2. NewsReX NewsReX Public

    The ultimate goal of NewsReX is to provide open access to the latest tools for training news recommendation models, making experiments faster and accessible to a wider range of GPUs.

    Python 11

  3. alphadl alphadl Public

    Lightning AI Project for Cutting-Edge Deep Learning Models in Stock Markets

    Jupyter Notebook

  4. deeplearning deeplearning Public

    Just a private repo with some code and references to the tutorias I write.

    Jupyter Notebook

  5. n2s n2s Public

    N2S - Knowledge Made Accessible. Learn what matters. Without the noise.

    HTML 1

  6. py_daily_bytes py_daily_bytes Public

    Daily Python code snippets for fun and practice!

    Python