Published:
Development of methods and tools for auditing and safeguarding Large Language Models against harmful outputs and adversarial attacks. This project includes SafeNudge, a real-time safeguarding method against red teaming attacks, and Output-Scouting, an open-source library for searching dangerous outputs in LLMs’ possible output space. 
Published:
Development of novel frameworks for interpreting and explaining machine learning model predictions. This project includes ExplainerPFN, a model-agnostic framework for output explainability (under development), and ShaRP (Shapley for Rankings and Preferences), which explains feature contributions to ranked outcomes using Shapley values. 
Published:
This project studies the importance of time in the reliability of algorithmic recourse. We highlight the lack of reliability in recourse recommendations over several competitive settings, potentially setting misguided expectations that could result in detrimental outcomes. These findings emphasize the importance of meticulous consideration when AI systems offer guidance in dynamic environments. Our paper, “Setting the Right Expectations: Algorithmic Recourse Over Time”, won the Best AI Track Paper award at EAAMO’23! 
Published:
ML-Research contains the software implementation of most algorithms used or developed in my research. Specifically, it contains scikit-learn compatible implementations for Active Learning, Oversampling, Datasets and various utilities to assist in experiment design and results reporting. Other techniques, such as self-supervised learning and semi-supervised learning are currently under development and are being implemented in pytorch and intended to be scikit-learn compatible.
Published:
This project aims to develop a Competitive Intelligence platform through Natural Language Processing and various visualization techniques. We employ text preprocessing and embedding techniques to encode a large corpus of text as well as Self-Organizing Maps, an unsupervised neural network that facilitates the development of multiple machine learning tasks and visualize high dimensional data.
Published:
The competition’s aim was to optimize a keyboard layout to minimize the workload for usage by an ALS patient. Anthony Carbajal inspired this challenge, a full-time daily life hacker that aims to find innovative ways to improve his and other ALS-patient lives, with whom NILG.AI worked together for developing a first version of this solution. 
Published:
Cyclone Amphan made landfall in South Asia on May 20, 2020. It was the most damaging storm in the history of the Indian Ocean, rendering hundreds of thousands of people homeless, ravaging agricultural lands and causing billions of dollars in damage. How were people affected by the storm? What were the responses of individuals, governments, corporates and NGOs? How was it covered by local, national and international media, as opposed to individuals’ accounts? Who has created the dominant narratives of Cyclone Amphan; and whose voices go unheard? We aim to use online data – such as Twitter posts, news headlines and research publications – to analyze people’s experiences of Cyclone Amphan.
Published:
This project focused on the exploration of several machine learning (ML) techniques, covering different stages of a Land Use/Land Cover Classification (LULC) pipeline. These techniques aimed to minimise problems typically found in this kind of data, namely data ingestion, feature selection, data filtering and classification. This work was a joint effort between me and Manvel Khudinyan. 
Published:
This project studied the potential of Big data to inform destination management organizations. To do so, three sources of Big data are discussed: Telecom, Social media and Airbnb data. This is done through the demonstration and analysis of a set of visualizations and tools, as well as a discussion of applications and recommendations for challenges that have been identified in the market.