Alex KAMENI

Alex KAMENI

Machine Learning Engineer | Data Scientist | AI Researcher

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

LLM Output Parser

less than 1 minute read

Published:

LLMs often return structured data buried inside unstructured text. Instead of writing custom regex or manual parsing, you can now use LLM Output Parser to instantly extract the most relevant JSON/XML structures with just one function call.

LangGraph AgentFlow

less than 1 minute read

Published:

AgentFlow is a Python library that automates the orchestration of multi-step agent workflows by integrating intelligent planning, routing, and execution of specialized operations.

Lightweight Language Identification

less than 1 minute read

Published:

Introducing our new 24.5M-parameter BERT-based language identification model! Trained on 121M sentences across 200 languages, this model is lightweight, CPU-friendly, and designed for real-time language identification tasks.

GraphRAG-Tagger

less than 1 minute read

Published:

GraphRAG-Tagger is an end-to-end lightweight toolkit for extracting topics from PDFs and visualizing their connections using graphs.

Dikoka: AI-Powered Document Analyzer

1 minute read

Published:

Dikoka is an AI-powered document analyzer that helps you navigate and uncover key insights from complex historical records. It extracts key insights, generates concise summaries, and suggests follow-up questions for deeper understanding.

Discursia: AI-Powered Language Learning Redefined

1 minute read

Published:

Discursia is a dynamic language-learning app that fosters conversational skills through interactive discussions. It blends personalized learning with robust AI capabilities to create an immersive and effective language development experience.

Fine-Tuning GLiNER for Location Mention Recognition (LMR)

1 minute read

Published:

Named Entity Recognition (NER) is an essential task in natural language processing (NLP) for identifying key information within text, such as locations, organizations, and people. This project focuses on fine-tuning GLiNER, a pre-trained model specifically designed for NER, to enhance its performance in Location Mention Recognition (LMR).

Specializing Large Language Models for Telecom Applications

less than 1 minute read

Published:

Large Language Models (LLMs) have become highly proficient in text generation, comprehension, and interaction. Despite their successes across various sectors, their application in the telecommunications industry remains limited. This project focuses on optimizing LLMs for telecom-specific knowledge tasks.

Object Detection Using Transformers

1 minute read

Published:

The people of Malawi have faced numerous natural disasters and climatic shocks in recent years, such as droughts, floods, and landslides. These events, compounded by the impacts of Covid-19 and other global issues, have severely affected the health and well-being of most Malawians. Rural areas, where more than 80% of the population resides, have been particularly hard-hit.

Continual Self Supervised Learning through Distillation and Replay

1 minute read

Published:

Self-supervised learning aims to learn useful representations of input data without relying on human annotations. When trained offline with enormous amounts of unlabeled data, self-supervised models have been found to provide visual representations that are equivalent to or better than supervised models. However, in continual learning (CL) circumstances, where data is fed to the model sequentially, their efficacy is drastically diminished.

portfolio

Semi-Supervised Learning with few labels

Published:

Semi Self-Supervised Learning: improving the performance of self-supervised learning models, especially in scenarios where only a small amount of labeled data is available

publications

Detecting Misinformation and its Sources on Social Media

Published in -, 2022

This work proposes an efficient solution for detecting and filtering misinformation on social networks, specifically targeting misinformation spreaders on Twitter during the COVID-19 crisis, using a Bidirectional GRU model that achieved a 95.3% F1-score on a COVID-19 misinformation dataset, surpassing state-of-the-art results.

Recommended citation: Alex Kameni, 2022
Download Paper | Download Slides

DATA INCREMENTAL LEARNING IN DEEP ARCHITECTURES

Published in -, 2022

This study presents a framework for continual self-supervised learning of visual representations that prevents forgetting by combining distillation and proofreading techniques, improving the quality of learned representations even when data is fed sequentially.

Recommended citation: Alex Kameni, 2022
Download Paper | Download Slides