The Learning Agency Lab - PII Data Detection || Develop automated techniques to detect and remove PII from educational data.

LMSYS - Chatbot Arena Human Preference Predictions | Predicting Human Preferences in the Wild

This JaraConverse model is a cutting-edge Transformer-based supervised Language Model (LLM) specifically designed for generating Python code snippets.

Fine-tune the Gemma2B language model on a climate-related question-answer dataset to improve its domain-specific knowledge using LoRA (Low Rank Adaptation).

Code & data for the Kaggle Competition "Detect AI Generated Text"

Automated Essay Scoring 2.0 | Improve upon essay scoring algorithms to improve student learning outcomes

Sentence Reconstruction using Transformer Model

A mini gpt style language model developed from wikipedia content

A generative AI project that builds a self-improving reasoning agent using multiple AI models and agentic workflows. The system generates answers to complex tasks, evaluates its own reasoning through a critic model, and refines responses iteratively to produce more reliable outputs.

Enhancing automated essay scoring with advanced AI techniques using Keras-NLP and LSTM, aimed at improving educational outcomes through accurate assessment of student essays.

AI Mathematical Olympiad - Progress Prize 1 | Solve national-level math challenges using artificial intelligence models

LLM Prompt Recovery

PoC мультимодального поиска изображений по текстовому описанию для фотохостинга с использованием ResNet50 и BERT. Использованы Python, TensorFlow, SentenceTransformers.

Using Transformer model to classify IMDb Reviews. Low-level implementation of data preprocessing and tokenization using keras_nlp library