Avaya Aggarwal

A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.

AI-powered irrigation scheduling system using machine learning, big data processing, and cross-language integration to optimize water usage in agriculture.

Post-training and deployment lab for open-weight diffusion models: LoRA, Diffusion-DPO, GRPO, and step-distillation, with a shared eval harness and Modal serving.

A unified evaluation framework for Vision Language Models for both discriminative and generative tasks

Docs: https://erasus.readthedocs.io/en/latest/ Forget data from any foundation model without retraining. Erasus surgically removes concepts, behaviors, or training samples from LLMs, VLMs, and Diffusion models using coreset selection. 90% less compute, certified removal, multimodal support.

The model predicts Bitcoin's closing price using an LSTM (Long Short-Term Memory) neural network. It's trained on historical 15-minute price data and includes a backtesting component to simulate a trading strategy based on Bollinger Bands and moving averages.