This project features a hierarchical cooperative multi-agent environment where agents must work together to solve a two-part puzzle.

A framework to train agents in a Unity environment using a genetic algorithm

Perception toolkit for sim2real training and validation in Unity

Showcase environment for ML-Agents

Code used for research in multi-agent maze exploration.

A senior research project on the ant colony optimization algorithm in Unity

Demonstration and Visualization of Ant Colony Optimization in Maze solving

MUI-TARE: Multi-Agent Cooperative Exploration with Unknown Initial Position

This repository contains an implementation of latent diffusion models for image generation as well as the weights of three models trained on three different datasets (Anime Faces dataset,Google's c…

An 'antidote' to the recently released AI poison pill project known as Nightshade.

Research code release for the Nightshade project from University of Chicago

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

✨✨Latest Papers on Vision Mamba and Related Areas

A simple self-playing snake game.

This repository contains some comprehensive approaches for the purpose of classifying breast cancer tissue using whole slide images (WSIs).

This is the official code repository for "MedMamba: Vision Mamba for Medical Image Classification"

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory wh…

PyTorch implementation of NMT models along with custom tokenizers, models, and datasets

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Grayscale image colorization using Generative Adversarial Networks

Image Colorization using GANs, written in Pytorch

Colorizing Black&White Japanese Manga using Generative Adversarial Network.

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective…