Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Research Projects
Research Projects
Research Projects
Research Projects
Research Projects
Research Projects
Research Projects
Research Projects
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Collaborate on cutting-edge AI projects, gain hands-on experience, and contribute to innovative solutions at Georgia Tech.
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Open to students from all backgrounds, majors, and skill levels!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Applications to lead a project open in November 2024!
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Multi-Agent Interaction in Simulated Environment using Knowledge Graphs
The project aims to develop a sandbox environment where Non-Player Characters (NPCs) can interact and evolve using knowledge graphs. The goal is to test retrieval systems and memory of NPCs in a large-scale environment with 100+ agents using a novel framework to simulate human memory and behavior at SOTA level.
Matt Steele
Akshay Raj
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Intelligent Malware Detection using Static Analysis
Aarav Gupta
We aim to perform static analysis on software binaries to determine if they are malicious or benign. We will construct Control Flow Graphs (CFG) of the execution paths of suspicious binaries and use architectures such as Graph Neural Networks and Convolutional Neural Networks to predict whether a malware is benign or malicious based on the constructed CFG. For these architectures, we will then perform inference speedups and aim to deliver SOTA models for inference speed and classification accuracy.
Collaborative Autonomous Multi-Agent SLAM
The envisioned final product is an efficient and scalable multi-agent SLAM system which will allow for multiple autonomous robots to collaboratively map and navigate unknown environments with high accuracy, efficiency, and scalability. While this has been explored previously, the CAM-SLAM project aims to enhance these systems by integrating advanced reinforcement learning and deep learning techniques as well as optimized communication protocols.
Krish Mathur
Geronimo Gorostiaga
Intelligent Malware Detection using Static Analysis
Aarav Gupta
We aim to perform static analysis on software binaries to determine if they are malicious or benign. We will construct Control Flow Graphs (CFG) of the execution paths of suspicious binaries and use architectures such as Graph Neural Networks and Convolutional Neural Networks to predict whether a malware is benign or malicious based on the constructed CFG. For these architectures, we will then perform inference speedups and aim to deliver SOTA models for inference speed and classification accuracy.
Collaborative Autonomous Multi-Agent SLAM
The envisioned final product is an efficient and scalable multi-agent SLAM system which will allow for multiple autonomous robots to collaboratively map and navigate unknown environments with high accuracy, efficiency, and scalability. While this has been explored previously, the CAM-SLAM project aims to enhance these systems by integrating advanced reinforcement learning and deep learning techniques as well as optimized communication protocols.
Krish Mathur
Geronimo Gorostiaga
Georgia Tech RAG Chatbot
We have no way to find all information for GT anywhere, and most of our resources are very decentralized. This in turn makes us rely on word of mouth or official responses from faculty to answer questions students may have. To combat this, developing a chatbot that has RAG using a corpus of all Georgia Tech resources would allow students to have a site/app that can answer all their questions at any moment.
Veer Guda
Naman Talreja
Multi-Agent Interaction in Simulated Environment using Knowledge Graphs
The project aims to develop a sandbox environment where Non-Player Characters (NPCs) can interact and evolve using knowledge graphs. The goal is to test retrieval systems and memory of NPCs in a large-scale environment with 100+ agents using a novel framework to simulate human memory and behavior at SOTA level.
Matt Steele
Akshay Raj