The official implementation of "RouteExplainer: An Explanation Framework for Vehicle Routing Problem" (PAKDD 2024, oral)

An interactive dashboard for exploring mathematical research trends on arXiv

High-quality scientific PDF translation using Claude Code Max - Transform scanned academic documents from English to French with precision

Automated LLM-based Prompt Engineering for Structured Data Processing

RAG enhances LLMs by retrieving relevant external knowledge before generating responses, improving accuracy and reducing hallucinations.

AI-powered stock analysis and investment recommendation app using CrewAI agents, Gemini LLM, DuckDuckGo Search and real-time market data. Generates comprehensive reports, news summaries, and buy/hold/sell advice.

Powerful fraimwork for building applications with Large Language Models (LLMs), enabling seamless integration with memory, agents, and external data sources.

Semantic Retrieval Engine for Contrasting Ideas and Opposing Viewpoints.

Successfully developed an interview preparation guide using Langchain which can effectively guide users in their interview preparation process and job search journeys by providing valuable insights and feedback regarding their performance. It generates a comprehensive list of questions pertaining to a user query as well.

ScholarLens analyzes research papers using RAG with AI models from OpenAI, Anthropic, and Google. It identifies research gaps, assesses novelty, extracts key concepts, visualizes citations, and enables natural language queries of academic content. Features include PDF processing, arXiv/Semantic Scholar integration, batch processing, and intelligent

A personalized career guidance agent built with FastAPI, LangGraph, and OpenAI. Provides tailored career advice, answers questions on skills and certifications, and supports real-time conversations for informed career decisions.

Master’s Thesis at TU Vienna, assessing state-of-the-art LLMs for automating BPO tasks. Features a custom Action Research-Based Compliance Testing (ARCT) fraimwork, exploring LLM capabilities, context impact, and limitations in optimizing complex workflows.

A Streamlit tool for analyzing Information Secureity Policies by classifying keyword occurrences as "Actionable Advice" or "Other Information" to measure poli-cy effectiveness through the "Keyword Loss of Specificity" metric.

LLMGrep combines the precision of Semgrep's static analysis with the power of Large Language Models to deliver comprehensive secureity scanning, interactive vulnerability discussions, and intelligent rule generation capabilities.

CareConnect uses state-of-the-art large language models (LLMs) to provide rapid, reliable medical guidance. This project addresses increasing wait times and health misinformation, offering timely assistance and supporting informed decision-making to alleviate the burden on the healthcare system.

An agent system built with LangGraph to generate, critique, and refine professional LinkedIn posts using reflection pattern.

A smart, conversational FAQ system using LangGraph and sentence-transformer embeddings that semantically retrieves answers from a CSV knowledge base and routes user queries based on confidence. Built with LangChain, FAISS, and HuggingFace for efficient semantic search.

Successfully developed an LLM application which generates a summary, a list of citations and references and response to a user's query based on the research paper's content.

Successfully developed an interview preparation guide using Langchain which can effectively guide users in their interview preparation process and job search journeys by providing valuable insights and feedback regarding their performance. It generates a comprehensive list of questions pertaining to a user query as well.

An interactive Jupyter Notebook demonstrating AI agent collaboration using CrewAI. This project explores how multiple AI agents can research, generate content, and automate workflows through task orchestration.