Rahel Gunaratne@rahel_gunaratne220

The goal is to provide an interactive tool for visualizing research papers in a 2D map where the papers are placed on the map based on some vector embedding of the summary. The papers that are similar to each other will cluster together. This will allow researchers to identify papers that have similar concepts and even allow users to look at concepts from different fields that are applicable in their own field.

The existing search bar in most websites performs keyword search. A slow and arduous process in which the user has to read through a myriad of information before finding the tidbit that they wanted in the first place. My goal was to create a question answering tool that can be easily integrated into any website. It allows you to find specific information, provides answers in a clear, understandable way and includes sources and more information should the user need it. Presenting Web Indexer. Developed to significantly improve the user experience by providing a service that ChatGPT, Google and standard search bars cannot. This project was made for the AI21 labs hackathon organized by lablab.ai.

This tool lets you create videos based off stable key frames and interpolate the results using custom apis.

A tool for language learning. Conversation mode: 1. Give basic roleplay scenario's 2. Evaluate conversation 3. Proper grammar/word usage Practice mode: 1. Read sentences 2. See your pronunciation mistakes 3. Play the audio of both ElevenLabs and your audio to compare the difference It uses a local proxy server with: - ElevenLabs for realistic TTS - OpenAI for LLM completions and transcriptions - For the pronunciation, I used Montreal forced alignment to get transcription intervals. It generates aligned phones with the transcription. The Montreal Forced Aligner (MFA) is a tool used in speech processing and linguistics to align speech recordings with their corresponding transcriptions. It takes a speech recording and a corresponding text transcript as input and automatically aligns the words in the transcript with their corresponding segments in the audio. 1. Phones are generated (using MFA) for both the user recorded message and the ElevenLabs TTS. 2. Damerau-levenshtein distance is computed between the words and the phones of each word to get the difference in pronunciation. 3. The shortest-edit path is interpreted as replacing, inserting, deleting or transposing a word/phone. i.e. Do you have mispronunciation patterns like stressing your T's. This is done by comparing the generated phones to voices by ElevenLabs. You can learn different accents or languages by changing the voice/language of the ElevenLabs voice.

Front-end development can be frustrating. There is still no all-in-one solution that provides a good balance between customizability and efficiency. The current way to develop front end is with a website builder that lacks customizability or with a web framework which takes more time. So our goal was to create a tool that can be used to significantly speed up the front end development process. It does this by allowing you to click on UI elements to see and modify the corresponding source code (and this has never been done before). And by using AI, you can edit the code with natural language and easily create new components.

When learning something new, text alone sometimes falls short. For example, understanding the TLS handshake protocol through a textual explanation can be challenging, while an animation makes it much easier to grasp. VizMotion aims to simplify the creation of animated diagrams, allowing users to generate animations from text input, make real-time edits to shapes and text during playback, and pause to refine details seamlessly. It also offers the ability to export these animations as videos for easy sharing and presentation. Given that most people are visual learners, animations are an effective teaching tool, and the education market, valued in the billions, is vast. VizMotion can be applied to any educational or explainer-related service, such as educational resources, documentation, YouTube, blogs—essentially any context where users are learning something. It can also be easily integrated as an embed into existing websites.