[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Open source implementation of the paper "MM-Vid: Advancing Video Understanding with GPT-4V(ision)".

Official repo for MM-REACT

[ECCV 2024] Official GitHub repository for the paper "LingoQA: Visual Question Answering for Autonomous Driving"

Set-of-Mark Prompting for GPT-4V and LMMs

LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations.

A modern JavaScript library for handling Hangul characters.

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

🏠 My Personal Blog

Node.js example app from the OpenAI API quickstart tutorial

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

🕸️ Web apps in pure Python 🐍

A small Trello clone built with React and Redux

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

🎄 Christmas Lab - Dancing Tree

🐻 Bear necessities for state management in React

Pure react-based typeahead and typeahead-tokenizer

A contenteditable text editor with predictive typeahead, similar to Gmail's Smart Compose feature.

⚛️ Fast 3kB React alternative with the same modern API. Components & Virtual DOM.

R package for the tidy calculation of inter-rater reliability

JavaScript API for Chrome and Firefox

Delightful JavaScript Testing.

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

🎮 A list of popular/awesome video games, add-ons, maps, etc. hosted on GitHub. Any genre. Any platform. Any engine.

Pretrained Language Models for Korean

Venmo trasaction dataset for data analysis/visualization/anything

⚡️ Front End interview preparation materials for busy engineers