Parseltongue is a powerful prompt hacking tool/browser extension for real-time tokenization visualization and seamless text conversion, supporting formats like binary, base64, leetspeak, special ch…

Aura is like Siri, but in your browser. An AI voice assistant optimized for low latency responses.

GLOMAP - Global Structured-from-Motion Revisited

An Autonomous LLM Agent for Complex Task Solving

[ICML 2024 Oral] Official repository of the SparseTSF paper: "SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters". This work is developed by the Lab of Professor Weiwei Lin (l…

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

A browser extension for automating your browser by connecting blocks

OMG-LLaVA and OMG-Seg codebase

Desktop app for prototyping and debugging LangGraph applications locally.

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Whisper with Medusa heads

The fastest way to create an HTML app

STUMPY is a powerful and scalable Python library for modern time series analysis

Simple static web-based mask drawer, supporting semantic segmentation and video segmentation with interactive Segment Anything Model 2 (SAM2).

ComfyUI nodes to use segment-anything-2

A collection of some of the neat math and physics tricks that I've collected over the last few years.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

An Automated AI-Powered Prompt Optimization Framework

This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

Agent Zero AI framework

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model

Implementation of "Learning to Make Keypoints Sub-Pixel Accurate" (ECCV 2024).

A multimodal agent framework for solving complex tasks

Real-time and accurate open-vocabulary end-to-end object detection

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

Task-based Agentic Framework using StrictJSON as the core