Trending Projects

A Python-based emotional companionship program powered by large language models (LLMs) for building AI-driven chatbots and virtual characters.

A native Clojure dialect hosted on LLVM with seamless C++ interop, designed for vibe coders.

A TypeScript library that uses ChatGPT to deobfuscate JavaScript code.

2D Gaussian splatting for geometrically accurate radiance field reconstruction, useful for novel view synthesis.

An open-source Python3 tool for recognizing layouts, tables, math formulas, and text in images, converting them to Markdown.

A toolkit for creating, sharing, and using natural language prompts for machine learning tasks.

A custom node pack for ComfyUI, an AI-powered image enhancement tool, focused on convenience and productivity for 'vibe coders'.

A PyTorch library for processing spatiotemporal graph data using neural machine learning models.

A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop-like functionality.

Multimodal conversational video generation powered by AI, enabling new vibe-coder collaboration experiences.

Instant AI Face Swap, a TypeScript library for developers to easily add AI-powered face swapping to their projects.

A comprehensive AI content generation and publishing system for WeChat, supporting multi-source data collection, intelligent analysis, and automated publishing.

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets.

A Python library for grounding image matching in 3D using the MASt3R algorithm.

AnyCrawl is a Node.js/TypeScript web scraper that extracts structured data from search engines and websites for use in AI/LLM applications.

A Python-based tool for building Vtuber-like applications, similar to Vtube Studio.

NVIDIA GPU Operator manages GPUs in Kubernetes for developers building AI-powered applications.

Optical character recognition for Japanese manga comics, built with Python and deep learning.

A diverse and well-annotated dataset for license plate detection and recognition

An official implementation of a time series forecasting model using large language models.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

A self-hosted, local-only NVR and AI computer vision software with features like object detection and face recognition.

An open-source quantitative trading platform powered by reinforcement learning for finance and fintech developers.

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

A repository that contains interview notes and questions related to large language models (LLMs) for algorithm engineers.

Highly efficient transformer-based model for high-resolution image restoration tasks like deblurring, deraining, and denoising.

Autoformer: A deep learning model for long-term time series forecasting, focused on developers building with AI tools.

This GitHub repository provides a Bootcamp for dealing with unstructured data like reverse image search, audio search, and NLP.

Swin-Unet is a pure transformer-based model for medical image segmentation, with potential use in AI-powered coding tools.

Fully open data curation for reasoning models for vibe coders building with AI tools.

A PyTorch implementation of various Unet models for image segmentation, including Attention Unet and Nested Unet.

A highly efficient module for temporal modeling in video understanding tasks.

Official implementation of iTransformer, an effective transformer-based time series forecasting model.

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.

GPU programming related news and material links for developers who use AI tools.

A lightweight, high-performance voice activity detector (VAD) library for conversational AI and real-time speech processing.

A CVPR'24 highlighted Python library for building Gaussian Splatting SLAM systems for robotics.

A fractal graph-of-thought tool for AI agents, web links, notes, and code that enables rhizomatic mind-mapping and second brain workflows.

An automated translation solution for visual novels (Galgames) that supports major language models like GPT-4 and Claude.

A TypeScript-based tool that uses AI to auto-manage personal task context and todo lists.

An open-source text-to-speech tool supporting long-form text and multi-voice narration.

A curated list of efficient and compressed large language models for developers to explore.

A PyTorch-based implementation of the YOLO object detection model for the NVIDIA DeepStream SDK.

A simple vision transformer baseline for human pose estimation, with pre-trained models and advanced capabilities.

Aimbot tool using AI and machine learning to improve aim in various video games.

A curated collection of must-read papers and blogs on large language model-based long-context modeling.

A robotics research project focused on aligning simulation and real-world physics for learning agile humanoid whole-body skills.

Compares the performance of multiple NVIDIA GPUs and Apple Silicon for running large language model inference.

Recipes for shrinking, optimizing, and customizing cutting-edge computer vision models.

Official implementation of a decomposable multiscale mixing model for time series forecasting