Trending Projects

Experiments with local and API-based AI models for vibe coders building with AI tools.

Official implementation of a fashion image-to-video synthesis model using Stable Diffusion.

A PyTorch-dedicated tensor container for vibe coders building with AI tools.

This repository contains machine learning algorithm projects using Jupyter Notebook.

A curated list of awesome deep long-tailed learning resources for AI-focused developers.

A library for building and training discrete world models for Atari game environments using reinforcement learning.

A repository of projects focused on 3D reconstruction using deep learning methods.

A high-performance, GPU-accelerated multimedia/video processing framework for transcoding, AI inference, and more.

A repository containing research papers on text summarization, focused on language models and NLP.

MIRAI is a Rust mid-level IR Abstract Interpreter for analyzing and optimizing Rust code.

Central repository for the engineering and scaling working group of the BigScience AI research project.

A programming language with static memory management based on λ-calculus for vibe coders.

A clean and concise Python library that implements the SIFT (Scale-Invariant Feature Transform) algorithm for computer vision tasks.

A multimodal dataset for emotion recognition in conversation, useful for building conversational AI and chatbots.

Asynchronous reinforcement learning implementation in TensorFlow, Keras, and OpenAI Gym

Official implementation of the ADBench anomaly detection benchmark for machine learning models

A library for training neural models with structured signals, useful for AI and machine learning developers.

WarpFusion is an AI-powered tool for generating and manipulating images, videos, and text-to-video transformations.

Unofficial PyTorch implementation of Self-critical Sequence Training for Image Captioning.

A device management platform for developers to build AI-powered applications and services.

A Python library that implements Spatial Transformer Networks, a type of deep learning model that can learn spatial transformations.

A simple Java library for working with images, focused on developers who use AI tools.

An Android app for the Susi AI assistant, a conversational AI platform.

A Jupyter Notebook project that demonstrates sentiment analysis using LSTMs and TensorFlow.

TensorFlowASR is an almost state-of-the-art automatic speech recognition library in TensorFlow 2 for vibe coders.

This Python library provides a method for removing obstructions from images, useful for AI-powered computer vision applications.

A Java-based data insights platform for 'vibe coders' building with AI tools and frameworks.

Open-source repository of pre-trained language models for various AI and NLP applications.

An open-source Python library that helps developers quickly build and deploy RAG-based LLM web apps.

A contrastive learning-based semi-supervised medical image segmentation network for surgical tools and video analysis.

A PyTorch-based framework for non-autoregressive text-to-speech synthesis, including PortaSpeech and DiffSpeech models.

A flexible and efficient DNN compiler that generates high-performance executable from DNN models.

A Python-based tool for detecting and mitigating phishing attacks on social media using LLM-based modeling.

Lightweight PyTorch models for real-time semantic segmentation on computer vision tasks.

An infrared object detection dataset and benchmark for few-shot learning.

This Python-based suite of tools allows developers to interact with AI services directly from their terminal.

A Python library for Chinese named entity recognition using a Flat-Lattice Transformer model.

Official implementation of the RecurrentGPT paper for interactive generation of long text using AI.

Sample code for Microsoft's Cognitive Speech-to-Text API, featuring custom neural voices and text-to-speech functionality.

A Chinese dependency parser library that can be used for natural language processing tasks.

PyTorch implementation of Barlow Twins, a self-supervised learning technique for computer vision tasks.

A library for building Mixture-of-Experts (MoE) models from the LLaMA language model with continual pre-training.

CareGPT is an open-source, medical large language model (LLM) that aims to promote the rapid development of medical LLMs.

An efficient pose estimation algorithm for video-based object detection and tracking.

Picasso is a CNN visualizer that helps developers understand and interpret convolutional neural networks.

A beautiful and easy-to-use Stable Diffusion WebUI for generating AI-powered art and images.

High-level network definitions with pre-trained weights in TensorFlow for deep learning and computer vision tasks.

An open-source platform for building and deploying ML pipelines with a focus on MLOps

Efficient implementations of Native Sparse Attention, a key component in large language models.