Trending Projects

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation using PyTorch.

Guidance for training an AWS DeepRacer model using Amazon SageMaker, providing developers full control over the process.

Fast and embedded solvers for nonlinear optimal control and nonlinear model predictive control

A Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation

Official code for DragDiffusion, a CVPR 2024 highlight for AI-powered image editing.

A fast local neural text-to-speech engine for Mycroft, an open-source voice assistant.

An open-source toolkit for analyzing the internal workings of Transformer-based language models.

A PyTorch-based library for named entity recognition using the BERT language model.

Fine-tune LLMs with online reinforcement learning for building AI-powered applications and agents.

This repository provides hands-on examples and guidance for building, training, deploying and maintaining deep learning models in production.

A collection of paper reading notes on deep learning and machine learning topics.

A Python library for planning with diffusion models to enable flexible behavior synthesis.

A comprehensive survey of task-oriented dialogue research, including datasets and state-of-the-art methods.

Official implementation of HierSpeech++, a hierarchical speech recognition model.

Solution for the Data Science Bowl 2017 competition, focused on AI-powered coding and tools.

A framework for encrypted machine learning in TensorFlow, enabling confidential computing and privacy-preserving AI.

This repository provides a series of GPU optimization topics and CUDA kernel optimizations for high-performance computing.

Boosts the deployment and serving of deep learning models and web services.

A fast and differentiable PyTorch library for computing MS-SSIM and SSIM image quality metrics.

This project provides advanced voiceprint recognition models and data preprocessing methods using PyTorch.

A full-stack framework for building cross-platform mobile apps with AI capabilities using React Native and TypeScript.

Official implementation of a PyTorch-based library for semantic keypoint detection and pose estimation.

Mulberry is an o1-like Reasoning and Reflection MLLM implemented via Collective MCTS for AI-powered coding tools.

This repository contains mini machine learning projects with Jupyter Notebook files.

Gerbil Scheme is a high-performance Scheme implementation suitable for building AI tools and applications.

A curated collection of resources for ChatTTS, including free demos, voice samples, and more for vibe coders.

A curated list of resources for the random forest machine learning algorithm.

This repository contains a PyTorch implementation of GIRAFFE, a generative model for representing 3D scenes as compositional neural feature fields.

PaddleViT is a state-of-the-art Visual Transformer and MLP model library for the PaddlePaddle 2.0+ deep learning framework.

Efficient Region-Aware Neural Radiance Fields for high-fidelity talking portrait synthesis

This is an open-source library for trajectory prediction, which could be useful for developers working on AI-powered applications.

An open-source, AI-powered web monitoring platform that helps developers automate web searches and email alerts.

A collection of papers on diffusion models for 3D generation, useful for developers working on AI-powered 3D content creation.

Official implementation of a multi-view consistent image generation model for AI-focused developers.

A Twitch bot built with SUSI.AI, an open-source AI assistant, for developers to interact with.

Self-evolving AI agent framework using Genome Evolution Protocol for autonomous agent improvement

Deep learning models to automatically correct errors in short, message-like text.

A speech recognition server based on Vosk and Kaldi libraries, supporting WebSocket, gRPC, and WebRTC protocols.

A repository with research notes on domain generalization, causality, robustness, and other ML topics.

A novel approach to model and reconstruct radiance fields for 3D rendering and reconstruction.

An AI-powered platform for discovering and retrieving meme images and stickers

The official implementation of Self-Play Fine-Tuning (SPIN), a deep learning technique for fine-tuning large language models.

Python tools for working with the KITTI computer vision and robotics dataset

A Python library that provides dynamic thresholding (CFG scale fix) for Stable Diffusion AI models.

A tiny Python library for coding with large language models (LLMs) like GPT-3 and ChatGPT.

A collection of Jupyter notebooks and tutorials on using LangChain and prompt engineering with large language models like ChatGPT.

SincNet is a neural architecture for efficiently processing raw audio samples for speech and audio processing tasks.

A mirror of ChatGPT based on the GPT-3.5-Turbo model, allowing developers to interact with and build upon the ChatGPT functionality.

A curated collection of awesome resources for image-to-image translation, a popular computer vision task.

An awesome list of resources for research on CLIP, a contrastive language-image pre-training model.