Trending Projects

A self-evolving AI agent that can learn and improve itself without any training data.

Unsupervised language modeling and robust sentiment classification for AI/ML developers.

An open-source SLAM (Simultaneous Localization and Mapping) library for 3D LiDAR odometry and mapping.

A comprehensive benchmark for spatio-temporal predictive learning, with a focus on AI-powered weather forecasting and video prediction.

A real-time portrait animation library that supports ONNX and TensorRT for fast inference on various platforms.

A library for explaining the decisions made by Vision Transformers, a type of AI model used for computer vision tasks.

A comprehensive SDK for adding camera effects, video editing, and live streaming features to Android apps.

Repository for the AdaBelief Optimizer, a NeurIPS 2020 Spotlight paper on an adaptive optimizer for AI/ML models.

A PyTorch implementation of a neural radiance field model for talking head synthesis driven by audio.

An AI-powered voice interviewer for hiring developers, built with TypeScript.

A high-quality, open-source text-to-speech library in Rust for developers to build AI-powered voice applications.

A universal, AI-powered chat application built with Go for developers to build on top of.

A CVPR 2024 and TPAMI 2025 AI-powered multimodal learning architecture for vibe coders.

Official implementation of a CVPR'25 oral paper on motion-controllable video diffusion models using real-time warped noise.

Official repository for the Uni-Mol Series Methods, a deep learning-based molecular modeling library.

A Python-based GUI tool for simulating VHS video effects, popular among vibe coders and AI enthusiasts.

This repository contains a list of speech synthesis papers for developers interested in AI-powered voice and speech technology.

An open-source app that allows users to search, read, bookmark, and summarize academic papers from arXiv using AI-powered features.

A Python library for training a humanoid robot to walk using reinforcement learning.

Open-source digital stylus using camera tracking and inertial measurements for vibe coders.

A deep learning-based library for efficient lane detection, using self-attention distillation.

Safe Rust wrapper around the CUDA toolkit for GPU acceleration in AI/ML applications.

A curated list of papers on trajectory and motion prediction, a key topic in computer vision and robotics.

Implementations of selected inverse reinforcement learning algorithms.

Algorithm to texture 3D reconstructions from multi-view stereo images, useful for computer vision and 3D graphics projects.

A collection of machine learning tutorials covering various topics like anomaly detection, time series forecasting, and object detection.

A series of math-focused large language models for AI-powered coding and analysis

An open-source Python library that helps curate better data for large language models (LLMs).

Real-time audio analysis in Python, with visualizations and FFT feature extraction from streaming audio.

A Python GUI tool for offline transcription of speech recordings, including speaker diarization, using state-of-the-art machine learning models.

A Python library that uses AI agents to classify bank transactions.

Neva is a dataflow programming language and compiler that enables parallel computing with static typing.

Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation.

An open-source Chinese medical multimodal model that can summarize chest radiographs.

A free and affordable virtual reality eye tracking platform for developers.

A general representation model for cross-modal learning across vision, audio, and language.

A transformer model that can handle unlimited length input for AI coding tools and applications.

Efficient GPU kernels for block-sparse matrix multiplication and convolution, useful for AI/ML developers.

A Python library for less-is-more reasoning with large language models, focused on the COLM 2025 conference.

A comprehensive guide for developers to stay up-to-date with the latest advancements in AI, ML, DL, and computer vision.

A PyTorch implementation of the TernausNet model for image segmentation, pre-trained on the Kaggle Carvana dataset.

Open source deep learning framework for building AI-powered iOS, macOS, and tvOS apps in Swift.

A PyTorch implementation of Prototypical Networks for Few-Shot Learning, a powerful technique for training AI models on small datasets.

A Jupyter Notebook-based library for exploring and analyzing multimedia datasets at scale.

A natural language detection library for Rust that can identify the language of text samples.

Tailor is an AI-powered video editing tool that simplifies video clipping, generation, and optimization.

A C++ implementation of Stable Diffusion, supporting txt2img and img2img, optimized for Android and other mobile devices.

Code for a model that learns to summarize text from human feedback, useful for AI-powered summarization.

A production-ready GraphRAG platform with multi-modal indexing, AI agents, and scalable Kubernetes deployment.

A fast Rust implementation of the LLaMA2 language model decoder for AI coding tools.