Trending Projects

A Python library that provides a fast and efficient keyword extraction algorithm using NLTK.

A Python library for fast reconstruction of neural radiance fields from direct voxel grid optimization.

Bayesian marketing toolbox in PyMC with models for media mix, customer lifetime value, and buy-till-you-die.

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

RStan is an R interface to the Stan probabilistic programming language, used for Bayesian data analysis and inference.

A tutorial course for building AI-powered applications using Stable Diffusion and PyTorch.

PixelLib is a Python library for image and video segmentation using deep learning models like Mask R-CNN, DeepLab, and PointRend.

Provides a powerful object detection and tracking solution for vehicle and pedestrian counting using YOLOv5 and DeepSort.

Utilities for decoding deep representations (like sentence embeddings) back to text.

A Python-based face editing tool for Stable Diffusion, a popular AI image generation model.

A curated list of practical natural language processing tools and libraries in Ruby for developers.

A powerful C++ library for building causal models and performing advanced statistical analysis.

Adds support for very large language models (vLLMs) to IndexTTS, enabling faster AI-powered text-to-speech inference.

A Python library focused on interpreting the behavior of large language models like OpenAI's GPT-3.

PyTorch code for a CVPR 2018 paper on few-shot learning, a technique for training ML models with limited data.

A challenging, contamination-free benchmark for large language models (LLMs) to evaluate their performance.

Vocos is a high-quality audio synthesis library that bridges the gap between time-domain and Fourier-based neural vocoders.

A curated list of resources for image captioning and related areas, useful for developers working on AI projects.

Flock is a low-code platform for rapidly building AI-powered chatbots, RAG, and multi-agent workflows.

Official implementation of CEBRA, a tool for joint behavioral and neural analysis using learnable latent embeddings.

A curated collection of research papers and resources for natural language processing (NLP) practitioners.

Powerful workflow engine and end-to-end pipeline solutions implemented with native Kubernetes resources.

A Python library for depth estimation and 3D/4D reconstruction using AI-powered prompts.

An interactive visualization tool to explore the geometric intuition behind diffusion models.

A Python library for generating expressive talking video using memory-guided diffusion models.

Code for high-fidelity 3D human avatar modeling using animatable Gaussians, a novel approach for pose-dependent 3D reconstruction.

OmniSafe is an infrastructural framework for accelerating safe reinforcement learning research.

VideoGPT is a Jupyter Notebook-based project for generating videos from text prompts using AI models.

Robust and accurate IMU + X sensor fusion localization for robot navigation and VIO applications.

Code for reproducing key results in the paper 'InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets'

A lightweight collaborative text span annotation tool for named entity recognition and event extraction.

A ChatGPT plugin for the Yunzai bot framework, enabling AI-powered chatbots on QQ platforms.

Deprecated Scikit-learn integration package for Apache Spark, useful for machine learning on big data.

A library of recommendation algorithms based on Graph Neural Networks for information retrieval and recommendation systems.

A Python library for sentiment analysis, text classification, and other machine learning tasks on Weibo data.

A PyTorch library for training and deploying efficient computer vision models using ViT-based architectures.

A real-time multimodal emotion recognition web app for text, sound, and video inputs.

A curated list of SLAM (Simultaneous Localization and Mapping) resources for developers working in computer vision and robotics.

A research project focused on open-world object detection using continual and contrastive learning techniques.

A learning platform that leverages LLMs to assist students, scholars, and lifelong learners.

A JavaScript library for creating neural style transfer images, a type of AI-powered image generation.

A collection of research papers and resources on computer vision tasks like image classification, object detection, and face recognition.

Open-source project for medical image segmentation using the Segment Anything Model (SAM) from Anthropic

A Python library that boosts cost efficiency, inference accuracy, and cross-domain adaptability for complex QA systems.

A multimodal large language model series for Chinese and English AI-powered coding and painting tools.

A library for training reusable controllers for physically simulated characters using adversarial skill embeddings.

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

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

Tutorials on implementing image classification architectures using PyTorch and TorchVision.

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