Showing 21-40 of 42 projects
Highly efficient transformer-based model for high-resolution image restoration tasks like deblurring, deraining, and denoising.
An open-source browser agent that autonomously performs complex web tasks using state-of-the-art AI tools.
A Python library that provides SOTA compression techniques and efficient LLM inference on Intel platforms to build chatbots quickly.
A Python library for optimizing deep learning models for faster inference on deployment platforms like TensorRT.
A Python toolkit for building machine/deep learning models on partially-observed time series data
Chai-1 is a state-of-the-art model for biomolecular structure prediction, built with Python.
A comprehensive NLP tutorial covering the latest SOTA models and techniques across various NLP tasks.
A collection of datasets and state-of-the-art results for various Chinese NLP tasks.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, with outstanding singing lyrics recognition.
A C++ fork of the llama.cpp project with additional SOTA quants and improved performance for AI-focused developers.
An open-source AI-powered drone location tracking system for developers.
A comprehensive survey of deep learning techniques for 3D point cloud analysis, covering classification, detection, segmentation, and tracking.
Open academic research on improving the LLaMA language model to state-of-the-art performance.
Frontier CoreML audio models for iOS and macOS apps with text-to-speech, speech-to-text, voice activity detection, and speaker diarization.
High-quality implementations of standard and state-of-the-art methods for Bayesian and probabilistic machine learning.
Realtime AI voice agents with state-of-the-art multimodal AI models for AI toys, companions, and devices.
An open-source, state-of-the-art image restoration library for deblurring, denoising, and deraining tasks.
A collection of high-quality, single-file implementations of state-of-the-art offline and offline-to-online reinforcement learning algorithms.
A curated list of the most impressive AI research papers for developers interested in cutting-edge AI.
A state-of-the-art discrete acoustic codec model for audio language modeling with 40/75 tokens per second.
Get weekly updates on trending AI coding tools and projects.