Showing 1-20 of 26 projects
This repository is an archived collection of papers and code related to computer vision and machine learning.
DouZero is a deep reinforcement learning framework for mastering the Chinese card game DouDizhu.
A highly efficient visual representation learning framework for AI-powered coding tools and applications.
Code and models for a multimodal large language model that can perform any-to-any tasks
Official repository for the OFA (Unifying Architectures, Tasks, and Modalities) AI model, supporting various vision-language tasks.
Official implementation of EAGLE, a framework for developing AI-powered coding tools and language models.
A powerful text-to-image diffusion model that can be used for recaptioning, planning, and generating with multimodal LLMs.
An LLM compiler that enables efficient parallel function calling for large language models.
A Python library that improves the stability and accuracy of convolutional neural networks (CNNs) in computer vision tasks.
SmoothQuant is an efficient post-training quantization tool for large language models, enabling accurate and fast inference.
An official repository for a paper on using executable code actions to elicit better LLM agents
Official repository for a paper on a large vision-language model for medical applications
Official TensorFlow implementation of the Noise2Noise: Learning Image Restoration without Clean Data paper.
A Vision-and-Language Transformer model for multimodal tasks without the need for convolution or region supervision.
A curated list of resources for deep reinforcement learning and the future of AI.
This TensorFlow code implements a curiosity-driven exploration algorithm for deep reinforcement learning.
An optimized library for running sub-billion parameter language models on mobile and edge devices.
SALMONN is a suite of advanced multi-modal large language models (LLMs) for audio, speech, and video understanding.
A Python library that breaks the sequential dependency of LLM inference using lookahead decoding for faster AI model inference.
A powerful GAN-based text-to-image synthesis model for fast large-scale image generation.
Get weekly updates on trending AI coding tools and projects.