Showing 21-40 of 79 projects
Official implementation of EAGLE, a framework for developing AI-powered coding tools and language models.
An open-source implementation of a Flow Matching Model for training AI agents via online reinforcement learning.
A benchmark for evaluating different implementations of Variational Autoencoders (VAEs) in PyTorch.
A reinforcement learning agent trained in a diffusion world model for AI research and development.
A simple vision transformer baseline for human pose estimation, with pre-trained models and advanced capabilities.
A powerful multimodal transformer for combining language, vision, and other modalities in AI applications.
MotionGPT is a unified motion-language generation model that can generate human motion using large language models.
Collection of CVPR and NeurIPS poster examples and templates for AI/ML researchers and developers.
Official code for a fast ODE solver for diffusion probabilistic model sampling in 10 steps
A research project from Facebook that explores multimodal AI models for computer vision and language tasks.
Official repository for C-Eval, a Chinese evaluation suite for foundation models.
An end-to-end autonomous driving benchmark with a world model RL expert for developers working on AI-powered driving systems.
An open-source text-to-image generation model that enables developers to create powerful AI-powered image generation capabilities.
An interactive visualization tool for discovering interpretable controls in Generative Adversarial Networks (GANs)
SOLO and SOLOv2 are instance segmentation models for computer vision tasks, built with PyTorch.
Generates 3D meshes from single images in 45 seconds without per-shape optimization
A rigorous benchmark for evaluating the code quality and efficiency of large language models like GPT-4.
TransGAN is a Python implementation of a GAN model using two pure transformers, suitable for vibe coders and AI tool developers.
A self-supervised video representation learning model for video understanding tasks.
A repository for ImageReward, a learning and evaluating human preferences for text-to-image generation
Get weekly updates on trending AI coding tools and projects.