Lightweight coding agent that runs in your terminal

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

Large Reasoning Models

code for paper "Accessing higher dimensions for unsupervised word translation"

Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?

A suite of image and video neural tokenizers

Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

The best OSS video generation models, created by Genmo

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Train VAE like a boss

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Text-to-Music Generation with Rectified Flow Transformers

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

Efficient Triton Kernels for LLM Training

High-resolution models for human tasks.

SGLang is a high-performance serving framework for large language models and multimodal models.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Benchmarking Legal Knowledge of Large Language Models

real time face swap and one-click video deepfake with only a single image

Official PyTorch implementation of "Authentic Hand Avatar from a Phone Scan via Universal Hand Model", CVPR 2024.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.