Starred repositories
AgentOpt automatically finds the best LLM model combination for each step of your agent — optimizing for accuracy, cost, and latency.
OpenClaw-RL: Train any agent simply by talking
Simple, reliable and well tested training code for quick experiments with transformer based models
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
📷 A composable image editor using Core Image and Metal.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.
Simple configuration GUI for FlexASIO
A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities
A high-throughput and memory-efficient inference and serving engine for LLMs
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
Online Finetuned Flow Submission to Musique QA Benchmark
The Sol Mate GPT but on your e-Paper display!
DiscoGrad - automatically differentiate across conditional branches in C++ programs
GIF encoder based on libimagequant (pngquant). Squeezes maximum possible quality from the awful GIF format.
interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI
An OpenAI-Gym Package for Training and Testing Reinforcement Learning algorithms with OpenSim Models
A mechanistic approach for understanding and detecting factual errors of large language models.