AI가 쓴 글이 아닌 것처럼 윤문해주는 스킬

Machine Learning Engineering Open Book

Official Repository for SAM2Act

Tracking Any Point (TAP)

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Wan: Open and Advanced Large-Scale Video Generative Models

Efficient Triton Kernels for LLM Training

The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Democratizing Reinforcement Learning for LLMs

Official Repo for Open-Reasoner-Zero

Witness the aha moment of VLM with less than $3.

Solve Visual Understanding with Reinforced VLMs

FlashMLA: Efficient Multi-head Latent Attention Kernels

Reinforcement Learning environments based on the 1993 game Doom

Chrome extension for running Generative AI in your browser locally

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Simulation platform for general-purpose robotics & embodied AI learning.

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

DayDreamer: World Models for Physical Robot Learning

Masked World Models for Visual Control

A curated list of awesome self-supervised learning methods in videos

Finetuning Offline World Models in the Real World

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Adaptive importance sampling modification to MPPI

A curated list of awesome model based RL resources (continually updated)

Stable-Baselines tutorial for Journées Nationales de la Recherche en Robotique 2019

PyTorch implementation of soft actor critic