AIPython★ 60
Tencent-Hunyuan/UniRL
UniRL: Multimodal Learning
UniRL is a Python framework for unified reinforcement learning of multimedia models. It enables joint training of vision, language, and audio in a single RL cycle.
// KEY FEATURES
- Supports joint training of vision, language, and audio models in a single RL cycle.
- Modular architecture with a plug-and-play API for modality policies and value networks.
- Includes ready-made environments for tasks with video control and text instructions.
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram