UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts

Code

• github.com/g-u-n/unirl
  OfficialIn paper★ 76

Abstract

We present UniRL-Zero, a unified reinforcement learning (RL) framework that boosts, multimodal language model understanding and reasoning, diffusion model multimedia generation, and their beneficial interaction capabilities within a unified model. Our work defines six scenarios for unified model reinforcement learning, providing systematic baselines for reinforcement learning of unified understanding and generation model. Our code is available at https://github.com/G-U-N/UniRL.

Reproductions