{"ID":2852858,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17937","arxiv_id":"2510.17937","title":"UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts","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.","short_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,...","url_abs":"https://arxiv.org/abs/2510.17937","url_pdf":"https://arxiv.org/pdf/2510.17937v1","authors":"[\"Fu-Yun Wang\",\"Han Zhang\",\"Michael Gharbi\",\"Hongsheng Li\",\"Taesung Park\"]","published":"2025-10-20T16:02:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608033,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2852858,"paper_url":"https://arxiv.org/abs/2510.17937","paper_title":"UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts","repo_url":"https://github.com/G-U-N/UniRL","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}