{"ID":2825219,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.21643","arxiv_id":"2512.21643","title":"Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation","abstract":"Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding.","short_abstract":"Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a...","url_abs":"https://arxiv.org/abs/2512.21643","url_pdf":"https://arxiv.org/pdf/2512.21643v3","authors":"[\"Zhiwang Zhou\",\"Yuandong Pu\",\"Xuming He\",\"Yidi Liu\",\"Yixin Chen\",\"Junchao Gong\",\"Xiang Zhuang\",\"Wanghan Xu\",\"Qinglong Cao\",\"Shixiang Tang\",\"Yihao Liu\",\"Wenlong Zhang\",\"Lei Bai\"]","published":"2025-12-25T12:08:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}