Saved in:
Bibliographic Details
Main Authors: Yang, Xiaomeng, Tan, Zhiyu, Zhong, Xiaohui, Yang, Mengping, Huang, Qiusheng, Chen, Lei, Wu, Libo, Li, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909981014491136
author Yang, Xiaomeng
Tan, Zhiyu
Zhong, Xiaohui
Yang, Mengping
Huang, Qiusheng
Chen, Lei
Wu, Libo
Li, Hao
author_facet Yang, Xiaomeng
Tan, Zhiyu
Zhong, Xiaohui
Yang, Mengping
Huang, Qiusheng
Chen, Lei
Wu, Libo
Li, Hao
contents Scientific discovery increasingly relies on integrating heterogeneous, high-dimensional data across disciplines nowadays. While AI models have achieved notable success across various scientific domains, they typically remain domain-specific or lack the capability of simultaneously understanding and generating multimodal scientific data, particularly for high-dimensional data. Yet, many pressing global challenges and scientific problems are inherently cross-disciplinary and require coordinated progress across multiple fields. Here, we present FuXi-Uni, a native unified multimodal model for scientific understanding and high-fidelity generation across scientific domains within a single architecture. Specifically, FuXi-Uni aligns cross-disciplinary scientific tokens within natural language tokens and employs science decoder to reconstruct scientific tokens, thereby supporting both natural language conversation and scientific numerical prediction. Empirically, we validate FuXi-Uni in Earth science and Biomedicine. In Earth system modeling, the model supports global weather forecasting, tropical cyclone (TC) forecast editing, and spatial downscaling driven by only language instructions. FuXi-Uni generates 10-day global forecasts at 0.25° resolution that outperform the SOTA physical forecasting system. It shows superior performance for both TC track and intensity prediction relative to the SOTA physical model, and generates high-resolution regional weather fields that surpass standard interpolation baselines. Regarding biomedicine, FuXi-Uni outperforms leading multimodal large language models on multiple biomedical visual question answering benchmarks. By unifying heterogeneous scientific modalities within a native shared latent space while maintaining strong domain-specific performance, FuXi-Uni provides a step forward more general-purpose, multimodal scientific models.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01363
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A unified multimodal understanding and generation model for cross-disciplinary scientific research
Yang, Xiaomeng
Tan, Zhiyu
Zhong, Xiaohui
Yang, Mengping
Huang, Qiusheng
Chen, Lei
Wu, Libo
Li, Hao
Artificial Intelligence
Scientific discovery increasingly relies on integrating heterogeneous, high-dimensional data across disciplines nowadays. While AI models have achieved notable success across various scientific domains, they typically remain domain-specific or lack the capability of simultaneously understanding and generating multimodal scientific data, particularly for high-dimensional data. Yet, many pressing global challenges and scientific problems are inherently cross-disciplinary and require coordinated progress across multiple fields. Here, we present FuXi-Uni, a native unified multimodal model for scientific understanding and high-fidelity generation across scientific domains within a single architecture. Specifically, FuXi-Uni aligns cross-disciplinary scientific tokens within natural language tokens and employs science decoder to reconstruct scientific tokens, thereby supporting both natural language conversation and scientific numerical prediction. Empirically, we validate FuXi-Uni in Earth science and Biomedicine. In Earth system modeling, the model supports global weather forecasting, tropical cyclone (TC) forecast editing, and spatial downscaling driven by only language instructions. FuXi-Uni generates 10-day global forecasts at 0.25° resolution that outperform the SOTA physical forecasting system. It shows superior performance for both TC track and intensity prediction relative to the SOTA physical model, and generates high-resolution regional weather fields that surpass standard interpolation baselines. Regarding biomedicine, FuXi-Uni outperforms leading multimodal large language models on multiple biomedical visual question answering benchmarks. By unifying heterogeneous scientific modalities within a native shared latent space while maintaining strong domain-specific performance, FuXi-Uni provides a step forward more general-purpose, multimodal scientific models.
title A unified multimodal understanding and generation model for cross-disciplinary scientific research
topic Artificial Intelligence
url https://arxiv.org/abs/2601.01363