Chaohui Yu

Interpreting computed tomography (CT) requires review of hundreds of volumetric slices and remains time-intensive and expertise-dependent. Automated CT report generation offers a promising route to improving clinical efficiency, yet the field still lacks a generalizable CT report generation foundation model that supports multi-region reporting and remains robust across external real-world cohorts. Here we present Astra, a generalizable CT report generation foundation model developed on 90,678 thoracoabdominal CT-report pairs collected from five sites worldwide (CTRgDB), comprising 353,671 abnormalities spanning eight organ systems. By harmonizing report style and further refining diagnostic consistency via reinforcement learning, Astra achieves style-consistent and diagnostically accurate report generation across diverse anatomical regions and institutions. Evaluated on CTRgDB and six external cohorts, Astra achieves state-of-the-art performance with a 38.4% average improvement in fine-grained diagnostic metrics (P<0.001). Deployed at external clinical sites without any site-specific fine-tuning, Astra accelerated chest report drafting by 29.6% and improved abdominal report completeness by 11.3% among junior and mid-level radiologists (P<0.001). Furthermore, Astra extends beyond report generation by improving multi-disease diagnostic performance across 18 thoracic and 30 abdominal conditions and by scaling vision-language pretraining through high-quality report synthesis. Together, these findings establish Astra as a generalizable foundation model for CT interpretation that improves chest CT reporting efficiency and abdominal CT report quality in real-world clinical settings while providing transferable representations for diagnostic model development.

The intrinsic variability of solar and wind energy, compounded by their rapid expansion, has intensified power curtailment challenges^1,2. Although spatiotemporal complementarity between these resources is widely recognized as a pathway to enhance renewable integration and reduce balancing requirements^{3,4,5,6,7,8,9,10,11,12,13,14,15,16}, existing assessments are largely based on hypothetical deployments^{17,18,19,20,21,22,23,24}. Consequently, how solar–wind complementarity manifests under real-world infrastructure and shapes system-level integration outcomes remains unclear. Here we develop a unified national inventory to enable a data-driven assessment of solar–wind complementarity. The inventory covers 319,972 solar photovoltaic facilities and 91,609 wind turbines in 2022, identified from sub-metre satellite imagery using a deep-learning-based framework. Using this dataset, we show that solar–wind complementarity substantially reduces generation variability, with effectiveness increasing as the geographic scope of pairing expands. At the system level, nationwide inter-provincial coordination raises effective renewable penetration by 99.88 TWh in an 80% dispatchable-flexibility system, corresponding to 9.1% of total solar and wind generation, or approximately 120 h of national average load. These findings demonstrate that energy complementarity is a scalable, system-wide mechanism for advancing solar and wind penetration, offering broadly applicable insights into the role of inter-regional coordination in enhancing renewable integration in large power systems.

Synthesizing 3D content from single image has great potential in many real-world applications. To deal with the inherent ambiguity of single image, existing methods usually leverage pre-trained 2D diffusion models for computational intensive per-instance optimization. Although having been able to create 3D assets in a feed-forward manner, the efficacy of recent advances in 3D foundation models is still limited due to neglecting geometric cues from images. To address this issue, we propose an efficient 3D foundation model named LPM to synthesize 3D content from an image. Like the masked modeling in the 2D image domain, the key of our approach is to learn 3D representations from incomplete visible shapes. By taking advantage of a synthesis-by-analysis paradigm, we establish an efficient pipeline to first estimate the visible portions and then generate the complete 3D representations. Based on the principle that an image is the projection of 3D model, we initially estimate partial 3D voxel features from single image, which are further projected onto orthogonal planes to form an incomplete yet efficient triplane representation. Subsequently, an autoencoder is employed to model a complete triplane representation based on the incomplete parts. We train our model on massive data with over 250 million parameters to enhance its generalization capability. The experimental results show that LPM can generate high-fidelity 3D objects from an image within 0.1 seconds, which is more effective than the existing feed-forward approaches. Our implementation and pre-trained models will be made publicly available.