Jinxi Xiang (Derek) is a Postdoctoral Researcher at Stanford University School of Medicine, working with Prof. Ruijiang Li on AI for precision oncology. He earned his Ph.D. from Tsinghua University in 2021 and previously served as a Senior Researcher at Tencent AI Lab, where he led computational pathology projects deployed in clinical settings.

His long-term vision is to build AI systems that can read the full complexity of a tumor, including its molecular programs, spatial architecture, and evolutionary dynamics, directly from data collected in routine clinical care. Realizing this vision requires bridging the gap between the richness of modern omics technologies and what is practically accessible at the point of care.

Dr. Xiang pursues this through multimodal foundation models that integrate histopathology images, spatial transcriptomics, proteomics, and clinical text, enabling comprehensive tumor characterization without relying on costly or specialized assays. The broader ambition is not merely to improve individual predictions, but to construct a new computational layer for oncology — one that transforms how tumors are understood, classified, and ultimately treated across diverse patient populations.

News

• [2026-08] Invited to serve as an Area Chair for ICLR 2027.
• [2026-07] Our paper, A unified vision-language model for precision oncology and biomarker prediction in neuroblastoma (NEVA), has been published in Nature Communications.
• [2026-05] Recognized as a Gold Reviewer for ICML 2026.
• [2026-04] Two new preprints of multimodal histopathology AI released: STORM and MUPAD.
• [2026-01] Our paper, AI-enabled virtual spatial proteomics from histopathology for interpretable biomarker discovery in lung cancer, has been published in Nature Medicine.
• [2025-12] Received the IEEE Transactions on Medical Imaging Reviewer Certificate of Excellence 2025.
• [2025-08] Invited to serve as an Area Chair for ICLR 2026.
• [2025-02] Nature Cancer highlighted the development of foundation models such as MUSK, which marks substantial progress in the field of digital pathology.
• [2025-01] Our study, MUSK, was featured by many platforms such as Stanford Medicine, Stanford Report, Stanford HAI, NVIDIA News, Stanford Daily, BioArt(Chinese), AdvanceBC(Chinese), and more.
• [2025-01] Our paper, A Vision-Language Foundation Model for Precision Oncology, has been published in Nature.
• [2024-11] Our paper, A Vision-Language Foundation Model for Precision Oncology, has been accepted by Nature!