Xiaoying Wu

Zhaolong Su, Leheng Zhao, Xiaoying Wu et al.

Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically trained in centralized settings where all training and downstream datasets are gathered in a central server, limiting the deployment in privacy-sensitive and geographically distributed scenarios. In this paper, we present FedUMM, a general federated learning framework for UMMs under non-IID multimodal data with low communication cost. Built on NVIDIA FLARE, FedUMM instantiates federation for a BLIP3o backbone via parameter-efficient fine-tuning: clients train lightweight LoRA adapters while freezing the foundation models, and the server aggregates only adapter updates. We evaluate on VQA v2 and the GenEval compositional generation benchmarks under Dirichlet-controlled heterogeneity with up to 16 clients. Results show slight degradation as client count and heterogeneity increase, while remaining competitive with centralized training. We further analyze computation--communication trade-offs and demonstrate that adapter-only federation reduces per-round communication by over an order of magnitude compared to full fine-tuning, enabling practical federated UMM training. This work provides empirical experience for future research on privacy-preserving federated unified multimodal models.

AJ Venkatakrishnan, Arjun Puranik, Akash Anand et al.

The COVID-19 pandemic demands assimilation of all available biomedical knowledge to decode its mechanisms of pathogenicity and transmission. Despite the recent renaissance in unsupervised neural networks for decoding unstructured natural languages, a platform for the real-time synthesis of the exponentially growing biomedical literature and its comprehensive triangulation with deep omic insights is not available. Here, we present the nferX platform for dynamic inference from over 45 quadrillion possible conceptual associations extracted from unstructured biomedical text, and their triangulation with Single Cell RNA-sequencing based insights from over 25 tissues. Using this platform, we identify intersections between the pathologic manifestations of COVID-19 and the comprehensive expression profile of the SARS-CoV-2 receptor ACE2. We find that tongue keratinocytes and olfactory epithelial cells are likely under-appreciated targets of SARS-CoV-2 infection, correlating with reported loss of sense of taste and smell as early indicators of COVID-19 infection, including in otherwise asymptomatic patients. Airway club cells, ciliated cells and type II pneumocytes in the lung, and enterocytes of the gut also express ACE2. This study demonstrates how a holistic data science platform can leverage unprecedented quantities of structured and unstructured publicly available data to accelerate the generation of impactful biological insights and hypotheses.