Bin Zhou

The developed BrainVLM model, which integrates an uncertainty quantification strategy to indicate prediction reliability and a module for generating radiology reports to elucidate the clinical rationale, was trained on multi-modal data from 40,043 individuals.

Offloading causal DAG discovery to LLM world knowledge enables Bayesian networks to generate high-fidelity synthetic tabular data from just a 2% sample while strictly retaining empirical grounding for numerical parameters.

LAB-Tab reduces overfitting in few-shot tabular generation by intelligently expanding Bayesian network structures with LLM-driven insights, leading to significant performance gains.

ARM CCA's hardware-enforced isolation slashes confidential container startup latency and overhead, making them practical for short-lived workloads.