Vinayak Agarwal

MetaMuse curates and harmonizes biomedical metadata using a multi-agent AI system, achieving high accuracy and scalability in standardizing unstructured data from repositories like GEO.

The paper shows humans can infer physical properties from impact sounds but struggle when object resonance distributions differ from real-world data.

This paper introduces a self-supervised foundation model for single-cell transcriptomes that predicts gene sets from context and outperforms baselines in downstream tasks.

Revive-Flow predicts and reverses blood DNA methylation aging using a flow-matching model trained on epigenetic data, achieving high accuracy in rejuvenation.

The paper introduces K-Dense, an AI system that creates accurate transcriptomic aging clocks with uncertainty estimates, showing continuous evolution of aging signatures.

This study evaluates TabPFN's performance on high-dimensional RNA-seq data and finds that adaptations underperform compared to classical methods when using full feature sets.