Search papers, labs, and topics across Lattice.
The United States' medical research agency, and the largest public funder of biomedical research in the world.
7
14
2
Hierarchical modeling of 3D facial geometry reveals significant insights into phenotype classification, but struggles with rare conditions highlight critical gaps in current methodologies.
A 3B parameter model, Med-V1, matches the evidence attribution performance of GPT-5 in biomedical contexts, offering a scalable alternative to frontier LLMs.
Decoding EEG gets easier when you're trying to guess broad categories instead of specific objects, suggesting our brains represent abstract concepts more clearly in EEG signals.
Unlike LDA and K-means, a new convex optimization approach guarantees globally optimal and reproducible topic clusters, revealing nuanced insights from 12,000 aging research papers.
CT-Bench reveals that even state-of-the-art multimodal models struggle with lesion understanding in CT scans, highlighting the need for specialized datasets and fine-tuning to bridge the gap between AI and radiologist performance.
Clinicians using a new medical literature mining LLM, LEADS, achieved 0.81 recall vs. 0.78 without it, while saving 20.8% of their time.
Clinicians using a medical literature-specific foundation model, LEADS, achieved 23-27% time savings and improved accuracy/recall compared to working alone.
