Search papers, labs, and topics across Lattice.
4
11
8
13
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
A 3B parameter model, Med-V1, matches the evidence attribution performance of GPT-5 in biomedical contexts, offering a scalable alternative to frontier LLMs.
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 medical literature-specific foundation model, LEADS, achieved 23-27% time savings and improved accuracy/recall compared to working alone.
