Search papers, labs, and topics across Lattice.
3
901
7
21
A 7B model trained on a new dataset of Chinese porcelain outperforms GPT-4 by 12% on expert connoisseurship tasks, demonstrating the power of domain-specific training and tool integration.
The medical imaging AI community is being held back by a fragmented data landscape, but a new metadata-driven fusion paradigm offers a path to unlocking the power of foundation models.
Open-source multimodal models just leveled up: InternVL3 rivals closed-source titans like GPT-4o by pre-training vision and language together from the start.
