Search papers, labs, and topics across Lattice.
3
0
6
9
Intern-S2-Preview-397B not only excels in multimodal scientific reasoning but also enhances biological instruction performance without altering its foundational architecture.
TimeLens2 outperforms models with up to 397B parameters by effectively grounding temporal evidence in videos, redefining expectations for multimodal LLM capabilities.
VideoChat3 achieves unprecedented generalization in video understanding while maintaining high efficiency, outperforming larger models with just 4 billion parameters.
