Search papers, labs, and topics across Lattice.
2
6
5
3
A surprisingly small 4B parameter model can achieve state-of-the-art multimodal embeddings by selectively applying chain-of-thought reasoning only when it demonstrably improves query-target alignment.
Open-sourcing SAIL-VL2 gives the multimodal community a new SOTA vision-language model under 4B parameters, driven by innovations in data curation, progressive training, and sparse MoE architectures.
