Search papers, labs, and topics across Lattice.
Southwest Minzu University, ByteDance {mhhan22@m.fudan.edu.cn, dicken@fyscis.ai, lihuazhang@fudan.edu.cn}
1
6
3
4
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.
