JUICE: Unified Multimodal Modeling in Pretrained Representation Spaces. Pretrained (Base) and SFT models, and the frozen image decoders they use.
CedLi
CedLJH
AI & ML interests
None yet
Recent Activity
authored a paper about 14 hours ago
Full-Atom Peptide Design based on Multi-modal Flow Matching authored a paper about 14 hours ago
Multimodal Filesystem Memory For Long-Horizon Embodied Agents authored a paper about 14 hours ago
JUICE: Unified Multimodal Modeling in Pretrained Representation SpacesOrganizations
