Open access
Aug 2026
MAMMa: adaptation of multimodal LLM embeddings to multilinguality
A Large Vision-Language Embedding Model trained on English multimodal tasks to support multilingual inputs is adapted and a new benchmark is introduced to evaluate the multilingual and multimodal capabilities of embedding models.
Elio Musacchio, Lucia Siciliani, Pierpaolo Basile et al.
· Neural computing & applicati... · 0 citations