[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
Manuel Faysse @ManuelFaysse on x 1943 followers
Created: 2025-07-17 09:36:22 UTC
@gigant_theo @antonio_loison @pteiletche Normally VLMs really attenuated the modality gap problem. Did you check out the latest Jina embeddings ? Or cohere X ? Everything is projected in the same latent space which is the one of the text model. The scoring func still might be a bit biased but VLMs helped a lot
XXX engagements
