12:05am PDT - July 8th, 2023
RT @roadjiang: We learn a vector quantizer to map an image, or non-linguisitic modalities, to the token space of a frozen LLM. This transl…
0 retweets 5 likes - Qingye Meng (@hilbertmeng)RT @roadjiang: We learn a vector quantizer to map an image, or non-linguisitic modalities, to the token space of a frozen LLM. This transl…
0 retweets 5 likes - Qingye Meng (@hilbertmeng)