Generative Multimodal Models are In-Context Learners · HackerPapers discussions

Generative Multimodal Models are In-Context Learners — HN submission

Fri, 22 Dec 2023 02:20:05 GMT

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

Hello HN, I'm excited to introduce Emu2, the latest generative multimodal model developed by the Beijing Academy of Artificial Intelligence (BAAI). Emu2 is an open-source initiative that reflects BAAI's commitment to fostering open, secure, and responsible AI research. It's designed to enhance AI's proficiency in handling tasks across various modalities with minimal examples and straightforward instructions. Emu2 has demonstrated superior performance over other large-scale models like Flamingo-80B in few-shot multimodal understanding tasks. It serves as a versatile base model for developers…

153 points; 27 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Generative Multimodal Models are In-Context Learners — HN submission

Thu, 21 Dec 2023 06:01:15 GMT

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.