News for hackers. Stuff that matters.
Re:Multimodal Chain-Of-Thought Reasoning In Language Models by txtai on Saturday February 04, 2023 @11:06AM (#34655438)
Outperforms GPT-3.5 by 16% with less than 1B parameters. There is even a 220M parameter version that scores well. Interesting model to watch.

Referenced snippet from the abstract:

With Multimodal-CoT, our model under 1 billion parameters outperforms the previous state-of-the-art LLM (GPT-3.5) by 16% (75.17%->91.68%) on the ScienceQA benchmark and even surpasses human performance.

Re:Multimodal Chain-Of-Thought Reasoning In Language Models by leobg on Saturday February 04, 2023 @05:06PM (#34658890)
There is no interactive demo anywhere yet, is there?
Re:Multimodal Chain-Of-Thought Reasoning In Language Models by txtai on Saturday February 04, 2023 @05:45PM (#34659240)
There is a GitHub repo: https://github.com/amazon-science/mm-cot

But it doesn't look all that easy to stand up.