Introducing ๐UniversalRAG โ a novel RAG framework that adaptively retrieves from multimodal corpora (๐text, ๐ผimage, ๐ฅvideo) at the right level of granularity, from short snippets to long content.
Huge thanks to @omarsar0 for sharing our work!
Paper: https://t.co/x2YgCXZuY4
So excited to drop PaperCoder, a multi-agent LLM system that turns ML papers into full codebases.
It looks like this:๐ (papers) โ ๐ง (planning) โ ๐ ๏ธ (full repos), all powered by ๐ค.
Big thanks to @_akhaliq for the shoutout!
Paper: https://t.co/LuKXPTd0df
๐ฃ Excited to introduce Sketch-of-Thought (SoT)
We've drawn inspiration from human cognition to make #LLM reasoning more efficient, reducing token usage by an avg. of 75% while having comparable accuracy to traditional CoT approaches.
๐Paper: https://t.co/miWx9ar49k
Excited to introduce VideoRAG๐ฝ๏ธ, which extends the current landscape of RAG systems (that largely focus on text) by holistically leveraging the video corpus, utilizing both textual and visual features.
Paper: https://t.co/5PDMGHYrMJ
@SoyeongJeong97@kangsan_kim_@SungJuHwang1
๐ July Post Series: The Urgent Need for GreenAI ๐ฑ
Did you know training one large AI model can emit as much CO2 as 5 cars over their lifetimes? ๐๐๐๐๐
ICT, including AI, could use 20% of electricity & emit up to 5.5% of global CO2 by 2025! [1]
(1/3)
๐ฅ This July is projected to be the warmest month ever recorded [2].
It's crucial we address AI's environmental impact.
Stay tuned for insights on AIโs carbon footprint, strategies for reducing energy use, and how AI can fight climate change. ๐ฟ
#ClimateChange#AI
(2/3)
Last year, I applied and was accepted to 12 graduate programs in #AI, including KAIST, Columbia, and UCL.
I am thrilled to share that an article I've written about my process for finding these programs is now live! ๐
https://t.co/5D4DoglRuL