Simon Aytes retweeted
Introducing 🌌UniversalRAG — a novel RAG framework that adaptively retrieves from multimodal corpora (📕text, 🖼image, 🎥video) at the right level of granularity, from short snippets to long content.
Huge thanks to @omarsar0 for sharing our work!
Paper: arxiv.org/abs/2504.20734
Simon Aytes retweeted
So excited to drop PaperCoder, a multi-agent LLM system that turns ML papers into full codebases.
It looks like this:📄 (papers) → 🧠 (planning) → 🛠️ (full repos), all powered by 🤖.
Big thanks to @_akhaliq for the shoutout!
Paper: arxiv.org/abs/2504.17192
📣 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.
🔗Paper: arxiv.org/abs/2503.05179
Amazing #LLM research from my colleagues at the @kaist_ai graduate school!
#ArtificialIntelligence #ComputerVision #Research
Excited to introduce VideoRAG📽️, 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: arxiv.org/abs/2501.05874
@SoyeongJeong97 @kangsan_kim_ @SungJuHwang1
🌍 July Post Series: The Urgent Need for GreenAI 🌱
Did you know training one large AI model can emit as much CO2 as 5 cars over their lifetimes? 🚗🚗🚗🚗🚗
ICT, including AI, could use 20% of electricity & emit up to 5.5% of global CO2 by 2025! [1]
(1/3)
🔥 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 AI’s carbon footprint, strategies for reducing energy use, and how AI can fight climate change. 🌿
#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! 🚀
towardsdatascience.com/findi…
