Virtually nobody is pricing in what's coming in AI. I wrote an essay series on the AGI strategic picture: from the trendlines in deep learning and counting the OOMs, to the international situation and The Project. SITUATIONAL AWARENESS: The Decade Ahead

"Think lightly of yourself and deeply of the world." - Miyamoto Musashi

LLM bullshit knife, to cut through bs RAG -> Provide relevant context Agentic -> Function calls that work CoT -> Prompt model to think/plan FewShot -> Add examples PromptEng -> Someone w/good written comm skills. Prompt Optimizer -> For

lol

How to stay calm (without any hacks) This is all you need.

This is really a 'WOW' paper. 🤯 Claims that MatMul operations can be completely eliminated from LLMs while maintaining strong performance at billion-parameter scales and by utilizing an optimized kernel during inference, their model’s memory consumption can be reduced by more

📢 In our new blogpost w/ Michael Bronstein Haitao Mao Jianan Zhao Zhaocheng Zhu we discuss foundation models in Graph & Geometric DL: from the core theoretical and data challenges to the most recent models that you can try already today! towardsdatascience.com/foundation-mod…

This thread is just ~30% of the full post, which you can find on Tivadar's book. You won't find better explanations anywhere else: tivadardanka.com/books/mathemat… Trust me on this one. This is the book you want to read.

📣Foundation models for graph reasoning become even stronger - in our new #NeurIPS2024 work we introduce UltraQuery going beyond simple one-hop link prediction to answering more complex queries on any graph in the zero-shot fashion better than trainable SOTA! 🧵1/7, arxiv, code

Cats are invariant under SO(3) transformations! 😼

Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission! Join our community! More information here mila.quebec/en/prospective…

I'm so surprised and offended to see the professor mention "Chinese students are dishonest" during one of the invited talk. This is against the code of conduct of #NeurIPS2024 . The Chair Committee should look into this and we want to make sure this won't happen again.

🚨 The 8th annual Graph Signal Processing Workshop is back this May 14-16! Held in Montreal, CA, at Mila - Institut québécois d'IA, we’re covering all things graphs, signals, learning, & applications 🕸️〰️ 🔗: gspworkshop.org 👉🏻Abstract submission opens Feb 1 👉🏻 Registration opens Mar 20