Profile avatar
dpetrini.bsky.social
PhD in computer vision/AI - medical imagens. Electronics projects, astronomy, and the history of science. Father, husband, electrical engineer and engineering manager.
15 posts 133 followers 492 following
Regular Contributor
Posts 21 Comments 9

Kkkkkk Lol

submitted 22 days ago • 0 comments

Great achievements of chip design.

submitted 22 days ago • 0 comments

Excellent, going to the point.

submitted 61 days ago • 1 comment

Riccioli's Almagestum Novum (1651) wasn't just the most comprehensive Astronomy Textbook ever. It also linked House Grimaldi to French Royal ancestors, pushing the diplomacy that would ally Monaco with France and protect them from Italian Unification. www.amazon.com/Almagestum-N...

submitted 75 days ago • 3 comments

That's a lot of parameters for a large language model. The human brain has ~100 trillion. About 60X GPT-4.

submitted 64 days ago • 34 comments

How to Accurately Time CUDA Kernels in Pytorch In a world of increasingly costly machine learning model deployments, ensuring accurate GPU operation timing is key to resource optimization. In this blog post, we explore best practices to achieve this in PyTorch. www.speechmatics.com/company/arti...

submitted 63 days ago • 0 comments

The best

submitted 69 days ago • 0 comments

Slides for "Table Foundation Models" I explain why these models can strongly outperform tree-based models, what are the intuitions, hopefully pointing to ways forward for more improvement speakerdeck.com/gaelvaroquau...

submitted 70 days ago • 3 comments

Ilya Sutskever NeurIPS talk [video] Discussion

submitted 72 days ago • 0 comments

I love Mad Magazine

submitted 79 days ago • 177 comments

Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list! go.bsky.app/2qnppia

submitted 93 days ago • 29 comments

Are you Sirius?

submitted 80 days ago • 113 comments

Stochastic Gradient Descent - AI Flashcards

submitted 80 days ago • 1 comment

I was deeply honored to receive the 2024 VinFuture Prize from the VinFuture Foundation in Hanoi, alongside Geoff Hinton, Jensen Huang, @ylecun.bsky.social and @drfeifei.bsky.social, for our contributions to the advancement of deeplearning. vinfutureprize.org/laureates/pr...

submitted 79 days ago • 0 comments

I’m on the academic job market this year! I’m completing my @uwcse.bsky.social @uwnlp.bsky.social Ph.D. (2025), focusing on overcoming LLM limitations like hallucinations, by building new LMs. My Ph.D. work focuses on Retrieval-Augmented LMs to create more reliable AI systems 🧵

submitted 82 days ago • 3 comments

PDF understanding is key issue for RAG.

submitted 84 days ago • 0 comments

Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io

submitted 91 days ago • 19 comments

Reposting our work here: ieeexplore.ieee.org/document/983...

submitted 91 days ago • 0 comments

Evaluating LLM output is hard. For many teams, it's the bottleneck to scaling AI-powered product. A key mistake is defining eval criteria w/o actually LOOKING AT THE DATA. This leads to irrelevant / unrealistic criteria + lots of wasted effort. Thus I built AlignEval.com

submitted 116 days ago • 3 comments

Motivation For Deep Learning

submitted 94 days ago • 0 comments

submitted 94 days ago • 51 comments