Andrew Fitzgibbon

I'm moving from extremely rarely posting interesting content on twitter to doing the same on, wow I'm old, linkedin...

🚨 Graphcore is hiring AI Research Interns! 🚨 Join us to work at the intersection of hardware and AI and help shape the future of AI systems. Whether you're excited about efficient inference, large-scale training, or advancing frontier-model capabilities, we’ve got cutting-edge projects for you to dive into. Interested? Apply below 👇

Our Papers of the Month for September is now live! We cover: - LLM self-correction via RL - Trillion-token FP8 training - SOAP (Shampoo + Adam) - Generative models for crystals All framed in terms of "proper conditioning" (🧵) graphcore-research.github.io/papers-of-the-…

Graphcore Research internships are now open 🎉 We're looking for PhD students for next summer We're interested in algorithms & tools for hardware-efficient ML, in areas like LLM training/inference, GNNs, knowledge graphs and frameworks Spread the word! graphcore.ai/jobs

Introducing `tandv` - a library for tracking and visualising the internal stats of your model. We hope this will help with low-precision, debugging and more. (link in 🧵)

Sure matplotlib is cool, but what if I want to load my loss curves into the 2006 hit Flash game LineRider?

Update: super helpful customer service got me the brass fixing kit, tap no longer wobbling.

As further feedback to the team that thought this would be a great innovation that would attract customers: I bought this tap because of Grohe's reputation for quality. The term "quickfix" had zero impact on my choice. However, that term now means "low quality gimmick".

Same problem, and based on online searches, many others have it too. Terrible wasteful design, saves 10 seconds when it works, costs hours when it doesn't, and a load of extra useless plastic is left in place having saved those 10 seconds.

Our u-µP paper hit arXiv this morning! I'm so proud of this one — and grateful for a wonderful team who put so much into it 🥰 We add lots of good things to µP. Better sweeping, transfer, simple FP8. Already @cloneofsimo has a great thread on it, which I highly recommend

Excited to present our work at @icmlconf WANT workshop: ⚖️ Scalify: scale propagation for efficient low-precision LLM training 🎉 github.com/graphcore-rese…

babe wake up, new muP paper dropped arxiv.org/abs/2407.17465 And holy smokes does this look promising!

Our team's summaries & analysis of our favourite papers from the last month. We give our take on: Mamba-2, sparse-µP, contextual position encoding & matmul-free models 🧵 graphcore-research.github.io/papers-of-the-…

Our latest edition of *Papers of the Month* is now available 📚 These are summaries of our team's favourite papers from March, including a new low-rank training procedure GaLore, and the supposed "Era of 1-bit LLMs" (really 1.58 bits) Mini-version in 🧵 graphcore-research.github.io/papers-of-the-…

@robin_kips @eccvconf Oops, will fix - this works in the meantime: eccv2024.ecva.net/Conferences/20…

@eccvconf The link seem to be dead

Submitting to #ECCV2024? Check out the FAQ! Includes info about preprints, anonymity, and media promotion. eccv2024.ecva.net/faqs.html

So pleased to share that our OGB-LSC winning model GPS++ has just been published in TMLR.

I love that I'm being offered these - I guess the ad targeting knows I'm going to have a sudden urge to take up jewellery making long before I do...

I’m biased obvs, but having seen a preview of this talk, I can recommend it highly!

I'll start with "Julia meets the Intelligence Processing Unit" (pretalx.com/juliacon2023/t…), about running #JuliaLang on the @graphcoreai IPU, spectacular example of how @llvmorg enables adopting new cool hardware in Julia, and how Julia opens up new doors in scientific computing

@3scorciav @samsungresearch I would be delighted - let's dm.

@Awfidius Would you be interested in giving a similar talk in town? We resume our in-person invited talks at @samsungresearch AI Center Cambridge 🇬🇧

Thank you! Really great to be here, and great conversations throughout the event!