Introducing Android XR, our new platform for headsets and glasses built for the Gemini era

Video to 4D is an incredibly challenging task! Excited to announce that Dynamic Gaussian Marbles was accepted to #SIGGRAPHAsia2024 with @AdamWHarley @mikacuy @fedassa @fpgDubost @GordonWetzstein @GuibasLeonidas. Check out our webpage and code! geometry.stanford.edu/projec…

How do we create realistic models of dressed humans directly from visual data? We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos. Page: qingqing-zhao.github.io/Phys… (1/6)

Oldies but goldies: A. Efros and T. Leung, Texture Synthesis by Non-parametric Sampling, 1999. The first copy-based texture synthesis method. people.eecs.berkeley.edu/~ef…

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points. Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today! There’s quite a lot of different material about Gemini available, starting with: Main blog post: blog.google/technology/ai/go… 60-page technical report authored by th Gemini Team: deepmind.google/gemini/gemin… In this thread, I’ll walk you through some of the highlights.

The future of education: An Immersive experience with #AR #AugmentedReality #education #Metaverse #DigitalTransformation #MixedReality #IoT #edtech

Is scaling your ML experiments really that easy? I have summarized weeks of learning and experimenting with Amazon Web Services (AWS) and SageMaker in a one-hour video and 7 steps GitHub tutorial. #machinelearning #ml #tensorflow #cloud #aws #sagemaker github.com/fpgdubost/sagemak…

Not only science! An Autumn School is also fun! Here are some pictures from the #ISACT2022 Night at @AmwayCenter watching the @OrlandoMagic NBA match against @Timberwolves. Exciting experience! @RupaliKhatun @cataldomusto #FlorianDubost @soumick1993 (with heart) and others...

Hey everyone, I will give a talk on explainable #ML and #medical #computervision at the #ISACT autumn school this November (isact.cogsy.de/) in Orlando, Florida. Hope to see you there, the program looks really cool. Definitely a nice event for graduate students and #PhDs!

Woa, this is incredible, looks like the inside of a dream! Reminds me of the movie Waking Life. thefocuspull.com/features/fr…

Would you like to segment vessels in #7T #brain #MRA without perfect training labels? Research paper on deformation-aware learning DS6 has been published by @MDPIOpenAccess providing a solution. Read more doi.org/10.3390/jimaging8100… @fpgDubost @gbortsova #deeplearning #segmentation

Do you remember when you joined Twitter? I do! #MyTwitterAnniversary

As a postdoc, I spend 70% of my income on rent alone. I am often not able to afford clothes and groceries without putting more on my credit card. I do not know what is going to happen with student loans kick back into repayment. Postdocs are struggling in CA. @UAW5810

Scrutinazing the past as never before! Very exciting! #Webb #telescope

Another accepted paper: "A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation" by R Camarasa @CamarasaRobin, D Bos, J Hendrikse, P Nederkoorn, M. E. Kooi, A. van der Lugt, & M. de Bruijne. Free for everyone to enjoy: melba-journal.org/article/27…

Nice #ML and #biotech initiative!

We’re joining forces with @TheCrick! We will be setting up a research laboratory to bring together the world-renowned research institute’s expertise with machine learning and AI techniques to advance our understanding of biology. Learn more: dpmd.ai/dm-crick

There is one big reason we love the logarithm function in machine learning. Logarithms help us reduce complexity by turning multiplication into addition. You might not know it, but they are behind a lot of things in machine learning. ↓ Here is the entire story. ↓

Very nice event for students curious about applied #ML research!

Insightful work! Multi-model ML with a gigantic dataset: 5654 of 7764 randomized patients (71%) with a median follow-up of 11.4 years. #ml #ai #cancer #prostate #computervision #imaging