julieta
@yoknapathawa.bsky.social
Currently at Meta. Prev researcher at Waabi and Uber ATG. I got a PhD from UBC.
I am based in Toronto 🇨🇦
https://una-dinosauria.github.io/
I am based in Toronto 🇨🇦
https://una-dinosauria.github.io/
Just got tickets to see Béla Fleck in Toronto next year. I’ve been listening to him for ~15 years and somehow never got a chance to see him live. Extremely happy! 😁
October 21, 2025 at 9:01 PM
Just got tickets to see Béla Fleck in Toronto next year. I’ve been listening to him for ~15 years and somehow never got a chance to see him live. Extremely happy! 😁
Welcome to another day of computer vs JPEG. The JPEG always wins.
PSA: go apply the urgent security update to your Apple devices. Don’t wait. Do it right now
Update Now: iOS 18.6.2 and macOS Sequoia 15.6.1 Fix Actively Exploited Vulnerability
Apple today released new iOS 18.6.2, iPadOS 18.6.2, and macOS Sequoia 15.6.1 updates, and the software addresses a security vulnerability that is...
www.macrumors.com
August 21, 2025 at 2:43 PM
Welcome to another day of computer vs JPEG. The JPEG always wins.
Reposted by julieta
The claim that it’s hard to get to the truth because of conflicting information, propaganda, or information overload has always struck me as deeply unserious.
July 28, 2025 at 8:59 PM
The claim that it’s hard to get to the truth because of conflicting information, propaganda, or information overload has always struck me as deeply unserious.
Reposted by julieta
We're excited to announce a second physical location for NeurIPS 2025, in Mexico City, which we hope will address concerns around skyrocketing attendance and difficulties in travel visas that some attendees have experienced in previous years.
Read more in our blog:
blog.neurips.cc/2025/07/16/n...
Read more in our blog:
blog.neurips.cc/2025/07/16/n...
July 16, 2025 at 10:05 PM
We're excited to announce a second physical location for NeurIPS 2025, in Mexico City, which we hope will address concerns around skyrocketing attendance and difficulties in travel visas that some attendees have experienced in previous years.
Read more in our blog:
blog.neurips.cc/2025/07/16/n...
Read more in our blog:
blog.neurips.cc/2025/07/16/n...
Reposted by julieta
My dream has been to take a photo of a person and extract the 2D sewing pattern of their clothing and then turn it into a 3D garment. ChatGarment does exactly this plus it lets you edit the garment, or create a completely new one, using text prompts. chatgarment.github.io At CVPR2025!
May 28, 2025 at 9:33 AM
My dream has been to take a photo of a person and extract the 2D sewing pattern of their clothing and then turn it into a 3D garment. ChatGarment does exactly this plus it lets you edit the garment, or create a completely new one, using text prompts. chatgarment.github.io At CVPR2025!
Reposted by julieta
Hello Friends!
I'm on the job market now!
I have a oodles of knowledge for all the software performance engineering tricks in Rust, Julia and other systems languages and would love to work with teams that are looking to skill up in those respects, from back ends to big data crunching!
I'm on the job market now!
I have a oodles of knowledge for all the software performance engineering tricks in Rust, Julia and other systems languages and would love to work with teams that are looking to skill up in those respects, from back ends to big data crunching!
May 9, 2025 at 6:03 PM
Hello Friends!
I'm on the job market now!
I have a oodles of knowledge for all the software performance engineering tricks in Rust, Julia and other systems languages and would love to work with teams that are looking to skill up in those respects, from back ends to big data crunching!
I'm on the job market now!
I have a oodles of knowledge for all the software performance engineering tricks in Rust, Julia and other systems languages and would love to work with teams that are looking to skill up in those respects, from back ends to big data crunching!
@dorastable.bsky.social Just got your book in the mail, looking forward to vegan pozole verde and huitlacoche crepes! 😋
April 3, 2025 at 1:00 AM
@dorastable.bsky.social Just got your book in the mail, looking forward to vegan pozole verde and huitlacoche crepes! 😋
Reposted by julieta
“Just tokenize it” is the “Will it blend” of ML today
February 23, 2025 at 3:08 PM
“Just tokenize it” is the “Will it blend” of ML today
Reposted by julieta
We created a new channel with daily new vision and graphics papers trending (liked/read) on www.scholar-inbox.com. This is the bsky equivalent of AK on X! Follow now, and never miss a beat again: bsky.app/profile/si-c...
February 21, 2025 at 10:37 AM
We created a new channel with daily new vision and graphics papers trending (liked/read) on www.scholar-inbox.com. This is the bsky equivalent of AK on X! Follow now, and never miss a beat again: bsky.app/profile/si-c...
Reposted by julieta
📢PSA: #NeurIPS2024 recordings are now publicly available!
The workshops always have tons of interesting things on at once, so the FOMO is real😵💫 Luckily it's all recorded, so I've been catching up on what I missed.
Thread below with some personal highlights🧵
The workshops always have tons of interesting things on at once, so the FOMO is real😵💫 Luckily it's all recorded, so I've been catching up on what I missed.
Thread below with some personal highlights🧵
January 22, 2025 at 9:04 PM
📢PSA: #NeurIPS2024 recordings are now publicly available!
The workshops always have tons of interesting things on at once, so the FOMO is real😵💫 Luckily it's all recorded, so I've been catching up on what I missed.
Thread below with some personal highlights🧵
The workshops always have tons of interesting things on at once, so the FOMO is real😵💫 Luckily it's all recorded, so I've been catching up on what I missed.
Thread below with some personal highlights🧵
A certain kind of lab produces computer vision papers that are like “We observe that horses are sometimes mistaken for zebras, so we introduce a horse-zebra divergence loss $\ell_{hzd}$. Our final loss thus consists of 17 terms.” and I find this not just exhausting but also so obviously non-scalable
January 13, 2025 at 3:51 AM
A certain kind of lab produces computer vision papers that are like “We observe that horses are sometimes mistaken for zebras, so we introduce a horse-zebra divergence loss $\ell_{hzd}$. Our final loss thus consists of 17 terms.” and I find this not just exhausting but also so obviously non-scalable
Reposted by julieta
(1/4)
I will present GGHead next week at SIGGRAPH Asia in Tokyo! Swing by in the Gaussian Humans session if you are interested.
Also, we have released the training code now 🎉
Check it out: github.com/tobias-kirsc...
I will present GGHead next week at SIGGRAPH Asia in Tokyo! Swing by in the Gaussian Humans session if you are interested.
Also, we have released the training code now 🎉
Check it out: github.com/tobias-kirsc...
November 28, 2024 at 2:59 PM
(1/4)
I will present GGHead next week at SIGGRAPH Asia in Tokyo! Swing by in the Gaussian Humans session if you are interested.
Also, we have released the training code now 🎉
Check it out: github.com/tobias-kirsc...
I will present GGHead next week at SIGGRAPH Asia in Tokyo! Swing by in the Gaussian Humans session if you are interested.
Also, we have released the training code now 🎉
Check it out: github.com/tobias-kirsc...
Reposted by julieta
I love that traditional CGI obeys the laws of physics but not the laws of the statistical structure of naturalistic images and generative video obeys the latter but not the former, leading to two equally but differently uncanny modes of video generation.
November 19, 2024 at 8:28 PM
I love that traditional CGI obeys the laws of physics but not the laws of the statistical structure of naturalistic images and generative video obeys the latter but not the former, leading to two equally but differently uncanny modes of video generation.