jnpmartel's profile picture. Postdoc @Stanford Computational Imaging Lab. Ph.D.'19 @ETH_en.

Julien N.P. Martel

@jnpmartel

Postdoc @Stanford Computational Imaging Lab. Ph.D.'19 @ETH_en.

Fijado

A year ago, I joined Perceptive to work on sensing & perception for autonomy! 👇 A thread with cool results from our very own sensing & perception platform including our LiDAR, Radar, and algs! 🧵1/n

📢📢 Join the Revolution in Autonomy: Follow Perceptive on Our Brand New YouTube Channel! lnkd.in/ga6kJbCh 🧵1/4



Julien N.P. Martel reposteó

Join us at the University of California, in the Santa Barbara campus located at a fabulous ocean location a few hours drive from San Francisco and Los Angeles ✨ I cannot imagine a better environment to start a research lab!

ninamiolane's tweet image. Join us at the University of California, in the Santa Barbara campus located at a fabulous ocean location a few hours drive from San Francisco and Los Angeles ✨

I cannot imagine a better environment to start a research lab!

UCSB ECE has an open tenure track position! We are looking for applicants with expertise in machine learning, artificial intelligence, and/or controls, automation, robotics, computer vision, optimization, and signal processing. Interested? Apply 👇 ece.ucsb.edu/employment



Julien N.P. Martel reposteó

Apple announced Vision Pro yesterday. Just like the iPhone, this system is poised to disrupt how we interact with digital information. Interestingly, perhaps not surprisingly, eye tracking is key to enabling future human-computer interfaces in their mixed reality system. (1/n)


Julien N.P. Martel reposteó

👀 Get ready for an exclusive look into the beating 💙 of our Universal Sensor! youtu.be/dHeKg-bahwM


Julien N.P. Martel reposteó

🧐 Now curious to see how Perceptive looks on a car? Check it out! 👇 youtu.be/_7prG5XtEXI


My favorite LLM: Large Lagrange Model...

jnpmartel's tweet image. My favorite LLM: Large Lagrange Model...

Julien N.P. Martel reposteó

Considering a PhD and interested in differentiable rendering, self-supervised representation learning in vision, and 3D scene representations? Apply to MIT and consider my research group! scenerepresentations.org Application under gradapply.mit.edu/eecs/apply/log…!


Julien N.P. Martel reposteó

The Realistic Graphics Lab is looking to recruit a *PhD student* and a *Research Engineer*. We develop algorithms and systems that invert the process of rendering to reconstruct realistic 3D worlds from images. A bit like "TensorFlow", but for physical simulations of light.

wenzeljakob's tweet image. The Realistic Graphics Lab is looking to recruit a *PhD student* and a *Research Engineer*. We develop algorithms and systems that invert the process of rendering to reconstruct realistic 3D worlds from images. A bit like "TensorFlow", but for physical simulations of light.

Julien N.P. Martel reposteó

Working with David has made the start of my PhD an absolute joy!!! Happy to answer any questions about life in Toronto, PhD at @UofT @UofTCompSci , or about the Toronto Comp Imaging Group! Please apply and reach out! 😁

I'm hiring grad students! Check out our group at tcig.ca—we're a multi-disciplinary team at #UofTCompSci that spans imaging, 3D vision, graphics, machine learning, sensors, and astronomy. Apply here cs.toronto.edu 🧵

DaveLindell's tweet image. I'm hiring grad students! Check out our group at tcig.ca—we're a multi-disciplinary team at #UofTCompSci that spans imaging, 3D vision, graphics, machine learning, sensors, and astronomy. Apply here cs.toronto.edu 🧵


Julien N.P. Martel reposteó

We present a new algorithm, cryoFIRE ❄️🔥, for fast ab initio heterogeneous reconstruction, appearing at @NeurIPSConf this Dec! Really proud to share our latest work, led by the amazing @axlevy0, and my first paper @PrincetonCS #EZlaboratory Paper: arxiv.org/abs/2210.07387 1/


Julien N.P. Martel reposteó

📢📢📢 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 𝗕𝗲𝗮𝘁𝘀 𝗖𝗼𝗻𝗰𝗮𝘁𝗲𝗻𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗖𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗶𝗻𝗴 𝗡𝗲𝘂𝗿𝗮𝗹 𝗙𝗶𝗲𝗹𝗱𝘀 We ran A LOT of experiments to find the best way to make neural fields generalize... so you don’t have to! arxiv.org/abs/2209.10684

taiyasaki's tweet image. 📢📢📢 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 𝗕𝗲𝗮𝘁𝘀 𝗖𝗼𝗻𝗰𝗮𝘁𝗲𝗻𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗖𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗶𝗻𝗴 𝗡𝗲𝘂𝗿𝗮𝗹 𝗙𝗶𝗲𝗹𝗱𝘀

We ran A LOT of experiments to find the best way to make neural fields generalize... so you don’t have to!
arxiv.org/abs/2209.10684

Julien N.P. Martel reposteó

📜🚨📜🚨 NN loss landscapes are full of permutation symmetries, ie. swap any 2 units in a hidden layer. What does this mean for SGD? Is this practically useful? For the past 5 yrs these Qs have fascinated me. Today, I am ready to announce "Git Re-Basin"! arxiv.org/abs/2209.04836


Loading...

Something went wrong.


Something went wrong.