Daniel Moyer (@dc_moyer) 's Twitter Profile
Daniel Moyer

@dc_moyer

Assistant Prof at @Vanderbilt_CS

ID: 2688850410

linkhttp://dcmoyer.github.io calendar_today29-07-2014 01:57:26

1,1K Tweet

761 Followers

773 Following

PyTorch (@pytorch) 's Twitter Profile Photo

If you installed PyTorch-nightly on Linux between Dec. 25 and Dec. 30, uninstall it and torchtriton immediately and use the latest nightly binaries. Read the security advisory here: pytorch.org/blog/compromis…

If you installed PyTorch-nightly on Linux between Dec. 25 and Dec. 30, uninstall it and torchtriton immediately and use the latest nightly binaries.

Read the security advisory here: pytorch.org/blog/compromis…
Sina Mansour L. (@sina_mansour_l) 's Twitter Profile Photo

1/7 Our latest preprint, "Eigenmodes of the brain: revisiting connectomics and geometry", offers new insights into brain eigenmodes constructed from geometry and connectivity. Read on for a brief overview! biorxiv.org/content/10.110…

Daniel Moyer (@dc_moyer) 's Twitter Profile Photo

Combinatorially hard horoscopes due to Starlink, and their approximations using Lagrange Point Relaxations arxiv link to follow?

Daniel Moyer (@dc_moyer) 's Twitter Profile Photo

The choice of baseline site can be a source of effect size. One answer is using the midpoint, which is implemented here in MidRISH. But the bigger picture idea is that we need to think about these effect size changes in harmonization.

Daniel Moyer (@dc_moyer) 's Twitter Profile Photo

We got surprisingly complete reviews for ECCV. They were largely negative, so that's sad, but just wanted to add our own experience to the reports of one-liners and similar.

Oscar Davis (@osclsd) 's Twitter Profile Photo

In fact, this Riemannian manifold is diffeomorphic to the positive orthant of a hypersphere! (With a very simple bijection.) So, instead, we can perform FM on the latter. But "Why?" you might wonder... (5/10)

In fact, this Riemannian manifold is diffeomorphic to the positive orthant of a hypersphere! (With a very simple bijection.) So, instead, we can perform FM on the latter. But "Why?" you might wonder... (5/10)
Daniel Moyer (@dc_moyer) 's Twitter Profile Photo

Medical Imaging Meets NeurIPS was rejected by the Workshop committee at NeurIPS 2024, and will not be returning this year. My sincere apologies to the hopeful participants, to previous organizers who had carried us thus far, and to the medical imaging community at large.

Bennett Landman (Vanderbilt MASI Lab) (@masi_lab) 's Twitter Profile Photo

Starting the first session of Vanderbilt Lab for Immersive AI Translation AI Summer School on neural networks. Looking forward to rising to VU Provost Office Raver's challenge to use our humanity - our capacity to be compassionate and brilliant.

Starting the first session of <a href="/VandyValiant/">Vanderbilt Lab for Immersive AI Translation</a> AI Summer School on neural networks. Looking forward to rising to <a href="/VU_Provost/">VU Provost Office</a> Raver's challenge to use our humanity - our capacity to be compassionate and brilliant.
Daniel Moyer (@dc_moyer) 's Twitter Profile Photo

This is an super useful variation on harmonization, and a nice set of baselines. Even though it's on EHR, it could be helpful for image harmonization in practice.