←
Mackenzie Weygandt Mathis, PhD4,614 posts
Mackenzie Weygandt Mathis, PhD avatar

Mackenzie Weygandt Mathis, PhD

@TrackingActions

merging adaptive motor control & machine learning | Prof @EPFL | 🐭@deeplabcut 🦓@cebraAI | @ELLISforEurope Scholar | @Harvard Alum | shorturl.at/Iu3MI

◷ Joined February 2011▧ 610 Photos and videos
Denis avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
Denis@Den_Kochetov·Nov 6

Can't believe I missed PRIMA! 🔥 Tried it on several videos — the SMAL-based 3D reconstructions look incredible. Finally, some really impressive animal mesh recovery! Just added it to @paperswithcodee. Congrats @TrackingActions!

0:42

🥳 New work from my lab (@MLabofAI) just dropped on @arxiv! Measuring the shape of an animal can be highly useful for biomedical applications and for avatars 😎 We introduce *PRIMA*:🔥SOTA 2D➡️3D animal shape by @xiaoyu912huang, @TiwangCS & I! 📝 arxiv.org/abs/2606.02366

0:05
Mackenzie Weygandt Mathis, PhD avatar
Mackenzie Weygandt Mathis, PhD@TrackingActions·Nov 3

🍾 Accepted to #WACV2027! Check out the newly updated preprint, and test our SOTA single image ➡️ 3D shape & pose models now!

🥳 New work from my lab (@MLabofAI) just dropped on @arxiv! Measuring the shape of an animal can be highly useful for biomedical applications and for avatars 😎 We introduce *PRIMA*:🔥SOTA 2D➡️3D animal shape by @xiaoyu912huang, @TiwangCS & I! 📝 arxiv.org/abs/2606.02366

0:05
James Whittington avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
James Whittington@jcrwhittington·Aug 12

We’re excited to announce DiG-bench, a new benchmark for discovery! Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a text-based environment, so they probe discovery capabilities in the natural domain of language models, rather than requiring additional, potentially confounding, visual understanding. TL;DR frontier models have improved a lot over the last few months. But they are still stumped by some surprisingly simple problems, even in their native text domain. With @cocosci_lab (@Princeton) @MITCoCoSci (@MIT) @SchmidhuberAI (@KAUST_News) @misovalko (@Inria) @tri_dao (@PrincetonCS) @RMBattleday @zebkDotCom @FraserGreenlee @akaijsa @ClareMaguire @TimMuller1 @kubicek_ales @physicscat0x7d @SukritSumant @thoughtchannel_ (1/5)

Post attachment
Mackenzie Weygandt Mathis, PhD avatar
Mackenzie Weygandt Mathis, PhD@TrackingActions·Sep 26

Now accepted at #Neurips 🙌💗🔥🫶

🧠 Can we recover the equations governing a system directly from noisy, high-dimensional observations? #DYSCO, by Paolo Muratore, is a first step: it learns latent spaces that capture the underlying dynamics & enables recovery of governing equations 📄arxiv.org/abs/2606.13260

0:43
Adrian Roggenbach avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
Adrian Roggenbach@a_roggenbach·Aug 24

⚠️PREPRINT ALERT⚠️ How can we better understand distributed brain activity across temporal and spatial scales? In this collaborative project, we combined ultra-flexible electrodes with two-photon imaging to illuminate brain-wide neural dynamics. doi.org/10.21203/rs.3.rs-102… 1/8

Post attachment
Laura Driscoll avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
Laura Driscoll@lndriscoll·Aug 8

Confused about all this talk of compositionality in neuroscience? Read our new perspective nature.com/articles/s41593-0… with authors Reidar Riveland and @pouget_alex.

Mackenzie Weygandt Mathis, PhD avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
Mackenzie Weygandt Mathis, PhD@TrackingActions·Jun 25

🧠 Can we recover the equations governing a system directly from noisy, high-dimensional observations? #DYSCO, by Paolo Muratore, is a first step: it learns latent spaces that capture the underlying dynamics & enables recovery of governing equations 📄arxiv.org/abs/2606.13260

0:43
allen institute avatar
⟳ Mackenzie Weygandt Mathis, PhD retweeted
allen institute@AllenInstitute·Jul 13

#OnThisDay in 2016, we launched the Allen Brain Observatory with the first standardized in vivo survey of physiological activity in the mouse visual cortex. Since its launch, the Observatory and its data has been critical to visual cortex research around the world.

Post attachment