M. Mathis Laboratory @EPFL (@mwmathislab) 's Twitter Profile
M. Mathis Laboratory @EPFL

@mwmathislab

Merging artificial and natural intelligence to study adaptive mechanisms | CV, ML, Neuro | PI: @trackingactions

ID: 875369349334392832

linkhttps://xn--1o8h2in6jtk.y.at calendar_today15-06-2017 15:08:11

711 Tweet

3,3K Followers

12 Following

Shaokai Ye (@shaokaiyeah) 's Twitter Profile Photo

We are releasing AmadeusGPT-0.1.3! Many use cases to demonstrate its capability. We also have invited DLC residents ( Anna Stuckert , Marc Canela, DikraMasrour to share their use cases. Seamless integration with #SuperAnimal and GPT-4o

M. Mathis Laboratory @EPFL (@mwmathislab) 's Twitter Profile Photo

#CellSeg3D hits 85K downloads, and we’ve updated our preprint to add a few more key details and added new demo videos 🎥! Check out the demos from Cyril Achard and Sebastien Hausmann, PhD 🔥 youtu.be/3UOvvpKxEAo?fe… m.youtube.com/watch?v=U2a9Ib… biorxiv.org/content/10.110…

Cell (@cellcellpress) 's Twitter Profile Photo

Featured content from our newest anniversary content on #Neuroscience! Mackenzie Mathis, PhD EPFL & colleagues Read the perspective: cell.com/cell/fulltext/… #50YearsofCell

Featured content from our newest anniversary content on #Neuroscience!

<a href="/TrackingActions/">Mackenzie Mathis, PhD</a> <a href="/EPFL_en/">EPFL</a> &amp; colleagues

Read the perspective: cell.com/cell/fulltext/…

#50YearsofCell
EARA_CH (@eara_ch) 's Twitter Profile Photo

Mackenzie Mathis Mackenzie Mathis, PhD, la neuroscientifique de l’EPFL «qui murmure à l’oreille des #souris», couronnée par plusieurs prix. #EARA via Le Temps letemps.ch/sciences/macke…

Guy Parmelin (@parmeling) 's Twitter Profile Photo

Comment fonctionne notre cerveau face au langage et comment décoder le fonctionnement de nos circuits neuronaux. C'est en cherchant à répondre à ces questions que les deux scientifiques Pascal Gygax et Mackenzie Mathis sont récompensés par les Prix Marcel Benoist et Latsis👏

Flückiger Yves (@flueckigeryves) 's Twitter Profile Photo

On behalf of all members of the board of the Latsis foundation, I'd like to convey our warmest congratulations on this well-deserved award! This is just the start of a very promising career

Mackenzie Mathis, PhD (@trackingactions) 's Twitter Profile Photo

🔥🙏🏼 #AROS 💍 is accepted to #ICLR2025! So proud of HOSSEIN - what an awesome way to kick off his first grad school project 👌👌 Check out the updated arXiv version of the paper, open code (including python package) below ⬇️ #AROS💍 leverages neural ODEs and Lyapunov

🔥🙏🏼 #AROS 💍 is accepted to #ICLR2025! So proud of <a href="/hsirm96/">HOSSEIN</a>  - what an awesome way to kick off his first grad school project 👌👌 Check out the updated arXiv version of the paper, open code (including python package) below ⬇️ 

#AROS💍 leverages neural ODEs and Lyapunov
🦓CEBRA (@cebraai) 's Twitter Profile Photo

We have a new release up! Check out 0.5.0rc1!! 🔥 Important maintenance updates to keep up with dependencies, some nee features, and preparing for much more coming in the next weeks 👀… github.com/AdaptiveMotorC… #cebra M. Mathis Laboratory @EPFL

🦓CEBRA (@cebraai) 's Twitter Profile Photo

Ready to start with #CEBRA for your behavioral clustering, neural data, or joint-modeling? Check out our new demo notebook to help you learn the best practices and how to develop models! cebra.ai/docs/demo_note… 🌈🦓 #ML4Science

DeepLabCut 🦄 (@deeplabcut) 's Twitter Profile Photo

👀 We hit a major milestone: the PR for DLC3 is merged into main, and rc7 is up for final testing: pypi.org/project/deepla… - this is the most powerful, most new-user (+ new GUI features!) & ML expert friendly code, & the highest performance ... ready to #AnimalPose?! 🚀

Mackenzie Mathis, PhD (@trackingactions) 's Twitter Profile Photo

✨ Introducing a new #SOTA action recognition large multimodal language model: #LLaVAction! Understanding human behavior requires recognizing actions—a challenging task given the complexity of behavior. Large multimodal language models (#MLLMs) offer a promising path forward,

✨ Introducing a new #SOTA action recognition large multimodal language model: #LLaVAction!
 
Understanding human behavior requires recognizing actions—a challenging task given the complexity of behavior. Large multimodal language models (#MLLMs) offer a promising path forward,
M. Mathis Laboratory @EPFL (@mwmathislab) 's Twitter Profile Photo

Check out the latest work from our lab! Our first very large - 7B parameter - model for behavioral analysis! Coming soon will be AmadeusGPT 2.0… and more 😎

DeepLabCut 🦄 (@deeplabcut) 's Twitter Profile Photo

Happy birthday #DeepLabCut! It was 7 years ago we first appeared on arXiv.org 🙌🎊- thanks to the incredible users, contributors, & the software team who continue to make it the leading software for animal pose estimation! 🙏🏼💜 arxiv.org/abs/1804.03142 DeepLabCut.org

Happy birthday #DeepLabCut! 

It was 7 years ago we first appeared on <a href="/arxiv/">arXiv.org</a> 🙌🎊- thanks to the incredible users, contributors, &amp; the software team who continue to make it the leading software for animal pose estimation! 🙏🏼💜

arxiv.org/abs/1804.03142

DeepLabCut.org
HOSSEIN (@hsirm96) 's Twitter Profile Photo

🚀 Excited to share our #ICLR2025 paper! 🤖 AROS: Adversarially Robust Out-of-Distribution Detection through Stability 📄 Paper:openreview.net/forum?id=GrDne… 🔹 #AI_safety 🔹 #Trustworthy_ML 🗓️ Poster Session: Fri 25 Apr 10-12:30 📍 Hall3+Hall 2B (#327)

🚀 Excited to share our #ICLR2025 paper!
🤖 AROS: Adversarially Robust Out-of-Distribution Detection through Stability
📄 Paper:openreview.net/forum?id=GrDne…
🔹 #AI_safety
🔹 #Trustworthy_ML
🗓️ Poster Session: Fri 25 Apr 10-12:30 
📍 Hall3+Hall 2B (#327)
DeepLabCut 🦄 (@deeplabcut) 's Twitter Profile Photo

#DLCProTip: Did you know you can use unsupervised learning to adapt a trained model on the fly to your video in DeepLabCut!? When you run video analysis, check out “video adaptation” - it reduces jitter and provides better poses! ⬇️ nature.com/articles/s4146…

#DLCProTip: Did you know you can use unsupervised learning to adapt a trained model on the fly to your video in DeepLabCut!? 

When you run video analysis, check out “video adaptation” - it  reduces jitter and provides better poses! ⬇️

nature.com/articles/s4146…
M. Mathis Laboratory @EPFL (@mwmathislab) 's Twitter Profile Photo

Congratulations to now-former postdoc tom sainsbury for landing an exciting role in industry to push the bounds of BCI! We wish you all the best in your next adventures! 🙌

Congratulations to now-former postdoc <a href="/sainsbury_tom/">tom sainsbury</a> for landing an exciting role in industry to push the bounds of BCI! 

We wish you all the best in your next adventures! 🙌
Mackenzie Mathis, PhD (@trackingactions) 's Twitter Profile Photo

🥳New Cell paper, where I was delighted to play a small part in their big discovery: 🚨They found *specific* neuropeptides that can determine AND *change* the cast of ants 🐜🍃👀 (and has a global similar role in naked mole rats 🐀) cell.com/cell/fulltext/… 👩‍🔬My

🥳New <a href="/CellCellPress/">Cell</a>  paper, where I was delighted to play a small part in their big discovery: 

🚨They found *specific* neuropeptides that can determine AND *change* the cast of ants 🐜🍃👀 (and has a global similar role in naked mole rats 🐀)

cell.com/cell/fulltext/…

👩‍🔬My
Mackenzie Mathis, PhD (@trackingactions) 's Twitter Profile Photo

🥰 Self-supervised, label-free 3D cell imaging is here actu.epfl.ch/news/self-supe… #epfl #elife Congrats to Cyril Achard on this very cool first, first author publication 🏆! This started when he was a bachelor's student (and he's now completing his masters!). And many thanks to my