Mackenzie Weygandt Mathis, PhD

🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in @Nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 doi.org/10.1038/s41586… 💻github.com/AdaptiveMotorC… 🦓 cebra.ai 🧵⬇️

Mice perform active sensing to acquire visual info: check out our collaborative effort, which is our 1st in motor+vision! Great to work with @AToliasLab Xaq and Cris - 💰by the Brain Initiative @NIH! Led by @celia_bqt & @sainsbury_tom @CurrentBiology cell.com/current-biolog…?

🧠 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

#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.

@OriolRibera Rather than PCA We use CEBRA as the base, which is a time-series method nonlinear ICA: nature.com/articles/s4158…

@TrackingActions Try with PCA Principal Component analisis to reduce dimensionality to capture 90% of entropy with the least dimensions as possible. Somerimes can be mappes to matrix equations and then exttact the eigevectors

@EliSennesh X character limited post ; )

@TrackingActions > Can we recover the equations governing a system directly from noisy, high-dimensional observations? Isn't that basically all system identification?

🥳 Excited that our Perspective about our new @SimonsFdn Collaboration: SCENE is out in @NeuroCellPress ! A great team effort across all the PIs, championed by @lengyel_m and @JP__NOEL 🙏 ➡️ cell.com/neuron/fulltex…

@pjreddie Horrendous :/

CVPR has reached its final form, a convention for weapons manufacturers

Also, please check out our @huggingface demo: huggingface.co/spaces/MLAdapt…

This nicely builds on top of our #SuperAnimal quadruped model (read more here: nature.com/articles/s4146… such that you can directly run shape inference with our pipeline!

🥳 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

Brilliant talk by @TonyZador kicking off the #NeuroAI session at @CSHL 90th anniversary symposium

Thrilled to share that I’ve been promoted to Associate Professor with tenure at @EPFL! 🎉 Deeply grateful to my incredible lab, collaborators, and mentors who’ve made this journey possible. Excited for what’s ahead! 🧠✨

Nature research paper: Prefrontal to ventral tegmental area dynamics drive contingency degradation go.nature.com/4wbtWwx

@maxhodak_ Switzerland 🇨🇭

as much as I love california, it does seem like it's time to plan more seriously about the prospect of not being able to stay here we're going to take steps to set up an office in NYC, but I'm curious where people think AI would go if it had to:

At #ICLR2026 Please check out our work #LlaVAction: By co-first aurhors @shaokaiyeah and Haozhe Qi TL;DR the first multi-modal LLM for action understanding and video captioning+ a new benchmark, + methods to train your MMLLMs for such tasks 🕺🏻💃🏼 💻 llavaction.epfl.ch 💙

From the neuroscience perspective, behavior is unmatched as noninvasive quantitative readout of brain function (and best of all, it is a readout that matters). This initial lifelong continuous screen of behaving vertebrates provided a wealth of new ideas regarding progression and staging of brain function across the adult lifespan. Truly impressive work from Claire, Ravi, and the whole creative and dedicated team. Lifelong work takes a long time, even with killifish!

💉 Finding clinical trials & knowing which are useful is an overwhelming task, even if you know where to start! I worked on a simple @Gradio app for parsing clinical trials+ adding a #DeepSeek model to rank trials + user Q&A. I hope its useful to many: clinicaltrialmatcher.org