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

Joined February 2011
607 Photos and videos
🦓 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/s41586-023-0… 💻github.com/AdaptiveMotorCont… 🦓 cebra.ai/ 🧵⬇️
31
269
964
248,741
🥳 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/fulltext/S08…
3
16
76
5,938
Brilliant talk by @TonyZador kicking off the #NeuroAI session at @CSHL 90th anniversary symposium
1
2
37
4,219
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! 🧠✨
6
4
148
6,267
Mackenzie Weygandt Mathis, PhD retweeted
May 8
Nature research paper: Prefrontal to ventral tegmental area dynamics drive contingency degradation go.nature.com/4wbtWwx

2
17
58
13,836
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 💙

10
1,126
Mackenzie Weygandt Mathis, PhD retweeted
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!
Replying to @clairebedbrook
Excited to share this work with an amazing team: @KarlDeisseroth @BrunetLab @Ravi__Nath @scott_linderman Libby Zhang Paper in Science: science.org/doi/10.1126/scie…
2
37
227
34,059
Mackenzie Weygandt Mathis, PhD retweeted
💉 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
1
7
32
5,579
Mackenzie Weygandt Mathis, PhD retweeted
How does the brain know which neurons to adjust during learning in order to optimize behavior? MIT researchers discovered that brains can use cell-by-cell error signals to do this — surprisingly similar to how AI systems are trained via backpropagation. mcgovern.mit.edu/2026/02/25/…
3
84
371
56,542
Mackenzie Weygandt Mathis, PhD retweeted
Swiss AI Visiting PhD Program at EPFL. Deadline Feb 28. "The program provides a fellowship contribution of CHF 2,500 ($3200) per month, access to the Alps supercomputer, and eligibility for a post-visit continuation grant of up to 50k GPU hours. The call is open to PhD students enrolled outside Switzerland, with applications supported by EPFL PIs contributing to the Swiss AI Initiative. The application closes on February 28." drive.google.com/file/d/1e0I… @ICepfl @EPFL_AI_Center
5
39
284
30,592
And now, accepted to #CVPR2026! 🙌🔥 @CVPR ⬇️
🚨 ✨ New 3D pose estimation method from @mwmathislab! #FMPose3D allows for monocular (i.e. single camera) 2D ➡️ 3D 🔥 Led by @TiwangCS & w/@xiaoyu912huang #FMPose3D is SOTA on human & animal 3D benchmarks, & will be integrated into @DeepLabCut ⬇️👀 📝 arxiv.org/abs/2602.05755
3
16
123
17,079
Mackenzie Weygandt Mathis, PhD retweeted
People often assume that state of the art vision models are *not recurrent* -- but what if it's not so clear-cut? It turns out DINOv2 activations can be fit approx. 1-to-1 with only 2 transformer blocks applied recurrently. Leb by @mozesjacobs @thomas_fel_ & @RichieHakim ⬇️
Are ViTs secretly RNNs? #ICLR2026 Our 2-block recurrent transformer recovers 96% of DINOv2’s IN-1k accuracy & reproduces its activations 1-to-1, motivating the Block-Recurrent Hypothesis: arxiv.org/abs/2512.19941 w/ @thomas_fel_ @RichieHakim @ABrondetta Demba Ba @t_andy_keller
19
108
11,170
🚨 ✨ New 3D pose estimation method from @mwmathislab! #FMPose3D allows for monocular (i.e. single camera) 2D ➡️ 3D 🔥 Led by @TiwangCS & w/@xiaoyu912huang #FMPose3D is SOTA on human & animal 3D benchmarks, & will be integrated into @DeepLabCut ⬇️👀 📝 arxiv.org/abs/2602.05755
6
42
320
30,492
Check out the demos & project page here: xiu-cs.github.io/FMPose3D/

1
7
1,889
Mackenzie Weygandt Mathis, PhD retweeted
Feb 4
Neural interfaces are the winners of the 2026 Queen Elisabeth Prize for Engineering. Nine scientists are honoured, including J.Bloch and G.Courtine (EPF/UNIL/CHUV,) recognized for their development of electronic spinal stimulation technology. actu.epfl.ch/news/neuroscien…
5
21
2,294
Mackenzie Weygandt Mathis, PhD retweeted
🐻 reID of unmarked Grizzly's in Alaskan wilderness from single images is a daunting task, but in our new work out in @CurrentBiology that is exactly what Beth Rosenberg & Mu Zhou & @TrackingPlumes! 🔥 Check out the work - many years in the making... sciencedirect.com/science/ar…
1
6
20
1,873
🐻 reID of unmarked Grizzly's in Alaskan wilderness from single images is a daunting task, but in our new work out in @CurrentBiology that is exactly what Beth Rosenberg & Mu Zhou & @TrackingPlumes! 🔥 Check out the work - many years in the making... sciencedirect.com/science/ar…
1
6
20
1,873
Biologically, it reveals that bears have a much larger range than previously documented. This has important implications for conservation efforts in Alaska ...
1
5
708