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

@EPFL πŸ‡¨πŸ‡­
πŸ¦“πŸ¦“πŸ¦“ #CEBRA is out πŸŽ‰πŸŽ‰πŸŽ‰ Check out the @Nature paper ⬇️ & the gorgeous code & resources built by current members @stes_io @BenquetCelia @TrackingActions @EPFL_en @epflSV πŸ“š how to use: cebra.ai/docs/usage.html πŸ’» install: cebra.ai/docs/installation.h… πŸ“–nature.com/articles/s41586-0…
πŸ¦“ 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. πŸ“ doi.org/10.1038/s41586-023-0… πŸ’»github.com/AdaptiveMotorCont… πŸ¦“ cebra.ai/ πŸ§΅β¬‡οΈ
4
16
55
21,653
M- Lab of Adaptive Intelligence @EPFL retweeted
Now accepted at #Neurips πŸ™ŒπŸ’—πŸ”₯🫢
🧠 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 πŸ“„arxiv.org/abs/2606.13260
7
42
358
34,378
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸŽ‚πŸ₯³ Wow! Happy 9 year anniversary of being published in @NatureNeuro #DeepLabCut πŸ’œ - what an amazing adventure that first paper kicked off πŸ™πŸΌ 1.14M installations πŸ’ͺ Original paper: rdcu.be/4Rep
1
22
133
4,578
M- Lab of Adaptive Intelligence @EPFL retweeted
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 - πŸ’°by the Brain Initiative @NIH! Led by @celia_bqt & @sainsbury_tom @CurrentBiology cell.com/current-biology/ful…?
1
40
170
17,536
M- Lab of Adaptive Intelligence @EPFL retweeted
🧠 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 πŸ“„arxiv.org/abs/2606.13260
38
221
1,410
132,635
M- Lab of Adaptive Intelligence @EPFL retweeted
Online now: The Simons Collaboration on Ecological Neuroscience: Studying how the brain interacts with the world dlvr.it/TSyBZX
12
43
3,505
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸ₯³ 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 πŸ™ ➑️ cell.com/neuron/fulltext/S08…
3
17
81
6,732
M- Lab of Adaptive Intelligence @EPFL retweeted
Interested in how we estimate 3D poses for humans and animals using flow matching? Come check out our work, #FMPose3D, at CVPR 2026! Today at the CV4Animals Workshop poster session: 11:30 a.m.–12:30 p.m., ExHall A Looking forward to seeing you there! πŸ˜€
1
1
4
259
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸ₯³ 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*:πŸ”₯SOTA 2D➑️3D animal shape by @xiaoyu912huang, @TiwangCS & I! πŸ“ arxiv.org/abs/2606.02366
1
13
75
5,181
M- Lab of Adaptive Intelligence @EPFL retweeted
And now, accepted to #CVPR2026! πŸ™ŒπŸ”₯ @CVPR ⬇️
🚨 ✨ New 3D pose estimation method from @mwmathislab! #FMPose3D allows for monocular (i.e. single camera) 2D ➑️ 3D πŸ”₯ Led by @TiwangCS & w/@xiaoyu912huang #FMPose3D is SOTA on human & animal 3D benchmarks, & will be integrated into @DeepLabCut β¬‡οΈπŸ‘€ πŸ“ arxiv.org/abs/2602.05755
3
16
124
17,281
M- Lab of Adaptive Intelligence @EPFL retweeted
🚨 ✨ New 3D pose estimation method from @mwmathislab! #FMPose3D allows for monocular (i.e. single camera) 2D ➑️ 3D πŸ”₯ Led by @TiwangCS & w/@xiaoyu912huang #FMPose3D is SOTA on human & animal 3D benchmarks, & will be integrated into @DeepLabCut β¬‡οΈπŸ‘€ πŸ“ arxiv.org/abs/2602.05755
6
45
332
40,622
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸ’‰ 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
33
5,728
M- Lab of Adaptive Intelligence @EPFL 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! πŸ”₯ Check out the work - many years in the making... sciencedirect.com/science/ar…
1
6
20
2,014
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸ”₯🍾 massive congratulations to @shaokaiyeah and Haozhe Qi for #LLaVAction to be accepted to #ICLR2026! TL;DR the first MMLLM for action understanding, + a new benchmark, + methods to train your MMLLMs for such tasks πŸ•ΊπŸ»πŸ’ƒπŸΌ πŸ’» llavaction.epfl.ch/ πŸ’™ arxiv.org/abs/2503.18712
4
21
2,903
M- Lab of Adaptive Intelligence @EPFL retweeted
🚨 Looking for a primer on the latest advances in joint neural-behavioral modeling? 🀩 Check out our new Nature Reviews Neuroscience piece! It was really an honor to write this 🫢 nature.com/articles/s41583-0…
2
23
78
8,814
M- Lab of Adaptive Intelligence @EPFL retweeted
Nature Neuroscience Leveraging insights from neuroscience to build adaptive artificial intelligence nature.com/articles/s41593-0…
9
41
3,135
M- Lab of Adaptive Intelligence @EPFL retweeted
πŸ‘€ How can we use new neuroscience insights to build *adaptive* AI agents and leverage the many foundation models ( which are much like different brain areas)? Check out my pitch in @NatureNeuro in the Jan 2026 issue πŸ’š ⬇️ nature.com/articles/s41593-0… #AIagents #neuroscience #AGI
4
26
159
8,918
M- Lab of Adaptive Intelligence @EPFL retweeted
Delighted to have my perspective on how we can leverage the latest insights from neuroscience to build adaptive AI agents out in @NatureNeuro πŸ–€πŸ’™ πŸ”— nature.com/articles/s41593-0…
4
43
4,580
M- Lab of Adaptive Intelligence @EPFL retweeted
Interested in the latest advances in neuroscience (neural dynamics and internal models) and how they can be leveraged to build smarter, adaptive AI? ➑️ My first real solo piece πŸ–€πŸ«Ά @NatureNeuro rdcu.be/eWVmA
5
90
437
27,381
M- Lab of Adaptive Intelligence @EPFL retweeted
The 2025 lab swag / holiday kit! πŸ«πŸ·πŸ§–β€β™€οΈ- happy holidays everyone!
2
21
1,534
M- Lab of Adaptive Intelligence @EPFL retweeted
The Swiss Laboratory Animal Science Association awarded on Wednesday its 2025 Prize to neuroscientist Mackenzie Mathis, Professor at EPFL, β€œfor her outstanding contribution to the refinement of animal research.”  go.epfl.ch/6689f9
1
4
25
2,751