Joined July 2022
42 Photos and videos
TopoTune is going to ICML 2025!🎉🇨🇦 Curious to try topological deep learning with your custom GNN or your specific dataset? We built this for you! Find out how to get started at geometric-intelligence.githu…
4
34
144
16,262
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Have you debugged your training data? You might not like what you find. Introducing predictive data debugging: reveal and shape what your model will learn before training. In DPO datasets, we found broken guardrails, hallucinations, and fish fart fan fiction (seriously). (1/9)
26
107
880
170,953
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Our new paper is out this week in @NatureNeuro! We built a BCI that works with the brain's natural geometry — and we found that people could learn to play a video game with their brains in <1 hr of training. This efficiency is groundbreaking & here's why: nature.com/articles/s41593-0…
2
51
232
17,957
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
🤖Computers hold in memory GBs of data with perfect fidelity for hrs. 🧠Yet a person asked to remember a long serial nb fails in seconds. This memory limit is shared across species from rodents to primates. It inspired over 50 years of research. Where does it come from?👇
A computer holds data perfectly for hours. A person asked to remember a long number fails in seconds. Why? The answer is tangled up with something both brains and neural nets do: they code in low dimensions. 🧵
2
7
72
2,122
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Incredible work from the most talented people @ninamiolane @mathildepapillo
Brains (and RNNs) are noisy and it turns out this has mega implications for working memory🧠 Helping this project (my first in NeuroAI!) was a learning curve so I’m super grateful to @fatihdin4en and team for including me. Preprint: biorxiv.org/content/10.64898…
2
11
1,567
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Great work from @fatihdin4en and co on the interplay between dimensionality of neural code and robustness to noise!
A computer holds data perfectly for hours. A person asked to remember a long number fails in seconds. Why? The answer is tangled up with something both brains and neural nets do: they code in low dimensions. 🧵
3
8
779
Brains (and RNNs) are noisy and it turns out this has mega implications for working memory🧠 Helping this project (my first in NeuroAI!) was a learning curve so I’m super grateful to @fatihdin4en and team for including me. Preprint: biorxiv.org/content/10.64898…
A computer holds data perfectly for hours. A person asked to remember a long number fails in seconds. Why? The answer is tangled up with something both brains and neural nets do: they code in low dimensions. 🧵
1
13
76
8,921
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
The ocean is inherently chaotic, yet existing data-driven ocean models produce deterministic forecasts. In our new preprint, we introduce Njord, a probabilistic graph neural network for ensemble ocean forecasting. Link: arxiv.org/abs/2605.15470 A couple highlights below 🧵
5
11
31
3,582
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Can geometry help explain how neuronal signals create consciousness?🤔🌐 Loved diving into this massive question with the brilliant @claire_i_webb thanks to @longnow & @berggruenInst ! Watch our full conversation here ⬇️ @ucsbece @geometric_intel @ai_ucsb
How do the binary electronic signals of neurons give rise to consciousness? Mathematician and machine learning researcher @ninamiolane joined science historian @claire_i_webb to explore this question from an unexpected direction: geometry. A fascinating conversation that included everything from Jennifer Aniston to the neuroscience of regret. Watch the full episode on YouTube -> youtube.com/watch?v=IUlBwKin…
9
30
152
19,320
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
⁠We're releasing OgBench: the first benchmark for GNNs on omics data in the n≪p regime. Every major benchmark (OGB, TUDataset, LRGB, GraphBench) operates where the number of graphs (n) far exceeds nodes per graph (p). But biology is the opposite: few patients, massive graphs.
4
15
36
8,517
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
🏥Congratulations to ECE Prof. Ramtin Pedarsani's team on receiving a UC Noyce Initiative award to develop robust vision-language models for clinical applications — part of a $3.4M UC-wide research push for computational health and cybersecurity.🤖 🔗tinyurl.com/mm9jb8x
2
6
12
709
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
🔬How do you study thousands of neurons at once? You build better tools. ECE Prof. Spencer Smith's SLAB Lab designed a scan angle multiplier that achieves the laser scanning trifecta: high speed, high resolution, and a larger area.🧠⚡ 📜tinyurl.com/36j7pa3d
2
7
19
2,036
🏆 The 2026 Topological Deep Learning Challenge is officially live, now in its 4th edition! 🏆 This year’s theme is “Bridging the Gap” between the GNN and TDL worlds. Win incredible prizes including up to $1000 in cash 💸 and AI research internships! Submission deadline: Aug. 1
4
49
267
19,593
A huge thank you to our partners! 📍 Special shoutout to @TAGinDS for hosting the challenge for a 2nd year. 💰 Cash prizes sponsored by the amazing teams at Arlequin AI @ARLQ_AI and New Theory @newtheoryai 🏛️ Internships hosted by world-class labs at @UCSB and @EPFL_en
2
7
17
1,222
Also a huge shoutout to the incredible team of organizers behind this! @gbg1441 , @lev_telyatnikov , @louisacornelis @LouisVLang Marco Montagna, Olga Fink , @ninamiolane
2
8
391
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
The next TDL challenge edition is out!!
🏆 The 2026 Topological Deep Learning Challenge is officially live, now in its 4th edition! 🏆 This year’s theme is “Bridging the Gap” between the GNN and TDL worlds. Win incredible prizes including up to $1000 in cash 💸 and AI research internships! Submission deadline: Aug. 1
2
4
538
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
✨The 2026 TDL Challenge is up 🚀 $1000 in prize money and the opportunity for AI research internships? I'm interested 😼
🏆 The 2026 Topological Deep Learning Challenge is officially live, now in its 4th edition! 🏆 This year’s theme is “Bridging the Gap” between the GNN and TDL worlds. Win incredible prizes including up to $1000 in cash 💸 and AI research internships! Submission deadline: Aug. 1
3
6
581
We can’t wait to see your submissions! Full challenge guidelines and requirements are available here: geometric-intelligence.githu… Results announced at @TAGinDS Boston, Aug. 18–20. Participation does not require attending! #TDLChallenge #TopologicalDeepLearning #AI #ML #TAGinDS

6
23
1,110
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
🎉 Congratulations to ECE Professor James Buckwalter on being inducted as a Senior Member of the National Academy of Inventors!🏆 @AcadofInventors @ucsantabarbara @UCSBengineering 🔗tinyurl.com/ubk93ahf
3
6
12
648
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Neural networks might speak English, but they think in shapes. Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision. Starting today, we’re releasing a series of posts on this research agenda. 🧵
306
1,674
11,183
3,158,172
Mathilde Papillon🦋 mathildepapillon .bsky .social retweeted
Replying to @UCSBengineering
@UCSBengineering is launching METL — the Master of Engineering & Technology Leadership — the first fully online master's degree at @ucsantabarbara, built for working tech professionals around the world.
2
9
10
733