Simone Azeglio (@simoneazeglio) header
Simone Azeglio (@simoneazeglio) profile picture

Vision, geometry & information in brains & machines | Guest Research Associate @univkyoto (@ykamit Lab) | PhD @InstVisionParis & @ENS_ULM

Kyoto, Japan
Joined July 2019
Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)Photo by Simone Azeglio (@simoneazeglio)
Simone Azeglio retweeted
Excited to share our work at #NeurIPS2026! 🎉 We solve a longstanding challenge: capturing the encoding of multiscale information in neural populations beyond the limitations of classical Fisher information. Oral in Sydney, Dec 8, 10am–1pm. I'll be there too. Come meet us! 🇦🇺
A monkey looks at a frog. Which image features does the activity in its visual cortex preserve, and which does it throw away? In our #NeurIPS2026 Oral, we derive a geometry of stimulus space that is exactly tied to the mutual information carried by neurons. 🧵 1/12
2
7
303
A monkey looks at a frog. Which image features does the activity in its visual cortex preserve, and which does it throw away? In our #NeurIPS2026 Oral, we derive a geometry of stimulus space that is exactly tied to the mutual information carried by neurons. 🧵 1/12
2
33
3
243
11,537
We will present it as an oral at NeurIPS 2026 (time TBA) and at Poster Session 1 in Sydney, Tue 8 Dec, 10am to 1pm. See you in Sydney! 🇦🇺🦘 11/12
1
10
594
Lastly, spoiler alert! Our longer neuro-preprint (w/ @ari_dibe) goes beyond visual codes: we consider somatosensory and motor too. Towards a single framework that maps the structure of encoded information. Thread soon: biorxiv.org/content/10.64898… 12/12
1
19
561
We’re excited to announce DiG-bench, a new benchmark for discovery! Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a text-based environment, so they probe discovery capabilities in the natural domain of language models, rather than requiring additional, potentially confounding, visual understanding. TL;DR frontier models have improved a lot over the last few months. But they are still stumped by some surprisingly simple problems, even in their native text domain. With @cocosci_lab (@Princeton) @MITCoCoSci (@MIT) @SchmidhuberAI (@KAUST_News) @misovalko (@Inria) @tri_dao (@PrincetonCS) @RMBattleday @zebkDotCom @FraserGreenlee @akaijsa @ClareMaguire @TimMuller1 @kubicek_ales @physicscat0x7d @SukritSumant @thoughtchannel_ (1/5)
44
325
242
1,183
1,198,306
🚨1 week away!🚨 The submission deadline for NeurReps 2026 is 1 week away (Monday, August 24th) Submit your work: neurreps.org/#cfp
5
2
12
2,769
Simone Azeglio retweeted
Signals of physical plausibility are hiding in the geometry of frozen image encoders. No video training. No physics supervision.
6
39
2
177
36,449
Simone Azeglio retweeted
🧠 Mechanistic interpretability for the brain 🧠 Early visual neurons have had a clean mathematical description for decades (Gabor functions), while higher visual areas have remained notoriously hard to characterize. Our new paper, led by @vedanglad, shows that natural language can provide that missing framework: concise, human-readable, verifiable descriptions of what higher visual neurons encode. To get there, we pair neural digital twins with vision-language models to run virtual neuroscience experiments at scale. Check out the full paper below.
How well can you describe the feature selectivity of a vision neuron … with words? Interpretability has long borrowed from neuroscience — and maybe it can give back too! 🧵
2
19
1
96
14,636
Simone Azeglio retweeted
Where does agency come from in a neural network? We trained RNNs to chase a moving target. Some learn to react. Others learn to predict, anticipate, and even wait (schematic gif attached) The difference comes down to the dimensionality of the neural code. 🧵 (1/7)
10
104
14
663
67,359
🧠Introducing OmniMouse: One of the largest datasets in neuroscience ever assembled along with a systematic study of scaling properties of brain models Co-led with🤩@pollytur1 @alexrgil14 3M neurons, >150B tokens from @AToliasLab @stanford, @alxecker @sinzlab @uniGoettingen 🧵
4
49
4
195
19,779
Simone Azeglio retweeted
Applications are open for the Junior Theoretical Neuroscientists Workshop which will take place July 21-24, 2026 at the Center for Computational Neuroscience, @FlatironInst Travel, lodging, and meals will be covered for accepted participants. Apply by April 15, 2026
3
20
3
75
12,695