🧵1/10
LLMs can answer in many languages.
But do they think in them?
Even when prompted in Swahili or Thai, models often switch to English for reasoning.
This breaks interpretability and trust.
So we ask: Can LLMs reason in the input language?
1/ Excited to share our recent work in #ICML2025, “A multi-region brain model to elucidate the role of hippocampus in spatially embedded decision-making”. 🎉
🔗 https://t.co/BZm1KwJzwt
Joint w/ @FieteGroup@jaedong_hwang, @brody_lab, @PrincetonNeuro
⬇️ 🧵 for key takeaways that lead to an ongoing neurophysiological experimental verification of our prediction on grid cell code!
1/ Our paper appeared in @Nature today! https://t.co/bsdYF8k6G6 @FieteGroup @KhonaMikail.
Explains emergence of multiple grid cell modules, w/ excellent match to data! Novel mechanism for applying across vast systems from development to ecosystems. 🧵👇
1/ Super-excited to share our new work “Episodic and associative memory from spatial scaffolds in the hippocampus”, out in Nature today! https://t.co/QYcLNhhEwr @FieteGroup@sugsharma@rischaudhuri. Key insights and ideas 👇#tweeprint
How does one brain circuit encode memories of both places and events? 🧠 The answer is out in Nature today! (proud to have lead this work as a Co-First author @FieteGroup )
🔗 https://t.co/Bg0kKwtis9
Talk: https://t.co/Hb2PpWB2G6
This work extends MESH: https://t.co/B0zDEfHLZv
How does one brain circuit encode memories of both places and events? 🧠 The answer is out in Nature today! (proud to have lead this work as a Co-First author @FieteGroup )
🔗 https://t.co/Bg0kKwtis9
Talk: https://t.co/Hb2PpWB2G6
This work extends MESH: https://t.co/B0zDEfHLZv
Finally a tweeprint on our recent preprint presenting Vector-HaSH !
Vector-HaSH extends MESH to unify two important and seemingly independent roles of hippocampus: Spatial Mapping and Episodic Memory !
Brief talk: https://t.co/Hb2PpWB2G6
Preprint: https://t.co/R6y7nKm4K7
1/n
Thank you so much @SebastianSeung for appreciating our work! I am glad to hear that you consider it a breakthrough in theoretical neuroscience!
For folks who would like to know more:
Short talk on Vector HaSH
https://t.co/1t7PDmuVKp
Short talk on MESH
https://t.co/21ocjqKNd8
Thanks @doristsao for your kind & thoughtful words about our work! I am glad that you find it beautiful, creative and conceptually insightful!
For folks who would like to know more:
Short talk on Vector-HaSH
https://t.co/1t7PDmuVKp
Short talk on MESH
https://t.co/21ocjqKNd8
This work from @FieteGroup looks pretty cool: https://t.co/pyt8ocD4l4
Showing how structure in the sensory cortex (hierarchy, topography, etc.) can emerge from self-organizing dynamics and spontaneous activity on a cortical sheet.
Looking forward to reading this one.
Excited to announce:
🔥🧠 Associative Memory Under the Probabilistic Lens 🧠🔥
w @KhonaMikail @Andr3yGR@sanmikoyejo@neurostrow@FieteGroup & Nika Zahedi
Appearing @ #NeurIPS2023 Associative Memory & Hopfield Networks Workshop !
🧵👇
1/7
Announcing #2 in our #NeurIPS2023 workshop & conference papers series (2/10)!!
🔎🧠Testing Assumptions Underlying a Unified Theory for the Origin of Grid Cells🔎🧠
w @KhonaMikail @FieteGroup@sanmikoyejo & Adrian Bertagnoli
Paper: https://t.co/REm5F1Kgrk
🧵👇
1/8
Mechanistic interpretability is not only for ML or LLM, but is even more promising for Science! A few months ago, we proposed a brain-inspired method (BIMT) for NN interpretability; Now we're happy to see that it can give something back to neuroscience - Growing brains in RNNs!
In this work, with @ZimingLiu11, we solved a problem that I’ve been struggling with for years: How to make functional modules emerge in RNNs that are also anatomically/topographically segregated! Have a look —
At #BernsteinConference2023 & interested in motor control? Visit poster III C06 (Thu, 12:30). @sunnyyduan@FieteGroup & I show a model that instantiates hypotheses about how different learning mechanisms in M1, cerebellum & integrative cortex help tackle challenging control tasks
🚨New Preprint! Wondered how grid cells form multiple discrete modules? Interested in continuous attractors and modularity? With @FieteGroup, we discover + generalize a physical mechanism for forming modules from smoothly varying parameters in a dynamical system!👇(1/15)