FieteGroup
@FieteGroup
Followers
4K
Following
167
Media
25
Statuses
143
Fiete group @MIT, theoretical and computational neuroscience. Run by the group. Follows and retweets are not an endorsement.
Cambridge, MA
Joined August 2019
🧵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?
2
10
39
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/kuNZhK8mMO Joint w/ @FieteGroup @jaedong_hwang, @brody_lab, @PrincetonNeuro ⬇️ 🧵 for key takeaways
4
12
42
This paper got into @Nature!!! 🚀🚀🚀 Look at @SarthakChandra’s thread for a summary
🚨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)
4
15
106
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. 🧵👇
nature.com
Nature - The principle of peak selection is described, by which local interactions and smooth gradients drive self-organization of discrete global modules.
2
47
193
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
nature.com
Nature - A neocortical–entorhinal–hippocampal network model based on grid cell states recapitulates experimental results and reconciles the spatial, associative and episodic memory...
4
45
163
Pleased to share that our work on "Episodic and associative memory from spatial scaffolds in the hippocampus" has been published in Nature today.
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
0
1
18
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
4
19
91
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
2
24
132
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
@doristsao @FieteGroup +1 to an amazing conceptual breakthrough in theoretical neuroscience that I think did not depend on big data or fancy technologies. What we can say is that BRAIN technologies will make the theory testable in a much more conclusive way than was ever possible.
1
11
57
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
@SebastianSeung Btw, I don't know if @FieteGroup is funded by BRAIN, but their recent work understanding grid cell-place cell dynamics as a general mechanism for episodic memory that factorizes problem of building attractors from problem of assigning content to them, is such a beautiful and
2
13
61
Tweet thread coming up!
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.
1
0
11
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
4
50
280
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
1
13
48
Excited to begin announcing our #NeurIPS2023 workshop & conference papers (1/10)! 🔥🚀An Information-Theoretic Understanding of Maximum Manifold Capacity Representations🚀🔥 w/ amazing cast @vclecomte @BerivanISIK @sanmikoyejo @ziv_ravid @Andr3yGR @KhonaMikail @ylecun 1/7
9
92
485
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!
8
111
593
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 —
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!
1
11
78
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
0
12
46
The CfP for our @NeurIPSConf Workshop on Associative Memory & Hopfield Networks is out! The deadline is Sep 29th! Details: https://t.co/sxEjEZ6rwF Speakers: @HopfieldJohn @DimaKrotov @HochreiterSepp @carlolucibello @kchorolab @FieteGroup
@MITIBMLab @Harvard @IBMResearch
amhn.vizhub.ai
Associative Memory & Hopfield Network Worshop @NeurIPS 2023. Discuss the latest multidisciplinary developments in Associative Memory and Hopfield Networks. Imagine new tools built around memory as...
0
12
43
🚨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)
3
57
168
Please consider submitting to our exciting #NeurIPS2023 workshop on the latest developments in Associative Memory & Hopfield Networks!
I am excited to announce Associative Memory & Hopfield Networks Workshop @NeurIPSConf 2023! We have a stellar lineup of invited speakers. The call for contributed papers is now open. See you in New Orleans! Website: https://t.co/yT12tCRX3N Submission: https://t.co/DeenyXbNDb
1
12
37