Sign in

DurstewitzLab

@durstewitzlab.bsky.social
1.1K followers 1.8K following 51 posts

Scientific AI/ machine learning, dynamical systems (reconstruction), generative surrogate models of brains & behavior, applications in neuroscience & mental health

PostsRepliesMedia
DurstewitzLab @durstewitzlab.bsky.social · 31/08/2026
Next week I will talk about *foundation models for dynamical systems reconstruction* at ECML in Naples, ml4its.github.io/ml4its2026/. I will cover some of the latest from the group, like efficient parallel-in-time training for DSR and minimal mechanisms for zero-shot DSR.
050
Reposted by DurstewitzLab
Machine Learning in Science @mackelab.bsky.social · 02/07/2026
We congratulate @matthijspals.bsky.social on his successful PhD defense! During his time in the Mackelab, he used RNNs to link neural activity with underlying mechanisms. Now he moved on to a Postdoc position in @durstewitzlab.bsky.social at the ZI Mannheim and the University of Heidelberg.
Left to right: Philipp Berens, Anna Levina, Matthijs Pals, Peter Dayan, Jakob Macke.
2374
DurstewitzLab @durstewitzlab.bsky.social · 10/05/2026
In a #ICML2026 position paper we argue a dynamical systems perspective is needed to drive time series models forward: arxiv.org/abs/2602.16864 For TS, we need to move away from transformers that do not respect a system’s dynamical structure, esp. if out-of-domain generalization & insight is sought.
05213
DurstewitzLab @durstewitzlab.bsky.social · 10/05/2026
Neural ODEs are great as continuous-time dynamical systems, but slow and tedious to train. In a new #ICML2026 paper we intro a novel solver for continuous-time RNNs that does not rely on numerical integration. It's not only way faster & robust, but enables explicit analysis: arxiv.org/abs/2602.15649
0192
Reposted by DurstewitzLab
Dr Abeba Birhane @abeba.blacksky.app · 14/03/2026
i need the “llms are might be conscious” folx to read this
1858341
Reposted by DurstewitzLab
Joao Barbosa @jbarbosa.org · 01/03/2026
From the top of my head, here some recent ones: "Two views on the cognitive brain" by @johnwkrakauer.bsky.social, @dlbarack.bsky.social "Reconstructing computational system dynamics from neural data with recurrent neural networks" by @durstewitzlab.bsky.social et al 1/3
1327
DurstewitzLab @durstewitzlab.bsky.social · 01/03/2026
In a new #ICLR2026 paper we provide an algorithm for semi-analytically constructing un-/stable manifolds of fixed points and cycles of ReLU-based RNNs: openreview.net/pdf?id=EAwLA... These manifolds provide a skeleton for the system’s dynamics, dissecting the state space into basins of attraction.
0132
DurstewitzLab @durstewitzlab.bsky.social · 19/02/2026
We had a go at a blog about our recent dynamical systems foundation model published at NeurIPS (with strong support from the Structures outreach team!) … let us know your thoughts!
051
Reposted by DurstewitzLab
Memming Park @memming.bsky.social · 16/12/2025
Fully-funded International Neuroscience Doctoral Programme🧠 Champalimaud Foundation, Lisbon, Portugal 🇵🇹 Deadline: Jan 31, 2026 fchampalimaud.org/champalimaud... Research program spans systems/computational/theoretical/clinical/sensory/motor neuroscience, neuroethology, intelligence, and more!!
12617
DurstewitzLab @durstewitzlab.bsky.social · 05/12/2025
Tomorrow Christoph will present DynaMix, the first foundation model for dynamical systems reconstruction, at #NeurIPS2025 Exhibit Hall C,D,E #2303
0113
DurstewitzLab @durstewitzlab.bsky.social · 29/11/2025
Unlike current AI systems, animals can quickly and flexibly adapt to changing environments. This is the topic of our new perspective in Nature MI (rdcu.be/eSeif), where we relate dynamical and plasticity mechanisms in the brain to in-context and continual learning in AI. #NeuroAI
rdcu.be
What neuroscience can tell AI about learning in continuously changing environments
Nature Machine Intelligence - Durstewitz et al. explore what artificial intelligence can learn from the brain’s ability to adjust quickly to changing environments. By linking neuroscience...
04711
DurstewitzLab @durstewitzlab.bsky.social · 28/10/2025
Revised version of our #NeurIPS2025 paper with full code base in Julia & Python now online, see arxiv.org/abs/2505.13192
arxiv.org
True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
Complex, temporally evolving phenomena, from climate to brain activity, are governed by dynamical systems (DS). DS reconstruction (DSR) seeks to infer generative surrogate models of these from observe...
0267
DurstewitzLab @durstewitzlab.bsky.social · 21/09/2025
Our #AI #DynamicalSystems #FoundationModel DynaMix was accepted to #NeurIPS2025 with outstanding reviews (6555) – first model which can *zero-shot*, w/o any fine-tuning, forecast the *long-term statistics* of time series provided a context. Test it on #HuggingFace: huggingface.co/spaces/Durst...
huggingface.co
DynaMix - a Hugging Face Space by DurstewitzLab
Upload your time series data in CSV or NPY format and generate future forecasts. Configure the forecast length and settings, then download the results as CSV or NPY.
1124
DurstewitzLab @durstewitzlab.bsky.social · 15/08/2025
We have openings for several fully-funded positions (PhD & PostDoc) at the intersection of AI/ML, dynamical systems, and neuroscience within a BMFTR-funded Neuro-AI consortium, at Heidelberg University & Central Institute of Mental Health: www.einzigartigwir.de/en/job-offer... More info below ...
171
Reposted by DurstewitzLab
GerstnerLab @gerstnerlab.bsky.social · 08/08/2025
Is it possible to go from spikes to rates without averaging? We show how to exactly map recurrent spiking networks into recurrent rate networks, with the same number of neurons. No temporal or spatial averaging needed! Presented at Gatsby Neural Dynamics Workshop, London.
youtu.be
From Spikes To Rates
YouTube video by Gerstner Lab
26216
Reposted by DurstewitzLab
Mike Dettinger @mdettinger.bsky.social · 31/03/2025
Today I joined >1900 members of US National Academies of Science, Engineering & Medicine signing this open letter (views our own). Leadership of science by US has been paramount for >70yrs & Admin is now acting to throw it all away! docs.google.com/document/d/1... www.nytimes.com/2025/03/31/s...
docs.google.com
Public Statement on Supporting Science for the Benefit of All Citizens
TO THE AMERICAN PEOPLE We all rely on science. Science gave us the smartphones in our pockets, the navigation systems in our cars, and life-saving medical care. We count on engineers when we drive acr...
47627
Reposted by DurstewitzLab
Steven Strogatz @stevenstrogatz.com · 03/08/2025
What a fantastic accomplishment -- and what a fantastic story! www.quantamagazine.org/at-17-hannah...
quantamagazine.org
At 17, Hannah Cairo Solved a Major Math Mystery | Quanta Magazine
After finding the homeschooling life confining, the teen petitioned her way into a graduate class at Berkeley, where she ended up disproving a 40-year-old conjecture.
631191
DurstewitzLab @durstewitzlab.bsky.social · 13/07/2025
Got prov. approval for 2 major grants in Neuro-AI & Dynamical Systems Reconstruction, on learning & inference in non-stationary environments, out-of-domain generalization, and DS foundation models. To all AI/math/DS enthusiasts: Expect job announcements (PhD/PostDoc) soon! Feel free to get in touch.
0348
DurstewitzLab @durstewitzlab.bsky.social · 06/07/2025
We wrote a little #NeuroAI piece about in-context learning & neural dynamics vs. continual learning & plasticity, both mechanisms to flexibly adapt to changing environments: arxiv.org/abs/2507.02103 We relate this to non-stationary rule learning tasks with rapid performance jumps. Feedback welcome!
arxiv.org
What Neuroscience Can Teach AI About Learning in Continuously Changing Environments
Modern AI models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task, and then deployed with fixed parameters. Their training ...
0358
DurstewitzLab @durstewitzlab.bsky.social · 03/07/2025
Happy to discuss our work on parsimonious & math. tractable RNNs for dynamical systems reconstruction next week at cns2025florence.sched.com/event/1z9Mt/...
cns2025florence.sched.com
CNS*2025 Florence: NeuroXAI: Explainable AI for Understandi...
View more about this event at CNS*2025 Florence
190
DurstewitzLab @durstewitzlab.bsky.social · 26/06/2025
How do animals learn new rules? By systematically testing diff. behavioral strategies, guided by selective attn. to rule-relevant cues: rdcu.be/etlRV Akin to in-context learning in AI, strategy selection depends on the animals' "training set" (prior experience), with similar repr. in rats & humans.
rdcu.be
Abstract rule learning promotes cognitive flexibility in complex environments across species
Nature Communications - Whether neurocomputational mechanisms that speed up human learning in changing environments also exist in other species remains unclear. Here, the authors show that both...
182
Reposted by DurstewitzLab
Eleonora Russo @russoel.bsky.social · 21/06/2025
What a line up!! With Lorenzo Gaetano Amato, Demian Battaglia, @durstewitzlab.bsky.social, @engeltatiana.bsky.social,‪ @seanfw.bsky.social‬, Matthieu Gilson, Maurizio Mattia, @leonardopollina.bsky.social‬, Sara Solla.
152
Reposted by DurstewitzLab
Eleonora Russo @russoel.bsky.social · 21/06/2025
Into population dynamics? Coming to #CNS2025 but not quite ready to head home? Come join us! at the Symposium on "Neural Population Dynamics and Latent Representations"! 🧠 📆 July 10th 📍 Scuola Superiore Sant’Anna, Pisa (and online) 👉 Free registration: neurobridge-tne.github.io #compneuro
12211
DurstewitzLab @durstewitzlab.bsky.social · 21/06/2025
I’m really looking so much forward to this! In wonderful Pisa!
010
DurstewitzLab @durstewitzlab.bsky.social · 19/06/2025
Just heading back from a fantastic workshop on neural dynamics at Gatsby/ London, organized by Tatiana Engel, Bruno Averbeck, & Peter Latham. Enjoyed seeing so many old friends, Memming Park, Carlos Brody, Wulfram Gerstner, Nicolas Brunel & many others … Discussed our recent DS foundation models …
060
DurstewitzLab @durstewitzlab.bsky.social · 20/05/2025
Can time series (TS) #FoundationModels (FM) like Chronos zero-shot generalize to unseen #DynamicalSystems (DS)? No, they cannot! But *DynaMix* can, the first TS/DS FM based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: arxiv.org/pdf/2505.131... (1/6)
1113
DurstewitzLab @durstewitzlab.bsky.social · 21/04/2025
I'm presenting our lab's work on *learning generative dynamical systems models from multi-modal and multi-subject data* in the world-wide theoretical neurosci seminar Wed 23rd, 11am ET: www.wwtns.online --> incl. recent work on building foundation models for #dynamical-systems reconstruction #AI 🧪
wwtns.online
Home | Neuroscience | World Wide Theoretical Neuroscience Seminar
WWTNS is a weekly digital seminar on Zoom targeting the theoretical neuroscience community. Its aim is to be a platform to exchange ideas among theoreticians.
0113
Reposted by DurstewitzLab
CLaE @claeneuro.bsky.social · 29/03/2025
Nature Communications Uncertainty estimation with prediction-error circuits www.nature.com/articles/s41...
nature.com
Uncertainty estimation with prediction-error circuits - Nature Communications
How the brain integrates sensory input and predictions to adapt to change is not fully understood. Here authors build a neural network model to show how prediction-error neurons compute uncertainty of...
0163
Reposted by DurstewitzLab
Prof Christina Pagel @chrischirp.bsky.social · 10/03/2025
My latest post is now out. I show how Trump's attacks on science and universities are neither random nor new - they fit very precisely into the authoritarian playbook. This means we can guess what might come next and prepare - and we must! christinapagel.substack.com/p/censor-pur...
christinapagel.substack.com
Censor, purge, defund: how Trump following the authoritarian playbook on science and universities
I have mapped 35 of the Trump administration's attacks on science and universities to the authoritarian playbook - and consider what it means for attacks still to come
361570911
DurstewitzLab @durstewitzlab.bsky.social · 09/02/2025
Our revised #iclr2025 paper and codebase for an architecture for foundation models for dynamical systems reconstruction is now online: openreview.net/pdf?id=Vp2OA... ... includes additional examples of how this may be harvested for identifying drivers (control par.) of non-stationary processes.
openreview.net
060
DurstewitzLab @durstewitzlab.bsky.social · 26/01/2025
Toward interpretable #AI foundation models for #DynamicalSystems reconstruction: Our paper on transfer & few-shot learning for dynamical systems just got accepted for #ICLR2025 ! Previous version: arxiv.org/pdf/2410.04814; strongly updated version will be available soon ... (1/4)
1122
Reposted by DurstewitzLab
Dr. Prakash Kashwan @pkashwan.bsky.social · 29/12/2024
A photo of a teacher with a blackboard in the background. The essence: Teaching is one of the best means of learning.
1234
DurstewitzLab @durstewitzlab.bsky.social · 25/12/2024
That paper discusses an important issue for RNNs as used in neurosci. But we would argue that many RNN approaches do not truly reconstruct DS, for which we demand also agreement in long-term stats, attractor geometry, and generative perform. (esp. in chaotic systems, MSE as stats can be misleading).
2152
Reposted by DurstewitzLab
Dan Lurie @danjlurie.bsky.social · 24/12/2024
Great to see this group on Bluesky. Durstewitz and Seamans 2008 is one of my all time favorite papers on the function of dopamine in the PFC www.researchgate.net/profile/Dani...
researchgate.net
161
DurstewitzLab @durstewitzlab.bsky.social · 24/12/2024
Now may be a good time to introduce our group on bsky with some of our contrib. to dynamical systems reconstruction (DSR) from past year. By DSR we mean learning a *generative surrogate model* of a dyn. process from TS data which reproduces full attractor & generalizes to new init. conditions (1/6)
2234
DurstewitzLab @durstewitzlab.bsky.social · 22/12/2024
Good targets for foundation/ inference models/ LLMs …
030
DurstewitzLab @durstewitzlab.bsky.social · 16/12/2024
Can really recommend this excellent talk by Christoph Bergmeir at neurips.cc/virtual/2024... yesterday … on the inability of Transformer- & LLM-based recent time series models to beat even simple baselines *if you do the stats and testing right*! A lesson in careful stat. eval.
neurips.cc
Time Series in the Age of Large ModelsNeurIPS 2024
0171
DurstewitzLab @durstewitzlab.bsky.social · 12/12/2024
Don't miss out on our 2 @neuripsconf.bsky.social papers on dynamical systems reconstruction today & tomorrow: 1) neurips.cc/virtual/2024...
neurips.cc
NeurIPS Poster Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems ReconstructionNeurIPS 2024
130
DurstewitzLab @durstewitzlab.bsky.social · 24/11/2024
Happy our team is among this years’ recipients of the Samsung Global Research Outreach Awards! www.sait.samsung.co.kr/saithome/abo... We will take #DynamicalSystems reconstruction to the next level, large-scale – looking forward to the collaboration with the Samsung team!
sait.samsung.co.kr
Global Collaboration | Samsung Advanced Institute of Technology
Global Collaboration | Samsung Advanced Institute of Technology
050
Reposted by DurstewitzLab
Eleonora Russo @russoel.bsky.social · 17/11/2024
And with a bit of delay now also here: 📢 New work on hippocampal assemblies & theta! www.nature.com/articles/s41... It was a pleasure to work with Nadine Becker, Aleks Domanski, Timothy Howe, Kipp Freud, @durstewitzlab.bsky.social, Matt Jones. @SantAnna Pisa @Bristol Neuro @ZI Mannheim 🧵[1/11]
nature.com
Integration of rate and phase codes by hippocampal cell-assemblies supports flexible encoding of spatiotemporal context - Nature Communications
Russo et al. show that context-specific place cell assemblies support hippocampal integration of past experiences into future plans during goal-directed behavior and propose a biophysical mechanism be...
1235