Scientific machine learning, AI & data analysis, dynamical systems theory, applications in (computat.) neuroscience & psychiatry. @durstewitzlab.bsky.social
Mannheim+Heidelberg
- Tweets 1,006
- Following 317
- Followers 1,981
- Likes 3,406
In a #ICML2026 position paper we argue a dynamical systems perspective is needed to drive time series models forward: arxiv.org/abs/2602.16864
We need to move away from transformers that do not respect a system’s dynamical structure, esp. for out-of-domain generalization & insight
10
47
3,960
Tomorrow Christoph will present DynaMix, the first foundation model for dynamical systems reconstruction, at #NeurIPS2025 Exhibit Hall C,D,E #2303
2
22
98
4,930
DurstewitzLab retweeted
Captivating perspective! The flexibility and adaptability of the human brain indeed set a high bar for AI systems. How do you envision the integration of these dynamical and plasticity mechanisms affecting future AI advancements? Could this also reshape our understanding of neurological disorders? For more in-depth reviews and discussions on topics like these, check out sciqst.com – a one-stop platform that answers every biomedical question and offers comprehensive biomedical reviews. #NeuroAI #Medicine
1
3
667
DurstewitzLab retweeted
Now that the AI overlords all started publicly admitting defeat with the current architecture, I believe we are going to see more and more folks turn to neuroscience for clues. About time.. 😁
Unlike current AI systems, brains can quickly & flexibly adapt to changing environments.
This is the topic of our perspective in Nature MI (rdcu.be/eSeif), where we relate dynamical & plasticity mechanisms in the brain to in-context & continual learning in AI. #NeuroAI
1
1
5
371
Unlike current AI systems, brains can quickly & flexibly adapt to changing environments.
This is the topic of our perspective in Nature MI (rdcu.be/eSeif), where we relate dynamical & plasticity mechanisms in the brain to in-context & continual learning in AI. #NeuroAI
7
84
470
24,851
Our #DynamicalSystems #FoundationModel was accepted to #NeurIPS2025 with outstanding reviews (6555) – first model which can *0-shot*, w/o any fine-tuning, forecast the *long-term statistics* of time series provided a context. Test it on #HuggingFace:
huggingface.co/spaces/Durste…
...
Can time series #FoundationModels like Chronos zero-shot generalize to unseen #DynamicalSystems (DS)?
No, they cannot.
But *DynaMix* can, the first FM based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: arxiv.org/pdf/2505.13192v1
(1/6)
1
2
16
1,198
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 (see below): einzigartigwir.de/en/job-off…
1
3
15
1,947
DurstewitzLab retweeted
Our new preprint compares naïve baselines, network models (incl. PLRNN-based SSMs), and Transformers on 3x40‑day EMA+EMI datasets. PLRNNs gave the most accurate forecasts, yielded interpretable networks, and flagged “sad” & “down” as top leverage points. doi.org/10.1101/2025.07.03.2…
1
12
35
4,151
Got prov. approval for 2 major grants in Neuro-AI & Dynamical Systems Recons., on learning & inference in non-stationary environments, OOD generalization, and DS foundation models. To all AI/math enthusiasts: Expect job announcements (PhD/PostDoc) soon! Feel free to get in touch.
1
7
32
2,461
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 w rapid jumps.
Feedback welcome!
18
79
4,630
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).
2
8
42
3,029
DurstewitzLab retweeted
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
📍@ScuolaSantAnna, Pisa (and online)
Free registration:
👉neurobridge-tne.github.io
1
8
48
3,955
Can time series #FoundationModels like Chronos zero-shot generalize to unseen #DynamicalSystems (DS)?
No, they cannot.
But *DynaMix* can, the first FM based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: arxiv.org/pdf/2505.13192v1
(1/6)
3
18
90
9,630
Remarkably, DynaMix not only generalizes zero-shot to novel DS, but it can even generalize to new initial conditions and regions of state space not covered by the in-context information.
(5/6)
1
4
392
We dive a bit into the reasons why current time series FMs not trained for DS reconstruction fail, and conclude that a DS perspective on time series forecasting & models may help to advance the #TimeSeriesAnalysis field.
(6/6)
1
3
306