Lukas Eisenmann

Exciting, foundation models for dynamical systems enter the scene and start outperforming time series FM. Here is another recent paper on DS FM: 👉 arxiv.org/abs/2505.13192 (@DurstewitzLab,@wgilpin0 )

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/2505.13192… (1/6)

Honored to receive prestigious #BMBF funding in #AI to establish my junior research group! Returning from @TU_Muenchen to @UniHeidelberg in Sept 2024. Seeking 1 Postdoc, and 2 PhD students. Apply by July 20 if you're passionate about the #Mathematical_Foundations_of_AI

Excited to share our work at #NeurIPS2023! Join me at poster #705 in Great Hall & Hall B1+B2 on Wednesday at 10:45. Looking forward to discussing dynamical systems reconstruction and connecting with fellow enthusiasts. See you there!

@patrickmineault Analysis of trained RNN (and training) with respect to their fixed points and cycles. arxiv.org/abs/2310.17561

Send me your NeurIPS stuff! I'm gathering a list of neuroAI papers and workshops to share on the NeuroAI archive.

How to analyze comput. & dynamic mechanisms of RNNs? 1/2 Our #NeurIPS2023 spotlight on a highly efficient algo for locating all fixed points, cycles, and bifurcation manifolds in RNNs: arxiv.org/abs/2310.17561 @NeurIPSConf By brilliant @Zahra__Monfared, @lukasironman, Nic Göring

Find us tommorow, 9am at @CNSorg Leipzig in the Goethesaal for our tutorial on reconstructing dynamical systems from neural measurements using RNNs, including a hands-on tutorial with code!

Would you like to learn how to use and interpret RNNs for dynamical systems reconstruction (DSR) from #neuroscience data? Then join in for our hands-on @CNSorg 2023 tutorial on DSR using RNNs from multiple single-unit recordings, fMRI, and/or behavior: durstewitzlab.github.io/cns-2023-tutor…