Jun.-Prof. Dr. Jan Stühmer

Am HITS leitet Jun.-Prof. Dr. Jan Stühmer die Forschungsgruppe für Maschinelles Lernen und Künstliche Intelligenz (MLI). Er ist ebenfalls Juniorprofessor an der Fakultät für Informatik am Karlsruher Institut für Technologie (KIT).

Forschungsschwerpunkte

Variationelle Inferenz
Geometric Deep Learning
Dateneffiziente Lernverfahren
Lerntheorie
Interpretierbare Repräsentationen

CV

Jan Stühmer studierte Informatik an der TU Dresden und promovierte 2016 an der TU München (TUM). Während der Promotion verbrachte er einen Forschungsaufenthalt am California Institute for Technology (Caltech). Anschließend ging er als Gastwissenschaftler an das Computer Science and Artificial Intelligence Laboratory am Massachusetts Institute of Technology (MIT CSAIL). Danach war er zunächst als PostDoc, dann als Researcher und Scientist bei Microsoft Research Cambridge und am Microsoft MR&AI Lab in Zürich tätig, bevor er Senior Researcher an das Samsung AI Center in Cambridge wechselte. Seit 2022 leitet er eine Juniorgruppe am HITS und ist Juniorprofessor am KIT.

Publikationen

2024

• Seute L, Hartmann E, Stühmer J, Gräter F (2024). Grappa – A Machine Learned Molecular Mechanics Force Field, arXiv,physics.chem-ph,2404.00050 1828
• Ruff R, Reiser P, Stühmer J, Friederich P (2024). Connectivity optimized nested line graph networks for crystal structures, Digital Discovery 3(3):594–601 1831

2023

• Cornelio C, Stuehmer J, Hu SX, Hospedales T (2023). Learning where and when to reason in neuro-symbolic inference, In International Conference on Learning Representations 1596
• Chavhan R, Gouk H, Stuehmer J, Heggan C, Yaghoobi M, Hospedales T (2023). Amortised Invariance Learning for Contrastive Self-Supervision, In The Eleventh International Conference on Learning Representations 1653

2022

• Hu SX, Li D, Stühmer J, Kim M, Hospedales TM (2022). Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9068–9077 1515
• Negri MM, Fortuin V, Stühmer J (2022). Meta-learning richer priors for VAEs, In Fourth Symposium on Advances in Approximate Bayesian Inference 1516

2021

• Kwon T, Tekin B, Stühmer J, Bogo F, Pollefeys M (2021). H2o: Two hands manipulating objects for first person interaction recognition, In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10138–10148 1517

2020

• Stühmer J, Turner R, Nowozin S (2020). Independent subspace analysis for unsupervised learning of disentangled representations, In International Conference on Artificial Intelligence and Statistics, pp. 1200–1210 1518

2019

• Stoehr N, Yilmaz E, Brockschmidt M, Stühmer J (2019). Disentangling interpretable generative parameters of random and real-world graphs, In NeurIPS Workshop on Graph Representation Learning 1519

2017

• Krieg M, Stühmer J, Cueva JG, Fetter R, Spilker K, Cremers D, Shen K, Dunn AR, Goodman MB (2017). Genetic defects in β-spectrin and tau sensitize C. elegans axons to movement-induced damage via torque-tension coupling, Elife 6:e20172 1520
• Krieg M, Stuehmer J, Cueva JG, Fetter R, Spilker K, Cremers D, Shen K, Dunn AR, Goodman MB (2017). Tau like proteins reduce torque generation in microtubule bundles, Biophysical Journal 112(3):29a–30a 1526

2015

• Stühmer J, Cremers D (2015). A fast projection method for connectivity constraints in image segmentation, In International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 183–196 1521
• Stuhmer J, Nowozin S, Fitzgibbon A, Szeliski R, Perry T, Acharya S, Cremers D, Shotton J (2015). Model-based tracking at 300hz using raw time-of-flight observations, In Proceedings of the IEEE International Conference on Computer Vision, pp. 3577–3585 1527

2014

• Oswald MR, Stühmer J, Cremers D (2014). Generalized connectivity constraints for spatio-temporal 3d reconstruction, In European Conference on Computer Vision, pp. 32–46 1522
• Triebel R, Stühmer J, Souiai M, Cremers D (2014). Active online learning for interactive segmentation using sparse Gaussian processes, In German Conference on Pattern Recognition, pp. 641–652 1528

2013

• Stühmer J, Schroder P, Cremers D (2013). Tree shape priors with connectivity constraints using convex relaxation on general graphs, In Proceedings of the IEEE International conference on Computer Vision, pp. 2336–2343 1523

2010

• Stühmer J, Gumhold S, Cremers D (2010). Real-Time Dense Geometry from a Handheld Camera, In Pattern Recognition: 32nd DAGM Symposium, Darmstadt, Germany, September 22-24, 2010, Proceedings, vol. 6376, p. 11 1524
• Stühmer J, Gumhold S, Cremers D (2010). Parallel generalized thresholding scheme for live dense geometry from a handheld camera, In Proceedings of the 11th European conference on Trends and Topics in Computer Vision-Volume Part II, pp. 450–462 1525
• Arboleda-Estudillo Y, Krieg M, Stühmer J, Licata NA, Muller DJ, Heisenberg C (2010). Movement directionality in collective migration of germ layer progenitors, Current Biology 20(2):161–169 1529

2009

• Carvalho L, Stühmer J, Bois JS, Kalaidzidis Y, Lecaudey V, Heisenberg C (2009). Control of convergent yolk syncytial layer nuclear movement in zebrafish 1530