---
title: "Jurgen Schmidhuber — author profile and papers in our library"
description: "Jurgen Schmidhuber, King Abdullah University of Science and Technology: 7 papers on Elamur Research (2015–2025), h-index 89…"
canonical: "https://research.elamur.ai/free/en/authors/jurgen-schmidhuber/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jurgen-schmidhuber/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jurgen Schmidhuber

# Jurgen Schmidhuber

Jurgen Schmidhuber has 7 papers in our library, in 2015–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/); often with [Mingchen Zhuge](https://md.research.elamur.ai/free/en/authors/mingchen-zhuge/), [Rupesh Kumar Srivastava](https://md.research.elamur.ai/free/en/authors/rupesh-kumar-srivastava/), [Dmitrii Khizbullin](https://md.research.elamur.ai/free/en/authors/dmitrii-khizbullin/).

7 papers in our library · 2015–2025

[OpenAlex](https://openalex.org/A5071172037) · [ORCID](https://orcid.org/0000-0002-1468-6758) · [**h-index 89**](https://openalex.org/authors/A5071172037) · [645 works](https://openalex.org/works?filter=author.id:A5071172037) · [185,998 citations](https://openalex.org/works?filter=author.id:A5071172037&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 7 works in our library](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/#papers) · [🔗 Cited 1,218 times in our library](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/cited-by/) · [25 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #423](https://md.research.elamur.ai/free/en/paper-stars/page/5/#star-423)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Jurgen+Schmidhuber) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jurgen+Schmidhuber) · [dblp](https://dblp.org/search?q=Jurgen+Schmidhuber) · [ACL Anthology](https://aclanthology.org/search/?q=Jurgen+Schmidhuber)

## Affiliations

[🎓**King Abdullah University of Science and Technology** Jeddah · Saudi Arabia 2020–2026 · 43 papers*current*](https://md.research.elamur.ai/free/en/universities/king-abdullah-university-of-science-and-technology/) · [🔬**Dalle Molle Institute for Artificial Intelligence Research** Lugano · Switzerland 1995–2025 · 364 papersEmployment · scientific director](https://md.research.elamur.ai/free/en/labs/dalle-molle-institute-for-artificial-intelligence-research/) · [🎓**Università della Svizzera italiana** Lugano · Switzerland 2007–2025 · 158 papers](https://md.research.elamur.ai/free/en/universities/universita-della-svizzera-italiana/) · [🎓**University of Applied Sciences and Arts of Southern Switzerland** Manno · Switzerland 2010–2025 · 145 papers](https://md.research.elamur.ai/free/en/universities/university-of-applied-sciences-and-arts-of-southern-switzerland/) · [🎓**Technical University of Munich** Munich · Germany 1989–2013 · 77 papers](https://md.research.elamur.ai/free/en/universities/technical-university-of-munich/) · [🎓**University of Colorado Boulder** Boulder · United States 1991–2002 · 8 papers](https://md.research.elamur.ai/free/en/universities/university-of-colorado-boulder/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 6 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 6 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Materials Science · 1 work](https://md.research.elamur.ai/free/en/shelves/materials-science/) · [Materials Chemistry · 1 work](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/)

🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Question answering · 1 work](https://md.research.elamur.ai/free/en/topics/question-answering/)

## Works by year

### 2020s

[**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/year/2025/) · [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/year/2024/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/year/2021/)

### 2010s

[**2016** 1 paper](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/year/2016/) · [**2015** 2 papers](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/year/2015/)

## Papers

The most cited first (OpenAlex and our library).

1. **[LSTM: A Search Space Odyssey](https://md.research.elamur.ai/free/en/papers/greff-2015-lstm-search-space-odyssey/)** *(2015 · 7,008 citations)* Since its introduction in the mid-1990s, LSTM has accumulated many architectural modifications, but no one had systematically tested which of its parts actually matter.
2. **[Highway Networks](https://md.research.elamur.ai/free/en/papers/srivastava-2015-highway-networks/)** *(2015 · 680 citations)* Deeper neural networks tend to perform better, but plain feedforward stacks get much harder to train with gradient descent as layers are added, even with careful variance-preserving initialization.
3. **[Recurrent Highway Networks](https://md.research.elamur.ai/free/en/papers/zilly-2016-recurrent-highway-networks/)** *(2016 · 147 citations)* Recurrent networks usually update their hidden state with a single nonlinear step per time step. Making this step-to-step transition deeper should add modeling power, but such models have very long gradient paths and are hard to train, even when built from LSTM cells. Zilly et al. study this problem using Geršgorin's…
4. **[Linear Transformers Are Secretly Fast Weight Programmers](https://md.research.elamur.ai/free/en/papers/schlag-2021-linear-transformers-secretly-fast-weight/)** *(2021 · 111 citations)* The paper shows that linear Transformers, which replace softmax attention with a kernel-based approximation, are mathematically the same as the outer-product Fast Weight Programmers (FWPs) Schmidhuber proposed in the early 1990s, apart from a normalisation term.
5. **[Language Agents as Optimizable Graphs](https://md.research.elamur.ai/free/en/papers/zhuge-2024-language-agents-optimizable-graphs/)** *(2024 · 91 citations)* Prompting schemes for LLM agents, such as chain of thought, tree of thought, Reflexion and multi-agent role play, each tend to arrive with their own code base and hand-crafted workflow.
6. **[ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering](https://md.research.elamur.ai/free/en/papers/chen-2024-scholarchemqa-unveiling-power-language-models/)** *(2024 · 19 citations)* Chemistry has lacked QA benchmarks built from real research. Existing chemical sets such as KGQA rely on templates over a knowledge graph and mostly test basic concepts. The authors address this gap with ScholarChemQA. They mined chemistry papers whose titles are phrased as questions and treated each abstract as the…
7. **[Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models](https://md.research.elamur.ai/free/en/papers/xiong-2025-beyond-outlining-heterogeneous-recursive-planning/)** *(2025 · 8 citations)* Most LLM writing agents first draft a fixed outline and then fill it in. This makes it hard to change course mid-writing, for example when new information or a plot problem appears. The authors present WriteHERE, which treats long-form writing as a planning problem inspired by Hierarchical Task Network planning. A…

## All works

32 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. **[Deep learning in neural networks: An overview ↗](https://doi.org/10.1016/j.neunet.2014.09.003) Neural Networks · no summary yet**Jürgen Schmidhuber*2014 · 18,565 citations*
2. **[LSTM: A Search Space Odyssey](https://md.research.elamur.ai/free/en/papers/greff-2015-lstm-search-space-odyssey/) [IEEE Transactions on Neural Networks and Learning Systems](https://md.research.elamur.ai/free/en/venues/ieee-transactions-on-neural-networks-and-learning-systems/)**Klaus Greff, Rupesh Kumar Srivastava, Jan Koutnik, et al.*2015 · 7,008 citations*
3. **[Framewise phoneme classification with bidirectional LSTM and other neural network architectures ↗](https://doi.org/10.1016/j.neunet.2005.06.042) Neural Networks · no summary yet**Alex Graves, Jürgen Schmidhuber*2005 · 6,015 citations*
4. **[Connectionist temporal classification ↗](https://doi.org/10.1145/1143844.1143891) International Conference on Machine Learning · no summary yet**Alex Graves et al.*2006 · 5,379 citations*
5. **[Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition ↗](https://doi.org/10.1007/11550907_126) Lecture notes in computer science · no summary yet**Alex Graves, Santiago Fernández, Jürgen Schmidhuber*2005 · 928 citations*
6. [**Highway Networks arXiv:1505.00387**Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber*2015 · 680 citations*](https://md.research.elamur.ai/free/en/papers/srivastava-2015-highway-networks/)
7. **[Multi-dimensional Recurrent Neural Networks ↗](https://doi.org/10.1007/978-3-540-74690-4_56) Lecture notes in computer science · no summary yet**Alex Graves, Santiago Fernández, Jürgen Schmidhuber*2007 · 297 citations*
8. **[An Application of Recurrent Neural Networks to Discriminative Keyword Spotting ↗](https://doi.org/10.1007/978-3-540-74695-9_23) Lecture notes in computer science · no summary yet**Santiago Fernández, Alex Graves, Jürgen Schmidhuber*2007 · 259 citations*
9. **[Parameter-exploring policy gradients ↗](https://doi.org/10.1016/j.neunet.2009.12.004) Neural Networks · no summary yet**Frank Sehnke et al.*2009 · 246 citations*
10. **[Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks ↗](https://openalex.org/W2167898728) Bern Open Repository and Information System (University of Bern) · no summary yet**Alex Graves et al.*2007 · 224 citations*
11. [**Recurrent Highway Networks arXiv:1607.03474**Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutnik, et al.*2016 · 147 citations*](https://md.research.elamur.ai/free/en/papers/zilly-2016-recurrent-highway-networks/)
12. **[The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers ↗](https://aclanthology.org/2021.emnlp-main.49/) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yet**Róbert Csordás, Kazuki Irie, Juergen Schmidhuber*2021 · 130 citations*
13. [**Linear Transformers Are Secretly Fast Weight Programmers arXiv:2102.11174**Imanol Schlag, Kazuki Irie, Jurgen Schmidhuber*2021 · 111 citations*](https://md.research.elamur.ai/free/en/papers/schlag-2021-linear-transformers-secretly-fast-weight/)
14. **[Biologically Plausible Speech Recognition with LSTM Neural Nets ↗](https://doi.org/10.1007/978-3-540-27835-1_10) Lecture notes in computer science · no summary yet**Alex Graves et al.*2004 · 105 citations*
15. **[Sequence labelling in structured domains with hierarchical recurrent neural networks ↗](http://mediatum.ub.tum.de/node?id=1289940) no summary yet**Santiago Fernández, Alex Graves, Jürgen Schmidhuber*2007 · 95 citations*
16. [**Language Agents as Optimizable Graphs arXiv:2402.16823**Mingchen Zhuge, Wenyi Wang, Louis Kirsch, et al.*2024 · 91 citations*](https://md.research.elamur.ai/free/en/papers/zhuge-2024-language-agents-optimizable-graphs/)
17. **[Stochastic search using the natural gradient ↗](https://doi.org/10.1145/1553374.1553522) International Conference on Machine Learning · no summary yet**Yi Sun et al.*2009 · 81 citations*
18. **[Policy Gradients with Parameter-Based Exploration for Control ↗](https://doi.org/10.1007/978-3-540-87536-9_40) Lecture notes in computer science · no summary yet**Frank Sehnke et al.*2008 · 64 citations*
19. **[Agent-as-a-Judge: Evaluate Agents with Agents ↗](https://arxiv.org/abs/2410.10934) arXiv:2410.10934 · no summary yet**Mingchen Zhuge et al.*2024 · 50 citations*
20. **[Facial Expression Recognition with Recurrent Neural Networks ↗](http://mediatum.ub.tum.de/node?id=1289310) no summary yet**Alex Graves et al.*2008 · 36 citations*
21. **[Phoneme recognition in TIMIT with BLSTM-CTC ↗](https://arxiv.org/abs/0804.3269) arXiv (Cornell University) · no summary yet**Santiago Fernández, Alex Graves, Jürgen Schmidhuber*2008 · 31 citations*
22. [**ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering arXiv:2407.16931**Xiuying Chen, Tairan Wang, Taicheng Guo, et al.*2024 · 19 citations*](https://md.research.elamur.ai/free/en/papers/chen-2024-scholarchemqa-unveiling-power-language-models/)
23. **[On Fast Deep Nets for AGI Vision ↗](https://doi.org/10.1007/978-3-642-22887-2_25) Lecture notes in computer science · no summary yet**Jürgen Schmidhuber et al.*2011 · 19 citations*
24. **[Large Language Model Programs ↗](https://arxiv.org/abs/2305.05364) arXiv:2305.05364 · no summary yet**Imanol Schlag et al.*2023 · 18 citations*
25. **[Compete to Compute ↗](https://doi.org/10.71910/supsi.6577) neural information processing systems · no summary yet**Rupesh K. Srivastava et al.*2013 · 15 citations*

[See all 32 works by Jurgen Schmidhuber →](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/works/)

## Co-authors here

12 co-authors with a page, the most papers together first.

- [Mingchen Zhuge](https://md.research.elamur.ai/free/en/authors/mingchen-zhuge/) ×3
- [Rupesh Kumar Srivastava](https://md.research.elamur.ai/free/en/authors/rupesh-kumar-srivastava/) ×3
- [Dmitrii Khizbullin](https://md.research.elamur.ai/free/en/authors/dmitrii-khizbullin/) ×2
- [Jan Koutnik](https://md.research.elamur.ai/free/en/authors/jan-koutnik/) ×2
- [Klaus Greff](https://md.research.elamur.ai/free/en/authors/klaus-greff/) ×2
- [Haoyang Li](https://md.research.elamur.ai/free/en/authors/haoyang-li/)
- [Imanol Schlag](https://md.research.elamur.ai/free/en/authors/imanol-schlag/)
- [Taicheng Guo](https://md.research.elamur.ai/free/en/authors/taicheng-guo/)
- [Xiangliang Zhang](https://md.research.elamur.ai/free/en/authors/xiangliang-zhang/)
- [Xin Gao](https://md.research.elamur.ai/free/en/authors/xin-gao/)
- [Xiuying Chen](https://md.research.elamur.ai/free/en/authors/xiuying-chen/)
- [Yimeng Chen](https://md.research.elamur.ai/free/en/authors/yimeng-chen/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- Lecture notes in computer science ×7
- Neural Networks ×3
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ×2: [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)
- International Conference on Machine Learning ×2
- neural information processing systems ×2
- [IEEE Transactions on Neural Networks and Learning Systems](https://md.research.elamur.ai/free/en/venues/ieee-transactions-on-neural-networks-and-learning-systems/): [IEEE Transactions on Neural Networks and Learning Systems 2015](https://md.research.elamur.ai/free/en/venues/ieee-transactions-on-neural-networks-and-learning-systems/2015/)
- Bern Open Repository and Information System (University of Bern)
- International Conference on Machine Learning and Applications

## Cited by

Papers of our library cite their works 1,218 times (of the 149,439 papers whose bibliographies we read); [199 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jurgen-schmidhuber/cited-by/).

Updated 2 November 2026