---
title: "An AI system to help scientists write expert-level empirical software"
description: "The authors, from Google DeepMind and Google Research, present Empirical Research Assistance… 92 references, cited by 12 papers here."
authors: ["Eser Aygün", "Anastasiya Belyaeva", "Gheorghe Comanici", "Marc Coram", "Hao Cui", "Jake Garrison", "Renee Johnston Anton Kast", "Cory Y. McLean", "Peter Norgaard", "Zahra Shamsi", "David Smalling", "James Thompson", "Subhashini Venugopalan", "Brian P. Williams", "Chujun He", "Sarah Martinson", "Martyna Plomecka", "Lai Wei", "Yuchen Zhou", "Qian-Ze Zhu", "Matthew Abraham", "Erica Brand", "Anna Bulanova", "Jeffrey A. Cardille", "Chris Co", "Scott Ellsworth", "Grace Joseph", "Malcolm Kane", "Ryan Krueger", "Johan Kartiwa", "Dan Liebling", "Jan-Matthis Lueckmann", "Paul Raccuglia", "Xuefei (Julie) Wang", "Katherine Chou", "James Manyika", "Yossi Matias", "John C. Platt", "Lizzie Dorfman", "Shibl Mourad", "Michael P. Brenner"]
year: 2025
venue: "arXiv:2509.06503"
source: "https://arxiv.org/abs/2509.06503"
doi: "10.48550/arxiv.2509.06503"
arxiv: "2509.06503"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/aygun-2025-ai-system-help-scientists/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/aygun-2025-ai-system-help-scientists/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / An AI system to help scientists write expert-level empirical software

# An AI system to help scientists write expert-level empirical software

**Authors:** Eser Aygün, Anastasiya Belyaeva, [Gheorghe Comanici](https://md.research.elamur.ai/free/en/authors/gheorghe-comanici/), Marc Coram, [Hao Cui](https://md.research.elamur.ai/free/en/authors/hao-cui/), Jake Garrison, Renee Johnston Anton Kast, Cory Y. McLean, [Peter Norgaard](https://md.research.elamur.ai/free/en/authors/peter-norgaard/), [Zahra Shamsi](https://md.research.elamur.ai/free/en/authors/zahra-shamsi/), David Smalling, James Thompson, Subhashini Venugopalan, Brian P. Williams, Chujun He, Sarah Martinson, Martyna Plomecka, [Lai Wei](https://md.research.elamur.ai/free/en/authors/lai-wei/), Yuchen Zhou, Qian-Ze Zhu, Matthew Abraham, Erica Brand, Anna Bulanova, Jeffrey A. Cardille, Chris Co, Scott Ellsworth, Grace Joseph, Malcolm Kane, Ryan Krueger, Johan Kartiwa, Dan Liebling, Jan-Matthis Lueckmann, Paul Raccuglia, Xuefei (Julie) Wang, Katherine Chou, James Manyika, Yossi Matias, John C. Platt, Lizzie Dorfman, Shibl Mourad and Michael P. Brenner · **Year:** 2025 · **Venue:** [arXiv:2509.06503](https://md.research.elamur.ai/free/en/venues/nature/) ([Nature 2025](https://md.research.elamur.ai/free/en/venues/nature/2025/)) · **Publisher:** [Nature Portfolio](https://md.research.elamur.ai/free/en/publishers/nature-portfolio/) · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2509.06503) · [PDF](https://arxiv.org/pdf/2509.06503) · [DOI 10.48550/arxiv.2509.06503](https://doi.org/10.48550/arxiv.2509.06503) · [arXiv 2509.06503](https://arxiv.org/abs/2509.06503) · [OpenAlex](https://openalex.org/W4414757142)

**Citations:** 15 citations (OpenAlex, 2026-10-14) · [12](https://md.research.elamur.ai/free/en/papers/aygun-2025-ai-system-help-scientists/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Software for computational experiments that must maximize a measurable score is slow to build by hand, and researchers seldom test alternative designs systematically. The authors, from Google DeepMind and Google Research, present Empirical Research Assistance (ERA). It treats such problems as scorable tasks. An LLM (Gemini) repeatedly rewrites candidate programs, each candidate is run and scored in a sandbox, and a tree search decides which candidates to develop further by trading off exploration against exploitation. Prompts can be enriched with research ideas, such as LLM-written summaries of papers, textbook knowledge, search-engine results or Deep Research output, and successful ideas can be recombined. The system was developed on Kaggle playground competitions. It was then tested on six scientific benchmarks: scRNA-seq batch integration, CDC COVID-19 hospitalization forecasting, GIFT-Eval time series forecasting, satellite-image segmentation, ZAPBench zebrafish neural activity prediction, and difficult numerical integrals. ERA matched or exceeded expert-built solutions across these tasks. This suggests that large-scale automated search over code could substantially speed up empirical research.

## Key points
- **Kaggle benchmark:** ERA was evaluated on 16 playground competitions from the 2023 season, scored by public-leaderboard percentile.
  - Tree search beat a single LLM call, best-of-1000 sampling and AIDE.
  - Adding expert Kaggle advice, or asking ERA to write a boosted decision tree from scratch, improved results further.
- **scRNA-seq batch integration (OpenProblems v2.0.0):** ERA found 40 novel methods that surpassed the top human-developed entries.
  - When given Gemini 2.5 Pro summaries of published methods, it beat the published results for 8 of 9 methods.
  - Its BBKNN (TS) implementation scored 14% higher overall than the best published method (ComBat).
  - Optimization used a separate dataset, and evaluation used holdout data of about 1.75M cells across 13 metrics.
- **COVID-19 forecasting:** ERA generated 14 models, each of which beat both the CDC's ensemble forecast and all of the individual models.
- **GIFT-Eval time series forecasting:** ERA ran 300-node searches separately for 92 of 97 datasets.
  - It also built a unified library restricted to numpy, pandas and holidays, using more than 1,000 search nodes and eight preset configurations.
  - The unified library's MASE improved from 0.82 to 0.77 and finally to 0.734, measured against the May 18, 2025 leaderboard snapshot.
- **Code adherence:** Expert review found that nearly all generated implementations followed the requested algorithms. ERA also implemented TabVI, which has no public code.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Google](https://md.research.elamur.ai/free/en/companies/google/) — Company, Mountain View, United States · 430 works · 424,363 citations
- [Massachusetts Institute of Technology](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) — University, Cambridge, United States · 211 works · 69,000 citations
- [Harvard University](https://md.research.elamur.ai/free/en/universities/harvard-university/) — University, Cambridge, United States · 112 works · 42,023 citations
- [McGill University](https://md.research.elamur.ai/free/en/universities/mcgill-university/) — University, Montreal, Canada · 87 works · 11,027 citations
- [California Institute of Technology](https://md.research.elamur.ai/free/en/universities/california-institute-of-technology/) — University, Pasadena, United States · 8 works · 745 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 209 works · [🎯 Information Systems and Management](https://md.research.elamur.ai/free/en/shelves/decision-sciences/information-systems-and-management/) · 41 works

💡 Concepts (1): [💡 Artificial intelligence](https://md.research.elamur.ai/free/en/concepts/artificial-intelligence/) · 49 works

## Cite

Cite as: Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici, Marc Coram, Hao Cui, Jake Garrison, Renee Johnston Anton Kast, Cory Y. McLean, Peter Norgaard, Zahra Shamsi, David Smalling, James Thompson, Subhashini Venugopalan, Brian P. Williams, Chujun He, Sarah Martinson, Martyna Plomecka, Lai Wei, Yuchen Zhou, Qian-Ze Zhu, Matthew Abraham, Erica Brand, Anna Bulanova, Jeffrey A. Cardille, Chris Co, Scott Ellsworth, Grace Joseph, Malcolm Kane, Ryan Krueger, Johan Kartiwa, Dan Liebling, Jan-Matthis Lueckmann, Paul Raccuglia, Xuefei (Julie) Wang, Katherine Chou, James Manyika, Yossi Matias, John C. Platt, Lizzie Dorfman, Shibl Mourad and Michael P. Brenner. 2025. An AI system to help scientists write expert-level empirical software. arXiv:2509.06503.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{aygun2025ai,
  title = {{An AI system to help scientists write expert-level empirical software}},
  author = {Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici, Marc Coram, Hao Cui, Jake Garrison, Renee Johnston Anton Kast, Cory Y. McLean, Peter Norgaard, Zahra Shamsi, David Smalling, James Thompson, Subhashini Venugopalan, Brian P. Williams, Chujun He, Sarah Martinson, Martyna Plomecka, Lai Wei, Yuchen Zhou, Qian-Ze Zhu, Matthew Abraham, Erica Brand, Anna Bulanova, Jeffrey A. Cardille, Chris Co, Scott Ellsworth, Grace Joseph, Malcolm Kane, Ryan Krueger, Johan Kartiwa, Dan Liebling, Jan-Matthis Lueckmann, Paul Raccuglia, Xuefei (Julie) Wang, Katherine Chou, James Manyika, Yossi Matias, John C. Platt, Lizzie Dorfman, Shibl Mourad and Michael P. Brenner},
  year = {2025},
  doi = {10.48550/arxiv.2509.06503},
  eprint = {2509.06503},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2509.06503}
}
```

- [← previous Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://md.research.elamur.ai/free/en/papers/balepur-2025-which-these-best-describes-multiple/)
- [next → AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://md.research.elamur.ai/free/en/papers/xu-2025-androidlab-training-systematic-benchmarking-android/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

92 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hannay, J. E. et al. How do scientists develop and use scientific software? In 2009 ICSE Workshop on Software Engineering for Computational Science and Engineering, 1–8 (IEEE, 2009). [find](https://scholar.google.com/scholar?q=Hannay%2C+J%2E+E%2E+et+al%2E+How+do+scientists+develop+and+use+scientific+software%3F+In+2009+ICSE+Workshop+on+Software+Engineering+for+Computational+Science+and+Engineering%2C+1%E2%80%938+%28IEEE%2C+2009%29%2E)
2. Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–489 (2016). [find](https://scholar.google.com/scholar?q=Silver%2C+D%2E+et+al%2E+Mastering+the+game+of+Go+with+deep+neural+networks+and+tree+search%2E+Nature+529%2C+484%E2%80%93489+%282016%29%2E)
3. Hohenberg, P. & Kohn, W. Inhomogeneous electron gas. Phys. Rev. 136, B864 (1964). [find](https://scholar.google.com/scholar?q=Hohenberg%2C+P%2E+%26+Kohn%2C+W%2E+Inhomogeneous+electron+gas%2E+Phys%2E+Rev%2E+136%2C+B864+%281964%29%2E)
4. Kohn, W. & Sham, L. J. Self-consistent equations including exchange and correlation effects. Phys. Rev. 140, A1133 (1965). [find](https://scholar.google.com/scholar?q=Kohn%2C+W%2E+%26+Sham%2C+L%2E+J%2E+Self%2Dconsistent+equations+including+exchange+and+correlation+effects%2E+Phys%2E+Rev%2E+140%2C+A1133+%281965%29%2E)
5. Warshel, A. & Levitt, M. Theoretical studies of enzymic reactions: dielectric, electrostatic and steric stabilization of the carbonium ion in the reaction of lysozyme. J. Mol. Biol. 103, 227–249 (1976). [find](https://scholar.google.com/scholar?q=Warshel%2C+A%2E+%26+Levitt%2C+M%2E+Theoretical+studies+of+enzymic+reactions%3A+dielectric%2C+electrostatic+and+steric+stabilization+of+the+carbonium+ion+in+the+reaction+of+lysozyme%2E+J%2E+Mol%2E+Biol%2E+103%2C+227%E2%80%93249+%281976)
6. Jumper, J. et al. [Highly accurate protein structure prediction with AlphaFold](https://md.research.elamur.ai/free/en/papers/jumper-2021-highly-accurate-protein-structure-prediction/). Nature 596, 583–589 (2021).
7. Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021). [find](https://scholar.google.com/scholar?q=Baek%2C+M%2E+et+al%2E+Accurate+prediction+of+protein+structures+and+interactions+using+a+three%2Dtrack+neural+network%2E+Science+373%2C+871%E2%80%93876+%282021%29%2E)
8. Hourdin, F. et al. The art and science of climate model tuning. Bull. Am. Meteorol. Soc. 98, 589–602 (2017). [find](https://scholar.google.com/scholar?q=Hourdin%2C+F%2E+et+al%2E+The+art+and+science+of+climate+model+tuning%2E+Bull%2E+Am%2E+Meteorol%2E+Soc%2E+98%2C+589%E2%80%93602+%282017%29%2E)
9. Anderson Jr., J. Basic philosophy of CFD. In Computational Fluid Dynamics, 3–14 (Springer, 2009). [find](https://scholar.google.com/scholar?q=Anderson+Jr%2E%2C+J%2E+Basic+philosophy+of+CFD%2E+In+Computational+Fluid+Dynamics%2C+3%E2%80%9314+%28Springer%2C+2009%29%2E)
10. Silver, N. The signal and the noise: why so many predictions fail-but some don’t (Penguin, 2012). [find](https://scholar.google.com/scholar?q=Silver%2C+N%2E+The+signal+and+the+noise%3A+why+so+many+predictions+fail%2Dbut+some+don%E2%80%99t+%28Penguin%2C+2012%29%2E)
11. Farmer, J. D. Making sense of chaos: a better economics for a better world (Yale Univ. Press, 2024). [find](https://scholar.google.com/scholar?q=Farmer%2C+J%2E+D%2E+Making+sense+of+chaos%3A+a+better+economics+for+a+better+world+%28Yale+Univ%2E+Press%2C+2024%29%2E)
12. Sculley, D. et al. Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems, vol. 28 (2015). [find](https://scholar.google.com/scholar?q=Sculley%2C+D%2E+et+al%2E+Hidden+technical+debt+in+machine+learning+systems%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+vol%2E+28+%282015%29%2E)
13. Jiang, Z. et al. AIDE: AI-driven exploration in the space of code. arXiv preprint arXiv:2502.13138 (2025). [find](https://scholar.google.com/scholar?q=Jiang%2C+Z%2E+et+al%2E+AIDE%3A+AI%2Ddriven+exploration+in+the+space+of+code%2E+arXiv+preprint+arXiv%3A2502%2E13138+%282025%29%2E)
14. Novikov, A. et al. [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/). arXiv preprint arXiv:2506.13131 (2025).
15. Romera-Paredes, B. et al. [Mathematical discoveries from program search with large language models](https://md.research.elamur.ai/free/en/papers/paredes-2023-mathematical-discoveries-program-search-large/). Nature 625, 468–475 (2024).
16. Hu, S., Lu, C. & Clune, J. Automated design of agentic systems. arXiv preprint arXiv:2408.08435 (2024). [find](https://scholar.google.com/scholar?q=Hu%2C+S%2E%2C+Lu%2C+C%2E+%26+Clune%2C+J%2E+Automated+design+of+agentic+systems%2E+arXiv+preprint+arXiv%3A2408%2E08435+%282024%29%2E)
17. Xu, C. et al. Automatic cell-type harmonization and integration across Human Cell Atlas datasets. Cell 186, 5876–5891.e20 (2023). [find](https://scholar.google.com/scholar?q=Xu%2C+C%2E+et+al%2E+Automatic+cell%2Dtype+harmonization+and+integration+across+Human+Cell+Atlas+datasets%2E+Cell+186%2C+5876%E2%80%935891%2Ee20+%282023%29%2E)
18. Centers for Disease Control and Prevention. COVID-19 forecast hub (2025). [https://github.com/cdcgov/covid19-forecast-hub?tab=readme-ov-file](https://github.com/cdcgov/covid19-forecast-hub?tab=readme-ov-file). [↗](https://github.com/cdcgov/covid19-forecast-hub?tab=readme-ov-file)
19. Aksu, T. et al. GIFT-Eval: a benchmark for general time series forecasting model evaluation. arXiv preprint arXiv:2410.10393 (2024). [https://huggingface.co/spaces/Salesforce/GIFT-Eval](https://huggingface.co/spaces/Salesforce/GIFT-Eval). — [arXiv:2410.10393](https://arxiv.org/abs/2410.10393) [↗](https://huggingface.co/spaces/Salesforce/GIFT-Eval)
20. Shao, Z., Yang, K. & Zhou, W. Performance evaluation of single-label and multi-label remote sensing image retrieval using a dense labeling dataset. Remote Sens. 10, 964 (2018). [find](https://scholar.google.com/scholar?q=Shao%2C+Z%2E%2C+Yang%2C+K%2E+%26+Zhou%2C+W%2E+Performance+evaluation+of+single%2Dlabel+and+multi%2Dlabel+remote+sensing+image+retrieval+using+a+dense+labeling+dataset%2E+Remote+Sens%2E+10%2C+964+%282018%29%2E)
21. Lueckmann, J.-M. et al. ZAPBench: a benchmark for whole-brain activity prediction in zebrafish. arXiv preprint arXiv:2503.02618 (2025). — [arXiv:2503.02618](https://arxiv.org/abs/2503.02618) [find](https://scholar.google.com/scholar?q=Lueckmann%2C+J%2E%2DM%2E+et+al%2E+ZAPBench%3A+a+benchmark+for+whole%2Dbrain+activity+prediction+in+zebrafish%2E+arXiv+preprint+arXiv%3A2503%2E02618+%282025%29%2E+%E2%80%94+%5BarXiv%3A2503%2E02618%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E02618%29)
22. Jovic, D. et al. Single-cell RNA sequencing technologies and applications: a brief overview. Clin. and Transl. Med. 12, e694 (2022). [find](https://scholar.google.com/scholar?q=Jovic%2C+D%2E+et+al%2E+Single%2Dcell+RNA+sequencing+technologies+and+applications%3A+a+brief+overview%2E+Clin%2E+and+Transl%2E+Med%2E+12%2C+e694+%282022%29%2E)
23. Svensson, V., Vento-Tormo, R. & Teichmann, S. A. Exponential scaling of single-cell RNA-seq in the past decade. Nat. Protoc. 13, 599–604 (2018). [find](https://scholar.google.com/scholar?q=Svensson%2C+V%2E%2C+Vento%2DTormo%2C+R%2E+%26+Teichmann%2C+S%2E+A%2E+Exponential+scaling+of+single%2Dcell+RNA%2Dseq+in+the+past+decade%2E+Nat%2E+Protoc%2E+13%2C+599%E2%80%93604+%282018%29%2E)
24. Regev, A. et al. The Human Cell Atlas. eLife 6, e27041 (2017). [find](https://scholar.google.com/scholar?q=Regev%2C+A%2E+et+al%2E+The+Human+Cell+Atlas%2E+eLife+6%2C+e27041+%282017%29%2E)
25. CZI Cell Science Program et al. CZ CELLxGENE Discover: a single-cell data platform for scalable exploration, analysis and modeling of aggregated data. Nucleic Acids Res. 53, D886–D900 (2025). [find](https://scholar.google.com/scholar?q=CZI+Cell+Science+Program+et+al%2E+CZ+CELLxGENE+Discover%3A+a+single%2Dcell+data+platform+for+scalable+exploration%2C+analysis+and+modeling+of+aggregated+data%2E+Nucleic+Acids+Res%2E+53%2C+D886%E2%80%93D900+%282025%29%2E)
26. Stuart, T. & Satija, R. Integrative single-cell analysis. Nat. Rev. Genet. 20, 257–272 (2019). [find](https://scholar.google.com/scholar?q=Stuart%2C+T%2E+%26+Satija%2C+R%2E+Integrative+single%2Dcell+analysis%2E+Nat%2E+Rev%2E+Genet%2E+20%2C+257%E2%80%93272+%282019%29%2E)
27. Zappia, L., Phipson, B. & Oshlack, A. Exploring the single-cell RNA-seq analysis landscape with the scRNA-tools database. PLoS Comput. Biol. 14, e1006245 (2018). [find](https://scholar.google.com/scholar?q=Zappia%2C+L%2E%2C+Phipson%2C+B%2E+%26+Oshlack%2C+A%2E+Exploring+the+single%2Dcell+RNA%2Dseq+analysis+landscape+with+the+scRNA%2Dtools+database%2E+PLoS+Comput%2E+Biol%2E+14%2C+e1006245+%282018%29%2E)
28. Tran, H. T. N. et al. A benchmark of batch-effect correction methods for single-cell RNA sequencing data. Genome Biol. 21, 1–32 (2020). [find](https://scholar.google.com/scholar?q=Tran%2C+H%2E+T%2E+N%2E+et+al%2E+A+benchmark+of+batch%2Deffect+correction+methods+for+single%2Dcell+RNA+sequencing+data%2E+Genome+Biol%2E+21%2C+1%E2%80%9332+%282020%29%2E)
29. Chazarra-Gil, R., van Dongen, S., Kiselev, V. Y. & Hemberg, M. Flexible comparison of batch correction methods for single-cell RNA-seq using BatchBench. Nucleic Acids Res. 49, e42 (2021). [find](https://scholar.google.com/scholar?q=Chazarra%2DGil%2C+R%2E%2C+van+Dongen%2C+S%2E%2C+Kiselev%2C+V%2E+Y%2E+%26+Hemberg%2C+M%2E+Flexible+comparison+of+batch+correction+methods+for+single%2Dcell+RNA%2Dseq+using+BatchBench%2E+Nucleic+Acids+Res%2E+49%2C+e42+%282021%29%2E)
30. Luecken, M. D. et al. Defining and benchmarking open problems in single-cell analysis. Nat. Biotechnol. 43, 1035–1040 (2025). [find](https://scholar.google.com/scholar?q=Luecken%2C+M%2E+D%2E+et+al%2E+Defining+and+benchmarking+open+problems+in+single%2Dcell+analysis%2E+Nat%2E+Biotechnol%2E+43%2C+1035%E2%80%931040+%282025%29%2E)
31. Google. Gemini Deep Research (2025). [https://gemini.google/overview/deep-research/](https://gemini.google/overview/deep-research/) ?hl=en. [↗](https://gemini.google/overview/deep-research/)
32. Gottweis, J. et al. Towards an AI co-scientist. arXiv preprint arXiv:2502.[18864 (2025)](https://md.research.elamur.ai/free/en/papers/gottweis-2025-accelerating-scientific-discovery-co/).
33. Johnson, W. E., Li, C. & Rabinovic, A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8, 118–127 (2007). [find](https://scholar.google.com/scholar?q=Johnson%2C+W%2E+E%2E%2C+Li%2C+C%2E+%26+Rabinovic%2C+A%2E+Adjusting+batch+effects+in+microarray+expression+data+using+empirical+Bayes+methods%2E+Biostatistics+8%2C+118%E2%80%93127+%282007%29%2E)
34. Polański, K. et al. BBKNN: fast batch alignment of single cell transcriptomes. Bioinformatics 36, 964–965 (2019). [find](https://scholar.google.com/scholar?q=Pola%C5%84ski%2C+K%2E+et+al%2E+BBKNN%3A+fast+batch+alignment+of+single+cell+transcriptomes%2E+Bioinformatics+36%2C+964%E2%80%93965+%282019%29%2E)
35. Chandrashekar, A. et al. TabVI: leveraging lightweight transformer architectures to learn biologically meaningful cellular representations. bioRxiv 2025–02 (2025). [find](https://scholar.google.com/scholar?q=Chandrashekar%2C+A%2E+et+al%2E+TabVI%3A+leveraging+lightweight+transformer+architectures+to+learn+biologically+meaningful+cellular+representations%2E+bioRxiv+2025%E2%80%9302+%282025%29%2E)
36. Koza, J. R. Genetic programming as a means for programming computers by natural selection. Stat. Comput. 4, 87–112 (1994). [find](https://scholar.google.com/scholar?q=Koza%2C+J%2E+R%2E+Genetic+programming+as+a+means+for+programming+computers+by+natural+selection%2E+Stat%2E+Comput%2E+4%2C+87%E2%80%93112+%281994%29%2E)
37. Schweim, D., Hemberg, E., Sobania, D., O’Reilly, U.-M. & Rothlauf, F. Using knowledge of human-generated code to bias the search in program synthesis with grammatical evolution. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, 331–332 (2021). [find](https://scholar.google.com/scholar?q=Schweim%2C+D%2E%2C+Hemberg%2C+E%2E%2C+Sobania%2C+D%2E%2C+O%E2%80%99Reilly%2C+U%2E%2DM%2E+%26+Rothlauf%2C+F%2E+Using+knowledge+of+human%2Dgenerated+code+to+bias+the+search+in+program+synthesis+with+grammatical+evolution%2E+In+Proceedings+of+the+)
38. Mernik, M., Heering, J. & Sloane, A. M. When and how to develop domain-specific languages. ACM computing surveys (CSUR) 37, 316–344 (2005). [find](https://scholar.google.com/scholar?q=Mernik%2C+M%2E%2C+Heering%2C+J%2E+%26+Sloane%2C+A%2E+M%2E+When+and+how+to+develop+domain%2Dspecific+languages%2E+ACM+computing+surveys+%28CSUR%29+37%2C+316%E2%80%93344+%282005%29%2E)
39. Czarnecki, K. Generative programming: Methods, techniques, and applications tutorial abstract. In International Conference on Software Reuse, 351–352 (Springer, 2002). [find](https://scholar.google.com/scholar?q=Czarnecki%2C+K%2E+Generative+programming%3A+Methods%2C+techniques%2C+and+applications+tutorial+abstract%2E+In+International+Conference+on+Software+Reuse%2C+351%E2%80%93352+%28Springer%2C+2002%29%2E)
40. Li, Y. et al. [Competition-level code generation with AlphaCode](https://md.research.elamur.ai/free/en/papers/li-2022-competition-level-code-generation-alphacode/). Science 378, 1092–1097 (2022).
41. Chen, M. et al. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv:2107.03374 (2021). arXiv preprint
42. Hutter, F., Kotthoff, L. & Vanschoren, J. Automated machine learning: methods, systems, challenges (Springer Nature, 2019). [find](https://scholar.google.com/scholar?q=Hutter%2C+F%2E%2C+Kotthoff%2C+L%2E+%26+Vanschoren%2C+J%2E+Automated+machine+learning%3A+methods%2C+systems%2C+challenges+%28Springer+Nature%2C+2019%29%2E)
43. Wu, X., Wu, S.-h., Wu, J., Feng, L. & Tan, K. C. Evolutionary computation in the era of large language model: survey and roadmap. IEEE Trans. Evol. Comput. (2024). [find](https://scholar.google.com/scholar?q=Wu%2C+X%2E%2C+Wu%2C+S%2E%2Dh%2E%2C+Wu%2C+J%2E%2C+Feng%2C+L%2E+%26+Tan%2C+K%2E+C%2E+Evolutionary+computation+in+the+era+of+large+language+model%3A+survey+and+roadmap%2E+IEEE+Trans%2E+Evol%2E+Comput%2E+%282024%29%2E)
44. Ma, Z., Guo, H., Gong, Y., Zhang, J. & Tan, K. Toward automated algorithm design: A survey and practical guide to meta-black-box-optimization. IEEE Transactions on Evolutionary Computation (2025). [find](https://scholar.google.com/scholar?q=Ma%2C+Z%2E%2C+Guo%2C+H%2E%2C+Gong%2C+Y%2E%2C+Zhang%2C+J%2E+%26+Tan%2C+K%2E+Toward+automated+algorithm+design%3A+A+survey+and+practical+guide+to+meta%2Dblack%2Dbox%2Doptimization%2E+IEEE+Transactions+on+Evolutionary+Computation+%282025%29%2E)
45. Ifargan, T., Hafner, L., Kern, M., Alcalay, O. & Kishony, R. Autonomous LLM-driven research— from data to human-verifiable research papers. NEJM AI 2, AIoa2400555 (2024). [find](https://scholar.google.com/scholar?q=Ifargan%2C+T%2E%2C+Hafner%2C+L%2E%2C+Kern%2C+M%2E%2C+Alcalay%2C+O%2E+%26+Kishony%2C+R%2E+Autonomous+LLM%2Ddriven+research%E2%80%94+from+data+to+human%2Dverifiable+research+papers%2E+NEJM+AI+2%2C+AIoa2400555+%282024%29%2E)
46. Xiao, Y. et al. CellAgent: An LLM-driven multi-agent framework for automated single-cell data analysis. arXiv preprint arXiv:2407.09811 (2024). — [arXiv:2407.09811](https://arxiv.org/abs/2407.09811) [find](https://scholar.google.com/scholar?q=Xiao%2C+Y%2E+et+al%2E+CellAgent%3A+An+LLM%2Ddriven+multi%2Dagent+framework+for+automated+single%2Dcell+data+analysis%2E+arXiv+preprint+arXiv%3A2407%2E09811+%282024%29%2E+%E2%80%94+%5BarXiv%3A2407%2E09811%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E09811%29)
47. Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354–359 (2017). [find](https://scholar.google.com/scholar?q=Silver%2C+D%2E+et+al%2E+Mastering+the+game+of+Go+without+human+knowledge%2E+Nature+550%2C+354%E2%80%93359+%282017%29%2E)
48. Coquelin, P.-A. & Munos, R. Bandit algorithms for tree search. arXiv preprint cs/0703062 (2007). [find](https://scholar.google.com/scholar?q=Coquelin%2C+P%2E%2DA%2E+%26+Munos%2C+R%2E+Bandit+algorithms+for+tree+search%2E+arXiv+preprint+cs%2F0703062+%282007%29%2E)
49. Hemberg, E., Moskal, S. & O’Reilly, U.-M. Evolving code with a large language model. Genetic Programming and Evolvable Machines 25, 21 (2024). [find](https://scholar.google.com/scholar?q=Hemberg%2C+E%2E%2C+Moskal%2C+S%2E+%26+O%E2%80%99Reilly%2C+U%2E%2DM%2E+Evolving+code+with+a+large+language+model%2E+Genetic+Programming+and+Evolvable+Machines+25%2C+21+%282024%29%2E)
50. Meyerson, E. et al. Language model crossover: Variation through few-shot prompting. ACM Transactions on Evolutionary Learning 4, 1–40 (2024). [find](https://scholar.google.com/scholar?q=Meyerson%2C+E%2E+et+al%2E+Language+model+crossover%3A+Variation+through+few%2Dshot+prompting%2E+ACM+Transactions+on+Evolutionary+Learning+4%2C+1%E2%80%9340+%282024%29%2E)
51. Grishina, A., Liventsev, V., Härmä, A. & Moonen, L. Fully autonomous programming using iterative multi-agent debugging with large language models. ACM Transactions on Evolutionary Learning 5, 1–37 (2025). [find](https://scholar.google.com/scholar?q=Grishina%2C+A%2E%2C+Liventsev%2C+V%2E%2C+H%C3%A4rm%C3%A4%2C+A%2E+%26+Moonen%2C+L%2E+Fully+autonomous+programming+using+iterative+multi%2Dagent+debugging+with+large+language+models%2E+ACM+Transactions+on+Evolutionary+Learning+5%2C+1%E2%80%9337+%2820)
52. He, X., Zhao, K. & Chu, X. Automl: A survey of the state-of-the-art. Knowledge-Based Systems 212, 106622 (2021). [find](https://scholar.google.com/scholar?q=He%2C+X%2E%2C+Zhao%2C+K%2E+%26+Chu%2C+X%2E+Automl%3A+A+survey+of+the+state%2Dof%2Dthe%2Dart%2E+Knowledge%2DBased+Systems+212%2C+106622+%282021%29%2E)
53. Fang, Y. et al. MLZero: A multi-agent system for end-to-end machine learning automation. arXiv preprint arXiv:2505.13941 (2024). — [arXiv:2505.13941](https://arxiv.org/abs/2505.13941) [find](https://scholar.google.com/scholar?q=Fang%2C+Y%2E+et+al%2E+MLZero%3A+A+multi%2Dagent+system+for+end%2Dto%2Dend+machine+learning+automation%2E+arXiv+preprint+arXiv%3A2505%2E13941+%282024%29%2E+%E2%80%94+%5BarXiv%3A2505%2E13941%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E13941%29)
54. Li, Z., Zang, Q., Ma, D. et al. AutoKaggle: A multi-agent framework for autonomous data science competitions. arXiv preprint arXiv:2410.20424 (2024). [find](https://scholar.google.com/scholar?q=Li%2C+Z%2E%2C+Zang%2C+Q%2E%2C+Ma%2C+D%2E+et+al%2E+AutoKaggle%3A+A+multi%2Dagent+framework+for+autonomous+data+science+competitions%2E+arXiv+preprint+arXiv%3A2410%2E20424+%282024%29%2E)
55. Grosnit, A. et al. Agent K v1.0: End-to-end autonomous data science agent. arXiv preprint arXiv:2410.02598 (2024). [find](https://scholar.google.com/scholar?q=Grosnit%2C+A%2E+et+al%2E+Agent+K+v1%2E0%3A+End%2Dto%2Dend+autonomous+data+science+agent%2E+arXiv+preprint+arXiv%3A2410%2E02598+%282024%29%2E)
56. Perplexity. Perplexity Deep Research (2025). introducing-perplexity-deep-research. [https://www.perplexity.ai/hub/blog/](https://www.perplexity.ai/hub/blog/) [↗](https://www.perplexity.ai/hub/blog/)
57. Du, M., Xu, B., Zhu, C., Wang, X. & Mao, Z. [DeepResearch Bench: a comprehensive benchmark for deep research agents](https://md.research.elamur.ai/free/en/papers/du-2025-deepresearch-bench-comprehensive-benchmark-deep/). arXiv preprint arXiv:2506.11763 (2025).
58. Coelho, J. et al. DeepResearchGym: A free, transparent, and reproducible evaluation sandbox for deep research. arXiv preprint arXiv:2505.19253 (2025). — [arXiv:2505.19253](https://arxiv.org/abs/2505.19253) [find](https://scholar.google.com/scholar?q=Coelho%2C+J%2E+et+al%2E+DeepResearchGym%3A+A+free%2C+transparent%2C+and+reproducible+evaluation+sandbox+for+deep+research%2E+arXiv+preprint+arXiv%3A2505%2E19253+%282025%29%2E+%E2%80%94+%5BarXiv%3A2505%2E19253%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E1)
59. Xu, R. & Peng, J. A comprehensive survey of deep research: Systems, methodologies, and applications. arXiv preprint arXiv:2506.12594 (2025). — [arXiv:2506.12594](https://arxiv.org/abs/2506.12594) [find](https://scholar.google.com/scholar?q=Xu%2C+R%2E+%26+Peng%2C+J%2E+A+comprehensive+survey+of+deep+research%3A+Systems%2C+methodologies%2C+and+applications%2E+arXiv+preprint+arXiv%3A2506%2E12594+%282025%29%2E+%E2%80%94+%5BarXiv%3A2506%2E12594%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E12594%29)
60. Baek, J., Jauhar, S. K., Cucerzan, S. & Hwang, S. J. [ResearchAgent: iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/). arXiv preprint arXiv:2404.07738 (2024).
61. Lehman, J. et al. Evolution through large models. In Handbook of evolutionary machine learning, 331–366 (Springer, 2023). [find](https://scholar.google.com/scholar?q=Lehman%2C+J%2E+et+al%2E+Evolution+through+large+models%2E+In+Handbook+of+evolutionary+machine+learning%2C+331%E2%80%93366+%28Springer%2C+2023%29%2E)
62. van Stein, N. & Bäck, T. Llamea: A large language model evolutionary algorithm for automatically generating metaheuristics. IEEE Transactions on Evolutionary Computation (2024). [find](https://scholar.google.com/scholar?q=van+Stein%2C+N%2E+%26+B%C3%A4ck%2C+T%2E+Llamea%3A+A+large+language+model+evolutionary+algorithm+for+automatically+generating+metaheuristics%2E+IEEE+Transactions+on+Evolutionary+Computation+%282024%29%2E)
63. Liu, F. et al. Evolution of heuristics: towards efficient automatic algorithm design using large language model. In Proceedings of the 41st International Conference on Machine Learning (2024). [find](https://scholar.google.com/scholar?q=Liu%2C+F%2E+et+al%2E+Evolution+of+heuristics%3A+towards+efficient+automatic+algorithm+design+using+large+language+model%2E+In+Proceedings+of+the+41st+International+Conference+on+Machine+Learning+%282024%29%2E)
64. Ye, H., Wang, J., Cao, Z., Wang, H. & Song, G. ReEvo: Large language models as hyper-heuristics with reflective evolution. In Advances in Neural Information Processing Systems, vol. 37, 43571–43608 (2024). [find](https://scholar.google.com/scholar?q=Ye%2C+H%2E%2C+Wang%2C+J%2E%2C+Cao%2C+Z%2E%2C+Wang%2C+H%2E+%26+Song%2C+G%2E+ReEvo%3A+Large+language+models+as+hyper%2Dheuristics+with+reflective+evolution%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+vol%2E+37%2C+43571%E2%80%9343608+%282)
65. Meyerson, E., Francon, O., Sargent, D., Hodjat, B. & Miikkulainen, R. Unlocking the potential of global human expertise. Advances in Neural Information Processing Systems 37, 119227–119259 (2024). [find](https://scholar.google.com/scholar?q=Meyerson%2C+E%2E%2C+Francon%2C+O%2E%2C+Sargent%2C+D%2E%2C+Hodjat%2C+B%2E+%26+Miikkulainen%2C+R%2E+Unlocking+the+potential+of+global+human+expertise%2E+Advances+in+Neural+Information+Processing+Systems+37%2C+119227%E2%80%93119259+%282024%29%2E)
66. Lee, J. et al. [Gemini Embedding: Generalizable embeddings from Gemini](https://md.research.elamur.ai/free/en/papers/lee-2025-gemini-embedding-generalizable-embeddings-gemini/). arXiv preprint arXiv:2503.07891 (2025).
67. Gigante, S., Cannoodt, R. et al. openproblems (2025). [https://github.com/openproblems-bio/](https://github.com/openproblems-bio/) openproblems. [↗](https://github.com/openproblems-bio/)
68. Cannoodt, R., Zappia, L., Burkhardt, D. et al. task_batch_integration (2025). [https://github.com/openproblems-bio/task_batch_integration](https://github.com/openproblems-bio/task_batch_integration). [↗](https://github.com/openproblems-bio/task_batch_integration)
69. Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. [Optuna: A next-generation hyperparameter optimization framework](https://md.research.elamur.ai/free/en/papers/akiba-2019-optuna-next-generation-hyperparameter-optimization/). In Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (2019).
70. Centers for Disease Control and Prevention. Weekly Hospital Respiratory Data (HRD) Metrics by Jurisdiction (2024). [https://data.cdc.gov/Public-Health-Surveillance/](https://data.cdc.gov/Public-Health-Surveillance/) Weekly-Hospital-Respiratory-Data-HRD-Metrics-by-Ju/mpgq-jmmr. Dataset ID: mpgq-jmmr. Last updated: June 14, 2024. [↗](https://data.cdc.gov/Public-Health-Surveillance/)
71. Yang, Y. & Newsam, S. Bag-of-visual-words and spatial extensions for land-use classification. In Proc. 18th SIGSPATIAL Int. Conf. on Adv. in Geogr. Inf. Syst., 270–279 (Association for Computing Machinery, 2010). [find](https://scholar.google.com/scholar?q=Yang%2C+Y%2E+%26+Newsam%2C+S%2E+Bag%2Dof%2Dvisual%2Dwords+and+spatial+extensions+for+land%2Duse+classification%2E+In+Proc%2E+18th+SIGSPATIAL+Int%2E+Conf%2E+on+Adv%2E+in+Geogr%2E+Inf%2E+Syst%2E%2C+270%E2%80%93279+%28Association+for+Computing+Machi)
72. Russakovsky, O. et al. [ImageNet large scale visual recognition challenge](https://md.research.elamur.ai/free/en/papers/russakovsky-2014-imagenet-large-scale-visual-recognition/). Int. J. Comput. Vis. 115, 211–252 (2015).
73. Krizhevsky, A., Sutskever, I. & Hinton, G. E. [ImageNet classification with deep convolutional neural networks](https://md.research.elamur.ai/free/en/papers/krizhevsky-2012-imagenet-classification-deep-convolutional/). Adv. Neural Inf. Process. Syst. 25 (2012).
74. Immer, A. et al. Forecasting whole-brain neuronal activity from volumetric video. arXiv preprint arXiv:2503.00073 (2025). — [arXiv:2503.00073](https://arxiv.org/abs/2503.00073) [find](https://scholar.google.com/scholar?q=Immer%2C+A%2E+et+al%2E+Forecasting+whole%2Dbrain+neuronal+activity+from+volumetric+video%2E+arXiv+preprint+arXiv%3A2503%2E00073+%282025%29%2E+%E2%80%94+%5BarXiv%3A2503%2E00073%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E00073%29)
75. Zeng, A., Chen, M., Zhang, L. & Xu, Q. Are transformers effective for time series forecasting? In Proc AAAI Conf. Artif. Intell., vol. 37, 11121–11128 (2023). [find](https://scholar.google.com/scholar?q=Zeng%2C+A%2E%2C+Chen%2C+M%2E%2C+Zhang%2C+L%2E+%26+Xu%2C+Q%2E+Are+transformers+effective+for+time+series+forecasting%3F+In+Proc+AAAI+Conf%2E+Artif%2E+Intell%2E%2C+vol%2E+37%2C+11121%E2%80%9311128+%282023%29%2E)
76. Das, A. et al. Long-term forecasting with TiDE: Time-series Dense Encoder. Trans. Mach. Learn. Res. (2023). [find](https://scholar.google.com/scholar?q=Das%2C+A%2E+et+al%2E+Long%2Dterm+forecasting+with+TiDE%3A+Time%2Dseries+Dense+Encoder%2E+Trans%2E+Mach%2E+Learn%2E+Res%2E+%282023%29%2E)
77. Chen, S.-A., Li, C.-L., Yoder, N., Arik, S. O. & Pfister, T. TSMixer: An All-MLP architecture for time series forecasting. Trans. Mach. Learn. Res. (2023). [find](https://scholar.google.com/scholar?q=Chen%2C+S%2E%2DA%2E%2C+Li%2C+C%2E%2DL%2E%2C+Yoder%2C+N%2E%2C+Arik%2C+S%2E+O%2E+%26+Pfister%2C+T%2E+TSMixer%3A+An+All%2DMLP+architecture+for+time+series+forecasting%2E+Trans%2E+Mach%2E+Learn%2E+Res%2E+%282023%29%2E)
78. Perez, E., Strub, F., De Vries, H., Dumoulin, V. & Courville, A. [FiLM: Visual reasoning with a general conditioning layer](https://md.research.elamur.ai/free/en/papers/perez-2017-film-visual-reasoning-general-conditioning/). In Proc AAAI Conf. Artif. Intell., vol. 32 (2018).
79. Deistler, M. et al. Differentiable simulation enables large-scale training of detailed biophysical models of neural dynamics. bioRxiv 2024–08 (2024). [find](https://scholar.google.com/scholar?q=Deistler%2C+M%2E+et+al%2E+Differentiable+simulation+enables+large%2Dscale+training+of+detailed+biophysical+models+of+neural+dynamics%2E+bioRxiv+2024%E2%80%9308+%282024%29%2E)
80. Hodgkin, A. L. & Huxley, A. F. A quantitative description of membrane current and its application to conduction and excitation in nerve. J. Physiol. 117, 500 (1952). [find](https://scholar.google.com/scholar?q=Hodgkin%2C+A%2E+L%2E+%26+Huxley%2C+A%2E+F%2E+A+quantitative+description+of+membrane+current+and+its+application+to+conduction+and+excitation+in+nerve%2E+J%2E+Physiol%2E+117%2C+500+%281952%29%2E)
81. Piessens, R., de Doncker-Kapenga, E., Überhuber, C. W. & Kahaner, D. QUADPACK: a subroutine package for automatic integration (Springer-Verlag, 1983). [find](https://scholar.google.com/scholar?q=Piessens%2C+R%2E%2C+de+Doncker%2DKapenga%2C+E%2E%2C+%C3%9Cberhuber%2C+C%2E+W%2E+%26+Kahaner%2C+D%2E+QUADPACK%3A+a+subroutine+package+for+automatic+integration+%28Springer%2DVerlag%2C+1983%29%2E)
82. Gradshteyn, I. & Ryzhik, I. Table of integrals, series, and products, 8th edn (Academic Press, 1994). [find](https://scholar.google.com/scholar?q=Gradshteyn%2C+I%2E+%26+Ryzhik%2C+I%2E+Table+of+integrals%2C+series%2C+and+products%2C+8th+edn+%28Academic+Press%2C+1994%29%2E)
83. Meurer, A. et al. SymPy: symbolic computing in Python. PeerJ Comput. Sci. 3, e103 (2017). [find](https://scholar.google.com/scholar?q=Meurer%2C+A%2E+et+al%2E+SymPy%3A+symbolic+computing+in+Python%2E+PeerJ+Comput%2E+Sci%2E+3%2C+e103+%282017%29%2E)
84. Brenner, M. P., Cohen-Addad, V. & Woodruff, D. Solving an open problem in theoretical physics using ai-assisted discovery. arXiv preprint arXiv:2603.04735 (2026). — [arXiv:2603.04735](https://arxiv.org/abs/2603.04735) [find](https://scholar.google.com/scholar?q=Brenner%2C+M%2E+P%2E%2C+Cohen%2DAddad%2C+V%2E+%26+Woodruff%2C+D%2E+Solving+an+open+problem+in+theoretical+physics+using+ai%2Dassisted+discovery%2E+arXiv+preprint+arXiv%3A2603%2E04735+%282026%29%2E+%E2%80%94+%5BarXiv%3A2603%2E04735%5D%28https%3A%2F%2Farxiv%2Eor)
85. Lueckmann, J.-M., Jain, V. & Januszewski, M. Discovering mechanistic models of neural activity: System identification in an in silico zebrafish (2026). https://arxiv.org/abs/2602.04492. 2602.04492. — [arXiv:2602.04492](https://arxiv.org/abs/2602.04492) [↗](https://arxiv.org/abs/2602.04492)
86. McInnes, L., Healy, J. & Melville, J. [UMAP: uniform manifold approximation and projection for dimension reduction](https://md.research.elamur.ai/free/en/papers/mcinnes-2018-umap-uniform-manifold-approximation-projection/). arXiv preprint arXiv:1802.03426 (2018).
87. Ho, S. L. & Xie, M. The use of ARIMA models for reliability forecasting and analysis. Comput. Ind. Eng. 35, 213–216 (1998). [find](https://scholar.google.com/scholar?q=Ho%2C+S%2E+L%2E+%26+Xie%2C+M%2E+The+use+of+ARIMA+models+for+reliability+forecasting+and+analysis%2E+Comput%2E+Ind%2E+Eng%2E+35%2C+213%E2%80%93216+%281998%29%2E)
88. Zhong, B., Du, J., Liu, M., Yang, A. & Wu, J. Region-enhancing network for semantic segmentation of remote-sensing imagery. Sensors 21 (2021). [find](https://scholar.google.com/scholar?q=Zhong%2C+B%2E%2C+Du%2C+J%2E%2C+Liu%2C+M%2E%2C+Yang%2C+A%2E+%26+Wu%2C+J%2E+Region%2Denhancing+network+for+semantic+segmentation+of+remote%2Dsensing+imagery%2E+Sensors+21+%282021%29%2E)
89. Zhang, Z., Liu, B. & Li, Y. FURSformer: semantic segmentation network for remote sensing images with fused heterogeneous features. Electronics 12 (2023). [find](https://scholar.google.com/scholar?q=Zhang%2C+Z%2E%2C+Liu%2C+B%2E+%26+Li%2C+Y%2E+FURSformer%3A+semantic+segmentation+network+for+remote+sensing+images+with+fused+heterogeneous+features%2E+Electronics+12+%282023%29%2E)
90. Atiampo, A. K. & Diédié, G. H. F. New fusion approach of spatial and channel attention for semantic segmentation of very high spatial resolution remote sensing images. Open J. Appl. Sci. 14, 288–319 (2024). [find](https://scholar.google.com/scholar?q=Atiampo%2C+A%2E+K%2E+%26+Di%C3%A9di%C3%A9%2C+G%2E+H%2E+F%2E+New+fusion+approach+of+spatial+and+channel+attention+for+semantic+segmentation+of+very+high+spatial+resolution+remote+sensing+images%2E+Open+J%2E+Appl%2E+Sci%2E+14%2C+288%E2%80%93319+%28)
91. Sun, Y., Bi, F., Gao, Y., Chen, L. & Feng, S. A multi-attention UNet for semantic segmentation in remote sensing images. Symmetry 14, 906 (2022). [find](https://scholar.google.com/scholar?q=Sun%2C+Y%2E%2C+Bi%2C+F%2E%2C+Gao%2C+Y%2E%2C+Chen%2C+L%2E+%26+Feng%2C+S%2E+A+multi%2Dattention+UNet+for+semantic+segmentation+in+remote+sensing+images%2E+Symmetry+14%2C+906+%282022%29%2E)
92. Elgamily, K. M., Mohamed, M. A., Abou-Taleb, A. M. & Ata, M. M. A novel W13 deep CNN structure for improved semantic segmentation of multiple objects in remote sensing imagery. Neural Comput. Appl. 37, 5397–5427 (2025). Code Availability [find](https://scholar.google.com/scholar?q=Elgamily%2C+K%2E+M%2E%2C+Mohamed%2C+M%2E+A%2E%2C+Abou%2DTaleb%2C+A%2E+M%2E+%26+Ata%2C+M%2E+M%2E+A+novel+W13+deep+CNN+structure+for+improved+semantic+segmentation+of+multiple+objects+in+remote+sensing+imagery%2E+Neural+Comput%2E+Appl%2E+37)

*Updated 1 November 2026*