🧑‍🔬 Stefanie Jegelka

🏛️ Affiliations

🎓Massachusetts Institute of TechnologyCambridge · United States2014–2026 · 91 paperscurrent🎓Technical University of MunichMunich · Germany2023–2026 · 30 paperscurrent🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2016–2026 · 28 paperscurrent🎓Munich Center for Machine LearningMunich · Germany2024–2026 · 6 paperscurrent🔬Max Planck Institute for Biological CyberneticsTübingen · Germany2005–2011 · 18 papers🔬Max Planck SocietyMunich · Germany2005–2011 · 17 papers🎓University of California, BerkeleyBerkeley · United States2013–2014 · 12 papers🔬Max Planck Institute for Intelligent SystemsStuttgart · Germany2011 · 4 papers🏢GoogleMountain View · United States2023–2024 · 3 papers🏢Artificial Intelligence in MedicineToronto · Canada2026 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. How Powerful are Graph Neural Networks? (2018 · 655 citations)
   Graph Neural Networks compute node embeddings by repeatedly pooling information from neighbours. Before this paper, there was little theory about which graph structures such models can or cannot tell apart. Xu, Hu, Leskovec and Jegelka treat neighbour pooling as a function over a multiset of feature vectors and ask…
2. When More is Less: Understanding Chain-of-Thought Length in LLMs (2025 · 73 citations)
   The paper asks whether longer Chain-of-Thought (CoT) reasoning always helps LLMs. The authors argue that it does not. They combine three lines of evidence: measurements on public models, controlled experiments, and a formal model. Public models include the Qwen2.5 Instruct series on MATH Level 5, plus RL runs. The…

All works

16 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Deep Metric Learning via Lifted Structured Feature Embedding ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHyun Oh Song et al.2016 · 1,679 citations
2. How Powerful are Graph Neural Networks?arXiv:1810.00826Keyulu Xu, Weihua Hu, Jure Leskovec, et al.2018 · 655 citations
3. Graph neural networks ↗Nature Reviews Methods Primers · no summary yetGabriele Corso et al.2024 · 457 citations
4. Deep Metric Learning via Facility Location ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHyun Oh Song et al.2017 · 294 citations
5. Weakly-supervised Discovery of Visual Pattern Configurations ↗arXiv (Cornell University) · no summary yetHyun Oh et al.2016 · 101 citations
6. Weakly-supervised Discovery of Visual Pattern Configurations ↗arXiv (Cornell University) · no summary yetHyun Oh Song et al.2014 · 94 citations
7. When More is Less: Understanding Chain-of-Thought Length in LLMsarXiv:2502.07266Yuyang Wu, Yifei Wang, Ziyu Ye, et al.2025 · 73 citations
8. A Principled Deep Random Field Model for Image Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetPushmeet Kohli, Anton Osokin, Stefanie Jegelka2013 · 59 citations
9. On learning to localize objects with minimal supervision ↗arXiv (Cornell University) · no summary yetHyun Oh Song et al.2014 · 28 citations
10. Auxiliary Image Regularization for Deep CNNs with Noisy Labels ↗arXiv (Cornell University) · no summary yetSamaneh Azadi et al.2015 · 23 citations
11. Learning Scalable Discriminative Dictionary with Sample Relatedness ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiashi Feng et al.2014 · 20 citations
12. Graph Adversarial Networks: Protecting Information against Adversarial Attacks ↗no summary yetPeiyuan Liao et al.2021 · 7 citations
13. Information Obfuscation of Graph Neural Networks ↗arXiv (Cornell University) · no summary yetPeiyuan Liao et al.2020 · 7 citations
14. Communal Cuts: sharing cuts across images ↗no summary yetEvan Shelhamer, Stefanie Jegelka, Trevor Jackson Darrell2015
15. On learning to localize objects with minimal supervision Hyun Oh Song ↗no summary yetRoss Girshick et al.2014
16. New Results - Visual recognition in images ↗no summary yetRamazan Gökberk Cinbiş et al.2013

🤝 Co-authors here

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

• Jure Leskovec
• Yifei Wang
• Yisen Wang
• Yuyang Wu

Venues

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

• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×4
• Nature Reviews Methods Primers

🔗 Cited by

Papers of our library cite their works 473 times (of the 149,439 papers whose bibliographies we read); 39 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/stefanie-jegelka/