🧑‍🔬 Alex J. Smola

🏛️ Affiliations

🏢BoseFramingham · United States2026 · 1 papercurrent🎓Australian National UniversityCanberra · Australia1998–2014 · 48 papers🔬Data61Sydney · Australia2003–2012 · 38 papers🎓Carnegie Mellon UniversityPittsburgh · United States2013–2021 · 27 papers🏢YahooSunnyvale · United States2008–2018 · 25 papers🏢AmazonSeattle · United States2018–2023 · 15 papers🏢GoogleMountain View · United States2012–2017 · 8 papers🎓Georgia Institute of TechnologyAtlanta · United States2014–2023 · 4 papers🎓Stanford UniversityStanford · United States2023 · 2 papers

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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Hierarchical Attention Networks for Document Classification (2016 · 5,436 citations)
   The paper addresses document-level text classification, such as predicting review ratings or question topics.
2. Stacked Attention Networks for Image Question Answering (2015 · 2,157 citations)
   The paper addresses image question answering (QA): answering a natural-language question about a given picture.
3. Automatic Chain of Thought Prompting in Large Language Models (2022 · 695 citations)
   Chain-of-thought prompting works best when a model sees a few worked examples, but writing those examples by hand is slow and has to be redone for each task.
4. Multimodal Chain-of-Thought Reasoning in Language Models (2023 · 308 citations)
   Chain-of-thought (CoT) prompting helps large language models solve multi-step problems, but earlier work used text only.
5. Parameter-Efficient Fine-Tuning Design Spaces (2023 · 47 citations)
   Existing parameter-efficient fine-tuning (PEFT) techniques such as Adapter, Prefix tuning, BitFit and LoRA were each designed by hand and usually applied identically to every layer.

All works

30 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Hierarchical Attention Networks for Document ClassificationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Zichao Yang, Diyi Yang, Chris Dyer, et al.2016 · 5,436 citations
2. Stacked Attention Networks for Image Question AnsweringIEEE Computer Society Conference on Computer Vision and Pattern RecognitionZichao Yang, Xiaodong He, Jianfeng Gao, et al.2015 · 2,157 citations
3. Feature hashing for large scale multitask learning ↗International Conference on Machine Learning · no summary yetKilian Q. Weinberger et al.2009 · 958 citations
4. Automatic Chain of Thought Prompting in Large Language ModelsarXiv:2210.03493Zhuosheng Zhang, Aston Zhang, Mu Li, et al.2022 · 695 citations
5. Learning Graph Matching ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetTibério S. Caetano et al.383 citations
6. COFI RANK - Maximum margin matrix factorization for collaborative ranking ↗HAL (Le Centre pour la Communication Scientifique Directe) · no summary yetMarkus Weimer et al.2007 · 349 citations
7. Fastfood: approximating kernel expansions in loglinear time ↗no summary yetQuoc Viet Le, Tamás Sarlós, Alex J. Smola2013 · 317 citations
8. Multimodal Chain-of-Thought Reasoning in Language ModelsarXiv:2302.00923Zhuosheng Zhang, Aston Zhang, Mu Li, et al.2023 · 308 citations
9. Hilbert space embeddings of conditional distributions with applications to dynamical systems ↗International Conference on Machine Learning · no summary yetLe Song et al.2009 · 255 citations
10. Bundle Methods for Regularized Risk Minimization ↗no summary yetChoon Hui Teo et al.2010 · 227 citations
11. Deep Sets ↗arXiv (Cornell University) · no summary yetManzil Zaheer et al.2017 · 199 citations
12. Slow Learners are Fast ↗neural information processing systems · no summary yetMartin Zinkevich, John C. Langford, Alex J. Smola2009 · 196 citations
13. Heteroscedastic Gaussian process regression ↗International Conference on Machine Learning · no summary yetQuoc Viet Le, Alex J. Smola, Stéphane Canu2005 · 181 citations
14. A scalable modular convex solver for regularized risk minimization ↗ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · no summary yetChoon Hui Teo et al.2007 · 174 citations
15. Estimating Labels from Label Proportions ↗no summary yetNovi Quadrianto et al.2009 · 154 citations
16. Super-Samples from Kernel Herding ↗arXiv (Cornell University) · no summary yetYutian Chen, Max Welling, Alex J. Smola2012 · 153 citations
17. Bundle Methods for Machine Learning ↗neural information processing systems · no summary yetQuoc Viet Le, Alex J. Smola, S. V. N. Vishwanathan2007 · 124 citations
18. Fastfood - Computing Hilbert Space Expansions in loglinear time ↗International Conference on Machine Learning · no summary yetQuoc Viet Le, Tamás Sarlós, Alexander Johannes Smola2013 · 101 citations
19. Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization ↗neural information processing systems · no summary yetSashank Jakkam Reddi et al.2016 · 96 citations
20. Direct Optimization of Ranking Measures ↗arXiv (Cornell University) · no summary yetQuoc Viet Le, Alexander Johannes Smola2007 · 94 citations
21. Symbolic Music Generation with Transformer-GANs ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetAashiq Muhamed et al.2021 · 66 citations
22. Tighter Bounds for Structured Estimation ↗no summary yetOlivier Chapelle et al.2008 · 62 citations
23. Learning Graph Matching ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetTibério S. Caetano et al.2007 · 62 citations
24. A Generic Approach for Escaping Saddle points ↗arXiv (Cornell University) · no summary yetSashank Jakkam Reddi et al.2017 · 52 citations
25. Parameter-Efficient Fine-Tuning Design SpacesarXiv:2301.01821Jiaao Chen, Aston Zhang, Xingjian Shi, et al.2023 · 47 citations

See all 30 works by Alex J. Smola →

🤝 Co-authors here

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

• Aston Zhang ×3
• Mu Li ×3
• Diyi Yang ×2
• Xiaodong He ×2
• Zhuosheng Zhang ×2
• Zichao Yang ×2
• Chris Dyer
• Eduard Hovy
• Hai Zhao
• Jiaao Chen
• Jianfeng Gao
• Li Deng

Venues

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

• International Conference on Machine Learning ×5
• neural information processing systems ×3
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition: IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2015
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2016
• ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)
• HAL (Le Centre pour la Communication Scientifique Directe)
• IEEE International Conference on Computer Vision (ICCV)
• IEEE Transactions on Pattern Analysis and Machine Intelligence
• Lecture notes in computer science
• Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 1,869 times (of the 149,439 papers whose bibliographies we read); 253 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/alex-j-smola/