🧑‍🔬 Fei Sha

🏛️ Affiliations

🎓Ocean University of ChinaQingdao · China2020–2026 · 50 papersEmployment since 2020 · Associate professor, College of Engineeringcurrent🎓Shandong UniversityJinan · China2015–2026 · 21 paperscurrent🎓University of Southern CaliforniaLos Angeles · United States2008–2022 · 83 papers🏢GoogleMountain View · United States2019–2024 · 40 papers🎓Beijing Jiaotong UniversityBeijing · China1996–2011 · 14 papers🎓University of PennsylvaniaPhiladelphia · United States2002–2007 · 8 papers🎓University of JinanJinan · China2013–2021 · 7 papers🎓University of California, Los AngelesLos Angeles · United States2016 · 7 papers🎓University of California, BerkeleyBerkeley · United States2007–2010 · 7 papers🎓Université de Versailles Saint-Quentin-en-YvelinesVersailles · France1996–2005 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 35 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

📄 Papers

The most cited first (OpenAlex and our library).

1. Improving Compositional Generalization with Latent Structure and Data Augmentation (2022 · 76 citations)
   Pre-trained sequence-to-sequence models such as T5 cope well with natural language variation. However, they often fail when test inputs combine familiar elements in unseen ways. Specialized models with discrete latent structure handle such compositions better, but their gains have mostly been limited to synthetic…
2. Graders Should Cheat: Privileged Information Enables Expert-Level Automated Evaluations (2025 · 3 citations)
   Using a language model to grade other models is cheap, but it breaks down on frontier tasks such as Olympiad math or graduate-level physics.

All works

10 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. Synthesized Classifiers for Zero-Shot Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSoravit Changpinyo et al.2016 · 722 citations
2. Deformable Spatial Pyramid Matching for Fast Dense Correspondences ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJaechul Kim et al.2013 · 245 citations
3. Summary Transfer: Exemplar-Based Subset Selection for Video Summarization ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKe Zhang et al.2016 · 222 citations
4. Attention Correctness in Neural Image Captioning ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetChenxi Liu et al.2017 · 218 citations
5. Analysis and extension of spectral methods for nonlinear dimensionality reduction ↗International Conference on Machine Learning · no summary yetFei Sha, Lawrence K. Saul2005 · 104 citations
6. Improving Compositional Generalization with Latent Structure and Data AugmentationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Linlu Qiu, Peter Shaw, Panupong Pasupat, et al.2022 · 76 citations
7. BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetWang Zhu et al.2020 · 76 citations
8. Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetGeoffrey Zweig et al.2011 · 37 citations
9. Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025 ↗arXiv:2504.09737 · no summary yetNitya Thakkar et al.2025 · 21 citations
10. Graders Should Cheat: Privileged Information Enables Expert-Level Automated EvaluationsConference on Empirical Methods in Natural Language Processing (EMNLP)Jin Peng Zhou, Séb Arnold, Nan Ding, et al.2025 · 3 citations

🤝 Co-authors here

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

• Jin Peng Zhou
• Kilian Q. Weinberger
• Kristina Toutanova
• Linlu Qiu
• Nan Ding
• Nan Hua
• Panupong Pasupat
• Pawel Nowak
• Peter Shaw
• Tal Linzen

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 ×3
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2022
• IEEE International Conference on Acoustics Speech and Signal Processing
• International Conference on Machine Learning
• Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 123 times (of the 149,439 papers whose bibliographies we read); 10 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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