--- title: "Oncel Tuzel — author profile and papers — Elamur Research" description: "Oncel Tuzel, Purdue University West Lafayette: 2 papers on Elamur Research (2024), h-index 42 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/oncel-tuzel/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/oncel-tuzel/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Oncel Tuzel # Oncel Tuzel Oncel Tuzel has 2 papers in our library, in 2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Chun-Liang Li](https://md.research.elamur.ai/free/en/authors/chun-liang-li/), [Iman Mirzadeh](https://md.research.elamur.ai/free/en/authors/iman-mirzadeh/), [Keivan Alizadeh](https://md.research.elamur.ai/free/en/authors/keivan-alizadeh/). 2 papers in our library · 2024 [OpenAlex](https://openalex.org/A5028613002) · [**h-index 42**](https://openalex.org/authors/A5028613002) · [153 works](https://openalex.org/works?filter=author.id:A5028613002) · [16,381 citations](https://openalex.org/works?filter=author.id:A5028613002&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/oncel-tuzel/#papers) · [🔗 Cited 332 times in our library](https://md.research.elamur.ai/free/en/authors/oncel-tuzel/cited-by/) · [12 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #5029](https://md.research.elamur.ai/free/en/paper-stars/page/51/#star-5029) 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=Oncel+Tuzel) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Oncel+Tuzel) · [dblp](https://dblp.org/search?q=Oncel+Tuzel) · [ACL Anthology](https://aclanthology.org/search/?q=Oncel+Tuzel) ## Affiliations [🏢**Apple** Cupertino · United States 2017–2026 · 35 papers*current*](https://md.research.elamur.ai/free/en/companies/apple/) · [🎓**Purdue University West Lafayette** West Lafayette · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/purdue-university-west-lafayette/) · [🏢**Mitsubishi Electric Research Laboratories** Cambridge · United States 2005–2017 · 35 papers](https://ror.org/00e2e3n51) · [🎓**Rutgers, The State University of New Jersey** New Brunswick · United States 2005–2009 · 12 papers](https://md.research.elamur.ai/free/en/universities/rutgers-the-state-university-of-new-jersey/) · [🏢**Mitsubishi Electric** Cypress · United States 2005–2016 · 8 papers](https://ror.org/053jnhe44) · [🏢**Apple** Herzliya · Israel 2019 · 2 papers](https://md.research.elamur.ai/free/en/companies/apple-israel/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) 🧭 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/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/oncel-tuzel/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/mirzadeh-2024-gsm-symbolic-understanding-limitations-mathematical/)** *(2024 · 273 citations)* Scores on GSM8K, the standard grade-school math benchmark, keep rising. The authors ask whether that reflects real reasoning or just familiarity with a fixed and possibly leaked test set. They build GSM-Symbolic by turning GSM8K problems into templates, where names, numbers and family terms become variables with… 2. **[Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum](https://md.research.elamur.ai/free/en/papers/pouransari-2024-dataset-decomposition-faster-llm-training/)** *(2024 · 16 citations)* Standard LLM pretraining uses concat-and-chunk: documents are shuffled, joined, and cut into fixed-length sequences. ## All works 14 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. **[Learning from Simulated and Unsupervised Images through Adversarial Training ↗](https://doi.org/10.1109/cvpr.2017.241) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Ashish Shrivastava et al.*2017 · 1,857 citations* 2. **[A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection ↗](https://doi.org/10.1109/cvpr.2016.216) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Bharat Singh et al.*2016 · 461 citations* 3. **[MobileOne: An Improved One millisecond Mobile Backbone ↗](https://doi.org/10.1109/cvpr52729.2023.00764) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Pavan Kumar Anasosalu Vasu et al.*2023 · 414 citations* 4. [**GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models arXiv:2410.05229**Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, et al.*2024 · 273 citations*](https://md.research.elamur.ai/free/en/papers/mirzadeh-2024-gsm-symbolic-understanding-limitations-mathematical/) 5. **[Joint Geodesic Upsampling of Depth Images ↗](https://doi.org/10.1109/cvpr.2013.29) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Ming-Yu Liu, Oncel Tuzel, Yuichi Taguchi*2013 · 245 citations* 6. **[FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization ↗](https://arxiv.org/abs/2303.14189) arXiv:2303.14189 · no summary yet**Pavan Kumar Anasosalu Vasu et al.*2023 · 198 citations* 7. **[Gaussian Conditional Random Field Network for Semantic Segmentation ↗](https://doi.org/10.1109/cvpr.2016.351) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Raviteja Vemulapalli et al.*2016 · 152 citations* 8. **[Deep hierarchical parsing for semantic segmentation ↗](https://doi.org/10.1109/cvpr.2015.7298651) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Abhishek Sharma, Oncel Tuzel, David W. Jacobs*2015 · 98 citations* 9. **[Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum](https://md.research.elamur.ai/free/en/papers/pouransari-2024-dataset-decomposition-faster-llm-training/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Hadi Pouransari, Chun-Liang Li, Jen-Hao Rick Chang, et al.*2024 · 16 citations* 10. **[TrajTok: Learning Trajectory Tokens enables better Video Understanding ↗](https://arxiv.org/abs/2602.22779) arXiv (Cornell University) · no summary yet**Chenhao Zheng et al.*2026 · 2 citations* 11. **[Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions ↗](https://arxiv.org/abs/2407.06723) arXiv (Cornell University) · no summary yet**Yu-Guan Hsieh et al.*2024 · 1 citation* 12. **[Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training ↗](https://aclanthology.org/2026.findings-eacl.307/) Findings of the Association for Computational Linguistics: EACL 2026 · no summary yet**Jeffrey Li et al.*2026* 13. **[Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining ↗](https://arxiv.org/abs/2602.19548) arXiv (Cornell University) · no summary yet**Jeffrey Li et al.*2026* 14. **[FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations ↗](https://arxiv.org/abs/2504.08368) arXiv (Cornell University) · no summary yet**Cheng-Yu Hsieh et al.*2025* ## Co-authors here 6 co-authors with a page, the most papers together first. - [Chun-Liang Li](https://md.research.elamur.ai/free/en/authors/chun-liang-li/) - [Iman Mirzadeh](https://md.research.elamur.ai/free/en/authors/iman-mirzadeh/) - [Keivan Alizadeh](https://md.research.elamur.ai/free/en/authors/keivan-alizadeh/) - [Mehrdad Farajtabar](https://md.research.elamur.ai/free/en/authors/mehrdad-farajtabar/) - [Samy Bengio](https://md.research.elamur.ai/free/en/authors/samy-bengio/) - [Vaishaal Shankar](https://md.research.elamur.ai/free/en/authors/vaishaal-shankar/) ## 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 ×6 - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2024](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2024/) - Findings of the Association for Computational Linguistics: EACL 2026 ## Cited by Papers of our library cite their works 332 times (of the 149,439 papers whose bibliographies we read); [40 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/oncel-tuzel/cited-by/). Updated 30 October 2026