---
title: "Tomas Pfister — author profile and papers — Elamur Research"
description: "Tomas Pfister, University of North Carolina at Chapel Hill: 4 papers on Elamur Research (2023–2026), h-index 38 — affiliations, topics…"
canonical: "https://research.elamur.ai/free/en/authors/tomas-pfister/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/tomas-pfister/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Tomas Pfister

# Tomas Pfister

Tomas Pfister has 4 papers in our library, in 2023–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Chen-Yu Lee](https://md.research.elamur.ai/free/en/authors/chen-yu-lee/), [Zifeng Wang](https://md.research.elamur.ai/free/en/authors/zifeng-wang/), [Alexander Ratner](https://md.research.elamur.ai/free/en/authors/alexander-ratner/).

4 papers in our library · 2023–2026

[OpenAlex](https://openalex.org/A5101265241) · [**h-index 38**](https://openalex.org/authors/A5101265241) · [172 works](https://openalex.org/works?filter=author.id:A5101265241) · [14,762 citations](https://openalex.org/works?filter=author.id:A5101265241&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/tomas-pfister/#papers) · [🔗 Cited 928 times in our library](https://md.research.elamur.ai/free/en/authors/tomas-pfister/cited-by/) · [21 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #2985](https://md.research.elamur.ai/free/en/paper-stars/page/30/#star-2985)

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=Tomas+Pfister) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Tomas+Pfister) · [dblp](https://dblp.org/search?q=Tomas+Pfister) · [ACL Anthology](https://aclanthology.org/search/?q=Tomas+Pfister)

## Affiliations

[🏢**Google** Mountain View · United States 2019–2026 · 83 papers*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**University of California, Santa Cruz** Santa Cruz · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-cruz/) · [🎓**University of Kentucky** Lexington · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-kentucky/) · [🎓**University of North Carolina at Chapel Hill** Chapel Hill · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) · [🎓**University of Oxford** Oxford · United Kingdom 2012–2023 · 13 papers](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · [🏢**Google DeepMind** London · United Kingdom 2024–2025 · 3 papers](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**University of Oulu** Oulu · Finland 2011–2013 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-oulu/) · [🎓**The University of Texas at Austin** Austin · United States 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/the-university-of-texas-at-austin/) · [🎓**University of Cambridge** Cambridge · United Kingdom 2010–2011 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/)

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.

📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Arts and Humanities · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/)

🧭 Topics 1 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/)

## Works by year

### 2020s

[**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/tomas-pfister/year/2026/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/tomas-pfister/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/tomas-pfister/year/2023/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://md.research.elamur.ai/free/en/papers/hsieh-2023-distilling-step-step-outperforming-larger/)** *(2023 · 690 citations)* Small task-specific models are cheap to serve, but they usually need many human labels (finetuning) or large pools of unlabeled data (distillation from an LLM) to approach LLM quality.
2. **[Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling](https://md.research.elamur.ai/free/en/papers/xu-2024-speculative-knowledge-distillation-bridging-teacher/)** *(2024 · 41 citations)* Distilling a large language model into a smaller one runs into two failure modes. Supervised KD trains on a fixed set of outputs, so it never sees the kind of text the student produces at inference time. On-policy KD trains on the student's own generations, but early on these are often poor and unfamiliar to the…
3. **[When One LLM Drools, Multi-LLM Collaboration Rules](https://md.research.elamur.ai/free/en/papers/feng-2026-when-one-llm-drools-multi/)** *(2026 · 14 citations)* This position paper by Feng et al. (ACL 2026) argues that a single general-purpose LLM cannot reliably handle complex, context-dependent, or subjective settings. It contributes no new dataset or model. Instead, it makes a conceptual case that any one model leaves gaps on three fronts. It misses parts of real-world…
4. **[DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding](https://md.research.elamur.ai/free/en/papers/zhu-2026-doclens-tool-augmented-multi-agent/)** *(2026 · 2 citations)* Long visual documents, such as financial reports, papers and manuals, spread their information over many pages of text, tables, charts and figures.

## All works

25 works of theirs in our library, the most cited first; 4 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. **[Learning to Prompt for Continual Learning ↗](https://arxiv.org/abs/2112.08654) arXiv:2112.08654 · no summary yet**Zifeng Wang et al.*2021 · 855 citations*
3. **[Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://md.research.elamur.ai/free/en/papers/hsieh-2023-distilling-step-step-outperforming-larger/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Cheng-Yu Hsieh, Chun-Liang Li, Chih-kuan Yeh, et al.*2023 · 690 citations*
4. **[Flowing ConvNets for Human Pose Estimation in Videos ↗](https://doi.org/10.1109/iccv.2015.222) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Tomas Pfister, James Charles, Andrew Zisserman*2015 · 520 citations*
5. **[Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos ↗](https://doi.org/10.1007/978-3-319-16865-4_35) Lecture notes in computer science · no summary yet**Tomas Pfister et al.*2015 · 137 citations*
6. **[Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding ↗](https://arxiv.org/abs/2401.04398) arXiv:2401.04398 · no summary yet**Zilong Wang et al.*2024 · 105 citations*
7. **[Chain of Agents: Large Language Models Collaborating on Long-Context Tasks ↗](https://arxiv.org/abs/2406.02818) arXiv:2406.02818 · no summary yet**Yusen Zhang et al.*2024 · 104 citations*
8. **[Domain-Adaptive Discriminative One-Shot Learning of Gestures ↗](https://doi.org/10.1007/978-3-319-10599-4_52) Lecture notes in computer science · no summary yet**Tomas Pfister, James Charles, Andrew Zisserman*2014 · 95 citations*
9. **[Personalizing Human Video Pose Estimation ↗](https://doi.org/10.1109/cvpr.2016.334) 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**James Charles et al.*2016 · 93 citations*
10. **[Automatic and Efficient Human Pose Estimation for Sign Language Videos ↗](https://doi.org/10.1007/s11263-013-0672-6) International Journal of Computer Vision · no summary yet**James Charles et al.*2013 · 74 citations*
11. **[Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models ↗](https://arxiv.org/abs/2308.00675) arXiv (Cornell University) · no summary yet**Cheng-Yu Hsieh et al.*2023 · 71 citations*
12. **[Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ↗](https://aclanthology.org/2024.findings-acl.890/) Findings of the Association for Computational Linguistics: ACL 2024 · no summary yet**Cheng-Yu Hsieh et al.*2024 · 61 citations*
13. **[Large-scale Learning of Sign Language by Watching TV (Using Co-occurrences). ↗](https://openalex.org/W2403878043) no summary yet**Tomas Pfister, James Charles, Andrew Zisserman*2013 · 55 citations*
14. [**Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling arXiv:2410.11325**Wenda Xu, Rujun Han, Zifeng Wang, et al.*2024 · 41 citations*](https://md.research.elamur.ai/free/en/papers/xu-2024-speculative-knowledge-distillation-bridging-teacher/)
15. **[Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts ↗](https://doi.org/10.5244/c.27.47) British Machine Vision Conference (BMVC) · no summary yet**James Charles et al.*2013 · 34 citations*
16. **[Large-scale Learning of Sign Language by Watching TV ↗](https://doi.org/10.5244/c.27.20) British Machine Vision Conference (BMVC) · no summary yet**Tomas Pfister, James Charles, Andrew Zisserman*2013 · 27 citations*
17. **[Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts ↗](https://doi.org/10.5244/c.26.4) British Machine Vision Conference (BMVC) · no summary yet**Tomas Pfister et al.*2012 · 24 citations*
18. **[Reverse Thinking Makes LLMs Stronger Reasoners ↗](https://aclanthology.org/2025.naacl-long.434/) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yet**Justin Chen et al.*2025 · 18 citations*
19. **[When One LLM Drools, Multi-LLM Collaboration Rules](https://md.research.elamur.ai/free/en/papers/feng-2026-when-one-llm-drools-multi/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Shangbin Feng, Wenxuan Ding, Alisa Liu, et al.*2026 · 14 citations*
20. **[Upper Body Pose Estimation with Temporal Sequential Forests ↗](https://doi.org/10.5244/c.28.54) British Machine Vision Conference (BMVC) · no summary yet**James Charles et al.*2014 · 14 citations*
21. **[Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems ↗](https://doi.org/10.52202/085713-3813) neural information processing systems · no summary yet**Shangbin Feng et al.*2025 · 7 citations*
22. **[DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding](https://md.research.elamur.ai/free/en/papers/zhu-2026-doclens-tool-augmented-multi-agent/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Dawei Zhu, Rui Meng, Jiefeng Chen, et al.*2026 · 2 citations*
23. **[Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems ↗](https://arxiv.org/abs/2605.23109) arXiv (Cornell University) · no summary yet**Shubham Agarwal et al.*2026 · 1 citation*
24. **[VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails ↗](https://arxiv.org/abs/2610.12813) arXiv (Cornell University) · no summary yet**Duy Nguyen et al.*2026*
25. **[SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback ↗](https://aclanthology.org/2026.findings-eacl.174/) Findings of the Association for Computational Linguistics: EACL 2026 · no summary yet**Fangyuan Xu et al.*2026*

## Co-authors here

12 of 27 co-authors with a page, the most papers together first.

- [Chen-Yu Lee](https://md.research.elamur.ai/free/en/authors/chen-yu-lee/) ×3
- [Zifeng Wang](https://md.research.elamur.ai/free/en/authors/zifeng-wang/) ×2
- [Alexander Ratner](https://md.research.elamur.ai/free/en/authors/alexander-ratner/)
- [Alisa Liu](https://md.research.elamur.ai/free/en/authors/alisa-liu/)
- [Cheng-Yu Hsieh](https://md.research.elamur.ai/free/en/authors/cheng-yu-hsieh/)
- [Chun-Liang Li](https://md.research.elamur.ai/free/en/authors/chun-liang-li/)
- [Dawei Zhu](https://md.research.elamur.ai/free/en/authors/dawei-zhu/)
- [Hootan Nakhost](https://md.research.elamur.ai/free/en/authors/hootan-nakhost/)
- [Hunter Lang](https://md.research.elamur.ai/free/en/authors/hunter-lang/)
- [Jiefeng Chen](https://md.research.elamur.ai/free/en/authors/jiefeng-chen/)
- [Jinsung Yoon](https://md.research.elamur.ai/free/en/authors/jinsung-yoon/)
- [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/)

## Venues

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

- British Machine Vision Conference (BMVC) ×4
- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×2
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
- Lecture notes in computer science ×2
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)
- [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/): [Findings of the Association for Computational Linguistics 2023](https://md.research.elamur.ai/free/en/venues/findings/2023/)
- Findings of the Association for Computational Linguistics: ACL 2024
- Findings of the Association for Computational Linguistics: EACL 2026
- IEEE International Conference on Computer Vision (ICCV)
- International Journal of Computer Vision
- Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- neural information processing systems

## Cited by

Papers of our library cite their works 928 times (of the 149,439 papers whose bibliographies we read); [150 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/tomas-pfister/cited-by/).

Updated 1 November 2026