🧑‍🔬 Tomas Pfister

🏛️ Affiliations

🏢GoogleMountain View · United States2019–2026 · 83 paperscurrent🎓University of California, Santa CruzSanta Cruz · United States2026 · 1 papercurrent🎓University of KentuckyLexington · United States2026 · 1 papercurrent🎓University of North Carolina at Chapel HillChapel Hill · United States2026 · 1 papercurrent🎓University of OxfordOxford · United Kingdom2012–2023 · 13 papers🏢Google DeepMindLondon · United Kingdom2024–2025 · 3 papers🎓University of OuluOulu · Finland2011–2013 · 3 papers🎓The University of Texas at AustinAustin · United States2023–2024 · 2 papers🎓University of CambridgeCambridge · United Kingdom2010–2011 · 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

📄 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 (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 (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 (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 (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 ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAshish Shrivastava et al.2017 · 1,857 citations
2. Learning to Prompt for Continual Learning ↗arXiv:2112.08654 · no summary yetZifeng Wang et al.2021 · 855 citations
3. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model SizesFindings of the Association for Computational LinguisticsCheng-Yu Hsieh, Chun-Liang Li, Chih-kuan Yeh, et al.2023 · 690 citations
4. Flowing ConvNets for Human Pose Estimation in Videos ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetTomas Pfister, James Charles, Andrew Zisserman2015 · 520 citations
5. Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos ↗Lecture notes in computer science · no summary yetTomas Pfister et al.2015 · 137 citations
6. Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding ↗arXiv:2401.04398 · no summary yetZilong Wang et al.2024 · 105 citations
7. Chain of Agents: Large Language Models Collaborating on Long-Context Tasks ↗arXiv:2406.02818 · no summary yetYusen Zhang et al.2024 · 104 citations
8. Domain-Adaptive Discriminative One-Shot Learning of Gestures ↗Lecture notes in computer science · no summary yetTomas Pfister, James Charles, Andrew Zisserman2014 · 95 citations
9. Personalizing Human Video Pose Estimation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJames Charles et al.2016 · 93 citations
10. Automatic and Efficient Human Pose Estimation for Sign Language Videos ↗International Journal of Computer Vision · no summary yetJames Charles et al.2013 · 74 citations
11. Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models ↗arXiv (Cornell University) · no summary yetCheng-Yu Hsieh et al.2023 · 71 citations
12. Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetCheng-Yu Hsieh et al.2024 · 61 citations
13. Large-scale Learning of Sign Language by Watching TV (Using Co-occurrences). ↗no summary yetTomas Pfister, James Charles, Andrew Zisserman2013 · 55 citations
14. Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingarXiv:2410.11325Wenda Xu, Rujun Han, Zifeng Wang, et al.2024 · 41 citations
15. Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts ↗British Machine Vision Conference (BMVC) · no summary yetJames Charles et al.2013 · 34 citations
16. Large-scale Learning of Sign Language by Watching TV ↗British Machine Vision Conference (BMVC) · no summary yetTomas Pfister, James Charles, Andrew Zisserman2013 · 27 citations
17. Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts ↗British Machine Vision Conference (BMVC) · no summary yetTomas Pfister et al.2012 · 24 citations
18. Reverse Thinking Makes LLMs Stronger Reasoners ↗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 yetJustin Chen et al.2025 · 18 citations
19. When One LLM Drools, Multi-LLM Collaboration RulesAnnual Meeting of the Association for Computational Linguistics (ACL)Shangbin Feng, Wenxuan Ding, Alisa Liu, et al.2026 · 14 citations
20. Upper Body Pose Estimation with Temporal Sequential Forests ↗British Machine Vision Conference (BMVC) · no summary yetJames Charles et al.2014 · 14 citations
21. Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems ↗neural information processing systems · no summary yetShangbin Feng et al.2025 · 7 citations
22. DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL)Dawei Zhu, Rui Meng, Jiefeng Chen, et al.2026 · 2 citations
23. Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems ↗arXiv (Cornell University) · no summary yetShubham Agarwal et al.2026 · 1 citation
24. VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails ↗arXiv (Cornell University) · no summary yetDuy Nguyen et al.2026
25. SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback ↗Findings of the Association for Computational Linguistics: EACL 2026 · no summary yetFangyuan Xu et al.2026

🤝 Co-authors here

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

• Chen-Yu Lee ×3
• Zifeng Wang ×2
• Alexander Ratner
• Alisa Liu
• Cheng-Yu Hsieh
• Chun-Liang Li
• Dawei Zhu
• Hootan Nakhost
• Hunter Lang
• Jiefeng Chen
• Jinsung Yoon
• 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) ×3: 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)
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 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 →.

Updated 1 November 2026

↑ back to top

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