Elamur Research⌕
☰
home / authors / Michael Tschannen

Michael Tschannen

Michael Tschannen has 2 papers in our library, in 2024–2025, most of them on Multilingual & cross-lingual NLP, Vision & language; often with Ibrahim Alabdulmohsin, Lucas Beyer, Xiao Wang.

2 papers in our library · 2024–2025

OpenAlex · ORCID · h-index 29 · 63 works · 4,913 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 437 times in our library · 7 more in our library without a page yet · ⭐ Paper Stars ranking: #5807

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓ETH ZurichZurich · Switzerland2013–2019 · 21 papers🏢GoogleMountain View · United States2019–2024 · 15 papers🏢Google DeepMindLondon · United Kingdom2023–2025 · 2 papers

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 3The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 works

🧭 Topics 2Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 1 workVision & language · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PaliGemma: A versatile 3B VLM for transfer (2024 · 142 citations)
    The paper targets a practical need: a compact, openly available vision-language model that works as a general base and can be fine-tuned to many downstream tasks.
  2. SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features (2025 · 126 citations)
    SigLIP 2 is Google DeepMind's second generation of open image-text encoders. CLIP-style models do well at zero-shot classification and retrieval, but they are weaker at localization and dense per-patch features. Earlier open checkpoints also rarely combine recent training advances. The authors merge several…

All works

9 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. Generative Adversarial Networks for Extreme Learned Image Compression ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetEirikur Agustsson et al.2019 · 588 citations
  2. Practical Full Resolution Learned Lossless Image Compression ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetFabian Mentzer et al.2019 · 230 citations
  3. Scaling Vision Transformers to 22 Billion Parameters ↗arXiv:2302.05442 · no summary yetMostafa Dehghani et al.2023 · 217 citations
  4. PaliGemma: A versatile 3B VLM for transferarXiv:2407.07726Lucas Beyer, Andreas Steiner, Andre Susano Pinto, et al.2024 · 142 citations
  5. SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense FeaturesarXiv:2502.14786Michael Tschannen, Alexey Gritsenko, Xiao Wang, et al.2025 · 126 citations
  6. PaLI-X: On Scaling up a Multilingual Vision and Language Model ↗arXiv (Cornell University) · no summary yetChen, Xi et al.2023 · 110 citations
  7. On Scaling Up a Multilingual Vision and Language Model ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXi Chen et al.2024 · 59 citations
  8. Semantic Bottleneck Scene Generation ↗arXiv (Cornell University) · no summary yetSamaneh Azadi et al.2019 · 7 citations
  9. Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck ↗no summary yetSamaneh Azadi et al.2021 · 1 citation

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 437 times (of the 149,439 papers whose bibliographies we read); 82 citing papers with a page here →.

Updated

↑ back to top

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