Johannes Welbl
Source-listed: Research Scientist · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- QAngaroo (WikiHop & MedHop)Saved credit: Creator · 2018Explore people connected to this work →
- Challenges in Detoxifying Language ModelsSaved credit: Contributor · 2021Explore people connected to this work →
- Training Compute-Optimal Large Language ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- Competition-level code generation with AlphaCodeSaved credit: Contributor · 2022Explore people connected to this work →
- Scalable watermarking for identifying large language model outputsSaved credit: Contributor · 2024Explore people connected to this work →