Pushkar Mishra
Source-listed: Lead AI Researcher · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Llama 2: Open Foundation and Fine-Tuned Chat ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- What do Reward Models Memorize?Saved credit: Contributor · 2026Explore people connected to this work →
- Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to SeveritySaved credit: Contributor · 2026Explore people connected to this work →
- Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image ModelsSaved credit: Contributor · 2025Explore people connected to this work →
- Value Profiles for Encoding Human VariationSaved credit: Contributor · 2025Explore people connected to this work →