Hongyuan Zhan
Source-listed: Staff Research Scientist and Research Lead · Meta Superintelligence Labs
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- The Llama 3 Herd of ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding ConversationsSaved credit: Contributor · 2024Explore people connected to this work →
- Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI ConversationsSaved credit: Contributor · 2024Explore people connected to this work →
- The Alignment Waltz: Jointly Training Agents to Collaborate for SafetySaved credit: Contributor · 2025Explore people connected to this work →
- Large Reasoning Models Learn Better Alignment from Flawed ThinkingSaved credit: Contributor · 2025Explore people connected to this work →