Richard Yuanzhe Pang
Source-listed: Research Scientist · Meta Superintelligence Labs
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Self-Rewarding Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Iterative Reasoning Preference OptimizationSaved credit: First author · 2024Explore people connected to this work →
- Self-Taught EvaluatorsSaved credit: Contributor · 2024Explore people connected to this work →
- GPQA: A Graduate-Level Google-Proof Q&A BenchmarkSaved credit: Contributor · 2024Explore people connected to this work →
- AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction FollowingSaved credit: Contributor · 2026Explore people connected to this work →