Jin Peng Zhou
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Q♯: Provably Optimal Distributional RL for LLM Post-TrainingSaved credit: First author · 2025Explore people connected to this work →
- Value-Guided Search for Efficient Chain-of-Thought ReasoningSaved credit: Contributor · 2025Explore people connected to this work →
- Graders Should Cheat: Privileged Information Enables Expert-Level Automated EvaluationsSaved credit: Contributor · 2025Explore people connected to this work →
- On Speeding Up Language Model EvaluationSaved credit: First author · 2025Explore people connected to this work →
- Gemma 2: Improving Open Language Models at a Practical SizeSaved credit: Contributor · 2024Explore people connected to this work →