← authors · overview

• Zephyr: Direct Distillation Of LM Alignment
  2023 · 573 citations
• The Alignment Ceiling: Objective Mismatch In Reinforcement Learning From Human Feedback
  2023 · 46 citations
• On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
  2021 · 33 citations
• Objective Mismatch in Model-based Reinforcement Learning
  2020 · 21 citations
• The Challenges of Exploration for Offline Reinforcement Learning
  2022 · 8 citations
• WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  2024 · 7 citations
• RewardBench: Evaluating Reward Models for Language Modeling
  2024 · 5 citations
• Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning
  2019 · 4 citations
• Investigating Compounding Prediction Errors in Learned Dynamics Models
  2022 · 4 citations
• Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems
  2022 · 3 citations
• The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback
  2023 · 3 citations
• Reinforcement Learning from Human Feedback
  2025 · 2 citations
• 2 OLMo 2 Furious
  2025 · 2 citations
• A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning
  2023 · 2 citations
• Tmax: A simple recipe for terminal agents
  2026