← authors · overview

• Longalign: A Recipe For Long Context Alignment Of Large Language Models
  2024 · 101 citations
• When Does In-context Learning Fall Short And Why? A Study On Specification-heavy Tasks
  2023 · 45 citations
• Agentic Reward Modeling: Integrating Human Preferences With Verifiable Correctness Signals For Reliable Reward Systems
  2025 · 40 citations