← authors · overview

• Walking Down The Memory Maze: Beyond Context Limit Through Interactive Reading
  2023 · 133 citations
• Contextual Position Encoding: Learning To Count What's Important
  2024 · 58 citations
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
  2023 · 9 citations
• Large Language Model Programs
  2023 · 5 citations
• Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
  2024 · 2 citations
• Iterative Reasoning Preference Optimization
  2024 · 1 citations
• Learning to Reason for Factuality
  2025
• Self-Improving Pretraining: using post-trained models to pretrain better models
  2026
• CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production
  2026
• Jointly Reinforcing Diversity and Quality in Language Model Generations
  2025
• MetaCLIP 2: A Worldwide Scaling Recipe
  2025
• The Era of Real-World Human Interaction: RL from User Conversations
  2025
• The Alignment Waltz: Jointly Training Agents to Collaborate for Safety
  2025
• Multi-Token Attention
  2025
• ALMA: Alignment with Minimal Annotation
  2024