← authors · overview

• Test-time Recursive Thinking: Self-Improvement without External Feedback
  2026
• OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities
  2025
• Explaining Patterns in Data with Language Models via Interpretable Autoprompting
  2022
• Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
  2023
• Explaining black box text modules in natural language with language models
  2023
• Rethinking Interpretability in the Era of Large Language Models
  2024