← authors · overview

• BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
  2025 · 1 citations
• Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
  2024 · 1 citations
• SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
  2024 · 1 citations
• Building Reliable Long-Form Generation via Hallucination Rejection Sampling
  2026
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
  2025
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL
  2025
• Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
  2025
• Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
  2025
• Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
  2025
• Towards Inverse Reinforcement Learning for Limit Order Book Dynamics
  2019
• Revisiting Automated Prompting: Are We Actually Doing Better?
  2023
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
  2024