Richard Ren

机构：University of Pennsylvania, Center for AI Safety · ORCID：0000-0001-5628-7926

发表论文 13 篇 · 总被引 1689 次 · h-index 9

代表论文

• Representation Engineering: A Top-Down Approach to AI Transparency (2023 · arXiv.org · 被引 1275)
• A benchmark of expert-level academic questions to assess AI capabilities (2025 · Nature · 被引 373)
• Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? (2024 · Neural Information Processing Systems · 被引 82)
• Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs (2025 · Neural Information Processing Systems · 被引 68)
• Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions (2021 · IEEE Robotics and Automation Letters · 被引 59)
• The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems (2025 · arXiv.org · 被引 50)