James Aung

发表论文 11 篇 · 总被引 4816 次 · h-index 5

代表论文

• GPT-4o System Card (2024 · 被引 4846)
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering (2024 · arXiv.org · 被引 367)
• PaperBench: Evaluating AI's Ability to Replicate AI Research (2025 · International Conference on Machine Learning · 被引 256)
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering (2025 · International Conference on Learning Representations · 被引 40)
• Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios (2026 · arXiv.org · 被引 11)
• Large Language Models as Misleading Assistants in Conversation (2024 · arXiv.org · 被引 11)