| AI Alignment: A Contemporary Survey J Ji, T Qiu, B Chen, J Zhou, B Zhang, D Hong, H Lou, K Wang, Y Duan, ... ACM Computing Surveys, 2025 | 878* | 2025 |
| Harms from Increasingly Agentic Algorithmic Systems A Chan, R Salganik, A Markelius, C Pang, N Rajkumar, D Krasheninnikov, ... Proceedings of the 2023 ACM Conference on Fairness, Accountability, and …, 2023 | 462* | 2023 |
| TransNAS-Bench-101: Improving transferability and Generalizability of Cross-Task Neural Architecture Search Y Duan, X Chen, H Xu, Z Chen, X Liang, T Zhang, Z Li Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | 139 | 2021 |
| Adversarial Policies Beat Superhuman Go AIs TT Wang, A Gleave, T Tseng, K Pelrine, N Belrose, J Miller, MD Dennis, ... Proceedings of the 40th International Conference on Machine Learning, 35655 …, 2023 | 122* | 2023 |
| The 2025 ai agent index: Documenting technical and safety features of deployed agentic ai systems L Staufer, K Feng, K Wei, L Bailey, Y Duan, M Yang, AP Ozisik, S Casper, ... The 2026 ACM Conference on Fairness, Accountability, and Transparency, 1536-1576, 2026 | 68 | 2026 |
| On the fragility of learned reward functions L McKinney, Y Duan, D Krueger, A Gleave arXiv preprint arXiv:2301.03652, 2023 | 32 | 2023 |
| CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search X Chen, Y Duan, Z Chen, H Xu, Z Chen, X Liang, T Zhang, Z Li Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 29 | 2020 |
| & Gao, W.(2023). Ai alignment: A comprehensive survey J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang, Y Duan, Z He, L Vierling, ... arXiv preprint arXiv:2310.19852 77, 0 | 15 | |
| Ai deception: Risks, dynamics, and controls B Chen, S Fang, J Ji, Y Zhu, P Wen, J Wu, Y Tan, B Zheng, M Yuan, ... arXiv preprint arXiv:2511.22619, 2025 | 12 | 2025 |
| Bare minimum mitigations for autonomous AI development J Clymer, I Duan, C Cundy, Y Duan, F Heide, C Lu, S Mindermann, ... arXiv preprint arXiv:2504.15416, 2025 | 11 | 2025 |
| Libra-leaderboard: Towards responsible ai through a balanced leaderboard of safety and capability H Li, X Han, Z Zhai, H Mu, H Wang, Z Zhang, Y Geng, S Lin, R Wang, ... Proceedings of the 2025 Conference of the Nations of the Americas Chapter of …, 2025 | 10 | 2025 |
| The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems J Luo, J Dai, Z Chen, J Xu, W Wang, Y Duan, B Tse, G Hong, X Pan, ... arXiv preprint arXiv:2606.13079, 2026 | | 2026 |
| Position: Preparing for AI Systems That Deceive Developers I Duan, X Pan, Y Duan, A Gleave, R Duan, Y Zhang, X Li, C Lu, N Hu, ... Forty-third International Conference on Machine Learning Position Paper Track, 2026 | | 2026 |
| Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report SAI Lab, X Chen, Y Chen, Z Chen, Z Chen, H Cui, Y Duan, J Guo, Q Guo, ... arXiv preprint arXiv:2507.16534, 2025 | | 2025 |
Zhonghao HeUniversity of Oxford, Johns Hopkins UniversityVerified email at cam.ac.uk
