Author

Yixiong Hao

Observed name: Hao, Yixiong

Institutions: Georgia Institute of Technology, Technion – Israel Institute of Technology, Columbia University, Tsinghua University

Observed institutions: Georgia Institute of Technology, Technion – Israel Institute of Technology, Columbia University, Tsinghua University

OpenAlex ID: A5119813063

Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts

2026 · Saeri, Alexander K., Graham, Jess, et al. · arXiv (Cornell University) · 9

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting

2026 · Ghosh, Avijit, Reuel, Anka, et al. · arXiv (Cornell University) · 8

Patterns and Mechanisms of Contrastive Activation Engineering

2025 · Hao, Yixiong, Panda, Ayush, et al. · arXiv (Cornell University) · 4

Shall We Play a Game? Language Models for Open-ended Wargames

2025 · Matlin, Glenn, Song, Isaac, et al. · arXiv (Cornell University) · 2

CoTs remain monitorable when being unfaithful requires computation: Replicating and Extending the Necessity Effect Across Eleven Models

2026 · Dhoot, Arav, Hao, Yixiong, et al. · arXiv (Cornell University)

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

2026 · Harris, Alec, Corra, Kasey, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 26

H-index: 3

I10-index: