Haohan Wang

Education

• MS, Computer Science (with emphasis on entrepreneurship), Language Technologies Institute & Computational Biology Department, Carnegie Mellon University, 2014
• Ph.D, Computer Science, Language Technologies Institute, Carnegie Mellon University, 2022

Selected Articles in Journals

• Lee, K. Y., Wang, H., Yook, Y., Rhodes, J. S., Christian-Hinman, C. A., & Tsai, N.-P. (2023). Tumor suppressor p53 modulates activity-dependent synapse strengthening, autism-like behavior and hippocampus-dependent learning. Molecular Psychiatry, 1–13.
• Zhang, J., Yu, Z., Zhang, X., & Wang, H. (2026). Stratifying Alzheimer’s disease by patient-specific genetic signatures reveals cognition-linked and cross-disease heterogeneity. npj Dementia.
• Li, Y., Chen, J., Lu, T., Tsai, N.-P., & Wang, H. (2026). Spatially varying gene regulation network inference from spatial transcriptomics. Bioinformatics Advances.
• Zhang, S. M., Yu, Z., Zhang, Z., Zhang, J., He, C., Liu, A., Chen, R., Wang, S., Yan, L., Ding, S., Li, L., Yang, Z., Xiao, G., Zhang, X., Bao, K., Wang, H., Vasilakos, A. V., Zhao, J., Chen, S., & Zhang, X. (2026). AI-powered medicinal chemistry and translational drug development. Chemical Society Reviews.

Articles in Conference Proceedings

• Kuang, P., Wang, Y., Han, X., Liu, Y., Xu, K., & Wang, H. (2026). Optimal aggregation of LLM and PRM signals for efficient test-time scaling. In Proceedings of the International Conference on Learning Representations (ICLR).
• Yu, Y., Zhang, P., Yu, Y., Wei, K., Luo, H., & Wang, H. (2026). SIPDO: Closed-loop prompt optimization via synthetic data feedback. In Proceedings of the International Conference on Learning Representations (ICLR).
• Liu, H., Li, Y., & Wang, H. (2026). GenoMAS: A multi-agent framework for scientific discovery via code-driven gene expression analysis. In Findings of the Association for Computational Linguistics: ACL 2026.
• Jin, H., Peng, K., Yu, Y., Yuan, X., & Wang, H. (2026). Agent primitives: Reusable latent building blocks for multi-agent systems. In Proceedings of the International Conference on Machine Learning (ICML).
• Hermon, M., Gupta, R., Ruan, W., Sabir, E., & Wang, H. (2026). Security–fidelity tradeoffs: No universal defense against prompt injection. In Proceedings of the International Conference on Machine Learning (ICML).
• Kuang, P., Jin, H., Han, X., Wang, Y., Yuan, X., Yu, Y., Xu, K., & Wang, H. (2026). KV-PRM: Efficient process reward modeling via KV-cache transfer for multi-agent test-time scaling. In Advances in Neural Information Processing Systems (NeurIPS).