Publications

Xin Qiu, Risto Miikkulainen (2024). Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space. The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).

Xin Qiu, Risto Miikkulainen (2023). Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search. Proceedings of the 40th International Conference on Machine Learning (ICML 2023).

Xin Qiu, Risto Miikkulainen (2022). Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2022), oral presentation (top ~4.5% of all submissions).

Elliot Meyerson, Xin Qiu, Risto Miikkulainen (2022). Simple genetic operators are universal approximators of probability distributions (and other advantages of expressive encodings). Proceedings of the Genetic and Evolutionary Computation Conference, Best Paper Award of the Genetic Algorithms (GA) track.

Risto Miikkulainen, Olivier Francon, Elliot Meyerson, Xin Qiu, Darren Sargent, Elisa Canzani, Babak Hodjat (2021). From Prediction to Prescription: Evolutionary Optimization of Nonpharmaceutical Interventions in the COVID-19 Pandemic. IEEE Transactions on Evolutionary Computation.

Risto Miikkulainen, Elliot Meyerson, Xin Qiu, Ujjayant Sinha, Raghav Kumar, Karen Hofmann, Yiyang Matt Yan, Michael Ye, Jingyuan Yang, Damon Caiazza, Stephanie Manson Brown (2021). Evaluating medical aesthetics treatments through evolved age-estimation models. Proceedings of the Genetic and Evolutionary Computation Conference, Silver Award in the Human Competitive Results Competition at GECCO 2022.

Xin Qiu, Elliot Meyerson, Risto Miikkulainen (2020). Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel. International Conference on Learning Representations (ICLR 2020).

Risto Miikulainen, Myles Brundage, Jonathan Epstein, Tyler Foster, Babak Hodjat, Neil Iscoe, Jingbo Jiang, Diego Legrand, Sam Nazari, Xin Qiu, Michael Scharff, Cory Schoolland, Robert Severn, Aaron Shagrin (2020). Ascend by Evolv: AI-Based Massively Multivariate Conversion Rate Optimization. AI Magazine.

Olivier Francon, Santiago Gonzalez, Babak Hodjat, Elliot Meyerson, Risto Miikkulainen, Xin Qiu, Hormoz Shahrzad (2020). Effective reinforcement learning through evolutionary surrogate-assisted prescription. Proceedings of the 2020 Genetic and Evolutionary Computation Conference, Best Paper Award of the General Evolutionary Computation and Hybrids (GECH) track.

Xin Qiu, Risto Miikkulainen (2019). Enhancing Evolutionary Conversion Rate Optimization via Multi-Armed Bandit Algorithms. Proceedings of the AAAI Conference on Artificial Intelligence.