Scholar
Xin Qiu
Google Scholar ID: SET9oYsAAAAJ
Cognizant AI Labs
Citations & Impact
Citations
530
H-index
12
i10-index
12
Publications
20
Co-authors
2
list available
Publications
Resume (English only)
Academic Achievements
- Featured Publications:
- - NeurIPS 2024: Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
- - ICML 2023: Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
- - AAAI 2022: Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model
- - ICLR 2020: Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel
Research Experience
- Currently Senior Director and Principal Research Scientist at Cognizant AI Lab.
Education
- Ph.D. in Artificial Intelligence from National University of Singapore Graduate School for Integrative Sciences and Engineering in 2016; B.Eng. in Electrical Engineering from Nanjing University in 2012.
Background
- An AI researcher at Cognizant AI Lab. Research interests include: evolutionary fine-tuning of large language models, developing systematic solutions to quantify the trustworthiness of responses returned by large language models, and utilizing the power of evolution to resolve architecture/graph search problems.
Miscellany
- Interests: Evolutionary Computation, Uncertainty Quantification, Large Language Models, Neural Architecture Search
