Yunfeng Zhang | 张云峰
I am a Senior ML engineer at EvolutionIQ. Previously, I worked at Twitter and IBM Research. At Twitter, I developed a distributed model evaluation system for evaluating model performance and fairness. I am passionate about developing fair, transparent, and trustworthy AI, as well as making machine learning systems more understandable and user friendly. My recent projects include AI Fairness 360 and AI Explainability 360 toolkits, chatbot development framework, multi-modal interactive systems, modeling social interactions, and understanding and remediating cognitive biases.
news
No news so far...
selected publications
-
FAccTDe-Biasing “Bias” MeasurementIn 2022 ACM Conference on Fairness, Accountability, and Transparency 2022
-
arXivOne Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability TechniquesarXiv:1909.03012 [cs, stat] Sep 2019
-
arXivAI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic BiasarXiv:1810.01943 [cs] Oct 2018
-
NeurIPSModel Agnostic Multilevel ExplanationsIn Advances in Neural Information Processing Systems Oct 2020
-
FAccTEffect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision MakingIn Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency Jan 2020