Furui Cheng

Furui Cheng

Postdoc

ETH Zürich

Biography

I am a Postdoc at ETH Zürich, working with Prof. Menna El-Assady and other amazing people in the recently established IVIA Lab.

My research focuses on Human-Centered AI with data visualization approaches. My research goal is to support people in understanding and interacting with machine learning models by developing scalable visual interfaces and explainable machine learning techniques. Recently, I have focused more on 1) facilitating interpretable and trustworthy AI-informed decision-making in high-stakes scenarios and 2) supporting users in steering machine learning models to align with their knowledge.

I received my Ph.D. at the Hong Kong University of Science and Technology in 2022, advised by Prof. Huamin Qu.

Download my resumé .

Interests
  • LLM Transparency
  • Explainable and Interactive ML
  • Human-AI Decision Making
  • Visual Analytics

Featured Projects

Polyphony: incorporate experts’ knowledge into ML models
Polyphony facilitates interactions between biologists and single-cell omics data annotation ML models with the integration of visualization and anchor-based interactive transfer learning.
Polyphony: incorporate experts' knowledge into ML models
VBridge: AI-informed clinical decision-making
VBridge incorporates ML explanations into clinicians’ decision-making workflow by connecting the dots between ML features, data and explanations in healthcare models.
VBridge: AI-informed clinical decision-making
DECE: explore ML models with counterfactual explanations
DECE supports exploratory visual analysis on ML models with counterfactual explanations. The system helps non-expert users propose, verify, and refine their hypotheses on ML predictions.
DECE: explore ML models with counterfactual explanations

Publications

(2024). RELIC: Investigating Large Language Model Responses using Self-Consistency. Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'24).

PDF Cite

(2022). Polyphony: an Interactive Transfer Learning Framework for Single-Cell Data Analysis. IEEE Transactions on Visualization and Computer Graphics (VIS'22). Best Abstract Award at BioVis@ISMB.

PDF Cite Code Project

(2022). In Defence of Visual Analytics Systems: Replies to Critics. IEEE Transactions on Visualization and Computer Graphics (VIS'22).

PDF Cite Project

(2021). VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models. IEEE Transactions on Visualization and Computer Graphics (VIS'21). Best Paper Honorable Mention Award.

PDF Cite Code Project Video

(2020). DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models. IEEE Transactions on Visualization and Computer Graphics (VIS'20).

PDF Cite Code Project

Contact