IETC Reading Group: AI Alignment, Trust, and Interpretability

USC Institute on Ethics and Trust in Computing is launching a biweekly reading group on AI alignment, trust, and interpretability. Researchers and students interested in evaluating, explaining, or governing AI systems are welcome.

The reading group is for people whose work touches how models are evaluated, explained, or governed, and for people who think the current answers are wrong. Sessions assume some machine learning background but are not required.

To lead a session: bring a paper, recent work of your own, or a problem you are stuck on. Slides are optional and a finished result is not expected.

Please contact Prof. Yue Zhao ([email protected]) if you would like to join or present in the reading group.