[Colloquium] Reminder - Han Liu Dissertation Defense/May 28, 2024

Megan Woodward via Colloquium colloquium at mailman.cs.uchicago.edu
Tue May 28 08:51:48 CDT 2024


This is an announcement of Han Liu's Dissertation Defense.
===============================================
Candidate: Han Liu

Date: Tuesday, May 28, 2024

Time: 10 am CT

Remote Location:  https://uchicago.zoom.us/j/5431475712?pwd=T2hsWXRWZHJTRzBXc2duSkE4bkpkdz09<https://urldefense.com/v3/__https://uchicago.zoom.us/j/5431475712?pwd=T2hsWXRWZHJTRzBXc2duSkE4bkpkdz09__;!!BpyFHLRN4TMTrA!_PlFHh1x3b0O_UNq1wcAcbdhNpbSQnWYMt2Y1ajF_sPJ9xuHunOYx-ePCMXneoUvL2aKH_YxeHAEF2ktzRbApkT2l5Y681bShH_Yo1ge_w$>

Location: JCL 298

Title: Empowering humans with machines: from explanations to teaching

Abstract: Artificial intelligence has demonstrated increasing potential to assist humans in decision-making tasks. However, AI systems solve problems differently than humans, leading to varying performance in human-AI teams. An ideal human-AI collaboration system should leverage the strengths of both humans and AI while mitigating their weaknesses. In this presentation, I will discuss how to empower humans with AI systems in decision-making tasks. First, I will explain how to understand human-AI teams under different distribution types and interactive interfaces. Then, I will describe how to align AI models with human perceptions for better decision support. Finally, I will explore how to build AI-driven tutorials using vision-language models to assist and teach humans in challenging image classification tasks.

Advisors: Chenhao Tan

Committee Members: Yuxin Chen, Chenhao Tan, and Aritrick Chatterjee









-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20240528/1dfc49bf/attachment.html>


More information about the Colloquium mailing list