活动预告｜智能化软件开发沙龙优秀学者报告·第1期：张天翼

最新推荐文章于 2025-05-26 10:15:16 发布

pengxin_ce

最新推荐文章于 2025-05-26 10:15:16 发布

阅读量150

点赞数

文章标签： https qt go cpu rabbitmq

原文链接：https://mp.weixin.qq.com/s?__biz=MzU4NDU4OTM4OQ==&mid=2247492533&idx=1&sn=8d2d5bcb04cfc4517ded79261a8c9fd1&chksm=fd952a97cae2a381a07ed8651670b9f89a2d5088d8f5c21595b7bea8bd70cccc5f8ec572302b&scene=126&&sessionid=0

版权

智能化软件开发沙龙优秀学者报告

第1期

张天翼

内容简介

Title

Rethinking Automated Code Generation with Human-Centered Intelligence

Abstract

As computation is woven into our everyday life, more people want or need to write code. But programming is hard, especially for novice programmers and computer end-users. Over the years, many intelligent tools have been invented to automate the programming workflow. However, recent studies have shown that the cost of automation often outweighs its benefit and, more importantly, people may have trust issues in automation.

In this talk, I will describe how we can overcome those limits by augmenting intelligent programming tools with human-centered interaction mechanisms. I will describe how we can redesign existing program synthesizers with enriched feedback loops and interpretability, so users can build a more accurate mental model of the underlying synthesis process and provide strategic feedback to guide the synthesizer. Then, I will describe a recent study on the usability of GitHub Copilot, a powerful code generation tool powered by an ultra-large language model. I will conclude my talk with future directions about supporting human-centered intelligence for code generation tools.

Biography

Tianyi Zhang is an assistant professor in Computer Science at Purdue University. He develops interactive systems that augment human intelligence with data-driven insights and augment machine intelligence with human guidance, with a particular focus on improving programming productivity. Previously, he was a postdoctoral fellow at Harvard SEAS. He obtained his PhD from UCLA CS and received the UCLA Dissertation Year Fellowship. His work has also been recognized with a Best Paper Honorable Mention Award from SIGCHI.