Home

Calendar

Filter

Search
FEATURED EVENTS
FILTER EVENTS Clear all filters
TODAY'S EVENTS
Feb 28, 2024

Feb 28, 2024

3:30 PM - 4:30 PM

Save to My Events

Speaker Thai Le Abstract Responsible AI models should not only be accurate but also resilient to security threats and transparent to users. Despite their high performance, many recent Natural Language Processing models are vulnerable to adversarial text attacks. As these models become more complex, understanding their decision-making process and ensuring compliance with societal standards is crucial. To illuminate these topics, this talk first introduces the first and most comprehensive c...

Mar 22, 2024

Mar 22, 2024

3:30 PM - 4:30 PM

Save to My Events

Speaker Jingyan Wang Abstract High-stakes evaluation problems—to estimate the quality of items or people—arise in many real-world applications such as admissions, hiring, grading, and peer review. My research focuses on understanding and improving these evaluation problems along the dimensions of accuracy, fairness, efficiency, and reliability. In this talk, I describe one line of my research on correcting human bias under different behavioral models. The first type of bias arises in a se...

Apr 8, 2024

Apr 8, 2024

3:30 PM - 4:30 PM

Save to My Events

Speaker Adithya Murali Abstract Software verification is key to engineering trustworthy and reliable systems. However, verification is at an impasse in techniques for practical adoption. In this talk, I will argue that the current state-of-the-art is fundamentally un-democratic: programmers have no hope of being able to use existing automated tools to verify their code without a PhD in programming languages! I address this challenge from both theoretical and practical standpoints, showin...