Abstract: Likelihood, although useful as a training loss, is a poor search objective for guiding open-ended generation from language models (LMs). Existing generation algorithms must avoid both unlikely strings, which are...
Abstract: Likelihood, although useful as a training loss, is a poor search objective for guiding open-ended generation from language models (LMs). Existing generation algorithms must avoid both unlikely strings, which are...
Title: Scalable and Trustworthy Learning in Heterogeneous Networks
Abstract: To build a responsible data economy and protect data ownership, it is crucial to enable learning models from separate, heterogeneous...
Title: Socially Responsible and Factual Reasoning for Equitable AI Systems
Abstract: Understanding the implications underlying a text is critical to assessing its impact, in particular the social dynamics that...
The Product Management Club meets weekly on Tuesday nights to discuss trends in technology, conduct product thinking seminars, work on case studies, read books, and occasionally prep together for PM recruitment. All UMass...
A close look at the history, design, and philosophy of Steampunk, exploring how to infuse elements of Steampunk into our daily lives.
Description: Steampunk is more than an aesthetic; it's a framework for creating...
Title: Analyzing and Securing Software with Robust and Generalizable Learning
Abstract: Software is powering every aspect of our society, but it remains plagued with errors and prone to critical failures and...
Title: A Holistic View on Machine Learning for Systems
Abstract: Improving computer system performance and resource efficiency are long-standing goals. Recent approaches that use machine learning methods to...
Join Kate Sonka, Executive Director of Teach Access, to develop a further understanding of why teaching accessibility to our students is as important as teaching accessibility. Teach Access envisions a fully accessible...
Title: Sequential Prediction: Calibration and Selectivity
Abstract: This talk will discuss new perspectives and results on sequential prediction/learning under minimal assumptions on the data. In the first part...
Title: Uncertainty in Information Retrieval?
Abstract: Search engines have become our main gateway to massive globally distributed repositories of human knowledge and cultural artifacts. Like all software systems...