Abstract In this talk, we will discuss two of our recent works aimed at enhancing the task-specific performance of Large Language Models (LLMs). In the first part, we explore the generation of high-quality synthetic data[…]

Read More

Abstract The shared universal properties of human languages have been at the heart of many linguistic debates for decades. A big part of these debates are two core questions: (1) learnability — can all linguistic[…]

Read More

Abstract The rapid advancement of large language models (LLMs) has unlocked a myriad of possibilities for positive societal impact, ranging from enhancing accessibility and communication to supporting disaster response and public health initiatives. However, the[…]

Read More

Abstract Self-consistency (SC) has been demonstrated to enhance the performance of large language models (LLMs) across various tasks and domains involving short content. However, does this evidence support its effectiveness for long-context problems? In this talk, we examine the[…]

Read More

Abstract We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from[…]

Read More

Abstract With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques has been growing in order to deploy these models widely. The sheer parameter count of some models makes[…]

Read More

Abstract Gradient-based sampling algorithms are a cornerstone of modern Bayesian computation, widely used in applications ranging from probabilistic programming to diffusion models.  While these methods perform exceptionally well in continuous domains, extending them to discrete[…]

Read More