Abstract I discuss the application of Foundation Models in Astronomy through the collaborative efforts of the UniverseTBD consortium with a mission to democratize Science for everyone. One of our key objectives is to overcome the[…]

Read More

Abstract We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x)[…]

Read More

Abstract Over the past three decades, the fields of automatic speech recognition (ASR) and machine translation (MT) have witnessed remarkable advancements, leading to exciting research directions such as speech-to-text translation (ST). This talk will delve[…]

Read More

Abstract There is an enormous data gap between how AI systems and children learn language: The best LLMs now learn language from text with a word count in the trillions, whereas it would take a[…]

Read More

Abstract Large language models like ChatGPT have shown extraordinary abilities for writing. While impressive at first glance, large language models aren’t perfect and often make mistakes humans would not make. The main architecture behind ChatGPT[…]

Read More

Abstract Our research focuses on improving speech processing algorithms, such as automatic speech recognition (ASR), speaker identification, and depression detection, under challenging conditions such as limited data (for example, children’s or clinical speech), mismatched conditions[…]

Read More

Abstract Non-invasive neural interfaces have the potential to transform human-computer interaction by providing users with low friction, information rich, always available inputs. Reality Labs at Meta is developing such an interface for the control of[…]

Read More